From 3ee1c5bbb89e691fe3bd590389cf2dcea007f2e6 Mon Sep 17 00:00:00 2001
From: wassname <wassname@users.noreply.github.com>
Date: Mon, 26 Oct 2020 14:41:07 +0800
Subject: [PATCH] tidy data

---
 Makefile                                 |    4 +-
 notebooks/00.00-mc-get_data.ipynb        | 1600 -----------------
 notebooks/00.01-mc-get_currentdata.ipynb |  725 --------
 notebooks/00.02-mc-load_data.ipynb       | 2009 ----------------------
 notebooks/00.03-mc-load_data.ipynb       | 1837 ++++++++++++++++++++
 requirements/requirements.txt            |  190 ++
 seq2seq_time/data/data.py                |  309 ++++
 seq2seq_time/data/dataset.py             |    8 +-
 seq2seq_time/data/make_dataset.py        |   30 -
 seq2seq_time/data/tidal.py               |   43 +
 seq2seq_time/data/util.py                |   19 +
 11 files changed, 2405 insertions(+), 4369 deletions(-)
 delete mode 100644 notebooks/00.00-mc-get_data.ipynb
 delete mode 100644 notebooks/00.01-mc-get_currentdata.ipynb
 delete mode 100644 notebooks/00.02-mc-load_data.ipynb
 create mode 100644 notebooks/00.03-mc-load_data.ipynb
 create mode 100644 seq2seq_time/data/data.py
 delete mode 100644 seq2seq_time/data/make_dataset.py
 create mode 100644 seq2seq_time/data/tidal.py
 create mode 100644 seq2seq_time/data/util.py

diff --git a/Makefile b/Makefile
index 3aade1f..e1952ed 100644
--- a/Makefile
+++ b/Makefile
@@ -8,7 +8,7 @@ PROJECT_DIR := $(shell dirname $(realpath $(lastword $(MAKEFILE_LIST))))
 BUCKET = [OPTIONAL] your-bucket-for-syncing-data (do not include 's3://')
 PROFILE = default
 PROJECT_NAME = seq2seq-time
-PYTHON_INTERPRETER = seq2seq-time
+PYTHON_INTERPRETER = python
 
 #################################################################################
 # COMMANDS                                                                      #
@@ -70,7 +70,7 @@ test:
 doc_reqs:
 	conda env export --no-builds --from-history --name $(PROJECT_NAME) > requirements/environment.min.yaml
 	conda env export  --name $(PROJECT_NAME) > requirements/environment.max.yaml
-	$(PYTHON_INTERPRETER) -m pip freeze > requirements/requirements.txt --name
+	$(PYTHON_INTERPRETER) -m pip freeze > requirements/requirements.txt
 
 #################################################################################
 # Self Documenting Commands                                                     #
diff --git a/notebooks/00.00-mc-get_data.ipynb b/notebooks/00.00-mc-get_data.ipynb
deleted file mode 100644
index eb7fbde..0000000
--- a/notebooks/00.00-mc-get_data.ipynb
+++ /dev/null
@@ -1,1600 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T07:08:04.786938Z",
-     "start_time": "2020-10-25T07:08:04.731940Z"
-    }
-   },
-   "source": [
-    "Here I load multiple multivariate timeseries regression datasets"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T06:19:30.815188Z",
-     "start_time": "2020-10-25T06:19:30.232189Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "# OPTIONAL: Load the \"autoreload\" extension so that code can change. But blacklist large modules\n",
-    "%load_ext autoreload\n",
-    "%autoreload 2\n",
-    "%aimport -pandas\n",
-    "%aimport -torch\n",
-    "%aimport -numpy\n",
-    "%aimport -matplotlib\n",
-    "%aimport -dask\n",
-    "%aimport -tqdm\n",
-    "%matplotlib inline"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T06:19:35.141361Z",
-     "start_time": "2020-10-25T06:19:30.817391Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "plt.rcParams['figure.figsize'] = (12.0, 3.0)\n",
-    "plt.style.use('ggplot')\n",
-    "\n",
-    "import holoviews as hv\n",
-    "from holoviews.operation.datashader import datashade, dynspread"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T06:19:35.664800Z",
-     "start_time": "2020-10-25T06:19:35.144881Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from seq2seq_time.data import ucimlr_regression"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T06:19:35.708123Z",
-     "start_time": "2020-10-25T06:19:35.668549Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "root = '../data/processed/'"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T06:23:55.853191Z",
-     "start_time": "2020-10-25T06:23:42.525442Z"
-    },
-    "scrolled": true
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>Time (s)</th>\n",
-       "      <th>CO (ppm)</th>\n",
-       "      <th>Humidity (%r.h.)</th>\n",
-       "      <th>Temperature (C)</th>\n",
-       "      <th>Flow rate (mL/min)</th>\n",
-       "      <th>Heater voltage (V)</th>\n",
-       "      <th>R1 (MOhm)</th>\n",
-       "      <th>R2 (MOhm)</th>\n",
-       "      <th>R3 (MOhm)</th>\n",
-       "      <th>R4 (MOhm)</th>\n",
-       "      <th>R5 (MOhm)</th>\n",
-       "      <th>R6 (MOhm)</th>\n",
-       "      <th>R7 (MOhm)</th>\n",
-       "      <th>R8 (MOhm)</th>\n",
-       "      <th>R9 (MOhm)</th>\n",
-       "      <th>R10 (MOhm)</th>\n",
-       "      <th>R11 (MOhm)</th>\n",
-       "      <th>R12 (MOhm)</th>\n",
-       "      <th>R13 (MOhm)</th>\n",
-       "      <th>R14 (MOhm)</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Time (s)</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:19:40.578</th>\n",
-       "      <td>-1.734310</td>\n",
-       "      <td>0.437913</td>\n",
-       "      <td>1.108828</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>-0.003454</td>\n",
-       "      <td>1.824243</td>\n",
-       "      <td>-0.650012</td>\n",
-       "      <td>-0.646344</td>\n",
-       "      <td>-0.795835</td>\n",
-       "      <td>-1.430269</td>\n",
-       "      <td>-1.339712</td>\n",
-       "      <td>-1.197026</td>\n",
-       "      <td>-1.312646</td>\n",
-       "      <td>-1.630336</td>\n",
-       "      <td>-1.596824</td>\n",
-       "      <td>-1.620911</td>\n",
-       "      <td>-1.672712</td>\n",
-       "      <td>-1.660328</td>\n",
-       "      <td>-1.650194</td>\n",
-       "      <td>-1.648545</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:19:40.886</th>\n",
-       "      <td>-1.728497</td>\n",
-       "      <td>0.437913</td>\n",
-       "      <td>1.108828</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>-0.032321</td>\n",
-       "      <td>1.824243</td>\n",
-       "      <td>-0.649951</td>\n",
-       "      <td>-0.646284</td>\n",
-       "      <td>-0.795761</td>\n",
-       "      <td>-1.430190</td>\n",
-       "      <td>-1.339655</td>\n",
-       "      <td>-1.196981</td>\n",
-       "      <td>-1.312590</td>\n",
-       "      <td>-1.630324</td>\n",
-       "      <td>-1.596824</td>\n",
-       "      <td>-1.620899</td>\n",
-       "      <td>-1.672712</td>\n",
-       "      <td>-1.660315</td>\n",
-       "      <td>-1.650173</td>\n",
-       "      <td>-1.648539</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:19:41.195</th>\n",
-       "      <td>-1.722665</td>\n",
-       "      <td>0.437913</td>\n",
-       "      <td>1.108828</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>-0.061189</td>\n",
-       "      <td>1.827306</td>\n",
-       "      <td>-0.649899</td>\n",
-       "      <td>-0.646231</td>\n",
-       "      <td>-0.795694</td>\n",
-       "      <td>-1.430129</td>\n",
-       "      <td>-1.339598</td>\n",
-       "      <td>-1.196947</td>\n",
-       "      <td>-1.312531</td>\n",
-       "      <td>-1.630305</td>\n",
-       "      <td>-1.596817</td>\n",
-       "      <td>-1.620893</td>\n",
-       "      <td>-1.672712</td>\n",
-       "      <td>-1.660309</td>\n",
-       "      <td>-1.650166</td>\n",
-       "      <td>-1.648539</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:19:41.505</th>\n",
-       "      <td>-1.716814</td>\n",
-       "      <td>0.437913</td>\n",
-       "      <td>1.108828</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>-0.027986</td>\n",
-       "      <td>1.824583</td>\n",
-       "      <td>-0.649847</td>\n",
-       "      <td>-0.646182</td>\n",
-       "      <td>-0.795634</td>\n",
-       "      <td>-1.430062</td>\n",
-       "      <td>-1.339541</td>\n",
-       "      <td>-1.196917</td>\n",
-       "      <td>-1.312486</td>\n",
-       "      <td>-1.630299</td>\n",
-       "      <td>-1.596817</td>\n",
-       "      <td>-1.620893</td>\n",
-       "      <td>-1.672712</td>\n",
-       "      <td>-1.660289</td>\n",
-       "      <td>-1.650152</td>\n",
-       "      <td>-1.648528</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:19:41.814</th>\n",
-       "      <td>-1.710981</td>\n",
-       "      <td>0.437913</td>\n",
-       "      <td>1.108828</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>0.010044</td>\n",
-       "      <td>1.822541</td>\n",
-       "      <td>-0.649799</td>\n",
-       "      <td>-0.646133</td>\n",
-       "      <td>-0.795581</td>\n",
-       "      <td>-1.430013</td>\n",
-       "      <td>-1.339492</td>\n",
-       "      <td>-1.196879</td>\n",
-       "      <td>-1.312442</td>\n",
-       "      <td>-1.630292</td>\n",
-       "      <td>-1.596824</td>\n",
-       "      <td>-1.620881</td>\n",
-       "      <td>-1.672712</td>\n",
-       "      <td>-1.660309</td>\n",
-       "      <td>-1.650152</td>\n",
-       "      <td>-1.648528</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:22:42.654</th>\n",
-       "      <td>1.702303</td>\n",
-       "      <td>-2.294832</td>\n",
-       "      <td>4.023714</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>-0.218337</td>\n",
-       "      <td>1.824243</td>\n",
-       "      <td>-0.649691</td>\n",
-       "      <td>-0.646004</td>\n",
-       "      <td>-0.795454</td>\n",
-       "      <td>-1.429860</td>\n",
-       "      <td>-1.339370</td>\n",
-       "      <td>-1.196777</td>\n",
-       "      <td>-1.315012</td>\n",
-       "      <td>-1.630254</td>\n",
-       "      <td>-1.596809</td>\n",
-       "      <td>-1.620881</td>\n",
-       "      <td>-1.672718</td>\n",
-       "      <td>-1.660270</td>\n",
-       "      <td>-1.654088</td>\n",
-       "      <td>-1.651725</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:22:42.960</th>\n",
-       "      <td>1.708078</td>\n",
-       "      <td>-2.294832</td>\n",
-       "      <td>4.023714</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>-0.259323</td>\n",
-       "      <td>1.824243</td>\n",
-       "      <td>-0.648385</td>\n",
-       "      <td>-0.638213</td>\n",
-       "      <td>-0.777433</td>\n",
-       "      <td>-1.406889</td>\n",
-       "      <td>-1.315353</td>\n",
-       "      <td>-1.168923</td>\n",
-       "      <td>-1.270079</td>\n",
-       "      <td>-1.618053</td>\n",
-       "      <td>-1.578022</td>\n",
-       "      <td>-1.598259</td>\n",
-       "      <td>-1.631450</td>\n",
-       "      <td>-1.575014</td>\n",
-       "      <td>-1.514371</td>\n",
-       "      <td>-1.526583</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:22:43.263</th>\n",
-       "      <td>1.713797</td>\n",
-       "      <td>-2.294832</td>\n",
-       "      <td>4.088219</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>-0.288881</td>\n",
-       "      <td>-0.510275</td>\n",
-       "      <td>-0.589259</td>\n",
-       "      <td>-0.509705</td>\n",
-       "      <td>-0.555600</td>\n",
-       "      <td>-1.132191</td>\n",
-       "      <td>-1.074530</td>\n",
-       "      <td>-0.900785</td>\n",
-       "      <td>-0.940728</td>\n",
-       "      <td>-1.213296</td>\n",
-       "      <td>-1.109063</td>\n",
-       "      <td>-1.151742</td>\n",
-       "      <td>-1.048204</td>\n",
-       "      <td>-0.753188</td>\n",
-       "      <td>-0.562590</td>\n",
-       "      <td>-0.690625</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:22:43.568</th>\n",
-       "      <td>1.719554</td>\n",
-       "      <td>-2.294832</td>\n",
-       "      <td>4.524372</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>-0.254594</td>\n",
-       "      <td>-0.524568</td>\n",
-       "      <td>-0.271973</td>\n",
-       "      <td>0.078964</td>\n",
-       "      <td>0.348624</td>\n",
-       "      <td>-0.179796</td>\n",
-       "      <td>-0.185164</td>\n",
-       "      <td>0.036141</td>\n",
-       "      <td>0.103386</td>\n",
-       "      <td>0.030704</td>\n",
-       "      <td>0.019792</td>\n",
-       "      <td>0.013480</td>\n",
-       "      <td>-0.033721</td>\n",
-       "      <td>0.448250</td>\n",
-       "      <td>0.553628</td>\n",
-       "      <td>0.302920</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-09-30 22:22:43.873</th>\n",
-       "      <td>1.725311</td>\n",
-       "      <td>-2.294832</td>\n",
-       "      <td>4.960795</td>\n",
-       "      <td>0.409225</td>\n",
-       "      <td>-0.220307</td>\n",
-       "      <td>-0.534097</td>\n",
-       "      <td>0.576004</td>\n",
-       "      <td>1.177383</td>\n",
-       "      <td>1.641545</td>\n",
-       "      <td>0.608808</td>\n",
-       "      <td>0.987882</td>\n",
-       "      <td>1.212339</td>\n",
-       "      <td>1.347734</td>\n",
-       "      <td>0.755638</td>\n",
-       "      <td>0.680784</td>\n",
-       "      <td>0.779500</td>\n",
-       "      <td>0.546623</td>\n",
-       "      <td>1.035454</td>\n",
-       "      <td>1.084656</td>\n",
-       "      <td>0.765242</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>600 rows × 20 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                         Time (s)  CO (ppm)  Humidity (%r.h.)  \\\n",
-       "Time (s)                                                        \n",
-       "2016-09-30 22:19:40.578 -1.734310  0.437913          1.108828   \n",
-       "2016-09-30 22:19:40.886 -1.728497  0.437913          1.108828   \n",
-       "2016-09-30 22:19:41.195 -1.722665  0.437913          1.108828   \n",
-       "2016-09-30 22:19:41.505 -1.716814  0.437913          1.108828   \n",
-       "2016-09-30 22:19:41.814 -1.710981  0.437913          1.108828   \n",
-       "...                           ...       ...               ...   \n",
-       "2016-09-30 22:22:42.654  1.702303 -2.294832          4.023714   \n",
-       "2016-09-30 22:22:42.960  1.708078 -2.294832          4.023714   \n",
-       "2016-09-30 22:22:43.263  1.713797 -2.294832          4.088219   \n",
-       "2016-09-30 22:22:43.568  1.719554 -2.294832          4.524372   \n",
-       "2016-09-30 22:22:43.873  1.725311 -2.294832          4.960795   \n",
-       "\n",
-       "                         Temperature (C)  Flow rate (mL/min)  \\\n",
-       "Time (s)                                                       \n",
-       "2016-09-30 22:19:40.578         0.409225           -0.003454   \n",
-       "2016-09-30 22:19:40.886         0.409225           -0.032321   \n",
-       "2016-09-30 22:19:41.195         0.409225           -0.061189   \n",
-       "2016-09-30 22:19:41.505         0.409225           -0.027986   \n",
-       "2016-09-30 22:19:41.814         0.409225            0.010044   \n",
-       "...                                  ...                 ...   \n",
-       "2016-09-30 22:22:42.654         0.409225           -0.218337   \n",
-       "2016-09-30 22:22:42.960         0.409225           -0.259323   \n",
-       "2016-09-30 22:22:43.263         0.409225           -0.288881   \n",
-       "2016-09-30 22:22:43.568         0.409225           -0.254594   \n",
-       "2016-09-30 22:22:43.873         0.409225           -0.220307   \n",
-       "\n",
-       "                         Heater voltage (V)  R1 (MOhm)  R2 (MOhm)  R3 (MOhm)  \\\n",
-       "Time (s)                                                                       \n",
-       "2016-09-30 22:19:40.578            1.824243  -0.650012  -0.646344  -0.795835   \n",
-       "2016-09-30 22:19:40.886            1.824243  -0.649951  -0.646284  -0.795761   \n",
-       "2016-09-30 22:19:41.195            1.827306  -0.649899  -0.646231  -0.795694   \n",
-       "2016-09-30 22:19:41.505            1.824583  -0.649847  -0.646182  -0.795634   \n",
-       "2016-09-30 22:19:41.814            1.822541  -0.649799  -0.646133  -0.795581   \n",
-       "...                                     ...        ...        ...        ...   \n",
-       "2016-09-30 22:22:42.654            1.824243  -0.649691  -0.646004  -0.795454   \n",
-       "2016-09-30 22:22:42.960            1.824243  -0.648385  -0.638213  -0.777433   \n",
-       "2016-09-30 22:22:43.263           -0.510275  -0.589259  -0.509705  -0.555600   \n",
-       "2016-09-30 22:22:43.568           -0.524568  -0.271973   0.078964   0.348624   \n",
-       "2016-09-30 22:22:43.873           -0.534097   0.576004   1.177383   1.641545   \n",
-       "\n",
-       "                         R4 (MOhm)  R5 (MOhm)  R6 (MOhm)  R7 (MOhm)  \\\n",
-       "Time (s)                                                              \n",
-       "2016-09-30 22:19:40.578  -1.430269  -1.339712  -1.197026  -1.312646   \n",
-       "2016-09-30 22:19:40.886  -1.430190  -1.339655  -1.196981  -1.312590   \n",
-       "2016-09-30 22:19:41.195  -1.430129  -1.339598  -1.196947  -1.312531   \n",
-       "2016-09-30 22:19:41.505  -1.430062  -1.339541  -1.196917  -1.312486   \n",
-       "2016-09-30 22:19:41.814  -1.430013  -1.339492  -1.196879  -1.312442   \n",
-       "...                            ...        ...        ...        ...   \n",
-       "2016-09-30 22:22:42.654  -1.429860  -1.339370  -1.196777  -1.315012   \n",
-       "2016-09-30 22:22:42.960  -1.406889  -1.315353  -1.168923  -1.270079   \n",
-       "2016-09-30 22:22:43.263  -1.132191  -1.074530  -0.900785  -0.940728   \n",
-       "2016-09-30 22:22:43.568  -0.179796  -0.185164   0.036141   0.103386   \n",
-       "2016-09-30 22:22:43.873   0.608808   0.987882   1.212339   1.347734   \n",
-       "\n",
-       "                         R8 (MOhm)  R9 (MOhm)  R10 (MOhm)  R11 (MOhm)  \\\n",
-       "Time (s)                                                                \n",
-       "2016-09-30 22:19:40.578  -1.630336  -1.596824   -1.620911   -1.672712   \n",
-       "2016-09-30 22:19:40.886  -1.630324  -1.596824   -1.620899   -1.672712   \n",
-       "2016-09-30 22:19:41.195  -1.630305  -1.596817   -1.620893   -1.672712   \n",
-       "2016-09-30 22:19:41.505  -1.630299  -1.596817   -1.620893   -1.672712   \n",
-       "2016-09-30 22:19:41.814  -1.630292  -1.596824   -1.620881   -1.672712   \n",
-       "...                            ...        ...         ...         ...   \n",
-       "2016-09-30 22:22:42.654  -1.630254  -1.596809   -1.620881   -1.672718   \n",
-       "2016-09-30 22:22:42.960  -1.618053  -1.578022   -1.598259   -1.631450   \n",
-       "2016-09-30 22:22:43.263  -1.213296  -1.109063   -1.151742   -1.048204   \n",
-       "2016-09-30 22:22:43.568   0.030704   0.019792    0.013480   -0.033721   \n",
-       "2016-09-30 22:22:43.873   0.755638   0.680784    0.779500    0.546623   \n",
-       "\n",
-       "                         R12 (MOhm)  R13 (MOhm)  R14 (MOhm)  \n",
-       "Time (s)                                                     \n",
-       "2016-09-30 22:19:40.578   -1.660328   -1.650194   -1.648545  \n",
-       "2016-09-30 22:19:40.886   -1.660315   -1.650173   -1.648539  \n",
-       "2016-09-30 22:19:41.195   -1.660309   -1.650166   -1.648539  \n",
-       "2016-09-30 22:19:41.505   -1.660289   -1.650152   -1.648528  \n",
-       "2016-09-30 22:19:41.814   -1.660309   -1.650152   -1.648528  \n",
-       "...                             ...         ...         ...  \n",
-       "2016-09-30 22:22:42.654   -1.660270   -1.654088   -1.651725  \n",
-       "2016-09-30 22:22:42.960   -1.575014   -1.514371   -1.526583  \n",
-       "2016-09-30 22:22:43.263   -0.753188   -0.562590   -0.690625  \n",
-       "2016-09-30 22:22:43.568    0.448250    0.553628    0.302920  \n",
-       "2016-09-30 22:22:43.873    1.035454    1.084656    0.765242  \n",
-       "\n",
-       "[600 rows x 20 columns]"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 864x216 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from ucimlr.regression_datasets import RegressionDataset, download_unzip, split_normalize_sequence, TRAIN\n",
-    "import os\n",
-    "from pathlib import Path\n",
-    "\n",
-    "class GasSensor(RegressionDataset):\n",
-    "    \"\"\"\n",
-    "    # Parameters\n",
-    "    root (str): Local path for storing/reading dataset files.\n",
-    "    split (str): One of {'train', 'validation', 'test'}\n",
-    "    validation_size (float): How large fraction in (0, 1) of the training partition to use for validation.\n",
-    "    \n",
-    "    http://archive.ics.uci.edu/ml/datasets/Gas+sensor+array+temperature+modulation\n",
-    "    \"\"\"\n",
-    "    def __init__(self, root, split=TRAIN, validation_size=0.2):\n",
-    "        dataset_path = os.path.join(root, self.name)\n",
-    "        url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00487/gas-sensor-array-temperature-modulation.zip'\n",
-    "        download_unzip(url, dataset_path)\n",
-    "        files = sorted(Path(root, 'GasSensor').glob('*.csv'))\n",
-    "        dfs = []\n",
-    "        for f in files:\n",
-    "            now = pd.to_datetime(f.stem, format='%Y%m%d_%H%M%S')\n",
-    "            df = pd.read_csv(f)\n",
-    "            df.index = pd.to_timedelta(df['Time (s)'], unit='s') + now\n",
-    "            dfs.append(df)\n",
-    "        self.df = df = pd.concat(dfs)\n",
-    "        \n",
-    "        \n",
-    "#         df.drop(columns=['url', ' timedelta'], inplace=True)\n",
-    "#         y_columns = [' shares']\n",
-    "#         df[y_columns[0]] = np.log(df[y_columns[0]])\n",
-    "#         self.x, self. y = split_normalize_sequence(df, y_columns, validation_size, split, self.type_)\n",
-    "        \n",
-    "dataset = GasSensor(root)\n",
-    "dataset.df\n",
-    "\n",
-    "df = dataset.df[20000:20600]\n",
-    "cols = ['CO (ppm)', 'Humidity (%r.h.)', 'Temperature (C)', 'Flow rate (mL/min)', 'Heater voltage (V)', 'R1 (MOhm)', ]\n",
-    "df2 = df - df.mean()\n",
-    "df2 = df2 / df2.std()\n",
-    "df2[cols].plot()\n",
-    "df2"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T06:23:58.054921Z",
-     "start_time": "2020-10-25T06:23:55.855659Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>holiday</th>\n",
-       "      <th>temp</th>\n",
-       "      <th>rain_1h</th>\n",
-       "      <th>snow_1h</th>\n",
-       "      <th>clouds_all</th>\n",
-       "      <th>weather_main</th>\n",
-       "      <th>weather_description</th>\n",
-       "      <th>date_time</th>\n",
-       "      <th>traffic_volume</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>date_time</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 09:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>288.28</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>40</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>scattered clouds</td>\n",
-       "      <td>2012-10-02 09:00:00</td>\n",
-       "      <td>5545</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 10:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>289.36</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>75</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>broken clouds</td>\n",
-       "      <td>2012-10-02 10:00:00</td>\n",
-       "      <td>4516</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 11:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>289.58</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>2012-10-02 11:00:00</td>\n",
-       "      <td>4767</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 12:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>290.13</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>2012-10-02 12:00:00</td>\n",
-       "      <td>5026</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 13:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>291.14</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>75</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>broken clouds</td>\n",
-       "      <td>2012-10-02 13:00:00</td>\n",
-       "      <td>4918</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 19:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>283.45</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>75</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>broken clouds</td>\n",
-       "      <td>2018-09-30 19:00:00</td>\n",
-       "      <td>3543</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 20:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>282.76</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>2018-09-30 20:00:00</td>\n",
-       "      <td>2781</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 21:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>282.73</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90</td>\n",
-       "      <td>Thunderstorm</td>\n",
-       "      <td>proximity thunderstorm</td>\n",
-       "      <td>2018-09-30 21:00:00</td>\n",
-       "      <td>2159</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 22:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>282.09</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>2018-09-30 22:00:00</td>\n",
-       "      <td>1450</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 23:00:00</th>\n",
-       "      <td>None</td>\n",
-       "      <td>282.12</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>2018-09-30 23:00:00</td>\n",
-       "      <td>954</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>48204 rows × 9 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                    holiday    temp  rain_1h  snow_1h  clouds_all  \\\n",
-       "date_time                                                           \n",
-       "2012-10-02 09:00:00    None  288.28      0.0      0.0          40   \n",
-       "2012-10-02 10:00:00    None  289.36      0.0      0.0          75   \n",
-       "2012-10-02 11:00:00    None  289.58      0.0      0.0          90   \n",
-       "2012-10-02 12:00:00    None  290.13      0.0      0.0          90   \n",
-       "2012-10-02 13:00:00    None  291.14      0.0      0.0          75   \n",
-       "...                     ...     ...      ...      ...         ...   \n",
-       "2018-09-30 19:00:00    None  283.45      0.0      0.0          75   \n",
-       "2018-09-30 20:00:00    None  282.76      0.0      0.0          90   \n",
-       "2018-09-30 21:00:00    None  282.73      0.0      0.0          90   \n",
-       "2018-09-30 22:00:00    None  282.09      0.0      0.0          90   \n",
-       "2018-09-30 23:00:00    None  282.12      0.0      0.0          90   \n",
-       "\n",
-       "                     weather_main     weather_description  \\\n",
-       "date_time                                                   \n",
-       "2012-10-02 09:00:00        Clouds        scattered clouds   \n",
-       "2012-10-02 10:00:00        Clouds           broken clouds   \n",
-       "2012-10-02 11:00:00        Clouds         overcast clouds   \n",
-       "2012-10-02 12:00:00        Clouds         overcast clouds   \n",
-       "2012-10-02 13:00:00        Clouds           broken clouds   \n",
-       "...                           ...                     ...   \n",
-       "2018-09-30 19:00:00        Clouds           broken clouds   \n",
-       "2018-09-30 20:00:00        Clouds         overcast clouds   \n",
-       "2018-09-30 21:00:00  Thunderstorm  proximity thunderstorm   \n",
-       "2018-09-30 22:00:00        Clouds         overcast clouds   \n",
-       "2018-09-30 23:00:00        Clouds         overcast clouds   \n",
-       "\n",
-       "                               date_time  traffic_volume  \n",
-       "date_time                                                 \n",
-       "2012-10-02 09:00:00  2012-10-02 09:00:00            5545  \n",
-       "2012-10-02 10:00:00  2012-10-02 10:00:00            4516  \n",
-       "2012-10-02 11:00:00  2012-10-02 11:00:00            4767  \n",
-       "2012-10-02 12:00:00  2012-10-02 12:00:00            5026  \n",
-       "2012-10-02 13:00:00  2012-10-02 13:00:00            4918  \n",
-       "...                                  ...             ...  \n",
-       "2018-09-30 19:00:00  2018-09-30 19:00:00            3543  \n",
-       "2018-09-30 20:00:00  2018-09-30 20:00:00            2781  \n",
-       "2018-09-30 21:00:00  2018-09-30 21:00:00            2159  \n",
-       "2018-09-30 22:00:00  2018-09-30 22:00:00            1450  \n",
-       "2018-09-30 23:00:00  2018-09-30 23:00:00             954  \n",
-       "\n",
-       "[48204 rows x 9 columns]"
-      ]
-     },
-     "execution_count": 7,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 864x216 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from ucimlr.helpers import download_file\n",
-    "# https://archive.ics.uci.edu/ml/datasets/Metro+Interstate+Traffic+Volume\n",
-    "url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00492/Metro_Interstate_Traffic_Volume.csv.gz'\n",
-    "filename = url.split('/')[-1]\n",
-    "download_file(url, root, filename)\n",
-    "\n",
-    "df = pd.read_csv(root +'/' +filename)\n",
-    "df.index = pd.to_datetime(df.date_time)\n",
-    "df[:300].traffic_volume.plot()\n",
-    "df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T06:24:04.886919Z",
-     "start_time": "2020-10-25T06:23:58.058364Z"
-    },
-    "scrolled": false
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>date</th>\n",
-       "      <th>Appliances</th>\n",
-       "      <th>lights</th>\n",
-       "      <th>T1</th>\n",
-       "      <th>RH_1</th>\n",
-       "      <th>T2</th>\n",
-       "      <th>RH_2</th>\n",
-       "      <th>T3</th>\n",
-       "      <th>RH_3</th>\n",
-       "      <th>T4</th>\n",
-       "      <th>...</th>\n",
-       "      <th>T9</th>\n",
-       "      <th>RH_9</th>\n",
-       "      <th>T_out</th>\n",
-       "      <th>Press_mm_hg</th>\n",
-       "      <th>RH_out</th>\n",
-       "      <th>Windspeed</th>\n",
-       "      <th>Visibility</th>\n",
-       "      <th>Tdewpoint</th>\n",
-       "      <th>rv1</th>\n",
-       "      <th>rv2</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>date</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:00:00</th>\n",
-       "      <td>2016-01-11 17:00:00</td>\n",
-       "      <td>60</td>\n",
-       "      <td>30</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>47.596667</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.790000</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>44.730000</td>\n",
-       "      <td>19.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>17.033333</td>\n",
-       "      <td>45.5300</td>\n",
-       "      <td>6.600000</td>\n",
-       "      <td>733.5</td>\n",
-       "      <td>92.000000</td>\n",
-       "      <td>7.000000</td>\n",
-       "      <td>63.000000</td>\n",
-       "      <td>5.300000</td>\n",
-       "      <td>13.275433</td>\n",
-       "      <td>13.275433</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:10:00</th>\n",
-       "      <td>2016-01-11 17:10:00</td>\n",
-       "      <td>60</td>\n",
-       "      <td>30</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>46.693333</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.722500</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>44.790000</td>\n",
-       "      <td>19.000000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>17.066667</td>\n",
-       "      <td>45.5600</td>\n",
-       "      <td>6.483333</td>\n",
-       "      <td>733.6</td>\n",
-       "      <td>92.000000</td>\n",
-       "      <td>6.666667</td>\n",
-       "      <td>59.166667</td>\n",
-       "      <td>5.200000</td>\n",
-       "      <td>18.606195</td>\n",
-       "      <td>18.606195</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:20:00</th>\n",
-       "      <td>2016-01-11 17:20:00</td>\n",
-       "      <td>50</td>\n",
-       "      <td>30</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>46.300000</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.626667</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>44.933333</td>\n",
-       "      <td>18.926667</td>\n",
-       "      <td>...</td>\n",
-       "      <td>17.000000</td>\n",
-       "      <td>45.5000</td>\n",
-       "      <td>6.366667</td>\n",
-       "      <td>733.7</td>\n",
-       "      <td>92.000000</td>\n",
-       "      <td>6.333333</td>\n",
-       "      <td>55.333333</td>\n",
-       "      <td>5.100000</td>\n",
-       "      <td>28.642668</td>\n",
-       "      <td>28.642668</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:30:00</th>\n",
-       "      <td>2016-01-11 17:30:00</td>\n",
-       "      <td>50</td>\n",
-       "      <td>40</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>46.066667</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.590000</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>45.000000</td>\n",
-       "      <td>18.890000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>17.000000</td>\n",
-       "      <td>45.4000</td>\n",
-       "      <td>6.250000</td>\n",
-       "      <td>733.8</td>\n",
-       "      <td>92.000000</td>\n",
-       "      <td>6.000000</td>\n",
-       "      <td>51.500000</td>\n",
-       "      <td>5.000000</td>\n",
-       "      <td>45.410389</td>\n",
-       "      <td>45.410389</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:40:00</th>\n",
-       "      <td>2016-01-11 17:40:00</td>\n",
-       "      <td>60</td>\n",
-       "      <td>40</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>46.333333</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.530000</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>45.000000</td>\n",
-       "      <td>18.890000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>17.000000</td>\n",
-       "      <td>45.4000</td>\n",
-       "      <td>6.133333</td>\n",
-       "      <td>733.9</td>\n",
-       "      <td>92.000000</td>\n",
-       "      <td>5.666667</td>\n",
-       "      <td>47.666667</td>\n",
-       "      <td>4.900000</td>\n",
-       "      <td>10.084097</td>\n",
-       "      <td>10.084097</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 17:20:00</th>\n",
-       "      <td>2016-05-27 17:20:00</td>\n",
-       "      <td>100</td>\n",
-       "      <td>0</td>\n",
-       "      <td>25.566667</td>\n",
-       "      <td>46.560000</td>\n",
-       "      <td>25.890000</td>\n",
-       "      <td>42.025714</td>\n",
-       "      <td>27.200000</td>\n",
-       "      <td>41.163333</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>23.200000</td>\n",
-       "      <td>46.7900</td>\n",
-       "      <td>22.733333</td>\n",
-       "      <td>755.2</td>\n",
-       "      <td>55.666667</td>\n",
-       "      <td>3.333333</td>\n",
-       "      <td>23.666667</td>\n",
-       "      <td>13.333333</td>\n",
-       "      <td>43.096812</td>\n",
-       "      <td>43.096812</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 17:30:00</th>\n",
-       "      <td>2016-05-27 17:30:00</td>\n",
-       "      <td>90</td>\n",
-       "      <td>0</td>\n",
-       "      <td>25.500000</td>\n",
-       "      <td>46.500000</td>\n",
-       "      <td>25.754000</td>\n",
-       "      <td>42.080000</td>\n",
-       "      <td>27.133333</td>\n",
-       "      <td>41.223333</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>23.200000</td>\n",
-       "      <td>46.7900</td>\n",
-       "      <td>22.600000</td>\n",
-       "      <td>755.2</td>\n",
-       "      <td>56.000000</td>\n",
-       "      <td>3.500000</td>\n",
-       "      <td>24.500000</td>\n",
-       "      <td>13.300000</td>\n",
-       "      <td>49.282940</td>\n",
-       "      <td>49.282940</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 17:40:00</th>\n",
-       "      <td>2016-05-27 17:40:00</td>\n",
-       "      <td>270</td>\n",
-       "      <td>10</td>\n",
-       "      <td>25.500000</td>\n",
-       "      <td>46.596667</td>\n",
-       "      <td>25.628571</td>\n",
-       "      <td>42.768571</td>\n",
-       "      <td>27.050000</td>\n",
-       "      <td>41.690000</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>23.200000</td>\n",
-       "      <td>46.7900</td>\n",
-       "      <td>22.466667</td>\n",
-       "      <td>755.2</td>\n",
-       "      <td>56.333333</td>\n",
-       "      <td>3.666667</td>\n",
-       "      <td>25.333333</td>\n",
-       "      <td>13.266667</td>\n",
-       "      <td>29.199117</td>\n",
-       "      <td>29.199117</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 17:50:00</th>\n",
-       "      <td>2016-05-27 17:50:00</td>\n",
-       "      <td>420</td>\n",
-       "      <td>10</td>\n",
-       "      <td>25.500000</td>\n",
-       "      <td>46.990000</td>\n",
-       "      <td>25.414000</td>\n",
-       "      <td>43.036000</td>\n",
-       "      <td>26.890000</td>\n",
-       "      <td>41.290000</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>23.200000</td>\n",
-       "      <td>46.8175</td>\n",
-       "      <td>22.333333</td>\n",
-       "      <td>755.2</td>\n",
-       "      <td>56.666667</td>\n",
-       "      <td>3.833333</td>\n",
-       "      <td>26.166667</td>\n",
-       "      <td>13.233333</td>\n",
-       "      <td>6.322784</td>\n",
-       "      <td>6.322784</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 18:00:00</th>\n",
-       "      <td>2016-05-27 18:00:00</td>\n",
-       "      <td>430</td>\n",
-       "      <td>10</td>\n",
-       "      <td>25.500000</td>\n",
-       "      <td>46.600000</td>\n",
-       "      <td>25.264286</td>\n",
-       "      <td>42.971429</td>\n",
-       "      <td>26.823333</td>\n",
-       "      <td>41.156667</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>23.200000</td>\n",
-       "      <td>46.8450</td>\n",
-       "      <td>22.200000</td>\n",
-       "      <td>755.2</td>\n",
-       "      <td>57.000000</td>\n",
-       "      <td>4.000000</td>\n",
-       "      <td>27.000000</td>\n",
-       "      <td>13.200000</td>\n",
-       "      <td>34.118851</td>\n",
-       "      <td>34.118851</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>19735 rows × 29 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                                    date  Appliances  lights         T1  \\\n",
-       "date                                                                      \n",
-       "2016-01-11 17:00:00  2016-01-11 17:00:00          60      30  19.890000   \n",
-       "2016-01-11 17:10:00  2016-01-11 17:10:00          60      30  19.890000   \n",
-       "2016-01-11 17:20:00  2016-01-11 17:20:00          50      30  19.890000   \n",
-       "2016-01-11 17:30:00  2016-01-11 17:30:00          50      40  19.890000   \n",
-       "2016-01-11 17:40:00  2016-01-11 17:40:00          60      40  19.890000   \n",
-       "...                                  ...         ...     ...        ...   \n",
-       "2016-05-27 17:20:00  2016-05-27 17:20:00         100       0  25.566667   \n",
-       "2016-05-27 17:30:00  2016-05-27 17:30:00          90       0  25.500000   \n",
-       "2016-05-27 17:40:00  2016-05-27 17:40:00         270      10  25.500000   \n",
-       "2016-05-27 17:50:00  2016-05-27 17:50:00         420      10  25.500000   \n",
-       "2016-05-27 18:00:00  2016-05-27 18:00:00         430      10  25.500000   \n",
-       "\n",
-       "                          RH_1         T2       RH_2         T3       RH_3  \\\n",
-       "date                                                                         \n",
-       "2016-01-11 17:00:00  47.596667  19.200000  44.790000  19.790000  44.730000   \n",
-       "2016-01-11 17:10:00  46.693333  19.200000  44.722500  19.790000  44.790000   \n",
-       "2016-01-11 17:20:00  46.300000  19.200000  44.626667  19.790000  44.933333   \n",
-       "2016-01-11 17:30:00  46.066667  19.200000  44.590000  19.790000  45.000000   \n",
-       "2016-01-11 17:40:00  46.333333  19.200000  44.530000  19.790000  45.000000   \n",
-       "...                        ...        ...        ...        ...        ...   \n",
-       "2016-05-27 17:20:00  46.560000  25.890000  42.025714  27.200000  41.163333   \n",
-       "2016-05-27 17:30:00  46.500000  25.754000  42.080000  27.133333  41.223333   \n",
-       "2016-05-27 17:40:00  46.596667  25.628571  42.768571  27.050000  41.690000   \n",
-       "2016-05-27 17:50:00  46.990000  25.414000  43.036000  26.890000  41.290000   \n",
-       "2016-05-27 18:00:00  46.600000  25.264286  42.971429  26.823333  41.156667   \n",
-       "\n",
-       "                            T4  ...         T9     RH_9      T_out  \\\n",
-       "date                            ...                                  \n",
-       "2016-01-11 17:00:00  19.000000  ...  17.033333  45.5300   6.600000   \n",
-       "2016-01-11 17:10:00  19.000000  ...  17.066667  45.5600   6.483333   \n",
-       "2016-01-11 17:20:00  18.926667  ...  17.000000  45.5000   6.366667   \n",
-       "2016-01-11 17:30:00  18.890000  ...  17.000000  45.4000   6.250000   \n",
-       "2016-01-11 17:40:00  18.890000  ...  17.000000  45.4000   6.133333   \n",
-       "...                        ...  ...        ...      ...        ...   \n",
-       "2016-05-27 17:20:00  24.700000  ...  23.200000  46.7900  22.733333   \n",
-       "2016-05-27 17:30:00  24.700000  ...  23.200000  46.7900  22.600000   \n",
-       "2016-05-27 17:40:00  24.700000  ...  23.200000  46.7900  22.466667   \n",
-       "2016-05-27 17:50:00  24.700000  ...  23.200000  46.8175  22.333333   \n",
-       "2016-05-27 18:00:00  24.700000  ...  23.200000  46.8450  22.200000   \n",
-       "\n",
-       "                     Press_mm_hg     RH_out  Windspeed  Visibility  Tdewpoint  \\\n",
-       "date                                                                            \n",
-       "2016-01-11 17:00:00        733.5  92.000000   7.000000   63.000000   5.300000   \n",
-       "2016-01-11 17:10:00        733.6  92.000000   6.666667   59.166667   5.200000   \n",
-       "2016-01-11 17:20:00        733.7  92.000000   6.333333   55.333333   5.100000   \n",
-       "2016-01-11 17:30:00        733.8  92.000000   6.000000   51.500000   5.000000   \n",
-       "2016-01-11 17:40:00        733.9  92.000000   5.666667   47.666667   4.900000   \n",
-       "...                          ...        ...        ...         ...        ...   \n",
-       "2016-05-27 17:20:00        755.2  55.666667   3.333333   23.666667  13.333333   \n",
-       "2016-05-27 17:30:00        755.2  56.000000   3.500000   24.500000  13.300000   \n",
-       "2016-05-27 17:40:00        755.2  56.333333   3.666667   25.333333  13.266667   \n",
-       "2016-05-27 17:50:00        755.2  56.666667   3.833333   26.166667  13.233333   \n",
-       "2016-05-27 18:00:00        755.2  57.000000   4.000000   27.000000  13.200000   \n",
-       "\n",
-       "                           rv1        rv2  \n",
-       "date                                       \n",
-       "2016-01-11 17:00:00  13.275433  13.275433  \n",
-       "2016-01-11 17:10:00  18.606195  18.606195  \n",
-       "2016-01-11 17:20:00  28.642668  28.642668  \n",
-       "2016-01-11 17:30:00  45.410389  45.410389  \n",
-       "2016-01-11 17:40:00  10.084097  10.084097  \n",
-       "...                        ...        ...  \n",
-       "2016-05-27 17:20:00  43.096812  43.096812  \n",
-       "2016-05-27 17:30:00  49.282940  49.282940  \n",
-       "2016-05-27 17:40:00  29.199117  29.199117  \n",
-       "2016-05-27 17:50:00   6.322784   6.322784  \n",
-       "2016-05-27 18:00:00  34.118851  34.118851  \n",
-       "\n",
-       "[19735 rows x 29 columns]"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 864x216 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from ucimlr.helpers import download_file\n",
-    "# https://archive.ics.uci.edu/ml/datasets/Appliances+energy+prediction\n",
-    "url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00374/energydata_complete.csv'\n",
-    "filename = url.split('/')[-1]\n",
-    "download_file(url, root, filename)\n",
-    "\n",
-    "df = pd.read_csv(root +'/' +filename)\n",
-    "df.index = pd.to_datetime(df.date)\n",
-    "# df[:300].traffic_volume.plot()\n",
-    "df[['Appliances', 'lights']].head(1000).plot()\n",
-    "df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T06:24:08.074733Z",
-     "start_time": "2020-10-25T06:24:04.889219Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>pm2.5</th>\n",
-       "      <th>DEWP</th>\n",
-       "      <th>TEMP</th>\n",
-       "      <th>PRES</th>\n",
-       "      <th>cbwd</th>\n",
-       "      <th>Iws</th>\n",
-       "      <th>Is</th>\n",
-       "      <th>Ir</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2010-01-01 00:00:00+08:00</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>-21</td>\n",
-       "      <td>-11.0</td>\n",
-       "      <td>1021.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>1.79</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2010-01-01 01:00:00+08:00</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>-21</td>\n",
-       "      <td>-12.0</td>\n",
-       "      <td>1020.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>4.92</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2010-01-01 02:00:00+08:00</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>-21</td>\n",
-       "      <td>-11.0</td>\n",
-       "      <td>1019.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>6.71</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2010-01-01 03:00:00+08:00</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>-21</td>\n",
-       "      <td>-14.0</td>\n",
-       "      <td>1019.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>9.84</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2010-01-01 04:00:00+08:00</th>\n",
-       "      <td>NaN</td>\n",
-       "      <td>-20</td>\n",
-       "      <td>-12.0</td>\n",
-       "      <td>1018.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>12.97</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 19:00:00+08:00</th>\n",
-       "      <td>8.0</td>\n",
-       "      <td>-23</td>\n",
-       "      <td>-2.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>231.97</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 20:00:00+08:00</th>\n",
-       "      <td>10.0</td>\n",
-       "      <td>-22</td>\n",
-       "      <td>-3.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>237.78</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 21:00:00+08:00</th>\n",
-       "      <td>10.0</td>\n",
-       "      <td>-22</td>\n",
-       "      <td>-3.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>242.70</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 22:00:00+08:00</th>\n",
-       "      <td>8.0</td>\n",
-       "      <td>-22</td>\n",
-       "      <td>-4.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>246.72</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 23:00:00+08:00</th>\n",
-       "      <td>12.0</td>\n",
-       "      <td>-21</td>\n",
-       "      <td>-3.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>249.85</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>43824 rows × 8 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                           pm2.5  DEWP  TEMP    PRES cbwd     Iws  Is  Ir\n",
-       "2010-01-01 00:00:00+08:00    NaN   -21 -11.0  1021.0   NW    1.79   0   0\n",
-       "2010-01-01 01:00:00+08:00    NaN   -21 -12.0  1020.0   NW    4.92   0   0\n",
-       "2010-01-01 02:00:00+08:00    NaN   -21 -11.0  1019.0   NW    6.71   0   0\n",
-       "2010-01-01 03:00:00+08:00    NaN   -21 -14.0  1019.0   NW    9.84   0   0\n",
-       "2010-01-01 04:00:00+08:00    NaN   -20 -12.0  1018.0   NW   12.97   0   0\n",
-       "...                          ...   ...   ...     ...  ...     ...  ..  ..\n",
-       "2014-12-31 19:00:00+08:00    8.0   -23  -2.0  1034.0   NW  231.97   0   0\n",
-       "2014-12-31 20:00:00+08:00   10.0   -22  -3.0  1034.0   NW  237.78   0   0\n",
-       "2014-12-31 21:00:00+08:00   10.0   -22  -3.0  1034.0   NW  242.70   0   0\n",
-       "2014-12-31 22:00:00+08:00    8.0   -22  -4.0  1034.0   NW  246.72   0   0\n",
-       "2014-12-31 23:00:00+08:00   12.0   -21  -3.0  1034.0   NW  249.85   0   0\n",
-       "\n",
-       "[43824 rows x 8 columns]"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAswAAADlCAYAAABH7aHNAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAABqEklEQVR4nO2dd5hU1fnHv+fObO+FpSy9iSACugRBEctGo7EQNMSuiDGKhYC9oQQLxh+soihqEI0tlggajdEgCtEVXUCQKiy9b5nZXqbc8/vj3Dptd2dndmZn38/z8DAz986dMzv3nPOe93zf92Wccw6CIAiCIAiCIHwiRboBBEEQBEEQBBHNkMFMEARBEARBEAEgg5kgCIIgCIIgAkAGM0EQBEEQBEEEgAxmgiAIgiAIgggAGcwEQRAEQRAEEQAymAmCIAiCIAgiANaWTnjxxRexYcMGZGRkYMGCBQCAuro6FBUVoby8HN26dcOsWbOQmpoKAFi+fDlWrVoFSZIwbdo0jB49GgCwZ88eLF68GA6HA2PGjMG0adPAGGtVI48cORLk1yMIItrJzc1FRUVFpJtBEF0W6oMEIejVq5ffYy16mM866yw8+OCDptdWrFiBkSNHYtGiRRg5ciRWrFgBADh06BCKi4uxcOFCPPTQQ1i6dClkWQYAvPrqq/jTn/6ERYsW4dixY9i4cWPw34ggCIIgCIIgOogWDebhw4dr3mOVkpISTJo0CQAwadIklJSUaK9PmDABcXFxyMvLQ48ePVBaWgq73Y7GxkYMHToUjDGceeaZ2nsIgiAIgiAIIpppUZLhi+rqamRlZQEAsrKyUFNTAwCw2WwYMmSIdl52djZsNhssFgtycnK013NycmCz2fxef+XKlVi5ciUAYP78+cjNzQ2mmQRBdAKsViv1cYKIINQHCaJlgjKY/cE5b9Pr/igsLERhYaH2nLRVBBG7kH6SICIL9UGCELRLw+yLjIwM2O12AIDdbkd6ejoA4TmurKzUzrPZbMjOzvZ6vbKyEtnZ2cF8NEEQBNGByF//G3zPL5FuBkEQREQJymAuKCjA6tWrAQCrV6/G2LFjtdeLi4vhdDpRVlaGo0ePYvDgwcjKykJSUhJ27twJzjnWrFmDgoKC0H0LgiAIIizwd5aAb14X6WYQBEFElBYlGc8++yy2bduG2tpa3HLLLZg6dSomT56MoqIirFq1Crm5uZg9ezYAoE+fPhg/fjxmz54NSZIwffp0SJKwyW+66Sa8+OKLcDgcGD16NMaMGRPeb0YQBEGEiNalACUIgohVGG+rwDgCUB5mgohdSD8ZvXDOId98KdjFV0C65KpIN4cIE9QHCUIQcg0zQRAE0ZUgDzNBEF0bMpgJgiAI30T/BiRBEESHQAYzQRAE4QfFYGbkYSYIomtDBjNBEAThG9XBTPYyQRBdHDKYCYIgCN9wspgJgiAAMpgJgiAIv5AkgyAIAiCDmSAIgvAHxfwRBEEAIIOZIAiC8At5mAmCIAAymAmCIAh/cDKYCYIgADKYCYIgiBYhg5kgiK4NGcwEQRCEb0jDTBAEAYAMZoIgCMIvqiQjsq0gCIKINGQwEwRBEL4hDTNBEAQAMpgJgiAIv1DhEoIgCIAMZoIgCMIfZC8TBEEAIIOZIAiC8AeVxiYIggBABjNBEAThF9IwEwRBAGQwEwRBEP4gBzNBEAQAMpgJgiAIv5DFTBAEAZDBTBAEQRAEQRABIYOZIAiC8A3lYSYIggAAWNvz5k8//RSrVq0CYwx9+vTBjBkz4HA4UFRUhPLycnTr1g2zZs1CamoqAGD58uVYtWoVJEnCtGnTMHr06FB8B4IgCCIcaKWxyWAmCKJrE7SH2Waz4fPPP8f8+fOxYMECyLKM4uJirFixAiNHjsSiRYswcuRIrFixAgBw6NAhFBcXY+HChXjooYewdOlSyLIcqu9BEARBhBwqjU0QBAG0U5IhyzIcDgfcbjccDgeysrJQUlKCSZMmAQAmTZqEkpISAEBJSQkmTJiAuLg45OXloUePHigtLW3/NyAIgiDCA0kyCIIgALRDkpGdnY2LL74Yt956K+Lj4zFq1CiMGjUK1dXVyMrKAgBkZWWhpqYGgPBIDxkyxPR+m83WzuYTBEEQ4YOyZBAEQQDtMJjr6upQUlKCxYsXIzk5GQsXLsSaNWv8ns+1ilEts3LlSqxcuRIAMH/+fOTm5gbbTIIgohyr1Up9PEpxWxgqAKSmpSKZfqOYhfogQbRM0Abz5s2bkZeXh/T0dADAuHHjsHPnTmRkZMButyMrKwt2u107npOTg8rKSu39NpsN2dnZPq9dWFiIwsJC7XlFRUWwzSQIIsrJzc2lPh6l8CqxC1hXV48G+o1iFuqDRGeBH9oLvn8PpNPPDcv1e/Xq5fdY0Brm3Nxc7Nq1C83NzeCcY/PmzcjPz0dBQQFWr14NAFi9ejXGjh0LACgoKEBxcTGcTifKyspw9OhRDB48ONiPJwiCIMIOaZgJgoge5HmzwF9/rk2qhVARtId5yJAhOO2003DffffBYrGgf//+KCwsRFNTE4qKirBq1Srk5uZi9uzZAIA+ffpg/PjxmD17NiRJwvTp0yFJlAaaIAgi6iF7mSCIaEDNrtZQB6SkdehHtysP89SpUzF16lTTa3FxcZgzZ47P86dMmYIpU6a05yMJgiCIjqLjnTgEQRD+SU0H6mqAKnuHG8zk4iUIgiB8wylLBkEQUURahvi/xt7hH00GM0EQBOEH0jATBBFFWBVhhNvd4R9NBjNBEAThG5JkEAQRTXCvBx0GGcwEQRCEH8jDTBBEFBKBxTwZzARBEIRvqDQ2QRBRCXmYCYIgiGiBgv4IgohGIpCHmQxmgiAIIjBkLxMEEU2QJIMgCIKIPshiJggiGuAe/3ccZDATBEEQvonAtidBEESLkCSDIAiCiB4o6I8giPYjv78U7mcfDeEVyWAmCIIgogWK+SMIIhRU2YDKstBdjzTMBEEQRNRAWTIIgggFsoyQjiMkySAIgiCiB5JkEATRfjh4aMYRTkF/BEEQRLRBMX8EQYSCUI8lJMkgCIIgogfyMBMEEQpC5GE2Xq+DIYOZIAiC8A2VxiYIIhTwEBvMpGEmCIIgog8ymAmCaAccITWYI5EingxmgiAIwjekYSYIIhTwEGfJIEkGQRAEET2ISYkUGQRBtJuQ2stkMBMEQRDRAmmYCYIIBaRhJgiCIGIXKlxCEEQI4BydfRyxtufN9fX1WLJkCQ4ePAjGGG699Vb06tULRUVFKC8vR7du3TBr1iykpqYCAJYvX45Vq1ZBkiRMmzYNo0ePDsV3IAiCIMIB2csEQYSKTu5hbpfBvGzZMowePRp33XUXXC4XmpubsXz5cowcORKTJ0/GihUrsGLFClxzzTU4dOgQiouLsXDhQtjtdsybNw/PPfccJImc3ARBEFEJlcYmCCIUhMrA7YyV/hoaGrB9+3acc845AACr1YqUlBSUlJRg0qRJAIBJkyahpKQEAFBSUoIJEyYgLi4OeXl56NGjB0pLS0PwFQiCIIjwQBpmgiBCAQdC6SCNQAafoD3MZWVlSE9Px4svvoj9+/dj4MCBuOGGG1BdXY2srCwAQFZWFmpqagAANpsNQ4YM0d6fnZ0Nm83WzuYTBEEQYUOZlOTP3oc0aBhYemZEm0MQRCdFDrGF25kkGW63G3v37sWNN96IIUOGYNmyZVixYoXf83kbvtzKlSuxcuVKAMD8+fORm5sbbDMJgohyrFYr9fEoxVldARsA7C9FpgTE0e8Uk1AfJMKNPc4K7opDdjvvswqLBW4AaampSOrgezZogzknJwc5OTma1/i0007DihUrkJGRAbvdjqysLNjtdqSnp2vnV1ZWau+32WzIzs72ee3CwkIUFhZqzysqKoJtJkEQUU5ubi718SiFV1Vpj6vsdrBU+p1iEeqDRLhxOxyA293u+8ztcgEAamtrUR+Ge7ZXr15+jwUtKMnMzEROTg6OHDkCANi8eTN69+6NgoICrF69GgCwevVqjB07FgBQUFCA4uJiOJ1OlJWV4ejRoxg8eHCwH08QBEGEG+POYCRq0RIEQfikE0kyAODGG2/EokWL4HK5kJeXhxkzZoBzjqKiIqxatQq5ubmYPXs2AKBPnz4YP348Zs+eDUmSMH36dMqQQRAEEc1wv08IgiBaTwwULmmXwdy/f3/Mnz/f6/U5c+b4PH/KlCmYMmVKez6SIAiC6DC4z4cEQRBtIgYMZnLxEgRBEL4xTUpkMRMEESShNpgjABnMBEEQhG9Iw0wQREgIcWls8jATBEEQUQnZywRBBEvIPcxkMBMEQRDRAkkyCIIIBaEePiIwHJHBTBAEQfiBJBkEQYQCCvojCIIgugJkMBMEESwkySAIgiBiFrKRCYIIFaEwmNWFO0kyCIIgiKiBsmQQBBEKZBkhzZJBHmaCIAgieqCgP4IgQkRI7WUymAmCIIhogexlgiBCQcgr/YXuUq2FDGaCIAjCDyTJIAgiBPAQFy4hSQZBdAy8uSnSTSCI6IfyMBMEESpC4mFWg/7IYCaIsCOXfAv59qngh/ZGuikEEd2Ygv4i1wyCIDo5lFaOIDohW9cDAPi+0gg3hCA6E2QxEwQRJFwG9u0C37I+RNcLzWXaAhnMRNfDYhX/u92RbQdBdCZIw0wQRLBwADVVkN99NUTXIw8zQYQf1WB2uSLbDoKIdigPM0EQIUHVHsuhvV4HQgYz0fXQPMxkMBNEYMhIJggiBPAQBetxj/87EDKYia6HxSL+J0kGQQTGlCSDjGeCINpJyMYR8jATRPjRPMzOyLaDIKIdSitHEEQoUMcSOUSSDNIwE0Ro4Pt2gW/f5PsgeZgJopVQWjmCIEIAD7GGOQLjkbXjP5Igwo/8xF0AAMurn3gftJKGmSBaBUkyCIIIBaHSMOsXDNF1Wg95mImui5MMZoIIDEkyCIIIBSGSZITc8G497fYwy7KM+++/H9nZ2bj//vtRV1eHoqIilJeXo1u3bpg1axZSU1MBAMuXL8eqVasgSRKmTZuG0aNHt/fjCSIgnHMwz+pCsiLFaKzv+AYRRGeCKv0RBBEKtOwWIRpIOqOG+d///jfy8/O15ytWrMDIkSOxaNEijBw5EitWrAAAHDp0CMXFxVi4cCEeeughLF26FHKoxN9El4aXHQF3+gngczR7v+YW9x2vrw1jqwgiBuB+nxAEQbSeCHqGQ0W7DObKykps2LAB5557rvZaSUkJJk2aBACYNGkSSkpKtNcnTJiAuLg45OXloUePHigtpdLERPvgTQ2QH7oF/O/P66+5dOOZ//S995tU7XJtdbibRxCxQyee6AiCiDShDvrrZB7m119/Hddcc41py7u6uhpZWVkAgKysLNTU1AAAbDYbcnJytPOys7Nhs9na8/EEATQ1AYC5Pr1b75B8aZH3e1RJBhnMBNECJMkgCCIExEDQX9Aa5vXr1yMjIwMDBw7E1q1bWzyft+GPtHLlSqxcuRIAMH/+fOTm5gbbTCLGcbmaUQmAgWn3idxYj3LDOZ73T218PBoAsLpapO7YCOvgE2HtkQ8iMlitVurjUUpTWhrUZWV6ehoS6HeKSagPEuGmQpLgBsC495zcputYxHWSk5KR2sH3bNAG8y+//IJ169bhp59+gsPhQGNjIxYtWoSMjAzY7XZkZWXBbrcjPT0dAJCTk4PKykrt/TabDdnZ2T6vXVhYiMLCQu15RUVFsM0kYhx+7Kj4X5a1+4Q31JnOKd+yEaxHb+25XFennVe9YA6QmgZL0dsd1GLCk9zcXOrjUQqv0Xdhaqqrweh3ikmoDxLhxu0SUkje1IDy7VvAuvUI7jpK/YSG+no0heGe7dWrl99jQUsyrrrqKixZsgSLFy/Gn//8Z5x00km48847UVBQgNWrVwMAVq9ejbFjxwIACgoKUFxcDKfTibKyMhw9ehSDBw8O9uMJQtAsJBmmbR6PYFK5aI75PbJHwZI6Cv4jCJ9Q0B9BECFGfvDmEFylE0ky/DF58mQUFRVh1apVyM3NxezZswEAffr0wfjx4zF79mxIkoTp06dDkigNNNFO1CwYxkACT4O4vg68rgZITAazWqnCH0G0FkorFzZ4fS1QZQPL7xfpphBE+Al1OrnOWulvxIgRGDFiBAAgLS0Nc+bM8XnelClTMGXKlFB8JEEINA+z4TXPdIVchjzrGrDx54Dd+GcymAmi1RgNZrKYQ4k8dyZgr/BdjZQgYg7z+OGzRkI7rtcRkIuX6NRwLc+yf0kGHA5xxrpvleNkMBNEqyBJRviwk2aY6EJ4Dh/KvNxm1Pm9s6WVI4iIo3qYLYbNEqVDsV+JfOBQtzzj4gEAvLFBewwASEoJdysJopNCkoxww2nHi+gKeOZfbm+l3QiMR2QwE50b1cNs9TaYcdIpQL/BQE2VeB6vGMlVNsCYRq5d20LRC+e8TekcCcITbtqtoXspLDh9VCMliFjDc/hobAjyOlqN7fa0JijIYCY6N6qH2WQwKx4bSQISEvQCJVU2uBf9Bai2m9LMaZX/YgjudEK++VLwT96NdFOIzoyh5DyXyWAOC8FuTRNEp8Jj/HA0te86JMkgiDbSrHpnDF5i1SsmSUB8ovn8zeuExzmvp/6aK/YMZnUw4v9dEdl2EJ0bQ5l58jCHDm78uzrIw0x0ATwNXM9Yo1Zfx+tBh0EGM9G5UVepRh2gqmGWJCA+wfs9XAYysyHNmgs28TzA7Yo96YJT8VqZDB6CaCPG+yfW+kgkMRrJTvIwE12AkBnMatBf+5oTDGQwE50SXlMF+YvluiTDKKvQPMwWMF8GMwCWmQ02fAyQ3U15f4wF3qhb6bH2vYiOxbj7QgZz6Gg2GMzkYY55uNMBTtmZzLTXwxyB8SjkhUsIoiOQ33wR2LhWf8FoGHKDJCPBt8GMjBzxv6p9drvNOujODukiiVBAOxQhR377JfBvPtdfoL4a88gzLgc77Wyw6bMi3ZTIESoPMyjojyDaRnOj+bnbMLG7DUF/fjzMyO8r/tcM5hgzDCjynggFJMkIKbymymwsA0BTo++TiZiCr/060k2ILF4Gc5Aed5kkGQTRNjwNYR8aZjA/BvPw0bpUw2LwMMcShuwG8tKiCDaE6NSYAmKjz2DmjQ3gO7dGuhmthn/0hvdrtVUd3xCiwyAphoKnweyZl7m1aJ5p8jATROvwlE+43XrgntqhLBYgwZAlY/hoSA8tgGXWX/TXVIM51jJlGDzMXd6zQQSPycMcuWb4Q178BORnHgBvDjZFVcfCN/0IVnCG+UU17SURm8Ta3BI0oQ76I4OZIFoFS071flEN/DNqmFVPct+BsMz6C1j/Ieb3aAZzrEkyYuz7EJEh2iUZe3eK/4OcfLnbDX7sUAgb5HF9zsF/LgGvqhRFYOrrgO69IM2eBzb5GlFMSS2sRMQmZDALOMSur0qwBjNJMrouvNruUU2LaBVGgzA9U/yvyip8STKYn1vdGpuSDE6BREQoiHJJht7ng+u//LP3IT8yA/zY4RA2ysDWnyA/Pw/8X+8BTQ1i0ZGcCnbiKEi/nQqkpgO1NeH5bCI6UO/RGK0o23q4cGKptNdgJklG14LbyiHffT34Z+9HuikRg1cch/zVv3wfO7DbnODfeKy5EejZB9Kji8DO+514UfUwtyboT4FZLOb3xgoU9NdpkJc8DTlaKzJGuSTDq8+3Eb6/VDwIk5eZb98kHtTXAg314nGKYXcsMVmMZV0YXn4MXP3bxCJqQLnUxc0tzgFLKD3MZDB3LeyVAAC+ZX2EGxI55MVPgv/jVfBqu+l1Xn4M8rxZkBf9xfcbmxqBpGSw3v3FtiagT5pc1zCzzGzx2F/demuMapg7iaaTAPj678D/FZ0GM29uBqxx6rOItsUTUzBVkB5mphivvL42FE3ygu/cIv53u4GGOvGZSSn6CUnJprFJfmcJ5C4Uc8CbmyA/eDPkF5+MdFPCh+Zh7uLmFucwVeQNNugvgtKwLv4LRhj1humkWzWcc8hrvwFvj7FZp2xHekSKa56Z7ZvAfWn87BVAlpJLWfUSq+0wlsbOyTN/jifMYn5PrKCmqjpxFABlwiaiDnntN5FuQmD27AD6DBCPo03DvOcX/bE7yP6bkib+D4PBzDkHDu0TT5oagLpa82cCQGKS1le5ywX+9b/Bu0hWG35wL+Tbp4onysIiJlHnJfIwmxa2QUtRycPcRZGVH1xZefKmRvBNJbqxGO2s/w586ULwzz8M/hqqh7fKZn5d8b57PYYyEdnKwVRjWEsN52EwMwnIFEY1GzfJ9+erg1ispf5pagQkCWzEKeI5STSiEr50of54764ItsQb7nICVTawaDWY4w0ZcILtv6r3vDkM/aOhTpe0NDaAq+OYutAHwBINHubyo9rrsb7AlT97H/Jn7+kv9OgducaEG9VgVh07MQivrwWvLBePZTf45vXgB/Z4nmVe2AZhMHPOI5olI4ZKm3VC1B9cEh5m+fXngPXF4qW/LgMzDKzRCFe2GGGvCP4iirHLq6tg8rMbPc7VNgCD9OcN9aI6lqeH2TPoT5LArFZIi/7hv+KfajAHuz0UrTQ1Cu+VquF2NAOJyZFtE2HC08PCd2wCGzDEz9kRQJX1hPm+kb/6F3jxV7A88mzb3mg0QII1MFVDOxw64iqDzKy5EbALgwJZufrrScnC+wwABlmafMvvYHn1k9C3qYOQP30PfMfPsNz9hNcx7nKCr3hLf2HwiUDZUa/zYgbVkSPFrsEsLy0CNq+DdPsj4A114K+JXRLp+X+IRSEgFF28fQazeZ4mD3PXghs8oQBwcK9+rDMEgkghkDOoE5ZHtSteWw0kJInHnt5n1VBPUoJnLIqXSFnJc6MkAwBLSgbzN1hpHuYYN5jD4UEj2oenDODQ/si0wx9NqsEs+mG4PDr8H68CB/aAt7Xinbv9GmY4lWwy1XY9j3uoqFbGrR75QH0d+P49QHYuWFycfk5yij6eqf8rhLw9HQj/+G3gl83gTT5iR8qP64+79QDrOyj20noacce2JIMfOwRsXice79gEHD2oHZPvuAJ804/KiSHIwywbrkFp5boYnl4R4w3lL0gtmgilnMFzYK2tFhMNoP0teMVx8PJj2nOWJFauXpkuZEOWjJaIUYOZNzUCCUlgyUqAUWMMR6F3Vjy0+fzwvog0wy+qAasazOGeoTykVy1i8lYFazALQ42v/Qb82/8Gdw0/8BrhMWaDhonxbONasFHjzCelZQAOB3hzk3emiFiQZfiSGVUaDObkVOF4ibHx10SsG8xq0gKLBdxW7tWP5X+8qp5pfmMwfZY8zF0Yl/90M/KTd0P+cU0HN6iNqF7bYANuAH1S8Mzq0NgAZGaLgEjFmJYf+CPkB2/WFxOKwexV3lr1zickoUVYbBrMaKwXf5+0dPGccr1GHfLT9+tPevYBjh2OrpzszR4Gc7jnp7ZKu4wGZbDGpTFfeen24K7hD1ViMfQk/bUhI8znpGWI/2uq9LRzJ4wU/zs7Zy51o2ecb9ngfdw4Fu0vFfNfDMWQ8GOHwZWAVO5ygh9X5CYxlCWD790F95zbwOtqwN9bKl48cTSwfzf4oX1CdqTe9916KG/yvEgwHmb9Pfybz8F/Lmn7NdpB0L9gRUUF5s6di1mzZmH27Nn497//DQCoq6vDvHnzcOedd2LevHmoq9O3mZYvX4477rgDM2fOxMaNG9vd+E6PajD7yZLB/eQnjhpUz257BjuHYih7bsc2NYr0S4nJ3t521Vuqek+14iPK31ONRk9NQ4toGubOu/3pk4Z6EY2fKgxmTuV3ow/lPpYefQ5s4nnCE+VrCztSNIdfksGNUqG27qrJ7TeYuUs3SnnxV5A/eSeo6/ikyg4kJAqvstUK9OgNdvJY0ylMNZjrasT9wBjYKePFa53UYDbKCfm6b72PGzMWDTxB5OaNpoViO5GX/x3ya8+Kxy8+Bf76c+JAGIP+eH0d3PNmhbVqpenzvvgIOHoQfNWn2mtS4SVAZRlwaC/YiDGw3PMkcOoEkemqvta71kFQkgzze+Tn5wXT/KAJ2mC2WCy49tprUVRUhCeeeAJffPEFDh06hBUrVmDkyJFYtGgRRo4ciRUrVgAADh06hOLiYixcuBAPPfQQli5dCjmGOkkw8ONHxAN/aeWifMBUdcG8PQazOmF6epibGoCkJCXtUoPJK8HViVUNJvAM+quvBeITwOLiW/589W8fa/difa3IMatNyGQwRxMmfWp2N72YRV148gEHhWL4sHBKMgw6bu5oo87eHQJJhhLZr7XhX/8I7jq+qLYB6ZlgKamQFr4Fae4LYJ7Bx2qKubpa4OghkdVHjTvorOXt6xWHRmKSly4bgDCYLRZIc1+AdOcckdqzPbuU0UZluS63UrS9APQdhDDAfy4BDuwG//S9lk8OBdkicJVvEh5edvWtYCPGiIU/IHbMADDFYSPPusb7Gu0O+ut4gjaYs7KyMHDgQABAUlIS8vPzYbPZUFJSgkmTRAqvSZMmoaRE/EFLSkowYcIExMXFIS8vDz169EBpaWkIvkLnhS9/UzzwJQvIzDFvF0Yjqnc2WO+O7NYWBcaAH8450NgoDOLEJPDvvoI829DhVA+F6kH2TCtXV2vOdRrwO8ReHmbudgMVx4U+UC2SUE8a5qjC6E1NSgFLUSaW+fdGTbCX5v1NUNK3haNZRm9jWw1mk4fZd//lnEP+/J8+i4Hw+lohCTjpVGD4mLZ9divg1XYgQxROEoHHPqbbBD2LDd+7E2zIcEBd6HfWVJCqkZzbHWhq9Hao1FYDqelgvfqCpaQJDzOXo+a+bzdVlUBjPbjTIebIwcPF60NHBH5fe/B0GoUbtd8e2A0AYCNE/2FTrgO7fBrY2b8Vx9WUeupv22+wfo0QeJg7mpCIasrKyrB3714MHjwY1dXVyMrKAiCM6poa8Ye12WzIydHTpGVnZ8Nms/m8XlfAVIxD9XKqE0bfQeIGdDSL3MzRtE1rRHWMB3sTGydIY1YQl1MYv0nJuk7ZSFWlmFSSFa+c1axh5rXVrZNjAAZJRgxp6Iq/Ev9XlolJOiHJW/JCdBicc/CdW8wGgeJZZVfeDMaYfr/WVkfPQlmd7LSdmjBIMvYbnCZtNRDlVniYK46Df/QG+NIi8Moy8zHFm8/GToR0yZV6m0I1KdsrwDKyAp+j5JLmjmaxy5aSqmfR6LQeZmXXQM2T3+iRAamuRpOKAYgppwV3u3Xv8tGDgCyDjTsTyO8XVkkGU9OzesoewgSvrtI/+5yLwBSdMktNh3T+77R7mF18pel9rH/nNpjbnYe5qakJCxYswA033IDkZP/5Otuyely5ciVWrlwJAJg/fz5yc3NbeEfno+q1hVCnh4TERGTm5qIyJw+u2mrkPvg06j9+F01OB/g908CbGtB9eXFE2+uLppRUVAOIt1qQFcRv5LZXQg3ziXO7kK1cQ66yoRxAak43NKdnwNN8iG+ogyunG3K7dQMAOGsqYQOQlpyExNxcVFSWwdpvEDJb0SZnrV28NyUViTFyn9UzoA5AxvmXIjE3F+UpKYiHjIwo/X5Wq7VT9nHhQbLoWVr80FS8CtXPPIz02x5EUuFFAABnVTlsANL7D0Jibi7kuBFQxQHZCXGwRMHfoyEhHrUAMrvlwQYgNSUFySFuV/WhvWhOSgZvbECK1YqUNly/OTUFVcrjVLgh7d+JhFMnmM5x1ldDdcukNzcgwXB9p60MNgAZPfORMPZ01N84E3WvPYechDhILRm6LbXt53WoKj+GpDPPQ1qA7+SWgAoAqXFW1DodSErPRHxON1QByExJRlwH3Qeh7INNFgnVAJJ690Pjph+RnZRgup9tzY1AVo423tenpaEOQG52VutkdFGMu6IMFYqtk1pVgRoA6X0HoD4uDpa4uFbNScHQlJGhzMXWoObitlLZUAfplPFIuew6xJ14slj0+yI3F5X9h8C1bxfAGLrdei8aBgxG3esvICUpqU39HdD7i/kjOm6sbJfB7HK5sGDBAkycOBHjxol0ORkZGbDb7cjKyoLdbkd6ulhJ5uTkoLJSTzdis9mQnZ3t87qFhYUoLCzUnldUtKMwRpQiO/WVoAMMFRUVcDfUg42dCLslHrIsgzc3aZKFaPwbqKtMR1NTUO3j5ce0x87aGu0avExou+vcMrjF+xZtPnwAyMjWz68VW4A1P3yL2v7DIB8/DHnUr1rVJq7sgNRWV6EuCv/GwSAr8ovaPoNQV1EBOT4BzVX2qLyHADHgRWvbAuH+4yXAqRNgueV+v+fwGjvkZx4GANTuLUV9RQX44f2aZ7VW5vp9128wsL8UtkP7wSBpTga/k1GYkZXCG1X1YoerrrYODSH+ndzbfxZb1ls3oN5uR2Mbrs/teqGPmiXPAA31kB5dBNa7v37OYT0IqnrndrDs7uA/rAbr2Rv8yAHxXrcbrKICPC0TAFCx8jNIk37Tvu/10VtARjaazrwAzQG+kxqPUVdZATia0eh2o0nxyFaVl4Fld29XO1pLKPugfEyM302KF9l2+BCYpOeedtsqwfL7aZ8nK/m+K8rKwBIS0Znhe/Q0erU7RLnvWskK2e2GK8h5sjXISl9wNDZ0yFjqtpWD9RmAmrx8wGDX+Tw3XlkEJSSisrYOfOwk4PUXUF9X26b+DkCvlmkg1N+3V69efo8FLcngnGPJkiXIz8/HRRddpL1eUFCA1atXAwBWr16NsWPHaq8XFxfD6XSirKwMR48exeDBg31eu9VtkGW4H7kV8g+r23WdiJCpLBZ69tHLoDY36RHp8QlRH/SntTtY3ZQa6Bcfbw76UyYMlpSkVwkycmAPWH4//bm6HfX1Z8CmH0R71FQ2LaFIMqIqnVd7UaUucYo+MjE5emU9nZ31gXd+uDE1pCI7kh+7A3yZEjlv0NpLl98gHtTXgTfUQZ51DeR7b2xfUG17ULP4aIU2QivJ4I0NwLFDYAOGivGuPRpmJaCK795hPseYf/z4EfAvloO/9SLkV/8P/O0l4nW1ANKJo8X/xiqjQcBrqoDtG8HGnKbnQfeHGuCn6n7j4nUJTGfIxa/AXU7IP64Rizzlu7Bcxdj3zAFfV6OnuwRiK7VnlW7QaUH9KWlCdhJOjbYqZ+oADTOX3SJNaXpm696glrBXZYHtqX3QWSUZv/zyC9asWYO+ffvinnvuAQBceeWVmDx5MoqKirBq1Srk5uZi9uzZAIA+ffpg/PjxmD17NiRJwvTp0yG1N5F3fa3IXfrG88C4SdrL3FYOpGVE9/ZOc5MICLFY9WA1R5MeYBNvjqbmLheYtV0bAqFHjVgNVjelGslpmWaNbZMhC4YvDbPbBRi8SEZtGN+1DYBhsG6JWBqsVZzNgNWqSwUSScMcMY4eFv9breC/bAav98gaYAxOVTX5yrimaUHrals/OYUSVUOrjqOhnvD37QI4BxswBDwog9lHn/VIn6gVA4lPEDtX6t/UWD1UifhnFosYD5xBjmcqO7cADgfY+LNbPJVZLCIGQw2iio8HevQGEpLAN/0INnpc4AtEAF9zEV/xFvgXy8FS04D6OjEmZyoxS4bsEFx2i+NGDXMo0pNGCdxuuK/UHdTkVBGnFFaDWemrHTGP2SrE3J/dOimEdMavIW9ZD3bB5coL7TGYI3uPBG2BDRs2DO+//77PY3PmzPH5+pQpUzBlypRgP9IbtfSoYlzyajtQcRzy/HuBwcMh3TlHqwYXdTQ1CuPYYgHcbrEybzIYzJ5FN+qq9QEoWlBv+LKjwb1fnSAzssxlwVXjLilZTx3nATMZzPptzA8r5YVbazDHYqU/h0P3LgNiwFa2n4nQ0JLXl9fXAdU28MrjQL/BYL86E/yD18Df+5v5RNVIBoSxBIA7nWDG7BG11ZExmF1O0T+0svIh9jArxR0QpIeZ+/KmGf9ugG6s5fcTRnJdjZjobWIbl113u3mOiLMCrvbt7HGbokZXK5W2RHyCCIQDgLgEkQ5y6Aj97xNFyF9/Bv7Oy5AW/B3McE/yQ/vEA6dLGMSGDD28sUGLD0d9vTC2TEF/MTQGV1UqhVhkvUR0UpIwmMNp7Km70R2RJeOwmEtYr76tOp2dOgGWVz8xvNCO37uzppWLCqrMBrO84GFhLANA6TbIz/8lQg1rGa7KL6xWMTE5HeJmUAxlVnC6+Q3HgzRKw4l6w9dWa3rANqF6mNMzAadDmwBNeZaT/FTrM3ZWqyHoau9OMWBld2tdG1R9aKykNAKE4WHYoWDZuYCtHHzrT/rEHGNwpxPuv8wE3/Fzx3xgC15Ief69kB+9Hdj6E5DTDewEUfWKf79KPykpxeypsyrSB5fT/DtFquiM0yHapFo7Iewi3OkEL14lMgKlpAFx8W3Pw+xrwvW8vxsVeUBeT5G9oNoGNma8dpj1G2Q+3xrX/uwUtgoxtie1IMdQSUrRDHjVm8969wOOHQq7VIw7nXDPnQnH5vWtO/+dl8WDGrv5gEE+wuuqxc6JuhAxSjK0lKA+smR08lLgvPwY+OZ1wrFlmJ+YZBFzUlg9zKrBHP4sGbxckZp07x3U+xljwmjuhJKMTm0wayUnk1OERlNd0ako2/NRSVMjkJioa5VVr6qSl5OlZUC663HNs9RRFXzahLFMpZKPsS1wxWBm6UpEuppaTi2ykZgEZjB82WXX64+NwSEWPaAETY1AdrcWMxdoSLGzHajhaNa8lQCAnG6Aoxnys49CnnVNbOqZjx8GDu6F/O4rHfN57haMKkN/ZUNPAlIzvM/xXAyqxrPLZSplziNV1tzlVAy4MCwqS7cBZUfAzlHytbZXw6zgtSBsqBdOiIxs4f1zu4E+A/Tjnl4ya5yu3QbAjx6C+6l7wLdvanWz+C9bgG49Wh+s2bu/kKcAemGT9Ewxvnrqf0PN0YPAob2oXfps297nadwqvx1vahDGf3Y3fcFg1GIrvw9L8+Vh7txjsPzgzcDh/UBuHqQ/3Ws+GHZJRscZzKisEP21talbfSFJwaVyjbBjq1MbzGrSbMQngK/+wvu4jwwLUUNzkxjIExLFYyV3o3Gbiw07GdLTSp32aCxtbFztGfIythp1glQXBeu+g/v+m8A/e19sZ6ZlAINOFOckJUP6zWWQbrkf7Ka7zNeJizM/b23AH2DIwxwD24EK3Okwe5iHjTKfsGt7B7fIN7y2GnzbxtBcTJ0wrHGBzwsVLv8Tk8kr2HsA2NkX6pX8AK0Klu66VTB4mE2ac1eE8vG6XIqHOXgXM3c6IX/6nrgnja8r0e5siFLMISFEGmZPrX5DHZCcYgoyYyNO0fo987xf4uLNBnPpNmDPL5A//7BVTeJb1gOH9moFS1qDKYBZ1YurC6wQjfucc/D1xfrunYpikDPj/dkaPO9/1fHQ3AjYysFyuolcvAlJolyyivp9YiwPs7GuAuvWA6xXX0gzHwO77nbxohSkR7W1qL9rU1Pg80IAt5UD2bnty95jtQa3o9BZg/6iAa5qZxvrNY+O9JcXAYsF8lsvAjs2g8uy7wpLkaa5ESyhByBJYitSTZeSZRbSM2uc8BZGY8S00cg0FmJpLaokIyNTXO7Nxdoh6bo7xO+WlSNW64oByE6d4GlmgMUngE2dDv6+WFywEae0vg2xpJ9TaWzQtfDw0HtD6A3ZyFM7uFHeyE/fDxw/DH76We2/mBrM1VGBsYGMWFXDCkC6ax6YZAE3/h79BoMfPegV2GsymI0e7Eh53pwO8fdshySDr/oX+Mdvi1L1503WD9gVCUKWEpcRn9D2suCeE25GlpfBzBvqFYPZ4OFPz4D0zOu+vVXWOLMxqI672zeBlx0By/OfcgoA+A8iK4qW8aQ1qAU+AKC70D2ztAzx564sF0GAbYD/sgUYdIJ5MbCvFPKS+WAFZ4AZvZ9KEKqUkoY2jYDK/c+bGsG//1pfVFXZxVygfqcRo02LYm0HwLjjYun8Hmb5zRf1J0qsETvpFH2uYmGWZKjzb3P4DWbYK1ovefSHxRrQ6eAXkmS0A3XQbWwA37cLGD4GrGdvsLyeYCMLhEEXoe1nvucXyMWr/GtGmxQNc0Ii0NwM7jmBGElKDf/WXDCoN29CUrsMZuYroOmEkdpDVnAG2MljA15K+vWl+kD160tb34ZYNJgry0xSFkAJbrr4SjFQNdb5eWMHc1xkkOAhyOCh9bMo8DDjqLJ4v3c+mOJJM3pj2MRfAyMLIN32oPl9RkmG8foR0nZyp8MsyQjGYlY9ip4pMu0Vojyy6lENhSTDM9sOICQZSSna7wAITSlLz/Rdhc9qBTdqmI3a3N2Bg/D4scPgG74DO+1ss9e4BViuwWDO62n6X371/8ztaQF+cC/k/3sQ/MPXza9v+0n8f2iv+XW14mRKy9vr3JDtQr0/+Rcfgb+zRJQYB8D3ir+R+v1Zj95AZZn2+di1Vfxv3M4PQ6Yizjnk//wT8t9f6Ji0jOWGGCNtB8kAY2GdY7jazzoiG5Kt3Gt+aTPWyBvM3OmEvHShqR5ES3RaDzOX3brBXG0Hqu1gF/5KP0EdANSI3Q5Gfkqk2uMApJeXC+G/kWZDRgxHs7bSR0o6vEhKBm+IEiPHiHrzpqQEZ/Q4msVg6eM7t5i/1AfSY88DblfbdhRizGDmslt4pU4xVzyTJp4HAHCv/CR6Si8r8IZ6gLVzKKpUvLrtKHwgF38FNmSEVuY1IAG0gvyoEgDb0+wZZNfeBr55PTBkBCxDT/J+oyohcznNRnKkgqFqlRLG7QmMVSdFj4UMt1eanAMsPsFLttEinoZQRiZQ5VHEoLFeLKRTfYyrvvDQMJvzOB/2+zb3nVcI4zo+AcxQZrtVDB0pygsPH60trFi3HmBTrgf/6A1g+0agBYeBRrUIxlODsHltDfiW9eArPxbHPfu+KgVMacV4a4wRUv9Gnvfmlg3i/35KjQXlnpaLHgW75Crwtd+IzzNKxiwWsRRzh3AMPnYY/J9viOsXnA4MHxO6a/vCGgcMHg52yniwsWd4H2csvLI/zcPcCM552IodcadT3GMhMZiDkJqF8m/4y2bwtd+A11TBMqt1CSI6r4fZ7Qabch1wkr79bqxTrq2Y69u4zRcOPDwEIoVco/DMxieI/MtNjcJ4NAZrqSSnRKckQzUyk1L0gL220NwktIuJ5uAnacaDft4QGJaS6ttbHfBNsWUwo75eGHOZfjSUCQkds23XBkyeq2CvcWBP+97vdIAvew7yk3e37g2BvH57dgKZOSavJgBIZ54Py20P+p3MGGN6lgaXK/L5aWvsihdWNZiDuIY6KXpOjvYKs/wsGA+zh4HF0jO9ZR0N9WDJqWZJRiDiPAzmhnqRhi4lTS8u4gFvbtLH574DW7fgMrbbaoV05c1go35lfv3sCwHG2hZQrS5qlHFNnn0N+GtF+t+l2mb2uCqeScZaNgVM8Qb+flcAGDIcTF0MGbz4/JN3xAMPiZgeRxLC+9xYQOT7r0N3XX801oNl50L69aXezjGg4yQZQHhjHtS/aytzMPullZIMXlUJ9/PzwNUsMj7maR7s31Vifq/p9y3BfVLkYXHxkM6fYt6qP8HgtVGDGNqqiwsBXltAnjeGmkIuUTGY3W6goVZkhfA1maZn6hrnaEK90ZJTgtsKcjQLj6BR3znxPLAxp4Woga0g1oL+VI+Yv5RW8YlRZzDLoVgMqoFFhu/GZTfkd5aAH9zr500GapQtzboa72pxvvDjYeacg2/fCHZSG3T0RqxKISO3U9c4d0Tkuy+q7cLg0YakICYmdTHkaWzaK3SjCghSkuHRZ5W+LH/1L/PnJ6eICX74GEgBypgD8M6S0VAn+lJKqr4L6InB88yMeuR2whKThCdPrRjXGtRxzNcuW498MdeUGoJ+FUOLt2Bk8X27dIMXongJAJ/B3uxXZ+qPJ/7adEy67UFYHl1kfoOWVi6E2+2qATn0JPB13+pV99p73boaUe/Bk8YG30W2VMKQVo5zDvfcmXD/8RKx8FE/P5w7iEp8RvslGXHgLWUaAsD/91/g5xKx0wJofZ5ddYu+ixHs+Cgrv0cbfpdOazBrqIZB34HCk6CieJi5wcMsf7EcfO/OkHws374J/LCf3MOeHjPPwUid1BMTNe8qV3N3+oD17i+2mJrbOKGEG3VhkJQSnBHW3CQmykzdC8EmXx2ixrWSGJNkqJ4uluxn8I5PaHu+2zDTkoeZu92+Jyn1ePkxTUNpWrgd2AP+9b8hL37Cu8Ke5zU2r9Mey88+2nKj/XmY7ZWi//cd5Pt4S6gGm9ttMJjDqH08fADuoke97gleXyvupexu7ZJkaIaLIdsDdzQLR4bRwxwX36LBzF0uyB8u06+pjKvSX14Eu3wa2NkiRR3//ENwWRbZShobgOQUMGscLLPmgp06wc/VFTzzMKsBTsmpfmVx8rxZ+pNQF5hJTNLSb/rD5GFT55qyo+aF4sgCSLc8IM437Mao2lceKOuL263tvLCxE02fwx3ebdPOgZKDWIlHYWf8Gmy0D2dIkGOw9hv7QilqJl18BeBygf+yuU3X9of85N2Q777e26vZWB8473aINMz8yAFwNQf27h0iI4uKasQ6wze+c1X61kEaZvV309I6KuM46zPAcC8GW2lYmSvasIPX6Q1mNlykzGLjzjIfUD3MyiDHa6rAP1wGuch3FcK2Ii98BPJjt/s+6Bno5/mDajmXE/XgkJ1b/BvMfQYIz8GR/e1ocRhQV3tBeJj5lvXgP64BLFYwYzU/X/lqw0msSTLUSd3f4B1M+q4wYJxweAsBrfzT98QkZSxnbEB+6yX9ieE+VMuko7IM8nOP+b++0wH+tu9r+MWfh3mHGNhZ34EtX8MXRkmGajCHUZIhv/sysO0ns9cR0Kt55fdFu/Iwqx5M44JH3db1NJjdbt/V+1Q2/QD+xXLd2+R0iPGjZ29I5/8OrN9gkcar2g6+vlj8jlxufQERKF5do7ysUqRIQ0oqUGWDXPI/7d6Vv/pUr3Cnvr/Ah361PcTFewdMGnDPnWm6tzWnStkRyH+ZKdp05m9guXOOXnnQuED1WHz4gv/zdfHbj/qVngtfndMMbWPjz4ZU9JZ3AGHFcfF/v8HwSRC58HllOeQ/TYb8p8k+ixXxPb8I7braD0MVDKcGiKnfCRCSGZfLnO3EE0kKyS6m/OjtkB+ZIT7XmK4P0D8/nB7mQMkJ2oI1rkXPMJdlQK12WVsNvncX5NefFX/LPgP0IOkgPcxa3FVX8jCz9CxIL3zgnRnBoGHmtgqRKB8QGTXWF7frM1uqvqTe0Bqeg5Ga+zIpxdyh/RjM6CPO4Qfbp9MMJe7n5+lbdEnJQFMj5A9eg/ztf0WGkI/fCfh++bm54oGaDvCORyDN+kvHpwCMNUlGQ0uSjI7TMPPmZiGJ8FV4wzDIyS15mJWiDvLLT/uOaDZOtMp3k197VkszCEBUgDRes7FBz6yhek1UAkx8/PB+8J9LfOpZub0S/IvlQsYw8IQA3ygAiiSDGw3mcEoyVAPVI2c9tymTcbeeXumi24RqkBklZWoOZpMkQ4ndCGS4qbIZ1cByOr1ysLMBQ8W5r/xVlye1JYA4KVnrQ9zpEDEwmTlgmTnAoX3grzwDbPwB3FYO/o9XIM+9U7wvvx+kF94HC/Z390d8vJcBxJubIK/8RPSrQ3uBrT/pC1BffbufmD+YxSLmGKMESvUw+9gx4U4H3H+aDP7fj4GBJ0D64z26fE79nQzv4+XHvXT7AMBGiIA7durpXscAGLT6rR+DuZptAwBfY67BwGU3sH0T2IjRWuXckI95hp1rvl0Y7AF3LxjTJQAe8OZmUx5nf2h2R0O92O3wMJiZmp2jrcGzrYBvXgf3fdPFWJyWYQraDIrWaJirbOK79OwDcA75ybvEzlT/IaJwmTpmBVuZU+0HbbjvOm2WDCNadSTjaxaLGPyqbJDvu9F0TP7qE1ha2poLRFsDCT1vjEZlZZOULDJ4JCheDX8Gc253YQC1IrCJcw7+5mKwU0/XBqpQw2UZ+LlEfyEpBWioA/9yhTiunnfBZT47Fj/mHW3eUtq4sBFDkgxeVQl5yXzxxF8hgoTE4FIABsPmEvCv/y0CrzyLzRi83IEkGVyWgS1K2d7S7ZAf+hMsr4iIf+50gv/9eX2COGEksE9Jb6WUoGbjzwZS0sHX/Md0XfnR2wF7BSyvfgLY9ImHFV4K/r8vvdtx+ACQkwv5sTvEeRdfYW6jcZzJakdS/7h4cIdDGMnWOLEDEkZJhmaMe7a3wWhsBudh5i6nPlZW67sDWgCP0cNsVQxmh8N/phP1WqozxNmsF/pQUXfs4uK179CmjDtJhgBrLXNRmhinv1sp2l+63WsXkY04xVx9NFTExXtpp/kXy8H/9a7ufQPE4iA51WQYSvc9LdLTGY3YpBQtrSSX3fr38LFQ4d/+VxsXpXueArNawdXAPKOHedAwYPcOsNG/8roGALArbgabcr3/4ijBVPo7dkjcs30Gehubh/aJ337YKGEHxMeHxMPMDfnVTV76Q/vEoipQYGkAD7O8+HFg+yZIr3wceNwwLNL520uEVCcnTzec1Xu/jR5mueRb8C8+gjT1RmDAUD3Vo/Gcj98R+mVbuf+dgrbQmiwZSmwAGzhU5K1XkK4XY7C2WDY4FDjn4D+sBis43bsokSdqyuE2ZCHq9B7mgCSnmrSJAIDeA7TtRr57h99t3oAYthcDbSGyK/4oHvjxMCMpWXQQJeKUpWX6vg5jQJ8BXpkA+IHdcP/xEriNHu26GvD/fQn52UdbtWoNirpq83N/OTz96E75ViUnZ+/+YH+4KYQNazvqAMX/+3FE2xESUtKAvF5iQPOjMWNJyR2WcUX1iGgFhowYBnWjJIMfPWTewfHMEKBuh3/3FeQZl4k0Vbt3iFLEQ0aItEqG97Px5whdqaPZrAVVthbd8/6sLeCkW+4X+WGbGyF/87kpUEh+7HbIc3QJFv/XP/RrNdabDXJ12zIYklPE+OB2iUnFYgmvh1n9W3l6pdR7JCk5+Ep/qkc4J094xVS5gK9tXdXD7Mc7xjevA1/3rXKusgh3Or0MZsaYyDfucuoLwzZIMpCcAjgdwtg3eKjZuElgk68RbTm0F7zkf+bPHX9W6z+jLcQlmP4mvL5WGMuAuQ1qcLtxPht4gsg3bdy1q60G/+4r4ZGurtL6k6+gP/7DagCAdOccMHX721hcBxC/QWo6pJf+Cen8KT6/AouLC1xJUEun2Ib7vKYKSM8E694L+GUz5Nef09utaLe1rFkJSSExmE3SL+OYVXlcz5/tj0ClsVV9bsVxcFsF3PPvBd/wvbh2czO4Iv8wlmfn2zcBP68DG3MapNseEnIZNTNSAA0zr6/zKvPOX/krsL8U8jMPamn/vDD2y/ZmyABapWHmO7cCTAIbqTjTrHGQ5v8NTC1n78vD/NP34EsXgv/7g5bboI5xbZAoxoSH2S8paV4TLjvtLKFlfu1Z4YUaeAIsDzzTtusaDEH5lt+ZVoZGbSbLzBZTjMdgxJsMkxEgqjsdPQik+1+hsr6DwNd8Du52i1UzAPmV/xMHFVmD/N1K8J/W6m86uBcIh5e50sMg8Gsw23yXqa48DsQnQJrzXNjyRbaZIAZUfvQgkJoBlua9DRkJWFw8pL8sBlwu/3/X5NAXwfGb91PVd/rwWBgHqfr3XgPeew1s0m/AV/8H7PIbwNTJ19h3hp2sbefzD5eZr5ecKoJo1Wv36gv0yAc7cZQ24aCuBkhINAe4HdgDnvideDxkOFAvPG787ZfAs3Jh+etren5gf4ZwTRV48SrgpFMBp8OUJaDNJKcKYyAhURjLFkt408qpxrjnpNFQL3IKW+P0rD9tlTCrwUn9BgkvWLVNGBbVduEsMHpkVW+Ry7fBLC8y5ElV26oVVvEgOxfgXM+H3Zayz+qY3Nhg8FCngiWngP12KuQjB8F/FIYkK7wUqKoEu/52cxxGCGEeQbry/PvEA4vVvJCqqwHyeupSGsC3vE3tT7VVwBFD0LqH8cIdzcD+UrBfXyqKgKlYrMIAVYM4XQ6wuPiWvXmBiAu8WPIFr60WqQIVI5F/9xX45GvAN68H//xD0X9UI7a2GnzNf+D++UdItz0E1n9IcO00yMF4Q72uVKqyaVIgfzAm+U9/lpEt0v2p2Xl274D80lNghZeI+byyDNIrHwuPPyACig/sBqxxYL+dCpaaDsvocWLnA/DpYeZNDcCxw5A/eRfYvA7s4ish+coX7qMUO9++Sdwrw04GGuogTTw/4HdtFa2QZPAdP4uxY9RYsBvuFLvmhl14ZrUq+bsNHmZ1ke6RVYzX14J//RnYsFGQV34sKnZqGXxaPx/GtodZHfwsFkiL/gFp4ZtgSidSt2z9pgoKgFfEvtHYUjt9fLxeMMWfJEMZZLUAoUA6q4EniI6w17ANZ6guxF0u8NcXAZt+1F8zBCaEFLuH5lOdSUePMyeI95fZQElXFTXGskJb8jlyziHPuQ3y/HtbPrkDYRaLT4mShpLTO1TVr3j5Mcg3Xwr5s/fNrx/eLyYuwHf1PR8LFL5aeGn5xh/B9+4E3/Qj+B5de8zyeurGvqdujTG9v9XVCMNVmYiZOg6on+kpCVK9cknJ5nRJ9gq4b58K+PKQA5Bmimwa8pzbAHsFpDMKYbn7CUhnBj+hsOQUIT1wu8SkYrGEVy6kVmzzNJhNUf/+JRly8Vem7VITalEMNWNImeKxb2zw8vpq28Ct2U5WxknuQ8MMQOiNAeCI0q62eJjVcxvq9S1wo6RDzeiTmQM25TpIf7o3bMYyADGPGA1JNebjhffM5xn1+LndIT31qs/LsT9MFw8aG8HV+aNHvpABKfDmZsi3/V7cGx7GpbojqskT/PwGbcLTa90aVINZDWQEIN8zDfzvLwjDtnd/73zIVTbIT9ylZ5loK44mvSCUIg9S5VhqlVm/BMqSoXps95eagwlXfqLLLXZuBbb/LAzkAkUL3quvWTOu7tL4yFzC33kF8hN3AcqOO//Xu0KH71kJ2dO5xznkhY+IrzBoGCyPPAs28tTA37U1WK0Bd84458CBUrBBw8CscZBOLzQZy+Ia6n3jMr5R/K86MJubwY8fgTx3JvjH70B++j5gfbHIpKMayqpEqakR7sdnB2x2bBvM6iDidoMlJQuN0QDDANA9379uOBBKEJKGcVWm3IDs8hsNGhtDYATnwlNlsWgTPBt/tvg/gI6XDR8t3r9LrCJ5Q525Axo0gkjPFNrH9mwNB8Co5WKnna0F77AhI2CZNRfSk6+I86r8SDLU/K5RAjvzN+JBW4qv1FaJ/8uOBDwt6lAn/8b2b1ECgPy6yKnKv/jIfMAYnOdry8vmuegycOyQSN/0wuPgH7wGQKQOM+lLk5R+qw6aiUnCawCIvLUOh751r/ZxxWDWJEEqZUeFcWqNA4aPBjvrQr3wS3OTyOaikpULjBgjNNmeEiqPwhNBkZwqDDWXomGWwifJ4LJbM8A8fyNeW63fK34kGdzpFMVelKqmXtdXFszslPGiWqm6zdzkI2et5mUMYDT16C0ME83D7EPDDGhSDy2tWhs8zNriqrFen1CNBrOaNq7PALD2GoqtIU4P+lONG3bh74URcc9TYL+fJo6pc52tHGz4GLDc7j4vx3KU15satf7A+gyE69A+3WFgcMqwQcO8L5LTDVB16C5vWUybUf6ObSkBjiqbkJtMONf3cYMhKd0733RI/ttC8Xm1NXDPvtZckMUPvPwYYKsAS88Q9646fpVuEwualrLisABZMlRHWZVNjJuZ2dpiXGvzW4sBptQpOOM8kSbwgsvM1+nWE5Akb+mmy6ntigDQfi/5vukmmRkAb0eGwYBnv/1D4O/YBlicd/A5/2mtLt9rqBP3vbFsvCeqTMhHZU7+vy/Bt6yHfPvvIT98i8j7fsFlZqmiOoc7HJBfKwL279bTk/ohpg1m6fJpXq8xw0qQDRpm1ny1Al5ZBv4/c1SuKQBE81YlARZlQHUqXpw9v0C++VLhecvI0nRhLLc7pJdXgI0e5/dzWUqqMABqq4Sw/Z2Xxeunn6tdW0W64xHvaOgQwSuOC89NfILw2F8zA2z4GEj3PAlWeIk4KSdPLAiq/fxtq+1AevQYzNoiqi1FbvYG7lhRS5IwHvjGtXDPnWnKU94WeNlRMUnvVrYBB51oPq72ifx+vj0eykAsPb4Eee9+BWmxQXOmvlfJ3wpAGCpJyUJfqqRdY2eeD2nx+2AXXA7puts1bxM/dthsTGmR8orBvGOT9yQfnyD0r5IF0tW3QJr3kiZnUvVw7KI/QLrvaVj+PBfSuEnmSXnB39u3La2Skia8m1U23cMcptLYRr0iL/5KeyyXfAts/EELxtJ2gjwdzBXKosjfOKNqiHO7ixgM1RPtKyOQZjB7L67UHMFs3CSx1a4ZzH6MNXWM37dL6I+TW28w6wvKBkPgo+H9yiKM9RnQ+mu2h/gEEVB9YDf4p++bPpsNHQGmbo/X1QiNeG11YI2pcfGoasqHjhALJMUI5EpGKemx530WYmHpWfpv63T43kFqC22UZPCmRuF57dEbzBoHds0Mr3O0jBEA2JDhQjY5SXGMKEYRX/8dUFsN+cvlgT/P6QT/zz/Fk7RMILc7eIXw/PKdIluHSbbiizirz8UgLz+mSWN4TZXw+nfr4V3K+9hhIK8XWE4eWFo6LHfO8UphyJKSgX6DTTmnua0c2LbRNIaYKkraK8yf5WkwK7sQ0t1PhHaB2K07YK/Qdrbkkm8hv/gk5EduhfzDash/FvUYWFaAe9mX9t2Q5lHLxAUAKWmQplwP6d6n9HnFsDPGv/8afPvGFpsd0xpmdtIpYBdcBnaS+WZmZ54v9DFp6W3OeMF/WC0m6xvuFBIIQNdVOh2Q/74YSEgCG3aywcOtJHlf9al+IUOHBvzozTxxNIP/92PhOVFzTw4cBnz3FaB4zdg1M4RGKwzBXbyqEvIDSiCjR1QwG6pXWWSSJAxif4uRGjvYiaNC2rb2oGrN+cpP9EDNFpBfmCce+ImMlj9YBn78sNB8Tftzm8vlhgs2+ERwxvR7d89OoI1bbFx2Q37oT+K7qwOxpy5a3XXJ7Q4cPeR9kapKMdHm9QRLTBLZVNQ+oQxk0k13AS4n+OZ1YCmp4Kp3r6pS9Nu0DDDJAjblOqVdshhEqyuFd0KdiD08zKivE3k8PbMMGGCJSbD8eS7ci/6ibWOyE0eJnLwqBoO5zSXZ/aEGwlXbwHK6gR8oDZvBjK0/iSDHulotDzNvbBBBQABYfn+PN3hYzC1VT6upApJShMa1e74eX9HYID7XiB8Ps/z2S+DffC6eJCUDySn6Yszp8J0yLjlFDyrq1kIwlieqJKOx3mdOc/arSUBTo+4cCDPstLPAv/uvuTiKmg0BEPe2xSLmGtXrGSgfsLEvOEThKJbXS/yyFceBnDxhBOb302sEeJKWoTluIiLJUMYTtX1s4Ami/SMLIE2dLnZNRpgrbTLGwK6ZAZkx8BIRPMo3KvdjCynS5Mfu0HYS2QWXA+XHhFysoV7MxXk9W87Ekp4F1NjBZdk01/NPDdKaGjvQ2Ag2YgyYJImd2mo75L8tEAuEVuQ+ZsNGgn+5ArypESwxCfJ90/WDSopCNvE88M3rNQeCNPHXkLcpu24eBjM/rnh829qPWmpn7/7i/tm5FTjpFG3MgSyD/22BfmKPPr4vAOg7ExXHwE44SSxsNq8DTjpFxK58oMS5nDwW0iVXic/NyYP0m8sg/7JZS1GnKga4h6zQFzHtYQYAacr1YENHmF+79jZYnnhZeA5czlZXPuM1VeDL3xSTwPhzwK6+VZR43LIevLEB8t03iECJi68QnmxlIODNzeC2CmFsW61gl14lcloGiyFRu5o6Tt1WYqrGKikZPNQeZmPlqKpK/+cBZp2bAe5oFp6bKJJk4MTRQF4v8K/+Bb5/d4unc+N395U2z+UC/3K50JPv2ga+a5uoUrbiraA9uqGCde8lAuIUeEu/oy/UCpeqUZzfzzsWoLJMyCTSMnx6mFFXC6SmmXTslr8shjT3Bf2cjCyx+6JUcNO8DQf2CK2ax2KFSRKQkSkWsC6nlySDNyntaKgTnpozfg20UMJauu42/V7tnm86FlArHiRGw5tdcLmQZIQp6I/bykXWIGVnizc1avITdvWtYNfeamiYd5S/MfsJV7b0jTtdaiYDAMLrWVcjdgeaGrx1v+pvZSxt3tysG8uA0JgrabS40wEcP6xnBjDAGNO8TmzYSK/jAVEkGVz1MMfHmzxrLCUV0gWX+0y9FQ5Y7/5g5xqM86RkkQlHPc6YWLjV1Wp614DlubW+0CD+1gmJWmA2Lz8mMivt3AJ2UoBFdHqG+PvW1SqBl+3sB+rft5WSDK4W8FLGMdZnAKSHiyDd+gBYj3yw0eP8e0MzskVthoZ6YawB3jENnqjG8sTzRMaPwkuAxnrIi+aKHTbD7+GXrByx8PUIquOVZUD3fLDzfifaUW3Tv1e3HmCDTwR69xfPW9JJA2AnnOxd/lxBeuQ5sJvuAhs+GtLz/4BaGdO4k8c9PcyH9go7qb2FSjwZWSCymK37H7jdew5if5gOdtUtSuEkP/QdJPqDKrE7sBtoaoQ08XxI5/0O0ssrYHn1E1jueASsn6HyqsFrzfoN8p8f3Acx7WFuEXWrraFOlAx2OoH6GrDMHPCdW8GrbYCjGdLphaLC0ytKNo3GejBJAjvrArhL/gd+7BBQvErzSLAJ54jzcrsLb8f2jcLbCIBdfyek084KqrnstLPB134tnqSkwfLs22KVlpAotlbSDBkbkpL1PIMBcM+8Cuyc30K69GrT69zpBCySFjjBD+41R6qP8VHi1NjWbj3B134N951XQLr9Yc0DraXjCnUHbAfMYoE0fRbkp+4B/+Vnc+fyhRpdnpEltpVsFWDKNiivqgRf/735/NoqUaXss/eB2hqwa723EDsSlt8P/LCYdPjq/0DmHCw1TV9stYCabgqA2BbtM1D81i/NB8vIFDs4364Eho8W96aPYFZeX+szuwpjDDhxlNAnegaFKt5dWc2x3MeHbjAjWy9uogbBqNkYaquFjramWmzRXX2LMPL++brfQZNl5kB6fIkIIvSxmyDdch/Qy48nLhgUWQm74U6wjCwlG0KYPMx1NWC9B4CNPQPyxh9E3tNdW4GMbLBJvzH//X0Z7gb9Pj9yQBT2WLoQ0i33gZ16ugiuUjP/ZCiGbY1dGFqeHjnFW8/ravTsA8YAZ0B4qY8cBNZ9C2zdIPJ7n+wn9+9pZ4t8rBf7yAQQCMWbzF9fJNrcFjlHmGC/nSrKAKdlAHHxWpYkjYwskSFBXdAZd0E8URcqqiQjPgHI6QaWlgH+4evidbdbpGP0hyKnk+f9WbQvkFHTGlQPc2uzZBw5IHYkuuk67RbHbBV1cfD1Z3pRjPKj4LLbO0hQJSMb7MSThezL+FlKVgs2uuUy0SwrR/fiG51F1Tagdz+w8WcJJwvgVSWU9R8CvulHYGDgTBwAgMEnAhar2EFX4p4AAMNOFosJdXxhDJg6XWRBScsAO3+KiEPZ8TPklZ+AnXsxGGPCgdR3YMgD9FlcPDDwBPB9pcAvwgEoPVwEfngfULodUuGlgS8AiF3JvoPA1VgtdUdb+Y397tr3yBfjT0O9+D89E1BS/Xvu/HvStQ1mJRhEvne6+CP6ifZ2r/3G7NU9vVB/nJMH/v0qTdMEQJtYmTUObMxpYgsotzvQs0/QxjIASNNnAdNnCe3VEOE1Z4yJgb3siEjBopKUApQdhbz2a7CCiSIFy6YfwXdsBptyLVB2VJR1bagT20KXXi2Mb84BpwPy7VPBzjwf7NrbxBb80oV6Oxa+5R2040kv5cZrbABf+43wsv7nn2JAHjFGrwMfJbCBJwC9+oJ/sAzuLRsgnXuJCAAzeCr4vl0iCEypDCdNnw25aI5IV3PZ9eC11ZDvv0kzcNiZvxH5eWuqwdWJN8Qp3YJCnTRT04D9peBvloIDYOf/zqT75zVVwtiVLEC2XozDZDDn5oGNHicWchuKhbTl638DkgRpyrXg2zaJe8CwqAAAbF4PqHlSPbDMnue73aqsZdOP4rGvqmqZ2ZqEQjPIk1PEgvjDZbqoQA24ZQzMR6yDEZaY5L9sfRu8E62B9egN6dl39Ly1khS4XHQLeKb847t3iAwCCYliGz81XZsk5L8+IPTBJ53qPUGqE4zx2mVHxXuPHhSGgNJOvneX+LvUVGmyDpYpDAZ54RwtBZoJVaJhiAfhm34EmARp5qPCIB94AhhEgKm8+Elxkh9DSR0r24zRkK+2tTiBdgSMMaC7fy8mO/cS8GXPilSLmdl6wKov0jOFNt1WAe4QHmYmWZB0/mTUf/gG+Iq3hOa/l//vzUb/CvzksXrxqsHDg/xmChaLCIpTJBnc6QSLixMZeB68GRg+BtKfHwNjDPIPq0WBLEnyb+AGgPXsLcaoFW+JHa4zzwN/bylQUeYzlzIvPybuA4+89uz0QnClkA0G+giM9KS/UoHyp7VaICWXZRFIeNKpYL0HQHp5hahI6jGusd9MEeNvK9JVsoREYMBQ8C8+0hIFAIB09oXe51qt2pgqXX4D5KpK8B9Wg7/3NyGbGnsGcHg/2Dm/bfn7BQHrP0QEYO8rFfdkfl9I/QYB/gI5fV0jKwd87TdwL3xEDzRvwRPPLBbxm21ZL+wkZZ5g4yZ5VTz1pEsbzCwrV0ygXDYby3m9hAGa11NE0O/4Wfygsgw2+RpIv52qnztkOPD9Kk2iwK6+1fwZF/5elOI+cgBs4nmhabc/b5ghCID17C2S/S8tAmprIO/cCiiaLb7yY68tVs45+FsvieIAiqecr/kCfOSpogqX4pEE0Kq8w2z0aeAf/V1cx1g5LSEJ0o1/7rAtzbYgXXKVqJS3fRNkJbm79HCRiM4/fkik5QHEvcAYMGQE2CkTwP/zT7h/2ayXX2YSpHufAht8Itw7NomiKFwv4uF+fh5Yv0GarqqjYRdfAcTFgY36lZYyCBCGLr/g95D//oLQdXlIaqTZ88TOgEHGwXr00bb0AQBDRwA7t4qcmb0HAGDCUFr2LFh2N7DfXCY0hm5Xm8vVMmscoEzU0vV36sUUjOdkZOtBYkpFKmaNA/v9jeBvK4UHklPBTjy5TZ/dkZiKPFgsYiGy42exNbt3l5bWSewCWcyaSFkG/88/wYaOgPzCE0LrPbJA7CAlJIo0iCedKjzjdbXCYFb1iYo0zWeQXHIqUF8nNM4rPwEbNRY4fgRsyHDxmd9/DaY6A2qrlWxAlbqWdMhwcQ11e9vDAFQrgvLlb4KfOApswFCxGzBqrNB0qtIzY77bU8b7LdATLIwxSLPn6f2ig8rItwc2bhJweD/4tp8gTZsZ0JBkFguQlSsWuD17a7svKVfdjPq1q0XQVPf8gB5FlpgM6fo7IP/1AaHrD2Sgt6b9jAHgwPEjkF8rAv9hNaT7ntbLX2/7Cfi5BPyEk3R9q5+dhRbJ7y+y2WzfCGnmY4DLJWyAY4dEHust6wG3G3zrBuH9VMd0z/v1+jtEsGH5MVNqO7/fMTMbGFkgFnt1NcKLf8mVos/17C3OkSRRNdHzvdY4/9lAfH3WCSeBl26DXDRHvDB8DDBmfIvvM8ox+CfvgH/yjrje0DbKmlrbziEngnMZ/Kt/icJTwQSPDhgKrP1GL/6SnOIdH+HrswcMFb91tR2sZx+xiHI6wPzVlFDocIN548aNWLZsGWRZxrnnnovJkyd3dBN0Bg2D9OACyEWPgI07C+zM8zW9EBwOsIQE8LIjojiFH1G/NPE8uP/3JbB3p8gUYQh+AwCW1wvS7Q+D/7IlbIEi0jW3gleWmToVu/RqMcF9txL8/aXeb/LQI8oP32LKN8vOuQh81afCk6NMVtIzr/sOsvEB69lbTGYGo0t64X2xtZ3assEdCZiPcuny4z68VLIsqkxZrcAZhcLjrw6sJ48VEhRlwpGu+KMuZZEkPW2Nep9FAJaZDXbFH4Vh2T0f7ISRwLCR4K88A/nP/o14o3HNrp0BWMQOCrNYwH53rVjZ19hF0JDimWO9+4OdN1kEosCcjUG6YWab2y796V6gsswUBW/CWAzDELQknXUB+OmFAHhULtb8ong85DcXC73xhmLglAkiqOXtl4DsbpDmPg+UHQN69wP/YY0wOo3X2LwO8uZ1YOdeLJ5vWa8t/tgJJ4FZrZDueVLsAh3YDXaxj/RRKaki+f/sa4SRoUym6D8YbPho8GXPCa8dxG/Mjx8WxqZ6HyQmQXr2bZH/dNc27ywABuQn7xbBt7ZyXd6mwCRJbMenpMFy6wNt/3u2AnbiKEiL/gF55lVgRudIlMIsFiW9XOCdEo28nsLAsJVrThbGGKQrb4b8zIMtV60DwNIzYXn8pRbPazWc65UcAT1VYaZYoMsvPK6fm5UrFnxBwCwWURmvuQksMUmkZ7VawTf+IDTc//CTv/pUj4wUjInAUsXYbQ3Sby6DvHmd5pnmWzeIa4Wi1LSxbWddYApgk66/o1WSCpbbHRwiv7yaYYKNnQiMDBznETQnjtbLqvsqotIK2Nm/FUWjlHlVunF2677raWeB/+tdodU/YSTY6YVgv52qF4fx9z7elmoN7USWZcycORMPP/wwcnJy8MADD2DmzJno3TvwTXfkSHhz3fqtVNbB1wgHfH8p+JovhL75tLOE1+n4YSAnT1Qn6t1fm+gAQPrrMhGYmJYBee3XwkMNABlZkJ55vU3fkXMugiNmXgWcdAosMx8L8bcLPfyXzZDfeF54DrJzwX49WZSgrSwH+/00sPgEyK8/B+na28AKzgCX3eBvvSQi56+82afOle/eAV66DWz8OZCLHgXr1Rfs6j+1Ld1VmFDvWy7LIgOLsYJeQiKkRxcBkgXy/dNN75MeeEbIWDyv19QI/vE7YBf9QfOU8oZ68M/eBz+4R/MESPc9LQJaAOTm5qKiIjQ5w/n2TZAXPgJ24VRIv7smJNeMJPzQPshz72zdyR4p6Nh1twtPohrcBAiN48F9IkI+Lh7S4g9a1afdCx/RvTiAkEfk9QS76hYgLg7yrZf5fJ/0yLNemkx/yG+9qBWvMX4HyWNnjjfUC8+6cXEUBqJ1TG8vvL4W8qO3A9V2rR/n5uaivLwcfO03YCNGi9RxHYh78RMileGIMSJtqb0C6D8E0h/vhvzq/5lqH0gL3/Q5zgb92S89BWwwxJ1YLGC/vxGoKAPf+wuk627XyzG3E/mrT8H/8Yr23Nf9HSp4ZTn47u2QWll5lDc3A0f2t1i1MJRwlwtwNLVrLuT7S8E3rAUSEiBd+PvWv89H/5Y//xC9p/sfbzvUYN65cyc++OADPPTQQwCA5cuFyP13v/tdwPeF22DuavAau5buCQDkj98G4hPBzvmt1yTEt28CP3IQbNjJQQd3cJczaM1ZJOCyG9hUAoweF5MTZiB4Q53Yqs/INmWBkIu/EpNUvFKyedCwNv9tuCyLCXngCVrwCRBagzkWkb/5XHiTM3PALrtOBFT+slkE4/xqksiVGp8AXn4crM8AsDGniVRXCYmKPIWD/7AG2PGz8ERarSJwKinFf+owzzZ88o4I2I2PhzR3sVdhDO5yCW15n/6Q/7ZQyS6S06ay8VyWhVTHViE80bXVkK66xZzKjwgJapEQNUYjGvogdzrEjkqNHSg7atqt5ZXlwME9It1diFN0yv/9WOzC5vWCdNPsDjEY+bHDQGJiqzJfEB0H374J+ede4Pd4hxrMa9euxcaNG3HLLbcAANasWYNdu3Zh+nSz92rlypVYuVJsW8yfPx+O1pRLJQiiU2K1WuHyLB9PaHBZBm9qhNRKOVTY2uF2A+BgLQTGEJ2PrtwHucsF1/5SxPmqakh0OeLj/Uv2OnTk82Wb+/JSFRYWorBQz0QR6ZUvQRDhIxq8W52ChtCUMycIT7p8H8zIBbry9yc0evXyn5GmQwuX5OTkoLJSj7CvrKxEVlYUFbAgCIIgCIIgCA861GAeNGgQjh49irKyMrhcLhQXF6OgoIUa7ARBEARBEAQRQTpUkmGxWHDjjTfiiSeegCzLOPvss9GnT+QTwxMEQRAEQRCEPzo8euOUU07BKaeEKa8fQRAEQRAEQYSYDpVkEARBEARBEERno0PTyhEEQRAEQRBEZyPqPcz3339/wOMvv/wyHafjETseDW3o7Mepj8f28WhoAx2nPtiZj0dDG7rK8UB9IeoN5pY49dRT6Tgdj9jxaGhDZz/eEpFuHx2nPhLrx1si0u3r6sejoQ1d/TjQCSQZ999/P+bPnx/pZhAEESaojxNEZKE+SBCCQH0h6j3Mxop/BEHEHtTHCSKyUB8kCEGgvhD1HmaCIAiCIAiCiCQdnoc5kmzcuBHLli2DLMs499xzMXnyZO3YJ598grfeegt/+9vfkJ6eHrlGtoMXX3wRGzZsQEZGBhYsWAAA+P777/HBBx/g8OHDePLJJzFo0KAItzJ4fH2/ffv24dVXX4XD4YDFYsFNN92EwYMHR7ilwVFRUYHFixejqqoKjDEUFhbiwgsvxPvvv4+vvvpKuy+vvPJKymUepfgaY2LpHvXVB2Pp/vTXB998802sX78eVqsV3bt3x4wZM5CSkhLp5hJ+iOV+SH0wgn2QdxHcbje//fbb+bFjx7jT6eR33303P3jwIOec8/Lycv7444/zW2+9lVdXV0e4pcGzdetWvnv3bj579mzttYMHD/LDhw/zRx99lJeWlkawde3H1/ebN28e37BhA+ec8/Xr1/NHH300Qq1rPzabje/evZtzznlDQwO/8847+cGDB/l7773HP/744wi3jmgJf2NMLN2jvvpgLN2f/vrgxo0bucvl4pxz/uabb/I333wzks0kAhDr/ZD6YOT6YNRrmENFaWkpevToge7du8NqtWLChAkoKSkBALzxxhu4+uqrwRiLcCvbx/Dhw5Gammp6rXfv3ujVq1eEWhRafH0/xhgaGxsBAA0NDcjKyopE00JCVlYWBg4cCABISkpCfn4+bDZbhFtFtBZ/Y0ws3aO++mAs4a8Pjho1ChaLBQAwdOhQ6pdRTKz3Q+qDkeuDXUaSYbPZkJOToz3PycnBrl27sG7dOmRnZ6N///6RaxwRNNdffz2eeOIJvPnmm5BlGY8//nikmxQSysrKsHfvXgwePBg7duzAF198gTVr1mDgwIG47rrrYnrA7Kz4G2Ni9R41Eov3p7EPGlm1ahUmTJgQoVYRLdFV+yH1wfDTZTzM3Edso9PpxEcffYQ//OEPEWgREQq+/PJLXH/99XjppZdw/fXXY8mSJZFuUrtpamrCggULcMMNNyA5ORnnnXcenn/+efz1r39FVlYW/v73v0e6iYQPfI0xjLGYvEeNxOL96dkHVT766CNYLBZMnDgxgq0jAtEV+yH1wY6hyxjMOTk5qKys1J5XVlYiNzcXZWVluOeee3DbbbehsrIS9913H6qqqiLXUKJNrF69GuPGjQMAjB8/HqWlpRFuUftwuVxYsGABJk6cqH2vzMxMSJIESZJw7rnnYvfu3RFuJeELX2NMVlZWzN2jnsTa/emrDwLAN998g/Xr1+POO+/s9PK9WKYr9kPqgx1DlzGYBw0ahKNHj6KsrAwulwvFxcUYN24c/va3v2Hx4sVYvHgxcnJy8PTTTyMzMzPSzSVaSXZ2NrZt2wYA2LJlC3r06BHhFgUP5xxLlixBfn4+LrroIu11u92uPf7xxx/Rp0+fSDSPaAFfY0xBQUFM3aO+iKX7018f3LhxIz7++GPcd999SEhIiGALiZboiv2Q+mDH0KXyMG/YsAFvvPEGZFnG2WefjSlTppiO33bbbXjqqac6bVq5Z599Ftu2bUNtbS0yMjIwdepUpKam4rXXXkNNTQ1SUlLQv39/PPTQQ5FualD4+n69evXS0gfFxcXhpptu0gIGOhs7duzAnDlz0LdvX231fOWVV+K7777Dvn37wBhDt27dcPPNN3fagJVYx9cYs2PHjpi5R331wa1bt8bM/emvDy5btgwul0vThQ4ZMgQ333xzJJtKBCCW+yH1wcj1wS5lMBMEQRAEQRBEW+kykgyCIAiCIAiCCAYymAmCIAiCIAgiAGQwEwRBEARBEEQAyGAmCIIgCIIgiACQwUwQBEEQBEEQASCDmSAIgiAIgiACQAYzQRAEQRAEQQSADGaCIAiCIAiCCAAZzARBEARBEAQRADKYCYIgCIIgCCIAZDATBEEQBEEQRADIYCYIgiAIgiCIAJDBTBAEQRAEQRABIIOZIAiCIAiCIAJABjNBEARBEARBBCBqDOZrr7020k0gCCIM/OEPf8A999yj/SsrK/N77mOPPYbdu3d3YOsIIvaZOnUqnn/+ee252+3G9OnTMX/+/Ai2iiA6F9ZIN4AgiNgmPj4ezzzzTKSbQRBdloSEBBw8eBAOhwPx8fH4+eefkZ2d3aZruN1uWCyWMLWQIKKfqDKYm5qa8Ne//hX19fVwuVy44oorMHbsWJSVleGpp57CCSecgJ07dyI7Oxv33nsv4uPjI91kgiCCYM+ePXjjjTfQ1NSE9PR0zJgxA1lZWQCA//3vf1i2bBkaGxtx6623YvDgwRFuLUF0fkaPHo0NGzbgtNNOw3fffYfTTz8dO3bsAACUlpbi9ddf1wzqGTNmoFevXvjmm2+wYcMGOBwONDc349FHH43wtyCIyBFVBnNcXBzuvvtuJCcno6amBg899BAKCgoAAEePHsXMmTNxyy23YOHChVi7di3OPPPMCLeYIIiWcDgcuOeeewAAeXl5mDVrFl577TXce++9SE9PR3FxMd59913MmDEDgFg4P/7449i2bRteeuklLFiwIJLNJ4iY4PTTT8eHH36IU045Bfv378fZZ5+tGcy9evXC3LlzYbFY8PPPP+Odd97B3XffDQDYuXMn/u///g+pqamRbD5BRJyoMpg553j33Xexfft2MMZgs9lQXV0NQEy0/fv3BwAMHDgQ5eXlEWwpQRCtxVOSceDAARw8eBDz5s0DAMiyrHmXAeCMM84AAAwfPhwNDQ2or69HSkpKxzaaIGKMfv36oby8HN999x3GjBljOtbQ0IDFixfj2LFjAIT8QuXkk08mY5kgEGUG87fffouamhrMnz8fVqsVt912GxwOBwDhfVaRJEl7nSCIzkfv3r3xxBNPtOpcxliYW0MQXYOCggK8+eabeOyxx1BbW6u9/t5772HEiBFaUO7cuXO1YwkJCZFoKkFEHVGTJQMQq9yMjAxYrVZs2bKFvMgEEYP06tULNTU12LlzJwDA5XLh4MGD2vHi4mIAwI4dO5CcnIzk5OSItJMgYo2zzz4bl19+Ofr27Wt6vaGhQQsC/OabbyLQMoKIfqLCw+x2uxEXF4czzjgDTz/9NO6//370798f+fn5kW4aQRAhxmq14q677sKyZcvQ0NAAt9uNCy+8EH369AEApKam4uGHH9aC/giCCA05OTm48MILvV6/9NJLsXjxYnz22WcYMWJEBFpGENEP45zzSDdi3759ePnll/HUU09FuikEQRAEQRAEYSLiHuYvv/wSn3/+OW644YZIN4UgCIIgCIIgvIgKDzNBEARBEARBRCtRFfRHEARBEARBENFGh0syKioqsHjxYlRVVYExhsLCQlx44YWoq6tDUVERysvL0a1bN8yaNQupqamora3FwoULUVpairPOOgvTp0/XrrVnzx4sXrwYDocDY8aMwbRp0ygFFUEQBEEQBBFSOlySYbfbYbfbMXDgQDQ2NuL+++/HPffcg2+++QapqamYPHkyVqxYgbq6OlxzzTVoamrCvn37tGIHRoP5gQcewLRp0zBkyBA89dRTuOCCC7wSshMEQRAEQRBEe+hwSUZWVhYGDhwIAEhKSkJ+fj5sNhtKSkowadIkAMCkSZNQUlICAEhMTMSwYcMQHx9vuo7dbkdjYyOGDh0KxhjOPPNM7T0EQRAEQRAEESoiqmEuKyvD3r17MXjwYFRXV2vlcbOyslBTUxPwvTabDTk5OdrznJwc2Gy2sLaXIAiCIAiC6HpEzGBuamrCggULcMMNNwRVyYuSexAEQRAEQRAdQUQMZpfLhQULFmDixIkYN24cACAjIwN2ux2AkFukp6cHvEZOTg4qKyu155WVlVppT4IgCIIgCIIIFR1uMHPOsWTJEuTn5+Oiiy7SXi8oKMDq1asBAKtXr8bYsWMDXicrKwtJSUnYuXMnOOdYs2YNCgoKwtp2giAIgiAIouvR4VkyduzYgTlz5qBv375aCrgrr7wSQ4YMQVFRESoqKpCbm4vZs2cjNTUVAHDbbbehoaEBLpcLKSkpePjhh9G7d2/s3r0bL774IhwOB0aPHo0bb7yR0soRBEEQBEEQIYUq/REEQRAEQRBEAKjSH0EQBEEQBEEEgAxmgiAIgiAIgggAGcwEQRAEQRAEEQAymAmCIAiCIAgiAGQwEwRBEARBEEQAyGAmCIIgCIIgiACQwUwQBEEQBEEQASCDmSAIgiAIgiAC8P9+xBkPWaXSrAAAAABJRU5ErkJggg==\n",
-      "text/plain": [
-       "<Figure size 864x216 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "from ucimlr.helpers import download_file\n",
-    "# http://archive.ics.uci.edu/ml/datasets/Beijing+PM2.5+Data\n",
-    "url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00381/PRSA_data_2010.1.1-2014.12.31.csv'\n",
-    "filename = url.split('/')[-1]\n",
-    "download_file(url, root, filename)\n",
-    "\n",
-    "df = pd.read_csv(root +'/' +filename)\n",
-    "df.index = pd.to_datetime(df[['year', 'month', 'day', 'hour']]).dt.tz_localize('Asia/Shanghai')\n",
-    "df = df[['pm2.5', 'DEWP', 'TEMP', 'PRES',\n",
-    "       'cbwd', 'Iws', 'Is', 'Ir']]\n",
-    "df['pm2.5'][:2000].plot()\n",
-    "df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 36,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T07:10:20.404629Z",
-     "start_time": "2020-10-25T07:10:19.600217Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<AxesSubplot:xlabel='TIME'>"
-      ]
-     },
-     "execution_count": 36,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 864x216 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "f = Path(\"../data/processed/currents/MOS_ANMN-WA_AETVZ_WATR20_FV01_WATR20-1909-Continental-194_currents.parquet\")\n",
-    "df = pd.read_parquet(f)\n",
-    "df['SPD'] = np.sqrt(df.VCUR**2 + df.UCUR**2)\n",
-    "df.SPD[-1000:].plot(style='.')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T07:07:20.694202Z",
-     "start_time": "2020-10-25T07:07:19.919451Z"
-    }
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "seq2seq-time",
-   "language": "python",
-   "name": "seq2seq-time"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.8"
-  },
-  "toc": {
-   "base_numbering": 1,
-   "nav_menu": {},
-   "number_sections": true,
-   "sideBar": true,
-   "skip_h1_title": false,
-   "title_cell": "Table of Contents",
-   "title_sidebar": "Contents",
-   "toc_cell": false,
-   "toc_position": {
-    "height": "755px",
-    "left": "10px",
-    "top": "146px",
-    "width": "165px"
-   },
-   "toc_section_display": true,
-   "toc_window_display": true
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/notebooks/00.01-mc-get_currentdata.ipynb b/notebooks/00.01-mc-get_currentdata.ipynb
deleted file mode 100644
index 9e447d1..0000000
--- a/notebooks/00.01-mc-get_currentdata.ipynb
+++ /dev/null
@@ -1,725 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Here I download and preprocess current data\n",
-    "\n",
-    "\n",
-    "see\n",
-    "- from https://catalogue-imos.aodn.org.au/geonetwork/srv/api/records/ae86e2f5-eaaf-459e-a405-e654d85adb9c\n",
-    "- http://thredds.aodn.org.au/thredds/catalog/IMOS/ANMN/WA/WATR20/Velocity/catalog.html"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T03:39:41.682896Z",
-     "start_time": "2020-10-26T03:39:40.104951Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from pathlib import Path\n",
-    "import xarray as xr\n",
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "from urllib import request\n",
-    "import os, shutil\n",
-    "from matplotlib import pyplot as plt"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T07:01:29.004548Z",
-     "start_time": "2020-10-25T07:01:29.001734Z"
-    }
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T03:39:42.553735Z",
-     "start_time": "2020-10-26T03:39:41.685439Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from torchvision.datasets.utils import download_url, extract_archive, download_and_extract_archive"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T03:39:42.560919Z",
-     "start_time": "2020-10-26T03:39:42.556898Z"
-    }
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import uptide\n",
-    "\n",
-    "# https://en.wikipedia.org/wiki/Theory_of_tides#Harmonic_analysis\n",
-    "default_tidal_constituents = [\n",
-    "        'M2', 'S2', 'N2', 'K2', # Semi-diurnal\n",
-    "        'K1', 'O1', 'P1', 'Q1',  # Diurnal\n",
-    "        'M4', 'M6', 'S4', 'MK3', # Short period\n",
-    "        'MM', 'SSA', 'SA' # Long period\n",
-    "    ]\n",
-    "\n",
-    "def generate_tidal_periods(t:pd.Series, constituents:list=default_tidal_constituents):\n",
-    "    tide = uptide.Tides(constituents)\n",
-    "    t0 = t[0]\n",
-    "    td = t-t0\n",
-    "    td = td.dt.total_seconds().to_numpy().astype(int)\n",
-    "    tide.set_initial_time(t0)\n",
-    "\n",
-    "    # calc tides\n",
-    "    amplitudes=np.ones_like(td)\n",
-    "    phases=np.zeros_like(td)\n",
-    "    eta = {}\n",
-    "    for name, f, amplitude, omega, phase, phi, u in zip(tide.constituents, tide.f, amplitudes, tide.omega,\n",
-    "                                                  phases, tide.phi, tide.u):\n",
-    "        eta[name] = f*amplitude*np.cos(omega*td-phase+phi+u)\n",
-    "    df_eta = pd.DataFrame(eta, index=t)\n",
-    "    return df_eta"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 30,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T03:59:16.671092Z",
-     "start_time": "2020-10-26T03:59:16.655680Z"
-    },
-    "scrolled": true
-   },
-   "outputs": [],
-   "source": [
-    "# 'ANMN Two Rocks, WA, 204m mooring, Jul2009 - Dec2009. Preprocessed with DepthPP.'\n",
-    "\n",
-    "def get_current_timeseries(\n",
-    "    cache_folder=Path(\"../data/raw/IMOS_ANMN/\"), \n",
-    "    outfile=Path('../data/processed/currents/MOS_ANMN-WA_AETVZ_WATR20_FV01_WATR20-1909-Continental-194_currents.nc')\n",
-    "    ):\n",
-    "    if not outfile.exists():\n",
-    "\n",
-    "        files = [\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20090715T080000Z_WATR20_FV01_WATR20-0907-Continental-194_END-20090716T181317Z_C-20191122T052830Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20100409T080000Z_WATR20_FV01_WATR20-1004-Continental-194_END-20100430T084500Z_C-20191122T053845Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20101222T080000Z_WATR20_FV01_WATR20-1012-Continental-194_END-20110518T051500Z_C-20200916T020035Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20110608T080000Z_WATR20_FV01_WATR20-1106-Continental-194_END-20111122T035000Z_C-20200916T025619Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20111221T060300Z_WATR20_FV01_WATR20-1112-Continental-194_END-20120704T050500Z_C-20200916T043212Z.nc\", \n",
-    "            \"IMOS_ANMN-WA_AETVZ_20120726T044000Z_WATR20_FV01_WATR20-1207-Continental-194_END-20130204T044000Z_C-20200916T032027Z.nc\",\n",
-    "\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20130221T080000Z_WATR20_FV01_WATR20-1302-Continental-194_END-20131003T035000Z_C-20180529T020609Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20131111T080000Z_WATR20_FV01_WATR20-1311-Continental-194_END-20140519T035000Z_C-20200114T033335Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20140710T080000Z_WATR20_FV01_WATR20-1407-Continental-194_END-20150121T021500Z_C-20180529T055902Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20150213T080000Z_WATR20_FV01_WATR20-1502-Continental-194_END-20150424T134002Z_C-20200114T035347Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20150914T080000Z_WATR20_FV01_WATR20-1509-Continental-194_END-20160331T043000Z_C-20180601T013623Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20160427T080000Z_WATR20_FV01_WATR20-1604-Continental-194_END-20160531T021800Z_C-20180531T071709Z.nc\",\n",
-    "        #     \"IMOS_ANMN-WA_AETVZ_20170512T080000Z_WATR20_FV01_WATR20-1705-Continental-194_END-20170717T014558Z_C-20190805T004647Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20171204T080000Z_WATR20_FV01_WATR20-1712-Continental-194_END-20180618T030000Z_C-20180620T233149Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20180802T080000Z_WATR20_FV01_WATR20-1807-Continental-194_END-20190225T054500Z_C-20190227T001343Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20190307T080000Z_WATR20_FV01_WATR20-1903-Continental-194_END-20190911T003144Z_C-20200114T045053Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20190926T080000Z_WATR20_FV01_WATR20-1909-Continental-194_END-20200326T030000Z_C-20200420T064334Z.nc\",\n",
-    "        ]\n",
-    "        base=\"http://thredds.aodn.org.au/thredds/fileServer/IMOS/ANMN/WA/WATR20/Velocity/\"\n",
-    "\n",
-    "        # Download files\n",
-    "        [download_url(base+f, cache_folder) for f in files]\n",
-    "\n",
-    "        # load and merge\n",
-    "        xds=[xr.open_dataset(cache_folder/f) for f in files]\n",
-    "        vars=['VCUR', 'UCUR', 'WCUR', 'TEMP', 'PRES_REL', 'DEPTH', 'ROLL', 'PITCH']\n",
-    "        xds2= [x[vars].isel(HEIGHT_ABOVE_SENSOR=18) for x in xds]\n",
-    "        xd = xr.concat(xds2, dim='TIME')\n",
-    "        xd = xd.where(xd.DEPTH>150) # remove outliers\n",
-    "\n",
-    "\n",
-    "        xd['TIME'] = xd['TIME'].dt.round('10T')\n",
-    "        xd = xd.dropna(dim='TIME', subset=['VCUR', 'UCUR', 'WCUR'])\n",
-    "        # xd = xd.resample(TIME='30T').first()\n",
-    "        # Add tides, these are features that can be forecast\n",
-    "\n",
-    "        # Generate tidal freqs\n",
-    "        t = xd.TIME.to_series()\n",
-    "        df_eta = generate_tidal_periods(t)\n",
-    "\n",
-    "        # Add tidal freqs\n",
-    "        xd = xd.merge(df_eta)\n",
-    "\n",
-    "        # Cache to nc\n",
-    "        xd.to_netcdf(outfile)\n",
-    "        print(f'wrote \"{outfile}\" with size {outfile.stat().st_size*1e-6:2.2f} MB')\n",
-    "    return outfile"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T04:04:08.230047Z",
-     "start_time": "2020-10-26T04:04:08.099310Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>VCUR</th>\n",
-       "      <th>UCUR</th>\n",
-       "      <th>WCUR</th>\n",
-       "      <th>TEMP</th>\n",
-       "      <th>PRES_REL</th>\n",
-       "      <th>DEPTH</th>\n",
-       "      <th>ROLL</th>\n",
-       "      <th>PITCH</th>\n",
-       "      <th>LATITUDE</th>\n",
-       "      <th>LONGITUDE</th>\n",
-       "      <th>...</th>\n",
-       "      <th>O1</th>\n",
-       "      <th>P1</th>\n",
-       "      <th>Q1</th>\n",
-       "      <th>M4</th>\n",
-       "      <th>M6</th>\n",
-       "      <th>S4</th>\n",
-       "      <th>MK3</th>\n",
-       "      <th>MM</th>\n",
-       "      <th>SSA</th>\n",
-       "      <th>SA</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>TIME</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2009-07-15 08:00:00</th>\n",
-       "      <td>-0.396391</td>\n",
-       "      <td>0.089687</td>\n",
-       "      <td>-0.009671</td>\n",
-       "      <td>18.549999</td>\n",
-       "      <td>205.076004</td>\n",
-       "      <td>203.550812</td>\n",
-       "      <td>4.6</td>\n",
-       "      <td>-3.4</td>\n",
-       "      <td>-31.728650</td>\n",
-       "      <td>115.037217</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.286288</td>\n",
-       "      <td>0.116457</td>\n",
-       "      <td>-1.014973</td>\n",
-       "      <td>-0.146817</td>\n",
-       "      <td>-0.801534</td>\n",
-       "      <td>-0.500000</td>\n",
-       "      <td>0.370082</td>\n",
-       "      <td>0.132683</td>\n",
-       "      <td>-0.686775</td>\n",
-       "      <td>-0.395743</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2009-07-15 08:10:00</th>\n",
-       "      <td>-0.407620</td>\n",
-       "      <td>0.085398</td>\n",
-       "      <td>-0.019875</td>\n",
-       "      <td>18.650000</td>\n",
-       "      <td>205.078003</td>\n",
-       "      <td>203.552795</td>\n",
-       "      <td>4.6</td>\n",
-       "      <td>-2.4</td>\n",
-       "      <td>-31.728650</td>\n",
-       "      <td>115.037217</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.242810</td>\n",
-       "      <td>0.159551</td>\n",
-       "      <td>-1.031149</td>\n",
-       "      <td>-0.304345</td>\n",
-       "      <td>-0.900573</td>\n",
-       "      <td>-0.642788</td>\n",
-       "      <td>0.494417</td>\n",
-       "      <td>0.134147</td>\n",
-       "      <td>-0.686601</td>\n",
-       "      <td>-0.395853</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2009-07-15 08:20:00</th>\n",
-       "      <td>-0.365314</td>\n",
-       "      <td>0.104038</td>\n",
-       "      <td>0.000991</td>\n",
-       "      <td>18.730000</td>\n",
-       "      <td>205.076996</td>\n",
-       "      <td>203.551788</td>\n",
-       "      <td>4.8</td>\n",
-       "      <td>-2.7</td>\n",
-       "      <td>-31.728650</td>\n",
-       "      <td>115.037217</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.198932</td>\n",
-       "      <td>0.202343</td>\n",
-       "      <td>-1.045759</td>\n",
-       "      <td>-0.453239</td>\n",
-       "      <td>-0.942304</td>\n",
-       "      <td>-0.766044</td>\n",
-       "      <td>0.610654</td>\n",
-       "      <td>0.135610</td>\n",
-       "      <td>-0.686427</td>\n",
-       "      <td>-0.395963</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2009-07-15 08:30:00</th>\n",
-       "      <td>-0.406632</td>\n",
-       "      <td>0.119376</td>\n",
-       "      <td>-0.003729</td>\n",
-       "      <td>18.799999</td>\n",
-       "      <td>205.067001</td>\n",
-       "      <td>203.541901</td>\n",
-       "      <td>4.7</td>\n",
-       "      <td>-2.4</td>\n",
-       "      <td>-31.728650</td>\n",
-       "      <td>115.037217</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.154727</td>\n",
-       "      <td>0.244751</td>\n",
-       "      <td>-1.058780</td>\n",
-       "      <td>-0.589276</td>\n",
-       "      <td>-0.924071</td>\n",
-       "      <td>-0.866025</td>\n",
-       "      <td>0.716890</td>\n",
-       "      <td>0.137073</td>\n",
-       "      <td>-0.686253</td>\n",
-       "      <td>-0.396072</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2009-07-15 08:40:00</th>\n",
-       "      <td>-0.383744</td>\n",
-       "      <td>0.090066</td>\n",
-       "      <td>-0.008921</td>\n",
-       "      <td>18.860001</td>\n",
-       "      <td>205.065994</td>\n",
-       "      <td>203.540894</td>\n",
-       "      <td>4.9</td>\n",
-       "      <td>-2.9</td>\n",
-       "      <td>-31.728650</td>\n",
-       "      <td>115.037217</td>\n",
-       "      <td>...</td>\n",
-       "      <td>0.110268</td>\n",
-       "      <td>0.286697</td>\n",
-       "      <td>-1.070194</td>\n",
-       "      <td>-0.708598</td>\n",
-       "      <td>-0.847034</td>\n",
-       "      <td>-0.939693</td>\n",
-       "      <td>0.811384</td>\n",
-       "      <td>0.138535</td>\n",
-       "      <td>-0.686080</td>\n",
-       "      <td>-0.396182</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2020-03-26 01:00:00</th>\n",
-       "      <td>-0.436635</td>\n",
-       "      <td>-0.784922</td>\n",
-       "      <td>-0.012147</td>\n",
-       "      <td>16.610001</td>\n",
-       "      <td>197.384003</td>\n",
-       "      <td>195.919662</td>\n",
-       "      <td>-2.9</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>-31.728717</td>\n",
-       "      <td>115.042133</td>\n",
-       "      <td>...</td>\n",
-       "      <td>-0.734741</td>\n",
-       "      <td>0.190139</td>\n",
-       "      <td>0.964792</td>\n",
-       "      <td>0.882484</td>\n",
-       "      <td>0.770444</td>\n",
-       "      <td>0.505439</td>\n",
-       "      <td>1.028587</td>\n",
-       "      <td>-0.881951</td>\n",
-       "      <td>0.990514</td>\n",
-       "      <td>0.997626</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2020-03-26 01:30:00</th>\n",
-       "      <td>-0.355067</td>\n",
-       "      <td>-0.845100</td>\n",
-       "      <td>-0.005201</td>\n",
-       "      <td>16.629999</td>\n",
-       "      <td>197.408005</td>\n",
-       "      <td>195.943497</td>\n",
-       "      <td>-2.7</td>\n",
-       "      <td>3.0</td>\n",
-       "      <td>-31.728717</td>\n",
-       "      <td>115.042133</td>\n",
-       "      <td>...</td>\n",
-       "      <td>-0.629257</td>\n",
-       "      <td>0.316317</td>\n",
-       "      <td>0.895545</td>\n",
-       "      <td>0.957914</td>\n",
-       "      <td>0.933774</td>\n",
-       "      <td>0.006292</td>\n",
-       "      <td>0.851981</td>\n",
-       "      <td>-0.880483</td>\n",
-       "      <td>0.990416</td>\n",
-       "      <td>0.997601</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2020-03-26 02:00:00</th>\n",
-       "      <td>-0.568277</td>\n",
-       "      <td>-0.816935</td>\n",
-       "      <td>-0.024944</td>\n",
-       "      <td>16.660000</td>\n",
-       "      <td>197.412994</td>\n",
-       "      <td>195.948425</td>\n",
-       "      <td>-2.6</td>\n",
-       "      <td>2.9</td>\n",
-       "      <td>-31.728717</td>\n",
-       "      <td>115.042133</td>\n",
-       "      <td>...</td>\n",
-       "      <td>-0.514470</td>\n",
-       "      <td>0.437113</td>\n",
-       "      <td>0.814067</td>\n",
-       "      <td>0.793395</td>\n",
-       "      <td>0.584762</td>\n",
-       "      <td>-0.494541</td>\n",
-       "      <td>0.551159</td>\n",
-       "      <td>-0.878996</td>\n",
-       "      <td>0.990316</td>\n",
-       "      <td>0.997576</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2020-03-26 02:30:00</th>\n",
-       "      <td>-0.306141</td>\n",
-       "      <td>-0.773147</td>\n",
-       "      <td>-0.028096</td>\n",
-       "      <td>16.719999</td>\n",
-       "      <td>197.419006</td>\n",
-       "      <td>195.954407</td>\n",
-       "      <td>-2.6</td>\n",
-       "      <td>2.7</td>\n",
-       "      <td>-31.728717</td>\n",
-       "      <td>115.042133</td>\n",
-       "      <td>...</td>\n",
-       "      <td>-0.392074</td>\n",
-       "      <td>0.550470</td>\n",
-       "      <td>0.721473</td>\n",
-       "      <td>0.430136</td>\n",
-       "      <td>-0.085096</td>\n",
-       "      <td>-0.862862</td>\n",
-       "      <td>0.169980</td>\n",
-       "      <td>-0.877489</td>\n",
-       "      <td>0.990217</td>\n",
-       "      <td>0.997551</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2020-03-26 03:00:00</th>\n",
-       "      <td>-0.218563</td>\n",
-       "      <td>-0.757217</td>\n",
-       "      <td>0.013233</td>\n",
-       "      <td>16.790001</td>\n",
-       "      <td>197.429001</td>\n",
-       "      <td>195.964340</td>\n",
-       "      <td>-2.8</td>\n",
-       "      <td>2.8</td>\n",
-       "      <td>-31.728717</td>\n",
-       "      <td>115.042133</td>\n",
-       "      <td>...</td>\n",
-       "      <td>-0.263881</td>\n",
-       "      <td>0.654460</td>\n",
-       "      <td>0.619026</td>\n",
-       "      <td>-0.040868</td>\n",
-       "      <td>-0.708264</td>\n",
-       "      <td>-0.999980</td>\n",
-       "      <td>-0.235982</td>\n",
-       "      <td>-0.875962</td>\n",
-       "      <td>0.990116</td>\n",
-       "      <td>0.997526</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>239075 rows × 25 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                         VCUR      UCUR      WCUR       TEMP    PRES_REL  \\\n",
-       "TIME                                                                       \n",
-       "2009-07-15 08:00:00 -0.396391  0.089687 -0.009671  18.549999  205.076004   \n",
-       "2009-07-15 08:10:00 -0.407620  0.085398 -0.019875  18.650000  205.078003   \n",
-       "2009-07-15 08:20:00 -0.365314  0.104038  0.000991  18.730000  205.076996   \n",
-       "2009-07-15 08:30:00 -0.406632  0.119376 -0.003729  18.799999  205.067001   \n",
-       "2009-07-15 08:40:00 -0.383744  0.090066 -0.008921  18.860001  205.065994   \n",
-       "...                       ...       ...       ...        ...         ...   \n",
-       "2020-03-26 01:00:00 -0.436635 -0.784922 -0.012147  16.610001  197.384003   \n",
-       "2020-03-26 01:30:00 -0.355067 -0.845100 -0.005201  16.629999  197.408005   \n",
-       "2020-03-26 02:00:00 -0.568277 -0.816935 -0.024944  16.660000  197.412994   \n",
-       "2020-03-26 02:30:00 -0.306141 -0.773147 -0.028096  16.719999  197.419006   \n",
-       "2020-03-26 03:00:00 -0.218563 -0.757217  0.013233  16.790001  197.429001   \n",
-       "\n",
-       "                          DEPTH  ROLL  PITCH   LATITUDE   LONGITUDE  ...  \\\n",
-       "TIME                                                                 ...   \n",
-       "2009-07-15 08:00:00  203.550812   4.6   -3.4 -31.728650  115.037217  ...   \n",
-       "2009-07-15 08:10:00  203.552795   4.6   -2.4 -31.728650  115.037217  ...   \n",
-       "2009-07-15 08:20:00  203.551788   4.8   -2.7 -31.728650  115.037217  ...   \n",
-       "2009-07-15 08:30:00  203.541901   4.7   -2.4 -31.728650  115.037217  ...   \n",
-       "2009-07-15 08:40:00  203.540894   4.9   -2.9 -31.728650  115.037217  ...   \n",
-       "...                         ...   ...    ...        ...         ...  ...   \n",
-       "2020-03-26 01:00:00  195.919662  -2.9    3.0 -31.728717  115.042133  ...   \n",
-       "2020-03-26 01:30:00  195.943497  -2.7    3.0 -31.728717  115.042133  ...   \n",
-       "2020-03-26 02:00:00  195.948425  -2.6    2.9 -31.728717  115.042133  ...   \n",
-       "2020-03-26 02:30:00  195.954407  -2.6    2.7 -31.728717  115.042133  ...   \n",
-       "2020-03-26 03:00:00  195.964340  -2.8    2.8 -31.728717  115.042133  ...   \n",
-       "\n",
-       "                           O1        P1        Q1        M4        M6  \\\n",
-       "TIME                                                                    \n",
-       "2009-07-15 08:00:00  0.286288  0.116457 -1.014973 -0.146817 -0.801534   \n",
-       "2009-07-15 08:10:00  0.242810  0.159551 -1.031149 -0.304345 -0.900573   \n",
-       "2009-07-15 08:20:00  0.198932  0.202343 -1.045759 -0.453239 -0.942304   \n",
-       "2009-07-15 08:30:00  0.154727  0.244751 -1.058780 -0.589276 -0.924071   \n",
-       "2009-07-15 08:40:00  0.110268  0.286697 -1.070194 -0.708598 -0.847034   \n",
-       "...                       ...       ...       ...       ...       ...   \n",
-       "2020-03-26 01:00:00 -0.734741  0.190139  0.964792  0.882484  0.770444   \n",
-       "2020-03-26 01:30:00 -0.629257  0.316317  0.895545  0.957914  0.933774   \n",
-       "2020-03-26 02:00:00 -0.514470  0.437113  0.814067  0.793395  0.584762   \n",
-       "2020-03-26 02:30:00 -0.392074  0.550470  0.721473  0.430136 -0.085096   \n",
-       "2020-03-26 03:00:00 -0.263881  0.654460  0.619026 -0.040868 -0.708264   \n",
-       "\n",
-       "                           S4       MK3        MM       SSA        SA  \n",
-       "TIME                                                                   \n",
-       "2009-07-15 08:00:00 -0.500000  0.370082  0.132683 -0.686775 -0.395743  \n",
-       "2009-07-15 08:10:00 -0.642788  0.494417  0.134147 -0.686601 -0.395853  \n",
-       "2009-07-15 08:20:00 -0.766044  0.610654  0.135610 -0.686427 -0.395963  \n",
-       "2009-07-15 08:30:00 -0.866025  0.716890  0.137073 -0.686253 -0.396072  \n",
-       "2009-07-15 08:40:00 -0.939693  0.811384  0.138535 -0.686080 -0.396182  \n",
-       "...                       ...       ...       ...       ...       ...  \n",
-       "2020-03-26 01:00:00  0.505439  1.028587 -0.881951  0.990514  0.997626  \n",
-       "2020-03-26 01:30:00  0.006292  0.851981 -0.880483  0.990416  0.997601  \n",
-       "2020-03-26 02:00:00 -0.494541  0.551159 -0.878996  0.990316  0.997576  \n",
-       "2020-03-26 02:30:00 -0.862862  0.169980 -0.877489  0.990217  0.997551  \n",
-       "2020-03-26 03:00:00 -0.999980 -0.235982 -0.875962  0.990116  0.997526  \n",
-       "\n",
-       "[239075 rows x 25 columns]"
-      ]
-     },
-     "execution_count": 40,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "xd.to_dataframe().drop(columns=['HEIGHT_ABOVE_SENSOR', 'NOMINAL_DEPTH'])#.columns#[['VCUR', 'UCUR', 'WCUR', 'TEMP', 'PRES_REL', 'DEPTH', 'ROLL', 'PITCH']]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T03:44:41.020269Z",
-     "start_time": "2020-10-26T03:44:41.017322Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "# for x in xds:\n",
-    "#     x.DEPTH.plot()\n",
-    "#     plt.ylim(190, 210)\n",
-    "\n",
-    "# plt.show()\n",
-    "# for x in xds:\n",
-    "#     x.plot.scatter('LONGITUDE', 'LONGITUDE')\n",
-    "# plt.show()\n",
-    "\n",
-    "# xd['VCUR'].plot(alpha=0.5)\n",
-    "# xd['UCUR'].plot(alpha=0.5)\n",
-    "# xd['WCUR'].plot(alpha=0.5)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T03:51:16.821117Z",
-     "start_time": "2020-10-26T03:51:16.606212Z"
-    }
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T03:51:17.614829Z",
-     "start_time": "2020-10-26T03:51:17.204376Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "PosixPath('../data/processed/currents/MOS_ANMN-WA_AETVZ_WATR20_FV01_WATR20-1909-Continental-194_currents.nc')"
-      ]
-     },
-     "execution_count": 18,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T03:51:18.335001Z",
-     "start_time": "2020-10-26T03:51:18.328504Z"
-    }
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "43.107293"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "seq2seq-time",
-   "language": "python",
-   "name": "seq2seq-time"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.8"
-  },
-  "toc": {
-   "base_numbering": 1,
-   "nav_menu": {},
-   "number_sections": true,
-   "sideBar": true,
-   "skip_h1_title": false,
-   "title_cell": "Table of Contents",
-   "title_sidebar": "Contents",
-   "toc_cell": false,
-   "toc_position": {
-    "height": "calc(100% - 180px)",
-    "left": "10px",
-    "top": "150px",
-    "width": "219.011px"
-   },
-   "toc_section_display": true,
-   "toc_window_display": true
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/notebooks/00.02-mc-load_data.ipynb b/notebooks/00.02-mc-load_data.ipynb
deleted file mode 100644
index 1ba5fe5..0000000
--- a/notebooks/00.02-mc-load_data.ipynb
+++ /dev/null
@@ -1,2009 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-25T07:08:04.786938Z",
-     "start_time": "2020-10-25T07:08:04.731940Z"
-    }
-   },
-   "source": [
-    "Here I load multiple multivariate timeseries regression datasets"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:24:49.597542Z",
-     "start_time": "2020-10-26T06:24:49.140731Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "# OPTIONAL: Load the \"autoreload\" extension so that code can change. But blacklist large modules\n",
-    "%load_ext autoreload\n",
-    "%autoreload 2\n",
-    "%aimport -pandas\n",
-    "%aimport -torch\n",
-    "%aimport -numpy\n",
-    "%aimport -matplotlib\n",
-    "%aimport -dask\n",
-    "%aimport -tqdm\n",
-    "%matplotlib inline"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:24:53.015854Z",
-     "start_time": "2020-10-26T06:24:49.600031Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "import pandas as pd\n",
-    "import numpy as np\n",
-    "import matplotlib.pyplot as plt\n",
-    "plt.rcParams['figure.figsize'] = (12.0, 3.0)\n",
-    "plt.style.use('ggplot')\n",
-    "\n",
-    "import holoviews as hv\n",
-    "from holoviews.operation.datashader import datashade, dynspread"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:24:53.571950Z",
-     "start_time": "2020-10-26T06:24:53.019038Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "import os\n",
-    "from tqdm.auto import tqdm\n",
-    "from pathlib import Path\n",
-    "from torchvision.datasets.utils import download_url, extract_archive, download_and_extract_archive"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:24:53.998896Z",
-     "start_time": "2020-10-26T06:24:53.574661Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "import sklearn\n",
-    "from sklearn.preprocessing import StandardScaler, OrdinalEncoder\n",
-    "from sklearn_pandas import DataFrameMapper\n",
-    "\n",
-    "def normalize_encode_dataframe(df, encoder=OrdinalEncoder):\n",
-    "    \"\"\"Normalise numeric data, encode categorical data.\"\"\"\n",
-    "    columns_input_numeric = list(df._get_numeric_data().columns)\n",
-    "    columns_categorical = list(set(df.columns)-set(columns_input_numeric))\n",
-    "    \n",
-    "    transformers= [([n], StandardScaler()) for n in columns_input_numeric] + \\\n",
-    "                  [([n], encoder()) for n in columns_categorical]\n",
-    "    scaler = DataFrameMapper(transformers, df_out=True)\n",
-    "    df_norm = scaler.fit_transform(df)\n",
-    "    return df_norm, scaler\n",
-    "    \n",
-    "def timeseries_split(df, test_fraction=0.2):\n",
-    "    \"\"\"Split timeseries data with test in the future\"\"\"\n",
-    "    i = int(len(df)*test_fraction)\n",
-    "    return df.iloc[:i], df.iloc[i:]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:24:54.050092Z",
-     "start_time": "2020-10-26T06:24:54.001084Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "from typing import List, Tuple\n",
-    "from seq2seq_time.data.dataset import Seq2SeqDataSet"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:24:54.095015Z",
-     "start_time": "2020-10-26T06:24:54.052468Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "datasets_root = Path('../data/processed/')"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:24:54.173346Z",
-     "start_time": "2020-10-26T06:24:54.097401Z"
-    }
-   },
-   "outputs": [],
-   "source": [
-    "class RegressionForecastData:   \n",
-    "    columns_forecast = None # The input colums which can be included in future (e.g. week or weather forecast)\n",
-    "    columns_target = None # Target columns\n",
-    "    \n",
-    "    def __init__(self, datasets_root):        \n",
-    "        self.datasets_root = datasets_root\n",
-    "        \n",
-    "        # Process data\n",
-    "        self.df = self.download()        \n",
-    "        self.df_norm, self.scaler = self.normalize(self.df)\n",
-    "        self.output_scaler = next(filter(lambda r:r[0][0] in self.columns_target, self.scaler.features))[-1]\n",
-    "        self.df_train, self.df_test = self.split(self.df_norm)\n",
-    "        \n",
-    "        # Check processing\n",
-    "        self.check()\n",
-    "    \n",
-    "    def download(self) -> pd.DataFrame:\n",
-    "        \"\"\"Implement this method to download data and return raw df\"\"\"\n",
-    "        raise NotImplementedError()\n",
-    "        return df\n",
-    "    \n",
-    "    def normalize(self, df) -> Tuple[pd.DataFrame, DataFrameMapper]:\n",
-    "        df_norm, scaler = normalize_encode_dataframe(df)\n",
-    "        return df_norm, scaler\n",
-    "    \n",
-    "    def split(self, df_norm: pd.DataFrame) -> Tuple[pd.DataFrame, pd.DataFrame]:\n",
-    "        df_train, df_test = timeseries_split(df_norm)\n",
-    "        return df_train, df_test \n",
-    "    \n",
-    "    def check(self) -> None:\n",
-    "        \"\"\"Check the resulting dataframe\"\"\"\n",
-    "        assert isinstance(self.df.index, pd.DatetimeIndex), 'index must be datetime'\n",
-    "        assert self.df.index.freq is not None, 'df must have freq'        \n",
-    "        assert self.columns_forecast is not None\n",
-    "        assert self.columns_target is not None\n",
-    "        assert ~set(self.columns_target).issubset(set(self.columns_forecast)), 'target columns should not be in forecast'\n",
-    "        assert set(self.columns_forecast).issubset(set(self.df.columns)), 'columns_forecast must be in df'\n",
-    "        assert set(self.columns_target).issubset(set(self.df.columns)), 'columns_target must be in df'\n",
-    "        \n",
-    "    def to_datasets(self, window_past: int, window_future: int, valid:bool=False) -> Tuple[Seq2SeqDataSet, Seq2SeqDataSet]:\n",
-    "        \"\"\"Convert to torch datasets\"\"\"\n",
-    "        ds_train = Seq2SeqDataSet(df_train, window_past=window_past, window_future=window_future, columns_target=self.columns_target, columns_past=self.columns_past)\n",
-    "        ds_test = Seq2SeqDataSet(df_test, window_past=window_past, window_future=window_future, columns_target=self.columns_target, columns_past=self.columns_past)\n",
-    "        return ds_train, ds_test\n",
-    "    \n",
-    "    def __repr__(self):\n",
-    "        return f'<{type(self).__name__} {self.df.shape if (self.df is not None) else None}>'"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:25:08.694514Z",
-     "start_time": "2020-10-26T06:24:54.177083Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<GasSensor (303034, 6)>\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>CO (ppm)</th>\n",
-       "      <th>Humidity (%r.h.)</th>\n",
-       "      <th>Temperature (C)</th>\n",
-       "      <th>Flow rate (mL/min)</th>\n",
-       "      <th>Heater voltage (V)</th>\n",
-       "      <th>R1 (MOhm)</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>Time (s)</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2016-10-16 05:36:55.800</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>48.4700</td>\n",
-       "      <td>24.6200</td>\n",
-       "      <td>247.4926</td>\n",
-       "      <td>0.2000</td>\n",
-       "      <td>0.6831</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-10-16 05:36:56.100</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>48.4700</td>\n",
-       "      <td>24.6200</td>\n",
-       "      <td>243.8282</td>\n",
-       "      <td>0.1998</td>\n",
-       "      <td>0.6649</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-10-16 05:36:56.400</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>48.4700</td>\n",
-       "      <td>24.6200</td>\n",
-       "      <td>243.0668</td>\n",
-       "      <td>0.2000</td>\n",
-       "      <td>0.6481</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-10-16 05:36:56.700</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>48.4700</td>\n",
-       "      <td>24.6200</td>\n",
-       "      <td>242.3030</td>\n",
-       "      <td>0.2000</td>\n",
-       "      <td>0.6318</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-10-16 05:36:57.000</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>48.4702</td>\n",
-       "      <td>24.6206</td>\n",
-       "      <td>241.5632</td>\n",
-       "      <td>0.2000</td>\n",
-       "      <td>0.6178</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-10-17 06:52:04.500</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>63.9400</td>\n",
-       "      <td>24.6200</td>\n",
-       "      <td>0.0000</td>\n",
-       "      <td>0.2080</td>\n",
-       "      <td>9.9322</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-10-17 06:52:04.800</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>63.9400</td>\n",
-       "      <td>24.6200</td>\n",
-       "      <td>0.0000</td>\n",
-       "      <td>0.2050</td>\n",
-       "      <td>31.7887</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-10-17 06:52:05.100</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>63.9400</td>\n",
-       "      <td>24.6200</td>\n",
-       "      <td>0.0000</td>\n",
-       "      <td>0.2040</td>\n",
-       "      <td>57.7304</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-10-17 06:52:05.400</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>63.9400</td>\n",
-       "      <td>24.6200</td>\n",
-       "      <td>0.0000</td>\n",
-       "      <td>0.2020</td>\n",
-       "      <td>71.9176</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-10-17 06:52:05.700</th>\n",
-       "      <td>0.0</td>\n",
-       "      <td>63.9400</td>\n",
-       "      <td>24.6200</td>\n",
-       "      <td>0.0000</td>\n",
-       "      <td>0.2010</td>\n",
-       "      <td>61.8035</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>303034 rows × 6 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                         CO (ppm)  Humidity (%r.h.)  Temperature (C)  \\\n",
-       "Time (s)                                                               \n",
-       "2016-10-16 05:36:55.800       0.0           48.4700          24.6200   \n",
-       "2016-10-16 05:36:56.100       0.0           48.4700          24.6200   \n",
-       "2016-10-16 05:36:56.400       0.0           48.4700          24.6200   \n",
-       "2016-10-16 05:36:56.700       0.0           48.4700          24.6200   \n",
-       "2016-10-16 05:36:57.000       0.0           48.4702          24.6206   \n",
-       "...                           ...               ...              ...   \n",
-       "2016-10-17 06:52:04.500       0.0           63.9400          24.6200   \n",
-       "2016-10-17 06:52:04.800       0.0           63.9400          24.6200   \n",
-       "2016-10-17 06:52:05.100       0.0           63.9400          24.6200   \n",
-       "2016-10-17 06:52:05.400       0.0           63.9400          24.6200   \n",
-       "2016-10-17 06:52:05.700       0.0           63.9400          24.6200   \n",
-       "\n",
-       "                         Flow rate (mL/min)  Heater voltage (V)  R1 (MOhm)  \n",
-       "Time (s)                                                                    \n",
-       "2016-10-16 05:36:55.800            247.4926              0.2000     0.6831  \n",
-       "2016-10-16 05:36:56.100            243.8282              0.1998     0.6649  \n",
-       "2016-10-16 05:36:56.400            243.0668              0.2000     0.6481  \n",
-       "2016-10-16 05:36:56.700            242.3030              0.2000     0.6318  \n",
-       "2016-10-16 05:36:57.000            241.5632              0.2000     0.6178  \n",
-       "...                                     ...                 ...        ...  \n",
-       "2016-10-17 06:52:04.500              0.0000              0.2080     9.9322  \n",
-       "2016-10-17 06:52:04.800              0.0000              0.2050    31.7887  \n",
-       "2016-10-17 06:52:05.100              0.0000              0.2040    57.7304  \n",
-       "2016-10-17 06:52:05.400              0.0000              0.2020    71.9176  \n",
-       "2016-10-17 06:52:05.700              0.0000              0.2010    61.8035  \n",
-       "\n",
-       "[303034 rows x 6 columns]"
-      ]
-     },
-     "execution_count": 8,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 864x216 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "class GasSensor(RegressionForecastData):\n",
-    "    \"\"\"\n",
-    "    See: http://archive.ics.uci.edu/ml/datasets/Gas+sensor+array+temperature+modulation\n",
-    "    \"\"\"\n",
-    "    \n",
-    "    columns_target = ['R1 (MOhm)']\n",
-    "    columns_forecast = ['Flow rate (mL/min)', 'Heater voltage (V)']\n",
-    "    \n",
-    "    def download(self):\n",
-    "        url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00487/gas-sensor-array-temperature-modulation.zip'\n",
-    "        \n",
-    "        # download if needed\n",
-    "        extract_path = self.datasets_root/'GasSensor'\n",
-    "        files = sorted(extract_path.glob('*.csv'))\n",
-    "        if len(files)<13:\n",
-    "            print('download_and_extract_archive')\n",
-    "            download_and_extract_archive(url, self.datasets_root, extract_path)\n",
-    "        \n",
-    "        # Load csv's\n",
-    "        files = sorted(extract_path.glob('*.csv'))\n",
-    "        dfs = []\n",
-    "        for f in files:\n",
-    "            now = pd.to_datetime(f.stem, format='%Y%m%d_%H%M%S')\n",
-    "            df = pd.read_csv(f)\n",
-    "            df.index = pd.to_timedelta(df['Time (s)'], unit='s') + now\n",
-    "            dfs.append(df)\n",
-    "        self.df = pd.concat(dfs).dropna(subset=self.columns_target)\n",
-    "\n",
-    "        df = df[[ 'CO (ppm)', 'Humidity (%r.h.)', 'Temperature (C)',\n",
-    "               'Flow rate (mL/min)', 'Heater voltage (V)', 'R1 (MOhm)']]\n",
-    "        df = df.resample('0.3S').first()\n",
-    "        \n",
-    "        return df\n",
-    "dataset = GasSensor(datasets_root)\n",
-    "print(dataset)\n",
-    "dataset.df[dataset.columns_target].head(1000).plot()\n",
-    "dataset.df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T01:01:04.653709Z",
-     "start_time": "2020-10-26T01:01:04.524050Z"
-    }
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:25:12.274174Z",
-     "start_time": "2020-10-26T06:25:08.697022Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Downloading https://archive.ics.uci.edu/ml/machine-learning-databases/00492/Metro_Interstate_Traffic_Volume.csv.gz to ../data/processed/00492_Metro_Interstate_Traffic_Volume.csv.gz\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "364da475e08247948c34e2a122b03920",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "HBox(children=(HTML(value=''), FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0…"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<MetroInterstateTraffic (52551, 14)>\n",
-      "\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>holiday</th>\n",
-       "      <th>temp</th>\n",
-       "      <th>rain_1h</th>\n",
-       "      <th>snow_1h</th>\n",
-       "      <th>clouds_all</th>\n",
-       "      <th>weather_main</th>\n",
-       "      <th>weather_description</th>\n",
-       "      <th>traffic_volume</th>\n",
-       "      <th>month</th>\n",
-       "      <th>day</th>\n",
-       "      <th>week</th>\n",
-       "      <th>hour</th>\n",
-       "      <th>minute</th>\n",
-       "      <th>dayofweek</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>date_time</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 09:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>288.28</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>40.0</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>scattered clouds</td>\n",
-       "      <td>5545.0</td>\n",
-       "      <td>10</td>\n",
-       "      <td>2</td>\n",
-       "      <td>40</td>\n",
-       "      <td>9</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 10:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>289.36</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>75.0</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>broken clouds</td>\n",
-       "      <td>4516.0</td>\n",
-       "      <td>10</td>\n",
-       "      <td>2</td>\n",
-       "      <td>40</td>\n",
-       "      <td>10</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 11:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>289.58</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90.0</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>4767.0</td>\n",
-       "      <td>10</td>\n",
-       "      <td>2</td>\n",
-       "      <td>40</td>\n",
-       "      <td>11</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 12:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>290.13</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90.0</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>5026.0</td>\n",
-       "      <td>10</td>\n",
-       "      <td>2</td>\n",
-       "      <td>40</td>\n",
-       "      <td>12</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2012-10-02 13:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>291.14</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>75.0</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>broken clouds</td>\n",
-       "      <td>4918.0</td>\n",
-       "      <td>10</td>\n",
-       "      <td>2</td>\n",
-       "      <td>40</td>\n",
-       "      <td>13</td>\n",
-       "      <td>0</td>\n",
-       "      <td>1</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 19:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>283.45</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>75.0</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>broken clouds</td>\n",
-       "      <td>3543.0</td>\n",
-       "      <td>9</td>\n",
-       "      <td>30</td>\n",
-       "      <td>39</td>\n",
-       "      <td>19</td>\n",
-       "      <td>0</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 20:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>282.76</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90.0</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>2781.0</td>\n",
-       "      <td>9</td>\n",
-       "      <td>30</td>\n",
-       "      <td>39</td>\n",
-       "      <td>20</td>\n",
-       "      <td>0</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 21:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>282.73</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90.0</td>\n",
-       "      <td>Thunderstorm</td>\n",
-       "      <td>proximity thunderstorm</td>\n",
-       "      <td>2159.0</td>\n",
-       "      <td>9</td>\n",
-       "      <td>30</td>\n",
-       "      <td>39</td>\n",
-       "      <td>21</td>\n",
-       "      <td>0</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 22:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>282.09</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90.0</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>1450.0</td>\n",
-       "      <td>9</td>\n",
-       "      <td>30</td>\n",
-       "      <td>39</td>\n",
-       "      <td>22</td>\n",
-       "      <td>0</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2018-09-30 23:00:00</th>\n",
-       "      <td>True</td>\n",
-       "      <td>282.12</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>90.0</td>\n",
-       "      <td>Clouds</td>\n",
-       "      <td>overcast clouds</td>\n",
-       "      <td>954.0</td>\n",
-       "      <td>9</td>\n",
-       "      <td>30</td>\n",
-       "      <td>39</td>\n",
-       "      <td>23</td>\n",
-       "      <td>0</td>\n",
-       "      <td>6</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>52551 rows × 14 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                     holiday    temp  rain_1h  snow_1h  clouds_all  \\\n",
-       "date_time                                                            \n",
-       "2012-10-02 09:00:00     True  288.28      0.0      0.0        40.0   \n",
-       "2012-10-02 10:00:00     True  289.36      0.0      0.0        75.0   \n",
-       "2012-10-02 11:00:00     True  289.58      0.0      0.0        90.0   \n",
-       "2012-10-02 12:00:00     True  290.13      0.0      0.0        90.0   \n",
-       "2012-10-02 13:00:00     True  291.14      0.0      0.0        75.0   \n",
-       "...                      ...     ...      ...      ...         ...   \n",
-       "2018-09-30 19:00:00     True  283.45      0.0      0.0        75.0   \n",
-       "2018-09-30 20:00:00     True  282.76      0.0      0.0        90.0   \n",
-       "2018-09-30 21:00:00     True  282.73      0.0      0.0        90.0   \n",
-       "2018-09-30 22:00:00     True  282.09      0.0      0.0        90.0   \n",
-       "2018-09-30 23:00:00     True  282.12      0.0      0.0        90.0   \n",
-       "\n",
-       "                     weather_main     weather_description  traffic_volume  \\\n",
-       "date_time                                                                   \n",
-       "2012-10-02 09:00:00        Clouds        scattered clouds          5545.0   \n",
-       "2012-10-02 10:00:00        Clouds           broken clouds          4516.0   \n",
-       "2012-10-02 11:00:00        Clouds         overcast clouds          4767.0   \n",
-       "2012-10-02 12:00:00        Clouds         overcast clouds          5026.0   \n",
-       "2012-10-02 13:00:00        Clouds           broken clouds          4918.0   \n",
-       "...                           ...                     ...             ...   \n",
-       "2018-09-30 19:00:00        Clouds           broken clouds          3543.0   \n",
-       "2018-09-30 20:00:00        Clouds         overcast clouds          2781.0   \n",
-       "2018-09-30 21:00:00  Thunderstorm  proximity thunderstorm          2159.0   \n",
-       "2018-09-30 22:00:00        Clouds         overcast clouds          1450.0   \n",
-       "2018-09-30 23:00:00        Clouds         overcast clouds           954.0   \n",
-       "\n",
-       "                     month  day  week  hour  minute  dayofweek  \n",
-       "date_time                                                       \n",
-       "2012-10-02 09:00:00     10    2    40     9       0          1  \n",
-       "2012-10-02 10:00:00     10    2    40    10       0          1  \n",
-       "2012-10-02 11:00:00     10    2    40    11       0          1  \n",
-       "2012-10-02 12:00:00     10    2    40    12       0          1  \n",
-       "2012-10-02 13:00:00     10    2    40    13       0          1  \n",
-       "...                    ...  ...   ...   ...     ...        ...  \n",
-       "2018-09-30 19:00:00      9   30    39    19       0          6  \n",
-       "2018-09-30 20:00:00      9   30    39    20       0          6  \n",
-       "2018-09-30 21:00:00      9   30    39    21       0          6  \n",
-       "2018-09-30 22:00:00      9   30    39    22       0          6  \n",
-       "2018-09-30 23:00:00      9   30    39    23       0          6  \n",
-       "\n",
-       "[52551 rows x 14 columns]"
-      ]
-     },
-     "execution_count": 9,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 864x216 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "class MetroInterstateTraffic(RegressionForecastData):\n",
-    "    \"\"\"\n",
-    "    See: https://archive.ics.uci.edu/ml/datasets/Metro+Interstate+Traffic+Volume\n",
-    "    \"\"\"\n",
-    "    \n",
-    "    columns_target = ['traffic_volume']\n",
-    "    columns_forecast = ['holiday', 'month', 'day', 'week', 'hour',\n",
-    "       'minute', 'dayofweek']\n",
-    "    \n",
-    "    def download(self):\n",
-    "        url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00492/Metro_Interstate_Traffic_Volume.csv.gz'\n",
-    "        \n",
-    "        # download if needed\n",
-    "        filename = '00492_Metro_Interstate_Traffic_Volume.csv.gz'\n",
-    "        local_path = self.datasets_root/filename\n",
-    "        if not local_path.exists():\n",
-    "            download_url(url, self.datasets_root, filename)\n",
-    "        df = (pd.read_csv(local_path, index_col='date_time', parse_dates=['date_time'])\n",
-    "              .dropna(subset=self.columns_target)\n",
-    "              .resample('1H').first()\n",
-    "             )\n",
-    "        \n",
-    "        # Make holiday a bool\n",
-    "        df['holiday'] = ~df['holiday'].isna()\n",
-    "        df['weather_main'] = df['weather_main'].fillna('none')\n",
-    "        df['weather_description'] = df['weather_description'].fillna('none')\n",
-    "        \n",
-    "        # Add time features \n",
-    "        time = df.index.to_series()\n",
-    "        df[\"month\"] = time.dt.month\n",
-    "        df['day'] = time.dt.day\n",
-    "        df['week'] = time.dt.isocalendar().week\n",
-    "        df['hour'] = time.dt.hour\n",
-    "        df['minute'] = time.dt.minute\n",
-    "        df['dayofweek'] = time.dt.dayofweek\n",
-    "        \n",
-    "        return df\n",
-    "    \n",
-    "\n",
-    "dataset = MetroInterstateTraffic(datasets_root)\n",
-    "dataset.df[dataset.columns_target].head(1000).plot()\n",
-    "print(dataset)\n",
-    "dataset.df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:20:52.874642Z",
-     "start_time": "2020-10-26T06:20:52.003940Z"
-    }
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:25:17.829014Z",
-     "start_time": "2020-10-26T06:25:12.276854Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Downloading https://archive.ics.uci.edu/ml/machine-learning-databases/00374/energydata_complete.csv to ../data/processed/00374_AppliancesEnergyPrediction.csv\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3a5bcd8759bb45faabdc3a9061f15abd",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "HBox(children=(HTML(value=''), FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0…"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<AppliancesEnergyPrediction (19735, 34)>\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>lights</th>\n",
-       "      <th>T1</th>\n",
-       "      <th>RH_1</th>\n",
-       "      <th>T2</th>\n",
-       "      <th>RH_2</th>\n",
-       "      <th>T3</th>\n",
-       "      <th>RH_3</th>\n",
-       "      <th>T4</th>\n",
-       "      <th>RH_4</th>\n",
-       "      <th>T5</th>\n",
-       "      <th>...</th>\n",
-       "      <th>Tdewpoint</th>\n",
-       "      <th>rv1</th>\n",
-       "      <th>rv2</th>\n",
-       "      <th>log_Appliances</th>\n",
-       "      <th>month</th>\n",
-       "      <th>day</th>\n",
-       "      <th>week</th>\n",
-       "      <th>hour</th>\n",
-       "      <th>minute</th>\n",
-       "      <th>dayofweek</th>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>date</th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "      <th></th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:00:00</th>\n",
-       "      <td>30</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>47.596667</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.790000</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>44.730000</td>\n",
-       "      <td>19.000000</td>\n",
-       "      <td>45.566667</td>\n",
-       "      <td>17.166667</td>\n",
-       "      <td>...</td>\n",
-       "      <td>5.300000</td>\n",
-       "      <td>13.275433</td>\n",
-       "      <td>13.275433</td>\n",
-       "      <td>4.094345</td>\n",
-       "      <td>1</td>\n",
-       "      <td>11</td>\n",
-       "      <td>2</td>\n",
-       "      <td>17</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:10:00</th>\n",
-       "      <td>30</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>46.693333</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.722500</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>44.790000</td>\n",
-       "      <td>19.000000</td>\n",
-       "      <td>45.992500</td>\n",
-       "      <td>17.166667</td>\n",
-       "      <td>...</td>\n",
-       "      <td>5.200000</td>\n",
-       "      <td>18.606195</td>\n",
-       "      <td>18.606195</td>\n",
-       "      <td>4.094345</td>\n",
-       "      <td>1</td>\n",
-       "      <td>11</td>\n",
-       "      <td>2</td>\n",
-       "      <td>17</td>\n",
-       "      <td>10</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:20:00</th>\n",
-       "      <td>30</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>46.300000</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.626667</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>44.933333</td>\n",
-       "      <td>18.926667</td>\n",
-       "      <td>45.890000</td>\n",
-       "      <td>17.166667</td>\n",
-       "      <td>...</td>\n",
-       "      <td>5.100000</td>\n",
-       "      <td>28.642668</td>\n",
-       "      <td>28.642668</td>\n",
-       "      <td>3.912023</td>\n",
-       "      <td>1</td>\n",
-       "      <td>11</td>\n",
-       "      <td>2</td>\n",
-       "      <td>17</td>\n",
-       "      <td>20</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:30:00</th>\n",
-       "      <td>40</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>46.066667</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.590000</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>45.000000</td>\n",
-       "      <td>18.890000</td>\n",
-       "      <td>45.723333</td>\n",
-       "      <td>17.166667</td>\n",
-       "      <td>...</td>\n",
-       "      <td>5.000000</td>\n",
-       "      <td>45.410389</td>\n",
-       "      <td>45.410389</td>\n",
-       "      <td>3.912023</td>\n",
-       "      <td>1</td>\n",
-       "      <td>11</td>\n",
-       "      <td>2</td>\n",
-       "      <td>17</td>\n",
-       "      <td>30</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-01-11 17:40:00</th>\n",
-       "      <td>40</td>\n",
-       "      <td>19.890000</td>\n",
-       "      <td>46.333333</td>\n",
-       "      <td>19.200000</td>\n",
-       "      <td>44.530000</td>\n",
-       "      <td>19.790000</td>\n",
-       "      <td>45.000000</td>\n",
-       "      <td>18.890000</td>\n",
-       "      <td>45.530000</td>\n",
-       "      <td>17.200000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>4.900000</td>\n",
-       "      <td>10.084097</td>\n",
-       "      <td>10.084097</td>\n",
-       "      <td>4.094345</td>\n",
-       "      <td>1</td>\n",
-       "      <td>11</td>\n",
-       "      <td>2</td>\n",
-       "      <td>17</td>\n",
-       "      <td>40</td>\n",
-       "      <td>0</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 17:20:00</th>\n",
-       "      <td>0</td>\n",
-       "      <td>25.566667</td>\n",
-       "      <td>46.560000</td>\n",
-       "      <td>25.890000</td>\n",
-       "      <td>42.025714</td>\n",
-       "      <td>27.200000</td>\n",
-       "      <td>41.163333</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>45.590000</td>\n",
-       "      <td>23.200000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>13.333333</td>\n",
-       "      <td>43.096812</td>\n",
-       "      <td>43.096812</td>\n",
-       "      <td>4.605170</td>\n",
-       "      <td>5</td>\n",
-       "      <td>27</td>\n",
-       "      <td>21</td>\n",
-       "      <td>17</td>\n",
-       "      <td>20</td>\n",
-       "      <td>4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 17:30:00</th>\n",
-       "      <td>0</td>\n",
-       "      <td>25.500000</td>\n",
-       "      <td>46.500000</td>\n",
-       "      <td>25.754000</td>\n",
-       "      <td>42.080000</td>\n",
-       "      <td>27.133333</td>\n",
-       "      <td>41.223333</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>45.590000</td>\n",
-       "      <td>23.230000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>13.300000</td>\n",
-       "      <td>49.282940</td>\n",
-       "      <td>49.282940</td>\n",
-       "      <td>4.499810</td>\n",
-       "      <td>5</td>\n",
-       "      <td>27</td>\n",
-       "      <td>21</td>\n",
-       "      <td>17</td>\n",
-       "      <td>30</td>\n",
-       "      <td>4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 17:40:00</th>\n",
-       "      <td>10</td>\n",
-       "      <td>25.500000</td>\n",
-       "      <td>46.596667</td>\n",
-       "      <td>25.628571</td>\n",
-       "      <td>42.768571</td>\n",
-       "      <td>27.050000</td>\n",
-       "      <td>41.690000</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>45.730000</td>\n",
-       "      <td>23.230000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>13.266667</td>\n",
-       "      <td>29.199117</td>\n",
-       "      <td>29.199117</td>\n",
-       "      <td>5.598422</td>\n",
-       "      <td>5</td>\n",
-       "      <td>27</td>\n",
-       "      <td>21</td>\n",
-       "      <td>17</td>\n",
-       "      <td>40</td>\n",
-       "      <td>4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 17:50:00</th>\n",
-       "      <td>10</td>\n",
-       "      <td>25.500000</td>\n",
-       "      <td>46.990000</td>\n",
-       "      <td>25.414000</td>\n",
-       "      <td>43.036000</td>\n",
-       "      <td>26.890000</td>\n",
-       "      <td>41.290000</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>45.790000</td>\n",
-       "      <td>23.200000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>13.233333</td>\n",
-       "      <td>6.322784</td>\n",
-       "      <td>6.322784</td>\n",
-       "      <td>6.040255</td>\n",
-       "      <td>5</td>\n",
-       "      <td>27</td>\n",
-       "      <td>21</td>\n",
-       "      <td>17</td>\n",
-       "      <td>50</td>\n",
-       "      <td>4</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2016-05-27 18:00:00</th>\n",
-       "      <td>10</td>\n",
-       "      <td>25.500000</td>\n",
-       "      <td>46.600000</td>\n",
-       "      <td>25.264286</td>\n",
-       "      <td>42.971429</td>\n",
-       "      <td>26.823333</td>\n",
-       "      <td>41.156667</td>\n",
-       "      <td>24.700000</td>\n",
-       "      <td>45.963333</td>\n",
-       "      <td>23.200000</td>\n",
-       "      <td>...</td>\n",
-       "      <td>13.200000</td>\n",
-       "      <td>34.118851</td>\n",
-       "      <td>34.118851</td>\n",
-       "      <td>6.063785</td>\n",
-       "      <td>5</td>\n",
-       "      <td>27</td>\n",
-       "      <td>21</td>\n",
-       "      <td>18</td>\n",
-       "      <td>0</td>\n",
-       "      <td>4</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>19735 rows × 34 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                     lights         T1       RH_1         T2       RH_2  \\\n",
-       "date                                                                      \n",
-       "2016-01-11 17:00:00      30  19.890000  47.596667  19.200000  44.790000   \n",
-       "2016-01-11 17:10:00      30  19.890000  46.693333  19.200000  44.722500   \n",
-       "2016-01-11 17:20:00      30  19.890000  46.300000  19.200000  44.626667   \n",
-       "2016-01-11 17:30:00      40  19.890000  46.066667  19.200000  44.590000   \n",
-       "2016-01-11 17:40:00      40  19.890000  46.333333  19.200000  44.530000   \n",
-       "...                     ...        ...        ...        ...        ...   \n",
-       "2016-05-27 17:20:00       0  25.566667  46.560000  25.890000  42.025714   \n",
-       "2016-05-27 17:30:00       0  25.500000  46.500000  25.754000  42.080000   \n",
-       "2016-05-27 17:40:00      10  25.500000  46.596667  25.628571  42.768571   \n",
-       "2016-05-27 17:50:00      10  25.500000  46.990000  25.414000  43.036000   \n",
-       "2016-05-27 18:00:00      10  25.500000  46.600000  25.264286  42.971429   \n",
-       "\n",
-       "                            T3       RH_3         T4       RH_4         T5  \\\n",
-       "date                                                                         \n",
-       "2016-01-11 17:00:00  19.790000  44.730000  19.000000  45.566667  17.166667   \n",
-       "2016-01-11 17:10:00  19.790000  44.790000  19.000000  45.992500  17.166667   \n",
-       "2016-01-11 17:20:00  19.790000  44.933333  18.926667  45.890000  17.166667   \n",
-       "2016-01-11 17:30:00  19.790000  45.000000  18.890000  45.723333  17.166667   \n",
-       "2016-01-11 17:40:00  19.790000  45.000000  18.890000  45.530000  17.200000   \n",
-       "...                        ...        ...        ...        ...        ...   \n",
-       "2016-05-27 17:20:00  27.200000  41.163333  24.700000  45.590000  23.200000   \n",
-       "2016-05-27 17:30:00  27.133333  41.223333  24.700000  45.590000  23.230000   \n",
-       "2016-05-27 17:40:00  27.050000  41.690000  24.700000  45.730000  23.230000   \n",
-       "2016-05-27 17:50:00  26.890000  41.290000  24.700000  45.790000  23.200000   \n",
-       "2016-05-27 18:00:00  26.823333  41.156667  24.700000  45.963333  23.200000   \n",
-       "\n",
-       "                     ...  Tdewpoint        rv1        rv2  log_Appliances  \\\n",
-       "date                 ...                                                    \n",
-       "2016-01-11 17:00:00  ...   5.300000  13.275433  13.275433        4.094345   \n",
-       "2016-01-11 17:10:00  ...   5.200000  18.606195  18.606195        4.094345   \n",
-       "2016-01-11 17:20:00  ...   5.100000  28.642668  28.642668        3.912023   \n",
-       "2016-01-11 17:30:00  ...   5.000000  45.410389  45.410389        3.912023   \n",
-       "2016-01-11 17:40:00  ...   4.900000  10.084097  10.084097        4.094345   \n",
-       "...                  ...        ...        ...        ...             ...   \n",
-       "2016-05-27 17:20:00  ...  13.333333  43.096812  43.096812        4.605170   \n",
-       "2016-05-27 17:30:00  ...  13.300000  49.282940  49.282940        4.499810   \n",
-       "2016-05-27 17:40:00  ...  13.266667  29.199117  29.199117        5.598422   \n",
-       "2016-05-27 17:50:00  ...  13.233333   6.322784   6.322784        6.040255   \n",
-       "2016-05-27 18:00:00  ...  13.200000  34.118851  34.118851        6.063785   \n",
-       "\n",
-       "                     month  day  week  hour  minute  dayofweek  \n",
-       "date                                                            \n",
-       "2016-01-11 17:00:00      1   11     2    17       0          0  \n",
-       "2016-01-11 17:10:00      1   11     2    17      10          0  \n",
-       "2016-01-11 17:20:00      1   11     2    17      20          0  \n",
-       "2016-01-11 17:30:00      1   11     2    17      30          0  \n",
-       "2016-01-11 17:40:00      1   11     2    17      40          0  \n",
-       "...                    ...  ...   ...   ...     ...        ...  \n",
-       "2016-05-27 17:20:00      5   27    21    17      20          4  \n",
-       "2016-05-27 17:30:00      5   27    21    17      30          4  \n",
-       "2016-05-27 17:40:00      5   27    21    17      40          4  \n",
-       "2016-05-27 17:50:00      5   27    21    17      50          4  \n",
-       "2016-05-27 18:00:00      5   27    21    18       0          4  \n",
-       "\n",
-       "[19735 rows x 34 columns]"
-      ]
-     },
-     "execution_count": 10,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 864x216 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "class AppliancesEnergyPrediction(RegressionForecastData):\n",
-    "    \"\"\"\n",
-    "    See: https://archive.ics.uci.edu/ml/datasets/Appliances+energy+prediction\n",
-    "    \"\"\"\n",
-    "    \n",
-    "    columns_target = ['log_Appliances']\n",
-    "    columns_forecast = ['month', 'day', 'week', 'hour',\n",
-    "       'minute', 'dayofweek']\n",
-    "    \n",
-    "    def download(self):\n",
-    "        url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00374/energydata_complete.csv'\n",
-    "        \n",
-    "        # download if needed\n",
-    "        filename = '00374_AppliancesEnergyPrediction.csv'\n",
-    "        local_path = self.datasets_root/filename\n",
-    "        if not local_path.exists():\n",
-    "            download_url(url, self.datasets_root, filename)\n",
-    "        df = pd.read_csv(local_path, index_col='date', parse_dates=['date'])\n",
-    "        \n",
-    "        # log target\n",
-    "        df['log_Appliances'] = np.log(df['Appliances'] + 1e-5)\n",
-    "        df = df.drop(columns=['Appliances'])\n",
-    "        df = df.dropna(subset=self.columns_target).resample('10T').first()\n",
-    "        \n",
-    "        # Add time features \n",
-    "        time = df.index.to_series()\n",
-    "        df[\"month\"] = time.dt.month\n",
-    "        df['day'] = time.dt.day\n",
-    "        df['week'] = time.dt.isocalendar().week\n",
-    "        df['hour'] = time.dt.hour\n",
-    "        df['minute'] = time.dt.minute\n",
-    "        df['dayofweek'] = time.dt.dayofweek\n",
-    "        \n",
-    "        return df\n",
-    "dataset = AppliancesEnergyPrediction(datasets_root)\n",
-    "print(dataset)\n",
-    "dataset.df[dataset.columns_target].head(1000).plot()\n",
-    "dataset.df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:19:53.791396Z",
-     "start_time": "2020-10-26T06:19:53.476265Z"
-    }
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:25:20.668980Z",
-     "start_time": "2020-10-26T06:25:17.831622Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Downloading http://archive.ics.uci.edu/ml/machine-learning-databases/00381/PRSA_data_2010.1.1-2014.12.31.csv to ../data/processed/00381_BejingPM25.csv\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d479f39fd7714412a2ca8189861a74f6",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "HBox(children=(HTML(value=''), FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0…"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "<BejingPM25 (43800, 14)>\n"
-     ]
-    },
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>DEWP</th>\n",
-       "      <th>TEMP</th>\n",
-       "      <th>PRES</th>\n",
-       "      <th>cbwd</th>\n",
-       "      <th>Iws</th>\n",
-       "      <th>Is</th>\n",
-       "      <th>Ir</th>\n",
-       "      <th>log_pm2.5</th>\n",
-       "      <th>month</th>\n",
-       "      <th>day</th>\n",
-       "      <th>week</th>\n",
-       "      <th>hour</th>\n",
-       "      <th>minute</th>\n",
-       "      <th>dayofweek</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>2010-01-02 00:00:00+08:00</th>\n",
-       "      <td>-16.0</td>\n",
-       "      <td>-4.0</td>\n",
-       "      <td>1020.0</td>\n",
-       "      <td>SE</td>\n",
-       "      <td>1.79</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>4.859812</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>53</td>\n",
-       "      <td>0</td>\n",
-       "      <td>0</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2010-01-02 01:00:00+08:00</th>\n",
-       "      <td>-15.0</td>\n",
-       "      <td>-4.0</td>\n",
-       "      <td>1020.0</td>\n",
-       "      <td>SE</td>\n",
-       "      <td>2.68</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>4.997212</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>53</td>\n",
-       "      <td>1</td>\n",
-       "      <td>0</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2010-01-02 02:00:00+08:00</th>\n",
-       "      <td>-11.0</td>\n",
-       "      <td>-5.0</td>\n",
-       "      <td>1021.0</td>\n",
-       "      <td>SE</td>\n",
-       "      <td>3.57</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5.068904</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>53</td>\n",
-       "      <td>2</td>\n",
-       "      <td>0</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2010-01-02 03:00:00+08:00</th>\n",
-       "      <td>-7.0</td>\n",
-       "      <td>-5.0</td>\n",
-       "      <td>1022.0</td>\n",
-       "      <td>SE</td>\n",
-       "      <td>5.36</td>\n",
-       "      <td>1.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>5.198497</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>53</td>\n",
-       "      <td>3</td>\n",
-       "      <td>0</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2010-01-02 04:00:00+08:00</th>\n",
-       "      <td>-7.0</td>\n",
-       "      <td>-5.0</td>\n",
-       "      <td>1022.0</td>\n",
-       "      <td>SE</td>\n",
-       "      <td>6.25</td>\n",
-       "      <td>2.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>4.927254</td>\n",
-       "      <td>1</td>\n",
-       "      <td>2</td>\n",
-       "      <td>53</td>\n",
-       "      <td>4</td>\n",
-       "      <td>0</td>\n",
-       "      <td>5</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>...</th>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "      <td>...</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 19:00:00+08:00</th>\n",
-       "      <td>-23.0</td>\n",
-       "      <td>-2.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>231.97</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>2.079443</td>\n",
-       "      <td>12</td>\n",
-       "      <td>31</td>\n",
-       "      <td>1</td>\n",
-       "      <td>19</td>\n",
-       "      <td>0</td>\n",
-       "      <td>2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 20:00:00+08:00</th>\n",
-       "      <td>-22.0</td>\n",
-       "      <td>-3.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>237.78</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>2.302586</td>\n",
-       "      <td>12</td>\n",
-       "      <td>31</td>\n",
-       "      <td>1</td>\n",
-       "      <td>20</td>\n",
-       "      <td>0</td>\n",
-       "      <td>2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 21:00:00+08:00</th>\n",
-       "      <td>-22.0</td>\n",
-       "      <td>-3.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>242.70</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>2.302586</td>\n",
-       "      <td>12</td>\n",
-       "      <td>31</td>\n",
-       "      <td>1</td>\n",
-       "      <td>21</td>\n",
-       "      <td>0</td>\n",
-       "      <td>2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 22:00:00+08:00</th>\n",
-       "      <td>-22.0</td>\n",
-       "      <td>-4.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>246.72</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>2.079443</td>\n",
-       "      <td>12</td>\n",
-       "      <td>31</td>\n",
-       "      <td>1</td>\n",
-       "      <td>22</td>\n",
-       "      <td>0</td>\n",
-       "      <td>2</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2014-12-31 23:00:00+08:00</th>\n",
-       "      <td>-21.0</td>\n",
-       "      <td>-3.0</td>\n",
-       "      <td>1034.0</td>\n",
-       "      <td>NW</td>\n",
-       "      <td>249.85</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>0.0</td>\n",
-       "      <td>2.484907</td>\n",
-       "      <td>12</td>\n",
-       "      <td>31</td>\n",
-       "      <td>1</td>\n",
-       "      <td>23</td>\n",
-       "      <td>0</td>\n",
-       "      <td>2</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "<p>43800 rows × 14 columns</p>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "                           DEWP  TEMP    PRES cbwd     Iws   Is   Ir  \\\n",
-       "2010-01-02 00:00:00+08:00 -16.0  -4.0  1020.0   SE    1.79  0.0  0.0   \n",
-       "2010-01-02 01:00:00+08:00 -15.0  -4.0  1020.0   SE    2.68  0.0  0.0   \n",
-       "2010-01-02 02:00:00+08:00 -11.0  -5.0  1021.0   SE    3.57  0.0  0.0   \n",
-       "2010-01-02 03:00:00+08:00  -7.0  -5.0  1022.0   SE    5.36  1.0  0.0   \n",
-       "2010-01-02 04:00:00+08:00  -7.0  -5.0  1022.0   SE    6.25  2.0  0.0   \n",
-       "...                         ...   ...     ...  ...     ...  ...  ...   \n",
-       "2014-12-31 19:00:00+08:00 -23.0  -2.0  1034.0   NW  231.97  0.0  0.0   \n",
-       "2014-12-31 20:00:00+08:00 -22.0  -3.0  1034.0   NW  237.78  0.0  0.0   \n",
-       "2014-12-31 21:00:00+08:00 -22.0  -3.0  1034.0   NW  242.70  0.0  0.0   \n",
-       "2014-12-31 22:00:00+08:00 -22.0  -4.0  1034.0   NW  246.72  0.0  0.0   \n",
-       "2014-12-31 23:00:00+08:00 -21.0  -3.0  1034.0   NW  249.85  0.0  0.0   \n",
-       "\n",
-       "                           log_pm2.5  month  day  week  hour  minute  \\\n",
-       "2010-01-02 00:00:00+08:00   4.859812      1    2    53     0       0   \n",
-       "2010-01-02 01:00:00+08:00   4.997212      1    2    53     1       0   \n",
-       "2010-01-02 02:00:00+08:00   5.068904      1    2    53     2       0   \n",
-       "2010-01-02 03:00:00+08:00   5.198497      1    2    53     3       0   \n",
-       "2010-01-02 04:00:00+08:00   4.927254      1    2    53     4       0   \n",
-       "...                              ...    ...  ...   ...   ...     ...   \n",
-       "2014-12-31 19:00:00+08:00   2.079443     12   31     1    19       0   \n",
-       "2014-12-31 20:00:00+08:00   2.302586     12   31     1    20       0   \n",
-       "2014-12-31 21:00:00+08:00   2.302586     12   31     1    21       0   \n",
-       "2014-12-31 22:00:00+08:00   2.079443     12   31     1    22       0   \n",
-       "2014-12-31 23:00:00+08:00   2.484907     12   31     1    23       0   \n",
-       "\n",
-       "                           dayofweek  \n",
-       "2010-01-02 00:00:00+08:00          5  \n",
-       "2010-01-02 01:00:00+08:00          5  \n",
-       "2010-01-02 02:00:00+08:00          5  \n",
-       "2010-01-02 03:00:00+08:00          5  \n",
-       "2010-01-02 04:00:00+08:00          5  \n",
-       "...                              ...  \n",
-       "2014-12-31 19:00:00+08:00          2  \n",
-       "2014-12-31 20:00:00+08:00          2  \n",
-       "2014-12-31 21:00:00+08:00          2  \n",
-       "2014-12-31 22:00:00+08:00          2  \n",
-       "2014-12-31 23:00:00+08:00          2  \n",
-       "\n",
-       "[43800 rows x 14 columns]"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "\n"
-     ]
-    },
-    {
-     "data": {
-      "image/png": "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\n",
-      "text/plain": [
-       "<Figure size 864x216 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "class BejingPM25(RegressionForecastData):\n",
-    "    \"\"\"\n",
-    "    See: http://archive.ics.uci.edu/ml/datasets/Beijing+PM2.5+Data\n",
-    "    \"\"\"\n",
-    "    \n",
-    "    columns_target = ['log_pm2.5']\n",
-    "    columns_forecast = ['month', 'day', 'week', 'hour',\n",
-    "       'minute', 'dayofweek']\n",
-    "    \n",
-    "    def download(self):\n",
-    "        url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00381/PRSA_data_2010.1.1-2014.12.31.csv'\n",
-    "        \n",
-    "        # download if needed\n",
-    "        filename = '00381_BejingPM25.csv'\n",
-    "        local_path = self.datasets_root/filename\n",
-    "        if not local_path.exists():\n",
-    "            download_url(url, self.datasets_root, filename)\n",
-    "        df = pd.read_csv(local_path)\n",
-    "        df.index = pd.to_datetime(df[['year', 'month', 'day', 'hour']]).dt.tz_localize('Asia/Shanghai')\n",
-    "        df = df.drop(columns=['year', 'month', 'day', 'hour', 'No'])\n",
-    "        \n",
-    "        # log target\n",
-    "        df['log_pm2.5'] = np.log(df['pm2.5'] + 1e-5)\n",
-    "        df = df.drop(columns=['pm2.5'])\n",
-    "        \n",
-    "        df.dropna(subset=self.columns_target, inplace=True)\n",
-    "        df = df.resample('1H').first()\n",
-    "        \n",
-    "        df['cbwd'] = df['cbwd'].fillna('none')\n",
-    "        \n",
-    "        \n",
-    "        \n",
-    "        # Add time features \n",
-    "        time = df.index.to_series()\n",
-    "        df[\"month\"] = time.dt.month\n",
-    "        df['day'] = time.dt.day\n",
-    "        df['week'] = time.dt.isocalendar().week\n",
-    "        df['hour'] = time.dt.hour\n",
-    "        df['minute'] = time.dt.minute\n",
-    "        df['dayofweek'] = time.dt.dayofweek\n",
-    "        \n",
-    "#         df['log_pm2.5'] = np.log(df['pm2.5']+1e-5)\n",
-    "        \n",
-    "        return df\n",
-    "dataset = BejingPM25(datasets_root)\n",
-    "print(dataset)\n",
-    "dataset.df[dataset.columns_target].head(1000).plot()\n",
-    "dataset.df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:06:15.058353Z",
-     "start_time": "2020-10-26T06:06:14.990663Z"
-    }
-   },
-   "outputs": [],
-   "source": []
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {
-    "ExecuteTime": {
-     "end_time": "2020-10-26T06:25:23.345365Z",
-     "start_time": "2020-10-26T06:25:20.671318Z"
-    }
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20090715T080000Z_WATR20_FV01_WATR20-0907-Continental-194_END-20090716T181317Z_C-20191122T052830Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20100409T080000Z_WATR20_FV01_WATR20-1004-Continental-194_END-20100430T084500Z_C-20191122T053845Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20101222T080000Z_WATR20_FV01_WATR20-1012-Continental-194_END-20110518T051500Z_C-20200916T020035Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20110608T080000Z_WATR20_FV01_WATR20-1106-Continental-194_END-20111122T035000Z_C-20200916T025619Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20111221T060300Z_WATR20_FV01_WATR20-1112-Continental-194_END-20120704T050500Z_C-20200916T043212Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20120726T044000Z_WATR20_FV01_WATR20-1207-Continental-194_END-20130204T044000Z_C-20200916T032027Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20130221T080000Z_WATR20_FV01_WATR20-1302-Continental-194_END-20131003T035000Z_C-20180529T020609Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20131111T080000Z_WATR20_FV01_WATR20-1311-Continental-194_END-20140519T035000Z_C-20200114T033335Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20140710T080000Z_WATR20_FV01_WATR20-1407-Continental-194_END-20150121T021500Z_C-20180529T055902Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20150213T080000Z_WATR20_FV01_WATR20-1502-Continental-194_END-20150424T134002Z_C-20200114T035347Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20150914T080000Z_WATR20_FV01_WATR20-1509-Continental-194_END-20160331T043000Z_C-20180601T013623Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20160427T080000Z_WATR20_FV01_WATR20-1604-Continental-194_END-20160531T021800Z_C-20180531T071709Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20171204T080000Z_WATR20_FV01_WATR20-1712-Continental-194_END-20180618T030000Z_C-20180620T233149Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20180802T080000Z_WATR20_FV01_WATR20-1807-Continental-194_END-20190225T054500Z_C-20190227T001343Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20190307T080000Z_WATR20_FV01_WATR20-1903-Continental-194_END-20190911T003144Z_C-20200114T045053Z.nc\n",
-      "Using downloaded and verified file: ../data/raw/IMOS_ANMN/IMOS_ANMN-WA_AETVZ_20190926T080000Z_WATR20_FV01_WATR20-1909-Continental-194_END-20200326T030000Z_C-20200420T064334Z.nc\n",
-      "wrote \"../data/processed/MOS_ANMN-WA_AETVZ_WATR20_FV01_WATR20-1909-Continental-194_currents.nc\" with size 43.11 MB\n"
-     ]
-    },
-    {
-     "ename": "NameError",
-     "evalue": "name 'xarray' is not defined",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
-      "\u001b[0;32m<ipython-input-12-53e5e67305d6>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m    140\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    141\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 142\u001b[0;31m \u001b[0mdataset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mIMOSCurrentsVel\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdatasets_root\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    143\u001b[0m \u001b[0mdataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns_target\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdropna\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1000\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    144\u001b[0m \u001b[0mdataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m<ipython-input-7-9fbff7440955>\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, datasets_root)\u001b[0m\n\u001b[1;32m      7\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      8\u001b[0m         \u001b[0;31m# Process data\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 9\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdf\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdownload\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     10\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdf_norm\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscaler\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnormalize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdf\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     11\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutput_scaler\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnext\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;32mlambda\u001b[0m \u001b[0mr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0mr\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcolumns_target\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscaler\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
-      "\u001b[0;32m<ipython-input-12-53e5e67305d6>\u001b[0m in \u001b[0;36mdownload\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    130\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    131\u001b[0m         \u001b[0;31m# made in previous notebook\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 132\u001b[0;31m         \u001b[0mxd\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mxarray\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mload_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutfile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    133\u001b[0m         df = xd.to_dataframe().drop(\n\u001b[1;32m    134\u001b[0m             columns=['HEIGHT_ABOVE_SENSOR', 'NOMINAL_DEPTH'])\n",
-      "\u001b[0;31mNameError\u001b[0m: name 'xarray' is not defined"
-     ]
-    }
-   ],
-   "source": [
-    "import uptide\n",
-    "import xarray as xr\n",
-    "\n",
-    "# https://en.wikipedia.org/wiki/Theory_of_tides#Harmonic_analysis\n",
-    "default_tidal_constituents = [\n",
-    "    'M2',\n",
-    "    'S2',\n",
-    "    'N2',\n",
-    "    'K2',  # Semi-diurnal\n",
-    "    'K1',\n",
-    "    'O1',\n",
-    "    'P1',\n",
-    "    'Q1',  # Diurnal\n",
-    "    'M4',\n",
-    "    'M6',\n",
-    "    'S4',\n",
-    "    'MK3',  # Short period\n",
-    "    'MM',\n",
-    "    'SSA',\n",
-    "    'SA'  # Long period\n",
-    "]\n",
-    "\n",
-    "\n",
-    "def generate_tidal_periods(t: pd.Series,\n",
-    "                           constituents: list = default_tidal_constituents):\n",
-    "    tide = uptide.Tides(constituents)\n",
-    "    t0 = t[0]\n",
-    "    td = t - t0\n",
-    "    td = td.dt.total_seconds().to_numpy().astype(int)\n",
-    "    tide.set_initial_time(t0)\n",
-    "\n",
-    "    # calc tides\n",
-    "    amplitudes = np.ones_like(td)\n",
-    "    phases = np.zeros_like(td)\n",
-    "    eta = {}\n",
-    "    for name, f, amplitude, omega, phase, phi, u in zip(\n",
-    "            tide.constituents, tide.f, amplitudes, tide.omega, phases,\n",
-    "            tide.phi, tide.u):\n",
-    "        eta[name] = f * amplitude * np.cos(omega * td - phase + phi + u)\n",
-    "    df_eta = pd.DataFrame(eta, index=t)\n",
-    "    return df_eta\n",
-    "\n",
-    "\n",
-    "# 'ANMN Two Rocks, WA, 204m mooring, Jul2009 - Dec2009. Preprocessed with DepthPP.'\n",
-    "\n",
-    "\n",
-    "def get_current_timeseries(\n",
-    "        cache_folder=Path(\"../data/raw/IMOS_ANMN/\"),\n",
-    "        outfile=Path(\n",
-    "            '../data/processed/currents/MOS_ANMN-WA_AETVZ_WATR20_FV01_WATR20-1909-Continental-194_currents.nc'\n",
-    "        )):\n",
-    "    \"\"\"\n",
-    "    Download Current data from the IMOS and pre-process.\n",
-    "    \"\"\"\n",
-    "    if not outfile.exists():\n",
-    "\n",
-    "        files = [\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20090715T080000Z_WATR20_FV01_WATR20-0907-Continental-194_END-20090716T181317Z_C-20191122T052830Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20100409T080000Z_WATR20_FV01_WATR20-1004-Continental-194_END-20100430T084500Z_C-20191122T053845Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20101222T080000Z_WATR20_FV01_WATR20-1012-Continental-194_END-20110518T051500Z_C-20200916T020035Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20110608T080000Z_WATR20_FV01_WATR20-1106-Continental-194_END-20111122T035000Z_C-20200916T025619Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20111221T060300Z_WATR20_FV01_WATR20-1112-Continental-194_END-20120704T050500Z_C-20200916T043212Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20120726T044000Z_WATR20_FV01_WATR20-1207-Continental-194_END-20130204T044000Z_C-20200916T032027Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20130221T080000Z_WATR20_FV01_WATR20-1302-Continental-194_END-20131003T035000Z_C-20180529T020609Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20131111T080000Z_WATR20_FV01_WATR20-1311-Continental-194_END-20140519T035000Z_C-20200114T033335Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20140710T080000Z_WATR20_FV01_WATR20-1407-Continental-194_END-20150121T021500Z_C-20180529T055902Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20150213T080000Z_WATR20_FV01_WATR20-1502-Continental-194_END-20150424T134002Z_C-20200114T035347Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20150914T080000Z_WATR20_FV01_WATR20-1509-Continental-194_END-20160331T043000Z_C-20180601T013623Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20160427T080000Z_WATR20_FV01_WATR20-1604-Continental-194_END-20160531T021800Z_C-20180531T071709Z.nc\",\n",
-    "            #     \"IMOS_ANMN-WA_AETVZ_20170512T080000Z_WATR20_FV01_WATR20-1705-Continental-194_END-20170717T014558Z_C-20190805T004647Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20171204T080000Z_WATR20_FV01_WATR20-1712-Continental-194_END-20180618T030000Z_C-20180620T233149Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20180802T080000Z_WATR20_FV01_WATR20-1807-Continental-194_END-20190225T054500Z_C-20190227T001343Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20190307T080000Z_WATR20_FV01_WATR20-1903-Continental-194_END-20190911T003144Z_C-20200114T045053Z.nc\",\n",
-    "            \"IMOS_ANMN-WA_AETVZ_20190926T080000Z_WATR20_FV01_WATR20-1909-Continental-194_END-20200326T030000Z_C-20200420T064334Z.nc\",\n",
-    "        ]\n",
-    "        base = \"http://thredds.aodn.org.au/thredds/fileServer/IMOS/ANMN/WA/WATR20/Velocity/\"\n",
-    "\n",
-    "        # Download files\n",
-    "        [download_url(base + f, cache_folder) for f in files]\n",
-    "\n",
-    "        # load and merge\n",
-    "        xds = [xr.open_dataset(cache_folder / f) for f in files]\n",
-    "        vars = [\n",
-    "            'VCUR', 'UCUR', 'WCUR', 'TEMP', 'PRES_REL', 'DEPTH', 'ROLL',\n",
-    "            'PITCH'\n",
-    "        ]\n",
-    "        xds2 = [x[vars].isel(HEIGHT_ABOVE_SENSOR=18) for x in xds]\n",
-    "        xd = xr.concat(xds2, dim='TIME')\n",
-    "        xd = xd.where(xd.DEPTH > 150)  # remove outliers\n",
-    "\n",
-    "        xd['TIME'] = xd['TIME'].dt.round('10T')\n",
-    "        xd = xd.dropna(dim='TIME', subset=['VCUR', 'UCUR', 'WCUR'])\n",
-    "\n",
-    "        # Generate tidal freqs\n",
-    "        t = xd.TIME.to_series()\n",
-    "        df_eta = generate_tidal_periods(t)\n",
-    "\n",
-    "        # Add tidal freqs\n",
-    "        xd = xd.merge(df_eta)\n",
-    "\n",
-    "        # Cache to nc\n",
-    "        xd.to_netcdf(outfile)\n",
-    "        print(\n",
-    "            f'wrote \"{outfile}\" with size {outfile.stat().st_size*1e-6:2.2f} MB'\n",
-    "        )\n",
-    "    return outfile\n",
-    "\n",
-    "\n",
-    "class IMOSCurrentsVel(RegressionForecastData):\n",
-    "    \"\"\"\n",
-    "    \n",
-    "    Current Speed at ANMN Two Rocks, WA, 204m mooring\n",
-    "    \n",
-    "    see:\n",
-    "    - http://thredds.aodn.org.au/thredds/fileServer/IMOS/ANMN/WA/WATR20/Velocity/\n",
-    "    from https://catalogue-imos.aodn.org.au/geonetwork/srv/api/records/ae86e2f5-eaaf-459e-a405-e654d85adb9c\n",
-    "    and http://thredds.aodn.org.au/thredds/catalog/IMOS/ANMN/WA/WATR20/Velocity/catalog.html\n",
-    "    And https://en.wikipedia.org/wiki/Theory_of_tides\n",
-    "    \"\"\"\n",
-    "\n",
-    "    columns_target = ['SPD']\n",
-    "    columns_forecast = [\n",
-    "        'M2', 'S2', 'N2', 'K2', 'K1', 'O1', 'P1', 'Q1', 'M4', 'M6', 'S4',\n",
-    "        'MK3', 'MM', 'SSA', 'SA'\n",
-    "    ]\n",
-    "\n",
-    "    def download(self):\n",
-    "        outfile = self.datasets_root / 'MOS_ANMN-WA_AETVZ_WATR20_FV01_WATR20-1909-Continental-194_currents.nc'\n",
-    "        get_current_timeseries(outfile=outfile)\n",
-    "\n",
-    "        # made in previous notebook\n",
-    "        xd = xarray.load_dataset(outfile)\n",
-    "        df = xd.to_dataframe().drop(\n",
-    "            columns=['HEIGHT_ABOVE_SENSOR', 'NOMINAL_DEPTH'])\n",
-    "        df['SPD'] = np.sqrt(df.VCUR**2 + df.UCUR**2)\n",
-    "        df.dropna(subset=self.columns_target, inplace=True)\n",
-    "        df = df.resample('30T').first()\n",
-    "\n",
-    "        return df\n",
-    "\n",
-    "\n",
-    "dataset = IMOSCurrentsVel(datasets_root)\n",
-    "dataset.df[dataset.columns_target].dropna().head(1000).plot()\n",
-    "dataset.df"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "seq2seq-time",
-   "language": "python",
-   "name": "seq2seq-time"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.7.8"
-  },
-  "toc": {
-   "base_numbering": 1,
-   "nav_menu": {},
-   "number_sections": true,
-   "sideBar": true,
-   "skip_h1_title": false,
-   "title_cell": "Table of Contents",
-   "title_sidebar": "Contents",
-   "toc_cell": false,
-   "toc_position": {
-    "height": "755px",
-    "left": "10px",
-    "top": "146px",
-    "width": "165px"
-   },
-   "toc_section_display": true,
-   "toc_window_display": true
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 2
-}
diff --git a/notebooks/00.03-mc-load_data.ipynb b/notebooks/00.03-mc-load_data.ipynb
new file mode 100644
index 0000000..172b95d
--- /dev/null
+++ b/notebooks/00.03-mc-load_data.ipynb
@@ -0,0 +1,1837 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-10-25T07:08:04.786938Z",
+     "start_time": "2020-10-25T07:08:04.731940Z"
+    }
+   },
+   "source": [
+    "Here I load multiple multivariate timeseries regression datasets"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-10-26T06:35:54.611051Z",
+     "start_time": "2020-10-26T06:35:54.331912Z"
+    }
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The autoreload extension is already loaded. To reload it, use:\n",
+      "  %reload_ext autoreload\n"
+     ]
+    }
+   ],
+   "source": [
+    "# OPTIONAL: Load the \"autoreload\" extension so that code can change. But blacklist large modules\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2\n",
+    "%aimport -pandas\n",
+    "%aimport -torch\n",
+    "%aimport -numpy\n",
+    "%aimport -matplotlib\n",
+    "%aimport -dask\n",
+    "%aimport -tqdm\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-10-26T06:36:36.152509Z",
+     "start_time": "2020-10-26T06:36:36.102274Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from pathlib import Path\n",
+    "from matplotlib import pyplot as plt\n",
+    "from seq2seq_time.data.data import IMOSCurrentsVel, AppliancesEnergyPrediction, BejingPM25, GasSensor, MetroInterstateTraffic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-10-26T06:36:36.299806Z",
+     "start_time": "2020-10-26T06:36:36.250307Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "datasets_root = Path('../data/processed/')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2020-10-26T06:36:51.271974Z",
+     "start_time": "2020-10-26T06:36:36.361497Z"
+    }
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAEECAYAAAAs+JM2AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAACXBIWXMAAAsTAAALEwEAmpwYAAAhxUlEQVR4nO3deZQc1ZXn8e+tRbsQIBW2hQSSQUhIUAJTDV7AEjYGBNOWabfNNoZ2263BDd7GhwG3zbC394191B4G3MbG7jZmswznYLM2i5EwCAQIZAmLQixCIBDaSlW688eLLGWmspbMyliq4vc5J09lRLyMdyMqM2++Fy8izN0REREpaEg7ABERyRYlBhERKaHEICIiJZQYRESkhBKDiIiUaEo7gIGaMGGCT5kyJe0wREQGlSVLlrzu7i2Vlg36xDBlyhQWL16cdhgiIoOKmf21p2XqShIRkRJKDCIiUkKJQURESgz6YwyVbNu2jfb2drZs2ZJ2KHU3YsQIJk2aRHNzc9qhiMgQNSQTQ3t7O2PHjmXKlCmYWdrh1I27s27dOtrb25k6dWra4YjIEDUku5K2bNnC+PHjh1RSADAzxo8fPyRbQiKSHUMyMQBDLikUDNXtEsmTjVs7+d3Sl9MOo0dDNjGIiGTVN377JGf+4jGeeumttEOpSIkhRpdeeimzZs2itbWVgw46iEceeYS5c+cyffp0Zs+ezYc+9CGWL18O0D2/tbWVGTNmcNZZZ7F+/fp0N0BEYvHS+s0AbOroSjmSypQYYvLQQw9x++2389hjj7F06VLuuusuJk+eDMANN9zAE088wemnn87ZZ5/d/ZobbriBpUuXsnTpUoYPH878+fPTCl9EckyJISYvv/wyEyZMYPjw4QBMmDCBiRMnlpT58Ic/zIoVK3Z67bBhw/jud7/L6tWreeKJJxKJV0SkYEgOVy124W3LeHrN23Vd58yJu3D+387qtczRRx/NRRddxH777cdRRx3FiSeeyJw5c0rK3HbbbRx44IEVX9/Y2Mjs2bN59tlnmT17dt1iFxHpy5BPDGkZM2YMS5Ys4f777+fuu+/mxBNP5Nvf/jYAp556KiNHjmTKlClcfvnlPa5D9+MWkTQM+cTQ1y/7ODU2NjJ37lzmzp3LgQceyPXXXw+EYwltbW29vrarq4snn3yS/fffP4lQRUS6JXqMwcyuNbPXzOypHpabmV1mZivMbKmZvS/J+Opp+fLlPP/8893Tjz/+OHvvvXe/Xrtt2za+/vWvM3nyZFpbW+MKUUSkoqQPPl8HHNvL8nnAtOixALg6gZhi8c4773D66aczc+ZMWltbefrpp7ngggt6fc2pp55Ka2srBxxwABs3buSWW25JJlgRkSKJdiW5+31mNqWXIvOBn3noXH/YzHY1s/e4e3ZPEezBIYccwoMPPrjT/Hvuuadi+Z7mi8jQldXjiFkbrron8GLRdHs0T0RkyDCyfWmbrCWGSntrp5RqZgvMbLGZLV67dm0CYYmI5EfWEkM7MLloehKwpryQuy909zZ3b2tpqXgv68w20QZqqG6XiGRH1hLDrcBp0eik9wNv1XJ8YcSIEaxbt27IfYkW7scwYsSItEMRkSEs0YPPZvZLYC4wwczagfOBZgB3vwZYBBwHrAA2AZ+tpZ5JkybR3t7OUOxmKtzBTUQkLkmPSjq5j+UOnDnQepqbm3WHMxGRGmWtK0lERFKmxCAiIiWUGEREUpLV4TFKDCIiScv2+W1KDCIiUkqJQUQkaVntQ4ooMYiIpCSrPUpKDCIiUkKJQURESigxiIhICSUGEREpocQgIpKSrA5OUmIQEUlaVocjRZQYRESkhBKDiIiUUGIQEZESSgwiIlJCiUFEREooMYiISAklBhERKaHEICKSEs/oGW5KDCIiCcv4+W1KDCIiUkqJQURESigxiIhIiUQTg5kda2bLzWyFmZ1bYfk4M7vNzJ4ws2Vm9tkk4xMRSUJGjzl3SywxmFkjcCUwD5gJnGxmM8uKnQk87e6zgbnAD8xsWFIxiogkyTJ6FDrJFsOhwAp3X+nuHcCNwPyyMg6MNTMDxgBvAJ0JxigikntJJoY9gReLptujecWuAPYH1gBPAl929+3JhCciIpBsYqjUaCrvajsGeByYCBwEXGFmu+y0IrMFZrbYzBavXbu23nGKiCRCJ7iFFsLkoulJhJZBsc8CN3mwAlgFzChfkbsvdPc2d29raWmJLWARkThk9NBCtyQTw6PANDObGh1QPgm4tazMauCjAGb2LmA6sDLBGEVEcq8pqYrcvdPMzgLuBBqBa919mZmdES2/BrgYuM7MniQk1XPc/fWkYhQRkQQTA4C7LwIWlc27puj5GuDoJGMSEZFSOvNZRERKKDGIiEgJJQYRESmhxCAiIiWUGEREUuIZvZyeEoOISMIKF8/7yV3P4xk8/VmJQUQkJY+seoMX39hc1Wtuefwlrrx7RUwRBYmexyAiIqWq7U768o2PA3DmkfvGEE2gFoOIiJRQYhARkRJKDCIiUkKJQUQkRZbBi3ArMYiIJCyDI1RLKDGIiEgJJQYRkYRZ9nqPSigxiIgMQq9t2BLbupUYREQGodfe3hrbupUYREQGoTi7o5QYRESkRK4Tw6W/e5obHvlr2mGIiGRKri+i92/3rwLg1MP2TjkSEcmrWruE4jwxLtctBhGRwUrHGEREpIQSg4jIEJLF6yMVU2IQERmEdIxBRCRHTl74MOf859JeywyZriQzO9bMlpvZCjM7t4cyc83scTNbZmb3JhmfiEjSFj358k7zHlq5jl8tfjGFaILEEoOZNQJXAvOAmcDJZjazrMyuwFXAx919FvCppOITEUnD1ff+Je0QdpJki+FQYIW7r3T3DuBGYH5ZmVOAm9x9NYC7v5ZgfCIiiau1RyjOw9dJJoY9geK2UXs0r9h+wG5mdo+ZLTGz0yqtyMwWmNliM1u8du3amMIVEYmfZfAa3EkmhkpbX34foybgEOB44BjgPDPbb6cXuS909zZ3b2tpaal/pCIiCXljY0dNr4sznyR5SYx2YHLR9CRgTYUyr7v7RmCjmd0HzAaeSyZEEZH4PbRyXR3WMjSGqz4KTDOzqWY2DDgJuLWszC3AEWbWZGajgMOAZxKMUUQk9xJrMbh7p5mdBdwJNALXuvsyMzsjWn6Nuz9jZncAS4HtwE/d/amkYhQRGSyGSlcS7r4IWFQ275qy6e8B30syLhGRwcbLj9DWkc58FhHJqGVr3mLLtq7u6X9/6IXu582NQ+MYQ2YdeuldaYcgIrKT4y97gK/f9GT39Hm3LOt+3tigxBCr1zbEd1NtEZGB+PPqNxOvU4lBRCTDejqUoGMMIiI5FWcC6IkSg4jIIHDBrcv6LlQnSgwiIhnmUWfSdQ++kFidSgwiIlJCiUFEJMN0jEFEREr0lBg0KklERBKjxCAiMgg99+qG2Nad28TQ2bU97RBERGr2+Z8tjm3duU0Mb27alnYIIiKZlNvEICKShjXrN1dV3lMYlqTEICKSoB/flf07Fec2MXiPl6YSEcmO3r6ptm+P53sst4lBRGSw21R0E596ym9iUINBRFJgVHeDnd4OMcR1q578JgYREakot4lBDQYRGQzSOB6a38SgzCAiGbKtaztbKhwz0EX0RERy6sT/8xAzzrujqte8VOU5Ef2V28Sg4aoikgbr4YjxY6vXV72uS373zMCC6UFuE4OIyGD39Jq3YllvoonBzI41s+VmtsLMzu2l3N+YWZeZ/X1csegYg4hk0bKyL/vevqpef6cjlhgSSwxm1ghcCcwDZgInm9nMHsp9B7gzzniUF0Qki46/7IGS6aF+8PlQYIW7r3T3DuBGYH6Fcl8EfgO8FmcwY4Y1xbl6EZG6WXjfXxKtL8nEsCfwYtF0ezSvm5ntCZwAXNPbisxsgZktNrPFa9eurSmYXUYqMYhI8no6+Nwz59u/fzaOUHqUZGKotDvKG0k/Bs5x914vAOLuC929zd3bWlpaagum+v+OiMiAdXRW3zcU07XyepTkz+Z2YHLR9CRgTVmZNuDG6Et7AnCcmXW6+82JRCgiEqOnXnqL3zzWXtVr0jjGkGRieBSYZmZTgZeAk4BTigu4+9TCczO7DrhdSUFEhorHVr9Z9WvSGCiTWGJw904zO4sw2qgRuNbdl5nZGdHyXo8riIhIMhI9Auvui4BFZfMqJgR3/4ckYhIRSUpPRzbb39yUaBx90ZnPIiIpa38znmse1UqJQUQkw97YGM/Zzb1RYhARSVnWBs8rMYiIJGWQnD+lxCAikqLWSePSDmEnSgwiIinK4lUYlBhERFL0xIvrufreZC+S1xclBhGRlN2zvLaLgcZFiUFEJCHZ6zSqTIlBRERKKDGIiEgJJQYRESmhxCAikoBX3trCfc9l6yBzT3R/SxGRmN32xBq++Ms/px1Gv6nFICISsyV/rf4GPT1paoh/bJMSg4hIzBrqeHbzIXvvVrd19STXiWHscPWkiUj86nnVi0dWvVG/lfUg14nhKx/bL+0QRCQHXnh9Y9ohVCXXiWGwnIUoIoPbSiWGwSOBYzgiIrh72iFUJd+JQZlBRBIwuNJCzhOD0oKIJGGQNRjynRgGy232RGRw22v3UWmHUJVcJwalBRFJwkf33yPtEKqS68RQz5NORESGikQTg5kda2bLzWyFmZ1bYfmpZrY0ejxoZrPjjSfOtYuIBDrG0AMzawSuBOYBM4GTzWxmWbFVwBx3bwUuBhbGGZMGJYlIEgZZXki0xXAosMLdV7p7B3AjML+4gLs/6O6Fq009DEyKMyDTUQYRScBgO48hyYsF7Qm8WDTdDhzWS/nPAb+vtMDMFgALAPbaa6+aAyruSrry7hWMGtbI6GFNjBoe/R3WyOjhpX9HDWuiUU0NEalCXHlh11HNsaw3ycRQ6du04u4ysyMJieHwSsvdfSFRN1NbW1vNu3zO9Jbu59+7c3m/XzeyuZHRw0OSKEkexUmlUnIpml94fWFec2OuxwGIDGlNjfH8mJw1cZdY1ptkYmgHJhdNTwLWlBcys1bgp8A8d18XZ0B7jB3R/Xz5JceyaWsXGzs62dTRxcatZX87Ontd/s7WTl57e2vJ8q2d2/sdy7DGhpJkMmp4E6OjFsqOJFI0v9LysmQ0vKkB0xF2kdS1jB2edghVSTIxPApMM7OpwEvAScApxQXMbC/gJuAz7v5cgrExvKmR4U2N7DZ6WN3W2dm1nU3bunYklO7E0snGrV2lfzu62LQ1+ls0f836zTst768GY6dWzE4JpmLi2bnFU1g2qrlRlxIRqVJ/u5KOmfUu7lz2at3XW63EEoO7d5rZWcCdQCNwrbsvM7MzouXXAP8bGA9cFf3S7XT3tqRirLemxgZ2aWxglxH16wfcvt3Z0tnV78Sy8/JO1m3sYPUbm7pbNhs7uuja3v93mLrSRKrT309XVj4Hid6pxt0XAYvK5l1T9PzzwOeTjGmwaWiw6Au5CahP89Td6ejaXtJV9s7W6lo4G7Z08urbW0qWd6grTQTQqCQZhMwslq60bV3b2dRnC6aHlk40/81Nm0vmb6q1K63QRVZNC6dCuZHqSpMMGfRdSZI/zY0NjBvZwLiR9e1K27yt78EAJcvLyq3dsLVk/satnVTRk9Y9bLliS6bKFk6hOy4rXQgyOHxh7j5cfc9fYlu/EoMMKg0NFn79D2+CsfVZp7uztXN7L6PQ+u5Ke3vzNl55a3PtXWlNDT0mjr4SS08tHnWlZUc9f9nP2a+Fc46dwZIX3uy7cI1ynxj+8LU5rN2wNe0wJEVmxojmRkY0N7J7xrrS3thYe1daY4P1ftKmutIS4/08/NyfUsWty/6ut1q5Twz7tIxhn5YxaYchQ1DaXWkbt1ZORK9t2LJTN1uaXWmjhzXSpK60futuBMaYn3OfGEQGkzi70kqTSnUtnLc2b+Pl9ZtLuuE6uurflTa6h/NsKrVwhjVmpyutP11JF8+fxcOr3uizXBJbpMQgknPFXWnj67jejs7tbO4oPU7TY0unh8EC697ZVNIdt3lb/7vSmgpdaRUTR+8tmJ6Wj2xurCnZ9CcxfOYDU/qXGBLIDEoMIhKLYU0NDGtqYFwdL/TWFXWlFVotlRNLz8dsNnZ08eqGLWx6vbauNDMY1dx311j58qXtb9VtHxRfFVrDVUUk9xobjDHDmxgzvH5fXfXoSlu/eVt0+ZrautJ2BLPj6bDGhorr+FRbuBtBnA0HJQYRybWkutKO+uF9A1rf7qOH8dh5H6tTdL1TYhARiUE1XWm7jKj+q/gnJx0c23BVjRETEUnAx2dP7HHZ21s6+3z9+/barWT63eNG8J5xIwccVyVKDCIiCejPaKLeWgCXnXxQ/YLpgxKDiEjK9h4/qs8y4YrKyVBiEBFJWWHYafFQ1EtOOCClaJQYREQS0VtPUqELqfD3ilMO5tNtk5n5nnju6dwXJQYRkQRUc8Z0oeVw0z9/kFkTd+GpC4+JK6yKlBhERFJW6Eo6YM9xAEzcdQQAI5ob+d2XjqjrCX39ofMYREQS0FN7ocHg7GOmA3DGh/fhyOl7sH9KXUgFSgwiIgkYOayx4vyV3zq++3lDg6WeFEBdSSIiiTh33oyd5t3+xcNTiKRvSgwiIgkYO2LnS2MUjilkjRKDiIiUUGIQEZESSgwiIlIi0cRgZsea2XIzW2Fm51ZYbmZ2WbR8qZm9L8n4RETi9IevzeGOrxzBPi2jmT1517TD6VFiw1XNrBG4EvgY0A48ama3uvvTRcXmAdOix2HA1dFfEZFBb5+WMQD84Wtz0w2kD0m2GA4FVrj7SnfvAG4E5peVmQ/8zIOHgV3N7D0JxigikntJJoY9gReLptujedWWwcwWmNliM1u8du3augcqIpJnSSaGSmeEl9+Voj9lcPeF7t7m7m0tLS11CU5ERIIkE0M7MLloehKwpoYyIiISoyQTw6PANDObambDgJOAW8vK3AqcFo1Oej/wlru/nGCMIiK5l9ioJHfvNLOzgDuBRuBad19mZmdEy68BFgHHASuATcBnk4pPRESCRK+u6u6LCF/+xfOuKXruwJlJxiQiIqXMfadju4OKmW0AlqccxgTg9ZzHkHb9aceQ9+1PO4Y8b3utde/t7hVH7wyF+zEsd/e2NAMws8V5jyHt+tOOIe/bn3YMed72OOrWtZJERKSEEoOIiJQYColhYdoBoBiyUD+kG0Pet78grRjyvO11r3vQH3wWEZH6GgotBhERqSMlBhERKaHEMIiYWaWLDIqI1NWgSAxm9jUzOzp6nsqXo5lNMbMR0fO09tvYongS3Q9mNi6tutOut6j+1PZ/2vWWxZD4fjCz3ZOus0IM+6dRb1H9c80skctJZzoxmNnRZnYncA5wGnRfNiPJGI4ys0eAnwC/jWLYnnAMHzOzB4Dvm9n/imJIZD+Y2UfM7HHgajP7lyTrLophvpldD8xOst6i+ueZ2d3AlWb2DcjfPohiSHw/RLcDvg/4sZn9IIk6e4jjcmCRmU1Joe7CPjgV2JpIpe6eqQfhngzDgEuA+wkX1fsEcCnQTDSSKqFYJgMPAn8XTT9QeJ5gDJOA/wL+ltBi+B3wncK+irnuMcBdwCejffFH4JKEt/9IYCmwBPgCsFuCdTcAZxCuDHwc4TaztwP/mFD9hVGDae4DI1z0MrH9UFTnAuBhwp0d9wLuAeYlue+Lpm8AHgM+DwxPaL83ACcDbwOfSup/7u7ZajGYmXnQAdzi7kd4uPDem8BJ7r7No70WZwxFk+8FniB8OQK8DDxvZs0JxjADeNLdb3P3DYT7Zn/VzKa5u8fVrI66y8YQ7qj3Z3d/kfChONHMZsRRZw9WAUcDZxO+kFqTqthDy3A1cLK7L3L3RwjvhV3jrrvwWYgmVwHHkPA+KPo8dhH2wylx74eyOh8ADnf3W4AtwGvAskJXbozv/e59H92rHkKCuprwq31aHPWW1x+9/9YAPyNccRoz+5SZTSp8B8W1DzKTGKJLct9kZl81s/e4+6PR/GZ3vxdYaWbzEoxhV+AZYDdC03kV4YPwTeAXCcWwC/AccLiZfSAqsgewLIqj3nX/s5l9Erq/FB1oISQI3H0loTvtoqh83d+UxTFE63/R3V9x9z8CrwJzzGyn273GUX/kLsJ7r/AFsT8V7ipY5xiK3wPvdvcX3P3lpPZBWQz/08wmRD/QVppZ4fpqdd8PFb4DnvZwuf73ATcDUwjdyj8svKSe9ZfF8BUzm+juXRbuH3Ms4b1/N3CSmf1dHP395fudkByXErpynwU+DVwOXFV4Sb1jALLRlQScQGimHgn8P+AKYHZRk2p34KfA0QnGcBWwb7TsLOCb0fNmYCUwpxBfjDFcDbwL+BxwHaFL6RfAVEJLZkqd6h0LXAO8ArwDNBUt+y7h3hmF6Qbgr8CsOu//ijFE9RW6VFqBn1PWnVeP/0Fv9RfXEf0fPljv+nt5D1wBHFS0PLZ90J8YivZLXfdDH3VOBfaKno8G1gNt9Xz/9RLDIdGyC6O/ha6dZ4A9Yq7/SmA6MBH4FnBwVG53YG0htjgeWWkxHAZc7e53AxcQms5fhnCgyd3fAEYSdlhco4LKY1gJfCNatgvhVzruvo3Qvzq1EF+MMawivCH/L/BPwFfd/RRCs/5PhDfogHnoorrX3d9N2LYrixZfBBxkZseZ2XAPLYnbCQmybnqJobtZ7+5LCR+cA6KD4udE8wf8P+it/kIdUfN9MvBY1Jz/fL3qL1LpPfClojhj2wf9icHDL/jh1H8/9PYdsMrdV0fPNwK/Jnwm661SDF+Ilh1vZvcTWiw3E7qW6vL566X+F4Cz3X0N4XvgzwDR9+HNRC35OCSaGMq7HoqmVwKnALj7XwkHWEeb2ceLiv8cONTMRvgARgVVEcPtwBgz+2C07OxodMA3gI8CDyUQw63AbmZ2gofjK3+Kyl1M+OW0oY51F26z+hXgZDObFsXxDqHVcBLwL2Z2EXAE4XhLTaqJwUNTvqmozC8Jxzp+RbgGfdVdWrXUH82fDownfEneGj2vqUttgJ+FAe+DGmOYHy2fQY37oco6R5VtN2b2TWAW8HS/NnLgMewadeP+BHjQ3Q9y99OAdxO60+Ks/zZgrJl93N23FJU/j7APnq2l/v5IusVQcv+Hol8Y/wlsKnrjvUwYgTCzaKeNBG4EuhKO4YPufiMhMZ0M7EPo0hrIzYGqjWE6gJlNM7NbgAMIrYdt9arb3TeaWYO7v0LoRvtpUZkbgX8l/HpuIYwMebWGumuKwd07o1/so4HLgCeBVnc/u/j1cdYfFd0HmEloLR7v7t+psX4oa3H197NgZmMIX1ID3Qe1xLB/9Hl8L+FLsZb9UPV2Q/dQ2QeA/YC/j/5Htaomhj8CHwZucPdzil52QuEXfMz138OOfXCEheHC+wGfHOBnsHfV9DvV+gDeTxju9a+EI/qN0fxCf6UR7u98Bzv6cs8Gzi9aR2NKMVxctI4BDVMbQAwXRM/HApPqXHcjO/rRG4rKrwY+QPhldFghvpi2v68Y3gX8TTSv5n7dAe6DGYSDn4cOcB98APgPwpf7zBreA00D2QcDjKHQz35g4f+RYJ1TgANS2u7zy98nKe33ycDMgeyD/j5ibzGY2QGEo+i3E4abLWDHyWqFX2IjgTsJGXKhmU0EDgYKy/EwfC2NGLqbcO5e88klA4xhW1Rug7u317nuLnffHv0SHVf0su8QDnbfB4yIytbchzzAGO4HRkVlX0uh/vuAwuigP1EjM9uDcEBzEbCO0If+j1EM/X0PdNa6D+oYw5MejRpMoM6OqNwL7v5UbVs94Bg6o3JdXmM3dp32wYvuXnMXWlXizjzA/wD+PXo+GriQMATwvdG8i6OdcTDhaPslhObTVQywlaAYqqr7DuCIaHoeof/y+0BzgtsfWwxp1x+t8yPAL4tiOIaQqGZE8y5J4H2YeAx53e4s1V91vHVfYeiHvxD4eDR9EGHs77Ro+nxCX9qF0Q76BbBP2TpGKYbaYxho3YRm7uQ0t3+gMaRdf7SOOUTdcNH0eOD5Qj3RF8D5hJbJqJjeh4nHkNftzlL9A33Ub0Whf+wM4M+EfrLngNMJ/cMXE7oDbiZkyZMIv8SK+3Nr7rtTDHWrux6/jFKNIe36o3WMBW4C3gCupegSFoRfgj8u/K+Bw4F/A3av8/sw8Rjyut1Zqr9ej/quDK4HToyeH0U40HdMND0L+ET0vA34fRw7I+8x5H37M1L/cMJJkcdFXwYLipYdTOiyOiqa3p8w5HP0YI8hr9udpfrr9RjQwWczO83M5tiOS+I+A+xpZk3ufhfhVO4jzWySuy9z95ujch8BHi4MRfWBnZeQ6xjyvv1ZqL8shl09DFL4KeEYxnNAm5lNj4o+QRh2/SMz25dwTowRDWEcbDHkdbuzVH8cmvouUir6EL2b0Ce2HfgL4eSXLxAuuHYgsC/hwN2vgB8RTsJpN7NDCX1q2wmZ1GsJOu8x5H37s1B/LzEsMLMvu/vrUZmHCOPOP00Y+rwduC4apfJ1wjkq/+Tu6wdLDHnd7izVH7sqm0mFcbf7AT+PnjcRjpxfT8h81wKfAcZFy68DLoqeTyC6xlCtj7zHkPftz0L9fcRwOfCbsrInRLHtSzjQXThnYthgiyGv252l+pN49KvFYOGSABcBjWa2iHCdki7ovnbKWYSxtzMJGfQThPsIfIuQTR+Jyr4O3NufOhVDdurOSgxp19/PGL4ErDGzOR6uCoy7/9bC3b/uIFzf5kjgGQ+Xlx8UMeR1u7NUf6L6kR3nEPrGriZcyO0+wiVoV1N0FihwJnBH9LyVcJ2RRwiXqh09wF8IuY4h79ufhfqrjOELwN1F058CNhJGoAz0rOXEY8jrdmep/qQf/dkhRwCfKZq+Ktr4fwCWRPMaCP1t/0F0KWjCvQv2rEuQOY8h79ufhfpriOHXwNSi1x0xWGPI63Znqf6kH/0ZlbQE+LXtuFHJfxGujX4doUn1RQ8HVSYBne7+AoC7r3f3l/qx/v7Iewx53/4s1F9tDF3uviqK4X53v38Qx5DX7c5S/YnqMzG4+yZ33+o7rlX0McJNIiCcQLS/md1OuBTwY3EEmfcY8r79Wag/zzHkdbuzVH/i+tu0ILqyIPB7dtzZbF9CU/1w6tRcVwzZrDsrMaRdf55jyOt2Z6n+pB7VnOC2nTAM8HWgNcqO5wHb3f0Br19zXTFks+6sxJB2/XmOIa/bnaX6k1Fltnw/Ycc8AHwujUyW9xjyvv1ZqD/PMeR1u7NUfxKPws0g+sXMJhFOGvqhD+DeBAOR9xjyvv1ZqD/PMeR1u7NUfxKqSgwiIjL0JX3PZxERyTglBhERKaHEICIiJZQYRESkhBKDiIiUUGIQqYKZjTezx6PHK2b2UtH0pqjMFDNzM7u46HUTzGybmV0RTV9Q9trHzWzXlDZLpETVd3ATyTN3XwccBOHLHXjH3b8fTb9TVHQl8N8IZ8VCuPzysrLV/ajwWpEsUYtBJB6bgWfMrC2aPpFwOWaRzFNiEInPjcBJ0ZmyXcCasuVfLepGujv58EQqU1eSSHzuAC4GXgV+VWG5upIkk9RiEImJh/v6LgG+Bvwm5XBE+k0tBpF4/QC4193XmVnasYj0ixKDSIzcfRk7j0Yq+KqZ/fei6U94dEtSkTTp6qoiIlJCxxhERKSEEoOIiJRQYhARkRJKDCIiUkKJQURESigxiIhICSUGEREp8f8B4go8hn9kEbIAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>VCUR</th>\n",
+       "      <th>UCUR</th>\n",
+       "      <th>WCUR</th>\n",
+       "      <th>TEMP</th>\n",
+       "      <th>PRES_REL</th>\n",
+       "      <th>DEPTH</th>\n",
+       "      <th>ROLL</th>\n",
+       "      <th>PITCH</th>\n",
+       "      <th>LATITUDE</th>\n",
+       "      <th>LONGITUDE</th>\n",
+       "      <th>M2</th>\n",
+       "      <th>S2</th>\n",
+       "      <th>N2</th>\n",
+       "      <th>K2</th>\n",
+       "      <th>K1</th>\n",
+       "      <th>O1</th>\n",
+       "      <th>P1</th>\n",
+       "      <th>Q1</th>\n",
+       "      <th>M4</th>\n",
+       "      <th>M6</th>\n",
+       "      <th>S4</th>\n",
+       "      <th>MK3</th>\n",
+       "      <th>MM</th>\n",
+       "      <th>SSA</th>\n",
+       "      <th>SA</th>\n",
+       "      <th>SPD</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TIME</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2009-07-15 08:00:00</th>\n",
+       "      <td>-0.396391</td>\n",
+       "      <td>0.089687</td>\n",
+       "      <td>-0.009671</td>\n",
+       "      <td>18.549999</td>\n",
+       "      <td>205.076004</td>\n",
+       "      <td>203.550812</td>\n",
+       "      <td>4.6</td>\n",
+       "      <td>-3.4</td>\n",
+       "      <td>-31.728650</td>\n",
+       "      <td>115.037217</td>\n",
+       "      <td>0.638670</td>\n",
+       "      <td>-5.000000e-01</td>\n",
+       "      <td>-0.646523</td>\n",
+       "      <td>-0.617351</td>\n",
+       "      <td>0.930835</td>\n",
+       "      <td>0.286288</td>\n",
+       "      <td>0.116457</td>\n",
+       "      <td>-1.014973</td>\n",
+       "      <td>-0.146817</td>\n",
+       "      <td>-0.801534</td>\n",
+       "      <td>-0.500000</td>\n",
+       "      <td>0.370082</td>\n",
+       "      <td>0.132683</td>\n",
+       "      <td>-0.686775</td>\n",
+       "      <td>-0.395743</td>\n",
+       "      <td>0.406411</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2009-07-15 08:30:00</th>\n",
+       "      <td>-0.406632</td>\n",
+       "      <td>0.119376</td>\n",
+       "      <td>-0.003729</td>\n",
+       "      <td>18.799999</td>\n",
+       "      <td>205.067001</td>\n",
+       "      <td>203.541901</td>\n",
+       "      <td>4.7</td>\n",
+       "      <td>-2.4</td>\n",
+       "      <td>-31.728650</td>\n",
+       "      <td>115.037217</td>\n",
+       "      <td>0.431959</td>\n",
+       "      <td>-2.588191e-01</td>\n",
+       "      <td>-0.808005</td>\n",
+       "      <td>-0.854013</td>\n",
+       "      <td>0.990437</td>\n",
+       "      <td>0.154727</td>\n",
+       "      <td>0.244751</td>\n",
+       "      <td>-1.058780</td>\n",
+       "      <td>-0.589276</td>\n",
+       "      <td>-0.924071</td>\n",
+       "      <td>-0.866025</td>\n",
+       "      <td>0.716890</td>\n",
+       "      <td>0.137073</td>\n",
+       "      <td>-0.686253</td>\n",
+       "      <td>-0.396072</td>\n",
+       "      <td>0.423792</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2009-07-15 09:00:00</th>\n",
+       "      <td>-0.445501</td>\n",
+       "      <td>0.136615</td>\n",
+       "      <td>-0.018275</td>\n",
+       "      <td>18.950001</td>\n",
+       "      <td>205.059998</td>\n",
+       "      <td>203.534958</td>\n",
+       "      <td>5.2</td>\n",
+       "      <td>-3.5</td>\n",
+       "      <td>-31.728650</td>\n",
+       "      <td>115.037217</td>\n",
+       "      <td>0.197760</td>\n",
+       "      <td>-3.355459e-08</td>\n",
+       "      <td>-0.919972</td>\n",
+       "      <td>-1.032158</td>\n",
+       "      <td>1.033000</td>\n",
+       "      <td>0.020878</td>\n",
+       "      <td>0.368881</td>\n",
+       "      <td>-1.088129</td>\n",
+       "      <td>-0.884126</td>\n",
+       "      <td>-0.539590</td>\n",
+       "      <td>-1.000000</td>\n",
+       "      <td>0.959177</td>\n",
+       "      <td>0.141459</td>\n",
+       "      <td>-0.685732</td>\n",
+       "      <td>-0.396401</td>\n",
+       "      <td>0.465978</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2009-07-15 09:30:00</th>\n",
+       "      <td>-0.476184</td>\n",
+       "      <td>0.106824</td>\n",
+       "      <td>-0.003664</td>\n",
+       "      <td>19.049999</td>\n",
+       "      <td>205.056000</td>\n",
+       "      <td>203.530975</td>\n",
+       "      <td>4.8</td>\n",
+       "      <td>-3.0</td>\n",
+       "      <td>-31.728650</td>\n",
+       "      <td>115.037217</td>\n",
+       "      <td>-0.049024</td>\n",
+       "      <td>2.588190e-01</td>\n",
+       "      <td>-0.975563</td>\n",
+       "      <td>-1.139580</td>\n",
+       "      <td>1.057791</td>\n",
+       "      <td>-0.113279</td>\n",
+       "      <td>0.486733</td>\n",
+       "      <td>-1.102618</td>\n",
+       "      <td>-0.957510</td>\n",
+       "      <td>0.140953</td>\n",
+       "      <td>-0.866025</td>\n",
+       "      <td>1.061620</td>\n",
+       "      <td>0.145843</td>\n",
+       "      <td>-0.685210</td>\n",
+       "      <td>-0.396730</td>\n",
+       "      <td>0.488019</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2009-07-15 10:00:00</th>\n",
+       "      <td>-0.455938</td>\n",
+       "      <td>0.073769</td>\n",
+       "      <td>-0.014929</td>\n",
+       "      <td>19.120001</td>\n",
+       "      <td>205.052002</td>\n",
+       "      <td>203.527023</td>\n",
+       "      <td>5.4</td>\n",
+       "      <td>-3.9</td>\n",
+       "      <td>-31.728650</td>\n",
+       "      <td>115.037217</td>\n",
+       "      <td>-0.292688</td>\n",
+       "      <td>4.999999e-01</td>\n",
+       "      <td>-0.971373</td>\n",
+       "      <td>-1.168919</td>\n",
+       "      <td>1.064384</td>\n",
+       "      <td>-0.245761</td>\n",
+       "      <td>0.596302</td>\n",
+       "      <td>-1.102049</td>\n",
+       "      <td>-0.791046</td>\n",
+       "      <td>0.744158</td>\n",
+       "      <td>-0.500000</td>\n",
+       "      <td>1.009281</td>\n",
+       "      <td>0.150223</td>\n",
+       "      <td>-0.684688</td>\n",
+       "      <td>-0.397059</td>\n",
+       "      <td>0.461867</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2020-03-26 01:00:00</th>\n",
+       "      <td>-0.436635</td>\n",
+       "      <td>-0.784922</td>\n",
+       "      <td>-0.012147</td>\n",
+       "      <td>16.610001</td>\n",
+       "      <td>197.384003</td>\n",
+       "      <td>195.919662</td>\n",
+       "      <td>-2.9</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>-31.728717</td>\n",
+       "      <td>115.042133</td>\n",
+       "      <td>0.960594</td>\n",
+       "      <td>8.675942e-01</td>\n",
+       "      <td>-0.841602</td>\n",
+       "      <td>0.704716</td>\n",
+       "      <td>-0.475311</td>\n",
+       "      <td>-0.734741</td>\n",
+       "      <td>0.190139</td>\n",
+       "      <td>0.964792</td>\n",
+       "      <td>0.882484</td>\n",
+       "      <td>0.770444</td>\n",
+       "      <td>0.505439</td>\n",
+       "      <td>1.028587</td>\n",
+       "      <td>-0.881951</td>\n",
+       "      <td>0.990514</td>\n",
+       "      <td>0.997626</td>\n",
+       "      <td>0.898194</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2020-03-26 01:30:00</th>\n",
+       "      <td>-0.355067</td>\n",
+       "      <td>-0.845100</td>\n",
+       "      <td>-0.005201</td>\n",
+       "      <td>16.629999</td>\n",
+       "      <td>197.408005</td>\n",
+       "      <td>195.943497</td>\n",
+       "      <td>-2.7</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>-31.728717</td>\n",
+       "      <td>115.042133</td>\n",
+       "      <td>0.980035</td>\n",
+       "      <td>7.093279e-01</td>\n",
+       "      <td>-0.939708</td>\n",
+       "      <td>0.438315</td>\n",
+       "      <td>-0.595895</td>\n",
+       "      <td>-0.629257</td>\n",
+       "      <td>0.316317</td>\n",
+       "      <td>0.895545</td>\n",
+       "      <td>0.957914</td>\n",
+       "      <td>0.933774</td>\n",
+       "      <td>0.006292</td>\n",
+       "      <td>0.851981</td>\n",
+       "      <td>-0.880483</td>\n",
+       "      <td>0.990416</td>\n",
+       "      <td>0.997601</td>\n",
+       "      <td>0.916660</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2020-03-26 02:00:00</th>\n",
+       "      <td>-0.568277</td>\n",
+       "      <td>-0.816935</td>\n",
+       "      <td>-0.024944</td>\n",
+       "      <td>16.660000</td>\n",
+       "      <td>197.412994</td>\n",
+       "      <td>195.948425</td>\n",
+       "      <td>-2.6</td>\n",
+       "      <td>2.9</td>\n",
+       "      <td>-31.728717</td>\n",
+       "      <td>115.042133</td>\n",
+       "      <td>0.937112</td>\n",
+       "      <td>5.027222e-01</td>\n",
+       "      <td>-0.980228</td>\n",
+       "      <td>0.141881</td>\n",
+       "      <td>-0.706228</td>\n",
+       "      <td>-0.514470</td>\n",
+       "      <td>0.437113</td>\n",
+       "      <td>0.814067</td>\n",
+       "      <td>0.793395</td>\n",
+       "      <td>0.584762</td>\n",
+       "      <td>-0.494541</td>\n",
+       "      <td>0.551159</td>\n",
+       "      <td>-0.878996</td>\n",
+       "      <td>0.990316</td>\n",
+       "      <td>0.997576</td>\n",
+       "      <td>0.995149</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2020-03-26 02:30:00</th>\n",
+       "      <td>-0.306141</td>\n",
+       "      <td>-0.773147</td>\n",
+       "      <td>-0.028096</td>\n",
+       "      <td>16.719999</td>\n",
+       "      <td>197.419006</td>\n",
+       "      <td>195.954407</td>\n",
+       "      <td>-2.6</td>\n",
+       "      <td>2.7</td>\n",
+       "      <td>-31.728717</td>\n",
+       "      <td>115.042133</td>\n",
+       "      <td>0.834555</td>\n",
+       "      <td>2.618567e-01</td>\n",
+       "      <td>-0.960681</td>\n",
+       "      <td>-0.164275</td>\n",
+       "      <td>-0.804410</td>\n",
+       "      <td>-0.392074</td>\n",
+       "      <td>0.550470</td>\n",
+       "      <td>0.721473</td>\n",
+       "      <td>0.430136</td>\n",
+       "      <td>-0.085096</td>\n",
+       "      <td>-0.862862</td>\n",
+       "      <td>0.169980</td>\n",
+       "      <td>-0.877489</td>\n",
+       "      <td>0.990217</td>\n",
+       "      <td>0.997551</td>\n",
+       "      <td>0.831552</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2020-03-26 03:00:00</th>\n",
+       "      <td>-0.218563</td>\n",
+       "      <td>-0.757217</td>\n",
+       "      <td>0.013233</td>\n",
+       "      <td>16.790001</td>\n",
+       "      <td>197.429001</td>\n",
+       "      <td>195.964340</td>\n",
+       "      <td>-2.8</td>\n",
+       "      <td>2.8</td>\n",
+       "      <td>-31.728717</td>\n",
+       "      <td>115.042133</td>\n",
+       "      <td>0.678892</td>\n",
+       "      <td>3.146174e-03</td>\n",
+       "      <td>-0.882264</td>\n",
+       "      <td>-0.459175</td>\n",
+       "      <td>-0.888754</td>\n",
+       "      <td>-0.263881</td>\n",
+       "      <td>0.654460</td>\n",
+       "      <td>0.619026</td>\n",
+       "      <td>-0.040868</td>\n",
+       "      <td>-0.708264</td>\n",
+       "      <td>-0.999980</td>\n",
+       "      <td>-0.235982</td>\n",
+       "      <td>-0.875962</td>\n",
+       "      <td>0.990116</td>\n",
+       "      <td>0.997526</td>\n",
+       "      <td>0.788129</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>187527 rows × 26 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                         VCUR      UCUR      WCUR       TEMP    PRES_REL       DEPTH  ROLL  PITCH   LATITUDE  ...        Q1        M4        M6        S4       MK3        MM       SSA        SA       SPD\n",
+       "TIME                                                                                                          ...                                                                                          \n",
+       "2009-07-15 08:00:00 -0.396391  0.089687 -0.009671  18.549999  205.076004  203.550812   4.6   -3.4 -31.728650  ... -1.014973 -0.146817 -0.801534 -0.500000  0.370082  0.132683 -0.686775 -0.395743  0.406411\n",
+       "2009-07-15 08:30:00 -0.406632  0.119376 -0.003729  18.799999  205.067001  203.541901   4.7   -2.4 -31.728650  ... -1.058780 -0.589276 -0.924071 -0.866025  0.716890  0.137073 -0.686253 -0.396072  0.423792\n",
+       "2009-07-15 09:00:00 -0.445501  0.136615 -0.018275  18.950001  205.059998  203.534958   5.2   -3.5 -31.728650  ... -1.088129 -0.884126 -0.539590 -1.000000  0.959177  0.141459 -0.685732 -0.396401  0.465978\n",
+       "2009-07-15 09:30:00 -0.476184  0.106824 -0.003664  19.049999  205.056000  203.530975   4.8   -3.0 -31.728650  ... -1.102618 -0.957510  0.140953 -0.866025  1.061620  0.145843 -0.685210 -0.396730  0.488019\n",
+       "2009-07-15 10:00:00 -0.455938  0.073769 -0.014929  19.120001  205.052002  203.527023   5.4   -3.9 -31.728650  ... -1.102049 -0.791046  0.744158 -0.500000  1.009281  0.150223 -0.684688 -0.397059  0.461867\n",
+       "...                       ...       ...       ...        ...         ...         ...   ...    ...        ...  ...       ...       ...       ...       ...       ...       ...       ...       ...       ...\n",
+       "2020-03-26 01:00:00 -0.436635 -0.784922 -0.012147  16.610001  197.384003  195.919662  -2.9    3.0 -31.728717  ...  0.964792  0.882484  0.770444  0.505439  1.028587 -0.881951  0.990514  0.997626  0.898194\n",
+       "2020-03-26 01:30:00 -0.355067 -0.845100 -0.005201  16.629999  197.408005  195.943497  -2.7    3.0 -31.728717  ...  0.895545  0.957914  0.933774  0.006292  0.851981 -0.880483  0.990416  0.997601  0.916660\n",
+       "2020-03-26 02:00:00 -0.568277 -0.816935 -0.024944  16.660000  197.412994  195.948425  -2.6    2.9 -31.728717  ...  0.814067  0.793395  0.584762 -0.494541  0.551159 -0.878996  0.990316  0.997576  0.995149\n",
+       "2020-03-26 02:30:00 -0.306141 -0.773147 -0.028096  16.719999  197.419006  195.954407  -2.6    2.7 -31.728717  ...  0.721473  0.430136 -0.085096 -0.862862  0.169980 -0.877489  0.990217  0.997551  0.831552\n",
+       "2020-03-26 03:00:00 -0.218563 -0.757217  0.013233  16.790001  197.429001  195.964340  -2.8    2.8 -31.728717  ...  0.619026 -0.040868 -0.708264 -0.999980 -0.235982 -0.875962  0.990116  0.997526  0.788129\n",
+       "\n",
+       "[187527 rows x 26 columns]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>lights</th>\n",
+       "      <th>T1</th>\n",
+       "      <th>RH_1</th>\n",
+       "      <th>T2</th>\n",
+       "      <th>RH_2</th>\n",
+       "      <th>T3</th>\n",
+       "      <th>RH_3</th>\n",
+       "      <th>T4</th>\n",
+       "      <th>RH_4</th>\n",
+       "      <th>T5</th>\n",
+       "      <th>RH_5</th>\n",
+       "      <th>T6</th>\n",
+       "      <th>RH_6</th>\n",
+       "      <th>T7</th>\n",
+       "      <th>RH_7</th>\n",
+       "      <th>T8</th>\n",
+       "      <th>RH_8</th>\n",
+       "      <th>T9</th>\n",
+       "      <th>RH_9</th>\n",
+       "      <th>T_out</th>\n",
+       "      <th>Press_mm_hg</th>\n",
+       "      <th>RH_out</th>\n",
+       "      <th>Windspeed</th>\n",
+       "      <th>Visibility</th>\n",
+       "      <th>Tdewpoint</th>\n",
+       "      <th>rv1</th>\n",
+       "      <th>rv2</th>\n",
+       "      <th>log_Appliances</th>\n",
+       "      <th>month</th>\n",
+       "      <th>day</th>\n",
+       "      <th>week</th>\n",
+       "      <th>hour</th>\n",
+       "      <th>minute</th>\n",
+       "      <th>dayofweek</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>date</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2016-01-11 17:00:00</th>\n",
+       "      <td>30</td>\n",
+       "      <td>19.890000</td>\n",
+       "      <td>47.596667</td>\n",
+       "      <td>19.200000</td>\n",
+       "      <td>44.790000</td>\n",
+       "      <td>19.790000</td>\n",
+       "      <td>44.730000</td>\n",
+       "      <td>19.000000</td>\n",
+       "      <td>45.566667</td>\n",
+       "      <td>17.166667</td>\n",
+       "      <td>55.200000</td>\n",
+       "      <td>7.026667</td>\n",
+       "      <td>84.256667</td>\n",
+       "      <td>17.200000</td>\n",
+       "      <td>41.626667</td>\n",
+       "      <td>18.2000</td>\n",
+       "      <td>48.900000</td>\n",
+       "      <td>17.033333</td>\n",
+       "      <td>45.5300</td>\n",
+       "      <td>6.600000</td>\n",
+       "      <td>733.5</td>\n",
+       "      <td>92.000000</td>\n",
+       "      <td>7.000000</td>\n",
+       "      <td>63.000000</td>\n",
+       "      <td>5.300000</td>\n",
+       "      <td>13.275433</td>\n",
+       "      <td>13.275433</td>\n",
+       "      <td>4.094345</td>\n",
+       "      <td>1</td>\n",
+       "      <td>11</td>\n",
+       "      <td>2</td>\n",
+       "      <td>17</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-01-11 17:10:00</th>\n",
+       "      <td>30</td>\n",
+       "      <td>19.890000</td>\n",
+       "      <td>46.693333</td>\n",
+       "      <td>19.200000</td>\n",
+       "      <td>44.722500</td>\n",
+       "      <td>19.790000</td>\n",
+       "      <td>44.790000</td>\n",
+       "      <td>19.000000</td>\n",
+       "      <td>45.992500</td>\n",
+       "      <td>17.166667</td>\n",
+       "      <td>55.200000</td>\n",
+       "      <td>6.833333</td>\n",
+       "      <td>84.063333</td>\n",
+       "      <td>17.200000</td>\n",
+       "      <td>41.560000</td>\n",
+       "      <td>18.2000</td>\n",
+       "      <td>48.863333</td>\n",
+       "      <td>17.066667</td>\n",
+       "      <td>45.5600</td>\n",
+       "      <td>6.483333</td>\n",
+       "      <td>733.6</td>\n",
+       "      <td>92.000000</td>\n",
+       "      <td>6.666667</td>\n",
+       "      <td>59.166667</td>\n",
+       "      <td>5.200000</td>\n",
+       "      <td>18.606195</td>\n",
+       "      <td>18.606195</td>\n",
+       "      <td>4.094345</td>\n",
+       "      <td>1</td>\n",
+       "      <td>11</td>\n",
+       "      <td>2</td>\n",
+       "      <td>17</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-01-11 17:20:00</th>\n",
+       "      <td>30</td>\n",
+       "      <td>19.890000</td>\n",
+       "      <td>46.300000</td>\n",
+       "      <td>19.200000</td>\n",
+       "      <td>44.626667</td>\n",
+       "      <td>19.790000</td>\n",
+       "      <td>44.933333</td>\n",
+       "      <td>18.926667</td>\n",
+       "      <td>45.890000</td>\n",
+       "      <td>17.166667</td>\n",
+       "      <td>55.090000</td>\n",
+       "      <td>6.560000</td>\n",
+       "      <td>83.156667</td>\n",
+       "      <td>17.200000</td>\n",
+       "      <td>41.433333</td>\n",
+       "      <td>18.2000</td>\n",
+       "      <td>48.730000</td>\n",
+       "      <td>17.000000</td>\n",
+       "      <td>45.5000</td>\n",
+       "      <td>6.366667</td>\n",
+       "      <td>733.7</td>\n",
+       "      <td>92.000000</td>\n",
+       "      <td>6.333333</td>\n",
+       "      <td>55.333333</td>\n",
+       "      <td>5.100000</td>\n",
+       "      <td>28.642668</td>\n",
+       "      <td>28.642668</td>\n",
+       "      <td>3.912023</td>\n",
+       "      <td>1</td>\n",
+       "      <td>11</td>\n",
+       "      <td>2</td>\n",
+       "      <td>17</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-01-11 17:30:00</th>\n",
+       "      <td>40</td>\n",
+       "      <td>19.890000</td>\n",
+       "      <td>46.066667</td>\n",
+       "      <td>19.200000</td>\n",
+       "      <td>44.590000</td>\n",
+       "      <td>19.790000</td>\n",
+       "      <td>45.000000</td>\n",
+       "      <td>18.890000</td>\n",
+       "      <td>45.723333</td>\n",
+       "      <td>17.166667</td>\n",
+       "      <td>55.090000</td>\n",
+       "      <td>6.433333</td>\n",
+       "      <td>83.423333</td>\n",
+       "      <td>17.133333</td>\n",
+       "      <td>41.290000</td>\n",
+       "      <td>18.1000</td>\n",
+       "      <td>48.590000</td>\n",
+       "      <td>17.000000</td>\n",
+       "      <td>45.4000</td>\n",
+       "      <td>6.250000</td>\n",
+       "      <td>733.8</td>\n",
+       "      <td>92.000000</td>\n",
+       "      <td>6.000000</td>\n",
+       "      <td>51.500000</td>\n",
+       "      <td>5.000000</td>\n",
+       "      <td>45.410389</td>\n",
+       "      <td>45.410389</td>\n",
+       "      <td>3.912023</td>\n",
+       "      <td>1</td>\n",
+       "      <td>11</td>\n",
+       "      <td>2</td>\n",
+       "      <td>17</td>\n",
+       "      <td>30</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-01-11 17:40:00</th>\n",
+       "      <td>40</td>\n",
+       "      <td>19.890000</td>\n",
+       "      <td>46.333333</td>\n",
+       "      <td>19.200000</td>\n",
+       "      <td>44.530000</td>\n",
+       "      <td>19.790000</td>\n",
+       "      <td>45.000000</td>\n",
+       "      <td>18.890000</td>\n",
+       "      <td>45.530000</td>\n",
+       "      <td>17.200000</td>\n",
+       "      <td>55.090000</td>\n",
+       "      <td>6.366667</td>\n",
+       "      <td>84.893333</td>\n",
+       "      <td>17.200000</td>\n",
+       "      <td>41.230000</td>\n",
+       "      <td>18.1000</td>\n",
+       "      <td>48.590000</td>\n",
+       "      <td>17.000000</td>\n",
+       "      <td>45.4000</td>\n",
+       "      <td>6.133333</td>\n",
+       "      <td>733.9</td>\n",
+       "      <td>92.000000</td>\n",
+       "      <td>5.666667</td>\n",
+       "      <td>47.666667</td>\n",
+       "      <td>4.900000</td>\n",
+       "      <td>10.084097</td>\n",
+       "      <td>10.084097</td>\n",
+       "      <td>4.094345</td>\n",
+       "      <td>1</td>\n",
+       "      <td>11</td>\n",
+       "      <td>2</td>\n",
+       "      <td>17</td>\n",
+       "      <td>40</td>\n",
+       "      <td>0</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-05-27 17:20:00</th>\n",
+       "      <td>0</td>\n",
+       "      <td>25.566667</td>\n",
+       "      <td>46.560000</td>\n",
+       "      <td>25.890000</td>\n",
+       "      <td>42.025714</td>\n",
+       "      <td>27.200000</td>\n",
+       "      <td>41.163333</td>\n",
+       "      <td>24.700000</td>\n",
+       "      <td>45.590000</td>\n",
+       "      <td>23.200000</td>\n",
+       "      <td>52.400000</td>\n",
+       "      <td>24.796667</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>24.500000</td>\n",
+       "      <td>44.500000</td>\n",
+       "      <td>24.7000</td>\n",
+       "      <td>50.074000</td>\n",
+       "      <td>23.200000</td>\n",
+       "      <td>46.7900</td>\n",
+       "      <td>22.733333</td>\n",
+       "      <td>755.2</td>\n",
+       "      <td>55.666667</td>\n",
+       "      <td>3.333333</td>\n",
+       "      <td>23.666667</td>\n",
+       "      <td>13.333333</td>\n",
+       "      <td>43.096812</td>\n",
+       "      <td>43.096812</td>\n",
+       "      <td>4.605170</td>\n",
+       "      <td>5</td>\n",
+       "      <td>27</td>\n",
+       "      <td>21</td>\n",
+       "      <td>17</td>\n",
+       "      <td>20</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-05-27 17:30:00</th>\n",
+       "      <td>0</td>\n",
+       "      <td>25.500000</td>\n",
+       "      <td>46.500000</td>\n",
+       "      <td>25.754000</td>\n",
+       "      <td>42.080000</td>\n",
+       "      <td>27.133333</td>\n",
+       "      <td>41.223333</td>\n",
+       "      <td>24.700000</td>\n",
+       "      <td>45.590000</td>\n",
+       "      <td>23.230000</td>\n",
+       "      <td>52.326667</td>\n",
+       "      <td>24.196667</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>24.557143</td>\n",
+       "      <td>44.414286</td>\n",
+       "      <td>24.7000</td>\n",
+       "      <td>49.790000</td>\n",
+       "      <td>23.200000</td>\n",
+       "      <td>46.7900</td>\n",
+       "      <td>22.600000</td>\n",
+       "      <td>755.2</td>\n",
+       "      <td>56.000000</td>\n",
+       "      <td>3.500000</td>\n",
+       "      <td>24.500000</td>\n",
+       "      <td>13.300000</td>\n",
+       "      <td>49.282940</td>\n",
+       "      <td>49.282940</td>\n",
+       "      <td>4.499810</td>\n",
+       "      <td>5</td>\n",
+       "      <td>27</td>\n",
+       "      <td>21</td>\n",
+       "      <td>17</td>\n",
+       "      <td>30</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-05-27 17:40:00</th>\n",
+       "      <td>10</td>\n",
+       "      <td>25.500000</td>\n",
+       "      <td>46.596667</td>\n",
+       "      <td>25.628571</td>\n",
+       "      <td>42.768571</td>\n",
+       "      <td>27.050000</td>\n",
+       "      <td>41.690000</td>\n",
+       "      <td>24.700000</td>\n",
+       "      <td>45.730000</td>\n",
+       "      <td>23.230000</td>\n",
+       "      <td>52.266667</td>\n",
+       "      <td>23.626667</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>24.540000</td>\n",
+       "      <td>44.400000</td>\n",
+       "      <td>24.7000</td>\n",
+       "      <td>49.660000</td>\n",
+       "      <td>23.200000</td>\n",
+       "      <td>46.7900</td>\n",
+       "      <td>22.466667</td>\n",
+       "      <td>755.2</td>\n",
+       "      <td>56.333333</td>\n",
+       "      <td>3.666667</td>\n",
+       "      <td>25.333333</td>\n",
+       "      <td>13.266667</td>\n",
+       "      <td>29.199117</td>\n",
+       "      <td>29.199117</td>\n",
+       "      <td>5.598422</td>\n",
+       "      <td>5</td>\n",
+       "      <td>27</td>\n",
+       "      <td>21</td>\n",
+       "      <td>17</td>\n",
+       "      <td>40</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-05-27 17:50:00</th>\n",
+       "      <td>10</td>\n",
+       "      <td>25.500000</td>\n",
+       "      <td>46.990000</td>\n",
+       "      <td>25.414000</td>\n",
+       "      <td>43.036000</td>\n",
+       "      <td>26.890000</td>\n",
+       "      <td>41.290000</td>\n",
+       "      <td>24.700000</td>\n",
+       "      <td>45.790000</td>\n",
+       "      <td>23.200000</td>\n",
+       "      <td>52.200000</td>\n",
+       "      <td>22.433333</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>24.500000</td>\n",
+       "      <td>44.295714</td>\n",
+       "      <td>24.6625</td>\n",
+       "      <td>49.518750</td>\n",
+       "      <td>23.200000</td>\n",
+       "      <td>46.8175</td>\n",
+       "      <td>22.333333</td>\n",
+       "      <td>755.2</td>\n",
+       "      <td>56.666667</td>\n",
+       "      <td>3.833333</td>\n",
+       "      <td>26.166667</td>\n",
+       "      <td>13.233333</td>\n",
+       "      <td>6.322784</td>\n",
+       "      <td>6.322784</td>\n",
+       "      <td>6.040255</td>\n",
+       "      <td>5</td>\n",
+       "      <td>27</td>\n",
+       "      <td>21</td>\n",
+       "      <td>17</td>\n",
+       "      <td>50</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-05-27 18:00:00</th>\n",
+       "      <td>10</td>\n",
+       "      <td>25.500000</td>\n",
+       "      <td>46.600000</td>\n",
+       "      <td>25.264286</td>\n",
+       "      <td>42.971429</td>\n",
+       "      <td>26.823333</td>\n",
+       "      <td>41.156667</td>\n",
+       "      <td>24.700000</td>\n",
+       "      <td>45.963333</td>\n",
+       "      <td>23.200000</td>\n",
+       "      <td>52.200000</td>\n",
+       "      <td>21.026667</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>24.500000</td>\n",
+       "      <td>44.054000</td>\n",
+       "      <td>24.7360</td>\n",
+       "      <td>49.736000</td>\n",
+       "      <td>23.200000</td>\n",
+       "      <td>46.8450</td>\n",
+       "      <td>22.200000</td>\n",
+       "      <td>755.2</td>\n",
+       "      <td>57.000000</td>\n",
+       "      <td>4.000000</td>\n",
+       "      <td>27.000000</td>\n",
+       "      <td>13.200000</td>\n",
+       "      <td>34.118851</td>\n",
+       "      <td>34.118851</td>\n",
+       "      <td>6.063785</td>\n",
+       "      <td>5</td>\n",
+       "      <td>27</td>\n",
+       "      <td>21</td>\n",
+       "      <td>18</td>\n",
+       "      <td>0</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>19735 rows × 34 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     lights         T1       RH_1         T2       RH_2         T3       RH_3         T4       RH_4  ...        rv1        rv2  log_Appliances  month  day  week  hour  minute  dayofweek\n",
+       "date                                                                                                                 ...                                                                                 \n",
+       "2016-01-11 17:00:00      30  19.890000  47.596667  19.200000  44.790000  19.790000  44.730000  19.000000  45.566667  ...  13.275433  13.275433        4.094345      1   11     2    17       0          0\n",
+       "2016-01-11 17:10:00      30  19.890000  46.693333  19.200000  44.722500  19.790000  44.790000  19.000000  45.992500  ...  18.606195  18.606195        4.094345      1   11     2    17      10          0\n",
+       "2016-01-11 17:20:00      30  19.890000  46.300000  19.200000  44.626667  19.790000  44.933333  18.926667  45.890000  ...  28.642668  28.642668        3.912023      1   11     2    17      20          0\n",
+       "2016-01-11 17:30:00      40  19.890000  46.066667  19.200000  44.590000  19.790000  45.000000  18.890000  45.723333  ...  45.410389  45.410389        3.912023      1   11     2    17      30          0\n",
+       "2016-01-11 17:40:00      40  19.890000  46.333333  19.200000  44.530000  19.790000  45.000000  18.890000  45.530000  ...  10.084097  10.084097        4.094345      1   11     2    17      40          0\n",
+       "...                     ...        ...        ...        ...        ...        ...        ...        ...        ...  ...        ...        ...             ...    ...  ...   ...   ...     ...        ...\n",
+       "2016-05-27 17:20:00       0  25.566667  46.560000  25.890000  42.025714  27.200000  41.163333  24.700000  45.590000  ...  43.096812  43.096812        4.605170      5   27    21    17      20          4\n",
+       "2016-05-27 17:30:00       0  25.500000  46.500000  25.754000  42.080000  27.133333  41.223333  24.700000  45.590000  ...  49.282940  49.282940        4.499810      5   27    21    17      30          4\n",
+       "2016-05-27 17:40:00      10  25.500000  46.596667  25.628571  42.768571  27.050000  41.690000  24.700000  45.730000  ...  29.199117  29.199117        5.598422      5   27    21    17      40          4\n",
+       "2016-05-27 17:50:00      10  25.500000  46.990000  25.414000  43.036000  26.890000  41.290000  24.700000  45.790000  ...   6.322784   6.322784        6.040255      5   27    21    17      50          4\n",
+       "2016-05-27 18:00:00      10  25.500000  46.600000  25.264286  42.971429  26.823333  41.156667  24.700000  45.963333  ...  34.118851  34.118851        6.063785      5   27    21    18       0          4\n",
+       "\n",
+       "[19735 rows x 34 columns]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>DEWP</th>\n",
+       "      <th>TEMP</th>\n",
+       "      <th>PRES</th>\n",
+       "      <th>cbwd</th>\n",
+       "      <th>Iws</th>\n",
+       "      <th>Is</th>\n",
+       "      <th>Ir</th>\n",
+       "      <th>log_pm2.5</th>\n",
+       "      <th>month</th>\n",
+       "      <th>day</th>\n",
+       "      <th>week</th>\n",
+       "      <th>hour</th>\n",
+       "      <th>minute</th>\n",
+       "      <th>dayofweek</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2010-01-02 00:00:00+08:00</th>\n",
+       "      <td>-16.0</td>\n",
+       "      <td>-4.0</td>\n",
+       "      <td>1020.0</td>\n",
+       "      <td>SE</td>\n",
+       "      <td>1.79</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.859812</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>53</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-01-02 01:00:00+08:00</th>\n",
+       "      <td>-15.0</td>\n",
+       "      <td>-4.0</td>\n",
+       "      <td>1020.0</td>\n",
+       "      <td>SE</td>\n",
+       "      <td>2.68</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.997212</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>53</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-01-02 02:00:00+08:00</th>\n",
+       "      <td>-11.0</td>\n",
+       "      <td>-5.0</td>\n",
+       "      <td>1021.0</td>\n",
+       "      <td>SE</td>\n",
+       "      <td>3.57</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>5.068904</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>53</td>\n",
+       "      <td>2</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-01-02 03:00:00+08:00</th>\n",
+       "      <td>-7.0</td>\n",
+       "      <td>-5.0</td>\n",
+       "      <td>1022.0</td>\n",
+       "      <td>SE</td>\n",
+       "      <td>5.36</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>5.198497</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>53</td>\n",
+       "      <td>3</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2010-01-02 04:00:00+08:00</th>\n",
+       "      <td>-7.0</td>\n",
+       "      <td>-5.0</td>\n",
+       "      <td>1022.0</td>\n",
+       "      <td>SE</td>\n",
+       "      <td>6.25</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>4.927254</td>\n",
+       "      <td>1</td>\n",
+       "      <td>2</td>\n",
+       "      <td>53</td>\n",
+       "      <td>4</td>\n",
+       "      <td>0</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2014-12-31 19:00:00+08:00</th>\n",
+       "      <td>-23.0</td>\n",
+       "      <td>-2.0</td>\n",
+       "      <td>1034.0</td>\n",
+       "      <td>NW</td>\n",
+       "      <td>231.97</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.079443</td>\n",
+       "      <td>12</td>\n",
+       "      <td>31</td>\n",
+       "      <td>1</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2014-12-31 20:00:00+08:00</th>\n",
+       "      <td>-22.0</td>\n",
+       "      <td>-3.0</td>\n",
+       "      <td>1034.0</td>\n",
+       "      <td>NW</td>\n",
+       "      <td>237.78</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.302586</td>\n",
+       "      <td>12</td>\n",
+       "      <td>31</td>\n",
+       "      <td>1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2014-12-31 21:00:00+08:00</th>\n",
+       "      <td>-22.0</td>\n",
+       "      <td>-3.0</td>\n",
+       "      <td>1034.0</td>\n",
+       "      <td>NW</td>\n",
+       "      <td>242.70</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.302586</td>\n",
+       "      <td>12</td>\n",
+       "      <td>31</td>\n",
+       "      <td>1</td>\n",
+       "      <td>21</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2014-12-31 22:00:00+08:00</th>\n",
+       "      <td>-22.0</td>\n",
+       "      <td>-4.0</td>\n",
+       "      <td>1034.0</td>\n",
+       "      <td>NW</td>\n",
+       "      <td>246.72</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.079443</td>\n",
+       "      <td>12</td>\n",
+       "      <td>31</td>\n",
+       "      <td>1</td>\n",
+       "      <td>22</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2014-12-31 23:00:00+08:00</th>\n",
+       "      <td>-21.0</td>\n",
+       "      <td>-3.0</td>\n",
+       "      <td>1034.0</td>\n",
+       "      <td>NW</td>\n",
+       "      <td>249.85</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>2.484907</td>\n",
+       "      <td>12</td>\n",
+       "      <td>31</td>\n",
+       "      <td>1</td>\n",
+       "      <td>23</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>43800 rows × 14 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                           DEWP  TEMP    PRES cbwd     Iws   Is   Ir  log_pm2.5  month  day  week  hour  minute  dayofweek\n",
+       "2010-01-02 00:00:00+08:00 -16.0  -4.0  1020.0   SE    1.79  0.0  0.0   4.859812      1    2    53     0       0          5\n",
+       "2010-01-02 01:00:00+08:00 -15.0  -4.0  1020.0   SE    2.68  0.0  0.0   4.997212      1    2    53     1       0          5\n",
+       "2010-01-02 02:00:00+08:00 -11.0  -5.0  1021.0   SE    3.57  0.0  0.0   5.068904      1    2    53     2       0          5\n",
+       "2010-01-02 03:00:00+08:00  -7.0  -5.0  1022.0   SE    5.36  1.0  0.0   5.198497      1    2    53     3       0          5\n",
+       "2010-01-02 04:00:00+08:00  -7.0  -5.0  1022.0   SE    6.25  2.0  0.0   4.927254      1    2    53     4       0          5\n",
+       "...                         ...   ...     ...  ...     ...  ...  ...        ...    ...  ...   ...   ...     ...        ...\n",
+       "2014-12-31 19:00:00+08:00 -23.0  -2.0  1034.0   NW  231.97  0.0  0.0   2.079443     12   31     1    19       0          2\n",
+       "2014-12-31 20:00:00+08:00 -22.0  -3.0  1034.0   NW  237.78  0.0  0.0   2.302586     12   31     1    20       0          2\n",
+       "2014-12-31 21:00:00+08:00 -22.0  -3.0  1034.0   NW  242.70  0.0  0.0   2.302586     12   31     1    21       0          2\n",
+       "2014-12-31 22:00:00+08:00 -22.0  -4.0  1034.0   NW  246.72  0.0  0.0   2.079443     12   31     1    22       0          2\n",
+       "2014-12-31 23:00:00+08:00 -21.0  -3.0  1034.0   NW  249.85  0.0  0.0   2.484907     12   31     1    23       0          2\n",
+       "\n",
+       "[43800 rows x 14 columns]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>CO (ppm)</th>\n",
+       "      <th>Humidity (%r.h.)</th>\n",
+       "      <th>Temperature (C)</th>\n",
+       "      <th>Flow rate (mL/min)</th>\n",
+       "      <th>Heater voltage (V)</th>\n",
+       "      <th>R1 (MOhm)</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Time (s)</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2016-10-16 05:36:55.800</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>48.4700</td>\n",
+       "      <td>24.6200</td>\n",
+       "      <td>247.4926</td>\n",
+       "      <td>0.2000</td>\n",
+       "      <td>0.6831</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-10-16 05:36:56.100</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>48.4700</td>\n",
+       "      <td>24.6200</td>\n",
+       "      <td>243.8282</td>\n",
+       "      <td>0.1998</td>\n",
+       "      <td>0.6649</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-10-16 05:36:56.400</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>48.4700</td>\n",
+       "      <td>24.6200</td>\n",
+       "      <td>243.0668</td>\n",
+       "      <td>0.2000</td>\n",
+       "      <td>0.6481</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-10-16 05:36:56.700</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>48.4700</td>\n",
+       "      <td>24.6200</td>\n",
+       "      <td>242.3030</td>\n",
+       "      <td>0.2000</td>\n",
+       "      <td>0.6318</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-10-16 05:36:57.000</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>48.4702</td>\n",
+       "      <td>24.6206</td>\n",
+       "      <td>241.5632</td>\n",
+       "      <td>0.2000</td>\n",
+       "      <td>0.6178</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-10-17 06:52:04.500</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>63.9400</td>\n",
+       "      <td>24.6200</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>0.2080</td>\n",
+       "      <td>9.9322</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-10-17 06:52:04.800</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>63.9400</td>\n",
+       "      <td>24.6200</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>0.2050</td>\n",
+       "      <td>31.7887</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-10-17 06:52:05.100</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>63.9400</td>\n",
+       "      <td>24.6200</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>0.2040</td>\n",
+       "      <td>57.7304</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-10-17 06:52:05.400</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>63.9400</td>\n",
+       "      <td>24.6200</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>0.2020</td>\n",
+       "      <td>71.9176</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2016-10-17 06:52:05.700</th>\n",
+       "      <td>0.0</td>\n",
+       "      <td>63.9400</td>\n",
+       "      <td>24.6200</td>\n",
+       "      <td>0.0000</td>\n",
+       "      <td>0.2010</td>\n",
+       "      <td>61.8035</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>303034 rows × 6 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                         CO (ppm)  Humidity (%r.h.)  Temperature (C)  Flow rate (mL/min)  Heater voltage (V)  R1 (MOhm)\n",
+       "Time (s)                                                                                                               \n",
+       "2016-10-16 05:36:55.800       0.0           48.4700          24.6200            247.4926              0.2000     0.6831\n",
+       "2016-10-16 05:36:56.100       0.0           48.4700          24.6200            243.8282              0.1998     0.6649\n",
+       "2016-10-16 05:36:56.400       0.0           48.4700          24.6200            243.0668              0.2000     0.6481\n",
+       "2016-10-16 05:36:56.700       0.0           48.4700          24.6200            242.3030              0.2000     0.6318\n",
+       "2016-10-16 05:36:57.000       0.0           48.4702          24.6206            241.5632              0.2000     0.6178\n",
+       "...                           ...               ...              ...                 ...                 ...        ...\n",
+       "2016-10-17 06:52:04.500       0.0           63.9400          24.6200              0.0000              0.2080     9.9322\n",
+       "2016-10-17 06:52:04.800       0.0           63.9400          24.6200              0.0000              0.2050    31.7887\n",
+       "2016-10-17 06:52:05.100       0.0           63.9400          24.6200              0.0000              0.2040    57.7304\n",
+       "2016-10-17 06:52:05.400       0.0           63.9400          24.6200              0.0000              0.2020    71.9176\n",
+       "2016-10-17 06:52:05.700       0.0           63.9400          24.6200              0.0000              0.2010    61.8035\n",
+       "\n",
+       "[303034 rows x 6 columns]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>holiday</th>\n",
+       "      <th>temp</th>\n",
+       "      <th>rain_1h</th>\n",
+       "      <th>snow_1h</th>\n",
+       "      <th>clouds_all</th>\n",
+       "      <th>weather_main</th>\n",
+       "      <th>weather_description</th>\n",
+       "      <th>traffic_volume</th>\n",
+       "      <th>month</th>\n",
+       "      <th>day</th>\n",
+       "      <th>week</th>\n",
+       "      <th>hour</th>\n",
+       "      <th>minute</th>\n",
+       "      <th>dayofweek</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>date_time</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>2012-10-02 09:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>288.28</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>40.0</td>\n",
+       "      <td>Clouds</td>\n",
+       "      <td>scattered clouds</td>\n",
+       "      <td>5545.0</td>\n",
+       "      <td>10</td>\n",
+       "      <td>2</td>\n",
+       "      <td>40</td>\n",
+       "      <td>9</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2012-10-02 10:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>289.36</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>75.0</td>\n",
+       "      <td>Clouds</td>\n",
+       "      <td>broken clouds</td>\n",
+       "      <td>4516.0</td>\n",
+       "      <td>10</td>\n",
+       "      <td>2</td>\n",
+       "      <td>40</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2012-10-02 11:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>289.58</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>Clouds</td>\n",
+       "      <td>overcast clouds</td>\n",
+       "      <td>4767.0</td>\n",
+       "      <td>10</td>\n",
+       "      <td>2</td>\n",
+       "      <td>40</td>\n",
+       "      <td>11</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2012-10-02 12:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>290.13</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>Clouds</td>\n",
+       "      <td>overcast clouds</td>\n",
+       "      <td>5026.0</td>\n",
+       "      <td>10</td>\n",
+       "      <td>2</td>\n",
+       "      <td>40</td>\n",
+       "      <td>12</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2012-10-02 13:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>291.14</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>75.0</td>\n",
+       "      <td>Clouds</td>\n",
+       "      <td>broken clouds</td>\n",
+       "      <td>4918.0</td>\n",
+       "      <td>10</td>\n",
+       "      <td>2</td>\n",
+       "      <td>40</td>\n",
+       "      <td>13</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>...</th>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "      <td>...</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2018-09-30 19:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>283.45</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>75.0</td>\n",
+       "      <td>Clouds</td>\n",
+       "      <td>broken clouds</td>\n",
+       "      <td>3543.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>30</td>\n",
+       "      <td>39</td>\n",
+       "      <td>19</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2018-09-30 20:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>282.76</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>Clouds</td>\n",
+       "      <td>overcast clouds</td>\n",
+       "      <td>2781.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>30</td>\n",
+       "      <td>39</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2018-09-30 21:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>282.73</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>Thunderstorm</td>\n",
+       "      <td>proximity thunderstorm</td>\n",
+       "      <td>2159.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>30</td>\n",
+       "      <td>39</td>\n",
+       "      <td>21</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2018-09-30 22:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>282.09</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>Clouds</td>\n",
+       "      <td>overcast clouds</td>\n",
+       "      <td>1450.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>30</td>\n",
+       "      <td>39</td>\n",
+       "      <td>22</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2018-09-30 23:00:00</th>\n",
+       "      <td>True</td>\n",
+       "      <td>282.12</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>90.0</td>\n",
+       "      <td>Clouds</td>\n",
+       "      <td>overcast clouds</td>\n",
+       "      <td>954.0</td>\n",
+       "      <td>9</td>\n",
+       "      <td>30</td>\n",
+       "      <td>39</td>\n",
+       "      <td>23</td>\n",
+       "      <td>0</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>52551 rows × 14 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                     holiday    temp  rain_1h  snow_1h  clouds_all  weather_main     weather_description  traffic_volume  month  day  week  hour  minute  dayofweek\n",
+       "date_time                                                                                                                                                          \n",
+       "2012-10-02 09:00:00     True  288.28      0.0      0.0        40.0        Clouds        scattered clouds          5545.0     10    2    40     9       0          1\n",
+       "2012-10-02 10:00:00     True  289.36      0.0      0.0        75.0        Clouds           broken clouds          4516.0     10    2    40    10       0          1\n",
+       "2012-10-02 11:00:00     True  289.58      0.0      0.0        90.0        Clouds         overcast clouds          4767.0     10    2    40    11       0          1\n",
+       "2012-10-02 12:00:00     True  290.13      0.0      0.0        90.0        Clouds         overcast clouds          5026.0     10    2    40    12       0          1\n",
+       "2012-10-02 13:00:00     True  291.14      0.0      0.0        75.0        Clouds           broken clouds          4918.0     10    2    40    13       0          1\n",
+       "...                      ...     ...      ...      ...         ...           ...                     ...             ...    ...  ...   ...   ...     ...        ...\n",
+       "2018-09-30 19:00:00     True  283.45      0.0      0.0        75.0        Clouds           broken clouds          3543.0      9   30    39    19       0          6\n",
+       "2018-09-30 20:00:00     True  282.76      0.0      0.0        90.0        Clouds         overcast clouds          2781.0      9   30    39    20       0          6\n",
+       "2018-09-30 21:00:00     True  282.73      0.0      0.0        90.0  Thunderstorm  proximity thunderstorm          2159.0      9   30    39    21       0          6\n",
+       "2018-09-30 22:00:00     True  282.09      0.0      0.0        90.0        Clouds         overcast clouds          1450.0      9   30    39    22       0          6\n",
+       "2018-09-30 23:00:00     True  282.12      0.0      0.0        90.0        Clouds         overcast clouds           954.0      9   30    39    23       0          6\n",
+       "\n",
+       "[52551 rows x 14 columns]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for Dataset in [IMOSCurrentsVel, AppliancesEnergyPrediction, BejingPM25, GasSensor, MetroInterstateTraffic]:\n",
+    "    dataset = Dataset(datasets_root)\n",
+    "    dataset.df[dataset.columns_target].dropna().head(1000).plot()\n",
+    "    plt.show()\n",
+    "    display(dataset.df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "seq2seq-time",
+   "language": "python",
+   "name": "seq2seq-time"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.8"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {
+    "height": "755px",
+    "left": "10px",
+    "top": "146px",
+    "width": "165px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": true
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
diff --git a/requirements/requirements.txt b/requirements/requirements.txt
index e69de29..f139224 100644
--- a/requirements/requirements.txt
+++ b/requirements/requirements.txt
@@ -0,0 +1,190 @@
+absl-py @ file:///home/conda/feedstock_root/build_artifacts/absl-py_1602289403781/work
+aiohttp @ file:///tmp/build/80754af9/aiohttp_1602530305083/work
+appdirs==1.4.4
+argon2-cffi @ file:///home/conda/feedstock_root/build_artifacts/argon2-cffi_1602546578258/work
+async-generator==1.10
+async-timeout==3.0.1
+attrs @ file:///home/conda/feedstock_root/build_artifacts/attrs_1599308529326/work
+awscli @ file:///home/conda/feedstock_root/build_artifacts/awscli_1602890549104/work
+backcall @ file:///home/conda/feedstock_root/build_artifacts/backcall_1592338393461/work
+backports.functools-lru-cache==1.6.1
+black @ file:///home/conda/feedstock_root/build_artifacts/black-recipe_1599478779128/work
+bleach @ file:///home/conda/feedstock_root/build_artifacts/bleach_1600454382015/work
+blinker==1.4
+bokeh @ file:///home/conda/feedstock_root/build_artifacts/bokeh_1602690186583/work
+botocore @ file:///home/conda/feedstock_root/build_artifacts/botocore_1602884371056/work
+bpe==1.0
+brotlipy==0.7.0
+cachetools @ file:///home/conda/feedstock_root/build_artifacts/cachetools_1593420445823/work
+certifi==2020.6.20
+cffi @ file:///home/conda/feedstock_root/build_artifacts/cffi_1602537219008/work
+cftime @ file:///home/conda/feedstock_root/build_artifacts/cftime_1602504440833/work
+chardet @ file:///home/conda/feedstock_root/build_artifacts/chardet_1602255309768/work
+click==7.1.2
+cloudpickle @ file:///home/conda/feedstock_root/build_artifacts/cloudpickle_1598400192773/work
+colorama==0.4.3
+colorcet==2.0.2
+confuse @ file:///home/conda/feedstock_root/build_artifacts/confuse_1593279073800/work
+cryptography @ file:///home/conda/feedstock_root/build_artifacts/cryptography_1602614063317/work
+cycler==0.10.0
+cytoolz==0.11.0
+dask @ file:///home/conda/feedstock_root/build_artifacts/dask-core_1602029610262/work
+datashader @ file:///home/conda/feedstock_root/build_artifacts/datashader_1597664023361/work
+datashape==0.5.4
+decorator==4.4.2
+defusedxml==0.6.0
+distributed @ file:///home/conda/feedstock_root/build_artifacts/distributed_1602493186453/work
+docutils==0.15.2
+entrypoints @ file:///home/conda/feedstock_root/build_artifacts/entrypoints_1602701733603/work/dist/entrypoints-0.3-py2.py3-none-any.whl
+fastparquet @ file:///home/conda/feedstock_root/build_artifacts/fastparquet_1594909864671/work
+fsspec @ file:///home/conda/feedstock_root/build_artifacts/fsspec_1602700749102/work
+future @ file:///home/conda/feedstock_root/build_artifacts/future_1602538316704/work
+google-auth @ file:///tmp/build/80754af9/google-auth_1601995530934/work
+google-auth-oauthlib==0.4.1
+grpcio @ file:///home/conda/feedstock_root/build_artifacts/grpcio_1596715635580/work
+HeapDict==1.0.1
+holoviews @ file:///home/conda/feedstock_root/build_artifacts/holoviews_1600439907620/work
+htmlmin==0.1.12
+hypothesis==4.32.3
+idna @ file:///home/conda/feedstock_root/build_artifacts/idna_1593328102638/work
+ImageHash @ file:///home/conda/feedstock_root/build_artifacts/imagehash_1588182723834/work
+importlib-metadata @ file:///home/conda/feedstock_root/build_artifacts/importlib-metadata_1600910428305/work
+iniconfig @ file:///tmp/build/80754af9/iniconfig_1602780191262/work
+ipykernel @ file:///home/conda/feedstock_root/build_artifacts/ipykernel_1602682802500/work/dist/ipykernel-5.3.4-py3-none-any.whl
+ipython @ file:///home/conda/feedstock_root/build_artifacts/ipython_1602640393953/work
+ipython-genutils==0.2.0
+ipywidgets @ file:///home/conda/feedstock_root/build_artifacts/ipywidgets_1599554010055/work
+jedi @ file:///home/conda/feedstock_root/build_artifacts/jedi_1602395235501/work
+Jinja2==2.11.2
+jmespath @ file:///home/conda/feedstock_root/build_artifacts/jmespath_1589369830981/work
+joblib @ file:///home/conda/feedstock_root/build_artifacts/joblib_1601671685479/work
+jsonschema==3.2.0
+jupyter-client @ file:///home/conda/feedstock_root/build_artifacts/jupyter_client_1598486169312/work
+jupyter-core @ file:///home/conda/feedstock_root/build_artifacts/jupyter_core_1602537277085/work
+jupyterlab-pygments @ file:///home/conda/feedstock_root/build_artifacts/jupyterlab_pygments_1601375948261/work
+kiwisolver @ file:///home/conda/feedstock_root/build_artifacts/kiwisolver_1602517221725/work
+llvmlite==0.34.0
+locket==0.2.0
+Markdown @ file:///home/conda/feedstock_root/build_artifacts/markdown_1602544730470/work
+MarkupSafe @ file:///home/conda/feedstock_root/build_artifacts/markupsafe_1602267316845/work
+matplotlib @ file:///home/conda/feedstock_root/build_artifacts/matplotlib-suite_1602600750896/work
+mccabe==0.6.1
+missingno==0.4.2
+mistune @ file:///home/conda/feedstock_root/build_artifacts/mistune_1602381812692/work
+more-itertools @ file:///home/conda/feedstock_root/build_artifacts/more-itertools_1598643641143/work
+msgpack @ file:///home/conda/feedstock_root/build_artifacts/msgpack-python_1602380760823/work
+multidict @ file:///tmp/build/80754af9/multidict_1600456400975/work
+multipledispatch==0.6.0
+mypy @ file:///home/conda/feedstock_root/build_artifacts/mypy_1602270162469/work
+mypy-extensions==0.4.3
+nbclient @ file:///home/conda/feedstock_root/build_artifacts/nbclient_1602859080374/work
+nbconvert @ file:///home/conda/feedstock_root/build_artifacts/nbconvert_1602715396354/work
+nbformat @ file:///home/conda/feedstock_root/build_artifacts/nbformat_1602732862338/work
+nc-time-axis==1.2.0
+nest-asyncio @ file:///home/conda/feedstock_root/build_artifacts/nest-asyncio_1601342677072/work
+netCDF4 @ file:///home/conda/feedstock_root/build_artifacts/netcdf4_1602508544050/work
+networkx @ file:///home/conda/feedstock_root/build_artifacts/networkx_1598210780226/work
+notebook @ file:///home/conda/feedstock_root/build_artifacts/notebook_1602720128568/work
+numba @ file:///home/conda/feedstock_root/build_artifacts/numba_1599084798687/work
+numpy @ file:///home/conda/feedstock_root/build_artifacts/numpy_1602429044575/work
+oauthlib==3.1.0
+olefile @ file:///home/conda/feedstock_root/build_artifacts/olefile_1602866521163/work
+packaging @ file:///home/conda/feedstock_root/build_artifacts/packaging_1589925210001/work
+pandas @ file:///home/conda/feedstock_root/build_artifacts/pandas_1602502751364/work
+pandas-profiling @ file:///home/conda/feedstock_root/build_artifacts/pandas-profiling_1599137999474/work
+pandocfilters==1.4.2
+panel @ file:///home/conda/feedstock_root/build_artifacts/panel_1592920888719/work
+param==1.9.3
+parso @ file:///home/conda/feedstock_root/build_artifacts/parso_1595548966091/work
+partd==1.1.0
+pathspec==0.8.0
+patsy==0.5.1
+pexpect==4.8.0
+phik @ file:///home/conda/feedstock_root/build_artifacts/phik_1590331950347/work
+pickleshare @ file:///home/conda/feedstock_root/build_artifacts/pickleshare_1602535628301/work
+Pillow @ file:///home/conda/feedstock_root/build_artifacts/pillow_1602708615436/work
+pluggy @ file:///home/conda/feedstock_root/build_artifacts/pluggy_1602337415071/work
+prometheus-client @ file:///home/conda/feedstock_root/build_artifacts/prometheus_client_1590412252446/work
+prompt-toolkit @ file:///home/conda/feedstock_root/build_artifacts/prompt-toolkit_1602524994744/work
+protobuf==3.13.0
+psutil @ file:///home/conda/feedstock_root/build_artifacts/psutil_1602264040045/work
+ptyprocess==0.6.0
+py @ file:///home/conda/feedstock_root/build_artifacts/py_1593088446458/work
+pyasn1==0.4.8
+pyasn1-modules==0.2.8
+pycodestyle @ file:///home/conda/feedstock_root/build_artifacts/pycodestyle_1589305246696/work
+pycparser @ file:///home/conda/feedstock_root/build_artifacts/pycparser_1593275161868/work
+pyct @ file:///tmp/build/80754af9/pyct_1600458283986/work
+pydocstyle @ file:///home/conda/feedstock_root/build_artifacts/pydocstyle_1598747747227/work
+pyflakes==2.2.0
+Pygments @ file:///home/conda/feedstock_root/build_artifacts/pygments_1600347314331/work
+PyJWT==1.7.1
+pylama==7.7.1
+pyOpenSSL==19.1.0
+pyparsing==2.4.7
+PyQt5==5.12.3
+PyQt5-sip==4.19.18
+PyQtChart==5.12
+PyQtWebEngine==5.12.1
+pyrsistent @ file:///home/conda/feedstock_root/build_artifacts/pyrsistent_1602259985647/work
+PySocks @ file:///home/conda/feedstock_root/build_artifacts/pysocks_1602326924965/work
+pytest==6.1.1
+python-dateutil==2.8.1
+pytorch-fast-transformers==0.3.0
+pytorch-lightning @ file:///home/conda/feedstock_root/build_artifacts/pytorch-lightning_1602786328955/work
+pytorch-lightning-bolts==0.2.5
+pytz==2020.1
+pyviz-comms @ file:///home/conda/feedstock_root/build_artifacts/pyviz_comms_1594121601757/work
+PyWavelets @ file:///home/conda/feedstock_root/build_artifacts/pywavelets_1602504439149/work
+PyYAML==5.3.1
+pyzmq==19.0.2
+regex @ file:///home/conda/feedstock_root/build_artifacts/regex_1602771401882/work
+requests @ file:///home/conda/feedstock_root/build_artifacts/requests_1592425495151/work
+requests-oauthlib @ file:///home/conda/feedstock_root/build_artifacts/requests-oauthlib_1595492159598/work
+rsa @ file:///home/conda/feedstock_root/build_artifacts/rsa_1591990902901/work
+s3transfer @ file:///home/conda/feedstock_root/build_artifacts/s3transfer_1602631002642/work
+scikit-learn @ file:///home/conda/feedstock_root/build_artifacts/scikit-learn_1596546074663/work
+scipy @ file:///home/conda/feedstock_root/build_artifacts/scipy_1602862657152/work
+seaborn @ file:///home/conda/feedstock_root/build_artifacts/seaborn-base_1599592695803/work
+Send2Trash==1.5.0
+# Editable Git install with no remote (seq2seq-time==0.1.0)
+-e /media/wassname/Storage5/projects2/3ST/seq2seq-time
+six @ file:///home/conda/feedstock_root/build_artifacts/six_1590081179328/work
+sklearn==0.0
+sklearn-pandas==2.0.2
+snowballstemmer==2.0.0
+sortedcontainers @ file:///home/conda/feedstock_root/build_artifacts/sortedcontainers_1591999956871/work
+statsmodels @ file:///home/conda/feedstock_root/build_artifacts/statsmodels_1602599914091/work
+tangled-up-in-unicode @ file:///home/conda/feedstock_root/build_artifacts/tangled-up-in-unicode_1589363771888/work
+tblib @ file:///tmp/build/80754af9/tblib_1597928476713/work
+tensorboard @ file:///home/conda/feedstock_root/build_artifacts/tensorboard_1595378845776/work/tensorboard-2.3.0-py3-none-any.whl
+tensorboard-plugin-wit @ file:///home/conda/feedstock_root/build_artifacts/tensorboard-plugin-wit_1592816951245/work/tensorboard_plugin_wit-1.6.0.post3-py3-none-any.whl
+terminado @ file:///home/conda/feedstock_root/build_artifacts/terminado_1602679584439/work
+testpath==0.4.4
+threadpoolctl @ file:///tmp/tmp79xdzxkt/threadpoolctl-2.1.0-py3-none-any.whl
+thrift==0.11.0
+toml @ file:///home/conda/feedstock_root/build_artifacts/toml_1589469402899/work
+toolz @ file:///home/conda/feedstock_root/build_artifacts/toolz_1600973991856/work
+torch==1.6.0
+torchsummaryX==1.3.0
+torchvision==0.7.0
+tornado @ file:///home/conda/feedstock_root/build_artifacts/tornado_1602488893411/work
+tqdm @ file:///home/conda/feedstock_root/build_artifacts/tqdm_1602171507552/work
+traitlets @ file:///home/conda/feedstock_root/build_artifacts/traitlets_1602771532708/work
+typed-ast==1.4.1
+typing-extensions @ file:///home/conda/feedstock_root/build_artifacts/typing_extensions_1602702424206/work
+ucimlr @ git+https://github.com/isacarnekvist/ucimlr@329ed0586effeb2d57f179f3abb0da9862feed01
+unlzw==0.1.1
+uptide==1.0
+urllib3 @ file:///home/conda/feedstock_root/build_artifacts/urllib3_1595434816409/work
+visions @ file:///home/conda/feedstock_root/build_artifacts/visions_1597645571032/work
+wcwidth @ file:///home/conda/feedstock_root/build_artifacts/wcwidth_1600965781394/work
+webencodings==0.5.1
+Werkzeug==1.0.1
+widgetsnbextension @ file:///home/conda/feedstock_root/build_artifacts/widgetsnbextension_1602769155190/work
+xarray @ file:///home/conda/feedstock_root/build_artifacts/xarray_1600638299066/work
+xlrd==1.2.0
+yapf @ file:///home/conda/feedstock_root/build_artifacts/yapf_1595950469082/work
+yarl @ file:///home/conda/feedstock_root/build_artifacts/yarl_1602671471836/work
+zict==2.0.0
+zipp @ file:///home/conda/feedstock_root/build_artifacts/zipp_1602852756910/work
diff --git a/seq2seq_time/data/data.py b/seq2seq_time/data/data.py
new file mode 100644
index 0000000..2fa02b8
--- /dev/null
+++ b/seq2seq_time/data/data.py
@@ -0,0 +1,309 @@
+from typing import List, Tuple
+from torchvision.datasets.utils import download_url, extract_archive, download_and_extract_archive
+import os
+from tqdm.auto import tqdm
+from pathlib import Path
+from sklearn_pandas import DataFrameMapper
+import xarray as xr
+import pandas as pd
+import numpy as np
+
+from .dataset import Seq2SeqDataSet
+from .util import normalize_encode_dataframe, timeseries_split
+from .tidal import generate_tidal_periods
+
+
+class RegressionForecastData:   
+    columns_forecast = None # The input colums which can be included in future (e.g. week or weather forecast)
+    columns_target = None # Target columns
+    
+    def __init__(self, datasets_root):        
+        self.datasets_root = datasets_root
+        
+        # Process data
+        self.df = self.download()        
+        self.df_norm, self.scaler = self.normalize(self.df)
+        self.output_scaler = next(filter(lambda r:r[0][0] in self.columns_target, self.scaler.features))[-1]
+        self.df_train, self.df_test = self.split(self.df_norm)
+        
+        # Check processing
+        self.check()
+    
+    def download(self) -> pd.DataFrame:
+        """Implement this method to download data and return raw df"""
+        raise NotImplementedError()
+        return df
+    
+    def normalize(self, df) -> Tuple[pd.DataFrame, DataFrameMapper]:
+        df_norm, scaler = normalize_encode_dataframe(df)
+        return df_norm, scaler
+    
+    def split(self, df_norm: pd.DataFrame) -> Tuple[pd.DataFrame, pd.DataFrame]:
+        df_train, df_test = timeseries_split(df_norm)
+        return df_train, df_test 
+    
+    def check(self) -> None:
+        """Check the resulting dataframe"""
+        assert isinstance(self.df.index, pd.DatetimeIndex), 'index must be datetime'
+        assert self.df.index.freq is not None, 'df must have freq'        
+        assert self.columns_forecast is not None
+        assert self.columns_target is not None
+        assert ~set(self.columns_target).issubset(set(self.columns_forecast)), 'target columns should not be in forecast'
+        assert set(self.columns_forecast).issubset(set(self.df.columns)), 'columns_forecast must be in df'
+        assert set(self.columns_target).issubset(set(self.df.columns)), 'columns_target must be in df'
+        
+    def to_datasets(self, window_past: int, window_future: int, valid:bool=False) -> Tuple[Seq2SeqDataSet, Seq2SeqDataSet]:
+        """Convert to torch datasets"""
+        ds_train = Seq2SeqDataSet(df_train, window_past=window_past, window_future=window_future, columns_target=self.columns_target, columns_past=self.columns_past)
+        ds_test = Seq2SeqDataSet(df_test, window_past=window_past, window_future=window_future, columns_target=self.columns_target, columns_past=self.columns_past)
+        return ds_train, ds_test
+    
+    def __repr__(self):
+        return f'<{type(self).__name__} {self.df.shape if (self.df is not None) else None}>'
+
+class GasSensor(RegressionForecastData):
+    """
+    See: http://archive.ics.uci.edu/ml/datasets/Gas+sensor+array+temperature+modulation
+    """
+    
+    columns_target = ['R1 (MOhm)']
+    columns_forecast = ['Flow rate (mL/min)', 'Heater voltage (V)']
+    
+    def download(self):
+        url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00487/gas-sensor-array-temperature-modulation.zip'
+        
+        # download if needed
+        extract_path = self.datasets_root/'GasSensor'
+        files = sorted(extract_path.glob('*.csv'))
+        if len(files)<13:
+            print('download_and_extract_archive')
+            download_and_extract_archive(url, self.datasets_root, extract_path)
+        
+        # Load csv's
+        files = sorted(extract_path.glob('*.csv'))
+        dfs = []
+        for f in files:
+            now = pd.to_datetime(f.stem, format='%Y%m%d_%H%M%S')
+            df = pd.read_csv(f)
+            df.index = pd.to_timedelta(df['Time (s)'], unit='s') + now
+            dfs.append(df)
+        self.df = pd.concat(dfs).dropna(subset=self.columns_target)
+
+        df = df[[ 'CO (ppm)', 'Humidity (%r.h.)', 'Temperature (C)',
+               'Flow rate (mL/min)', 'Heater voltage (V)', 'R1 (MOhm)']]
+        df = df.resample('0.3S').first()
+        
+        return df
+
+
+class MetroInterstateTraffic(RegressionForecastData):
+    """
+    See: https://archive.ics.uci.edu/ml/datasets/Metro+Interstate+Traffic+Volume
+    """
+    
+    columns_target = ['traffic_volume']
+    columns_forecast = ['holiday', 'month', 'day', 'week', 'hour',
+       'minute', 'dayofweek']
+    
+    def download(self):
+        url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00492/Metro_Interstate_Traffic_Volume.csv.gz'
+        
+        # download if needed
+        filename = '00492_Metro_Interstate_Traffic_Volume.csv.gz'
+        local_path = self.datasets_root/filename
+        if not local_path.exists():
+            download_url(url, self.datasets_root, filename)
+        df = (pd.read_csv(local_path, index_col='date_time', parse_dates=['date_time'])
+              .dropna(subset=self.columns_target)
+              .resample('1H').first()
+             )
+        
+        # Make holiday a bool
+        df['holiday'] = ~df['holiday'].isna()
+        df['weather_main'] = df['weather_main'].fillna('none')
+        df['weather_description'] = df['weather_description'].fillna('none')
+        
+        # Add time features 
+        time = df.index.to_series()
+        df["month"] = time.dt.month
+        df['day'] = time.dt.day
+        df['week'] = time.dt.isocalendar().week
+        df['hour'] = time.dt.hour
+        df['minute'] = time.dt.minute
+        df['dayofweek'] = time.dt.dayofweek
+        
+        return df
+
+class AppliancesEnergyPrediction(RegressionForecastData):
+    """
+    See: https://archive.ics.uci.edu/ml/datasets/Appliances+energy+prediction
+    """
+    
+    columns_target = ['log_Appliances']
+    columns_forecast = ['month', 'day', 'week', 'hour',
+       'minute', 'dayofweek']
+    
+    def download(self):
+        url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/00374/energydata_complete.csv'
+        
+        # download if needed
+        filename = '00374_AppliancesEnergyPrediction.csv'
+        local_path = self.datasets_root/filename
+        if not local_path.exists():
+            download_url(url, self.datasets_root, filename)
+        df = pd.read_csv(local_path, index_col='date', parse_dates=['date'])
+        
+        # log target
+        df['log_Appliances'] = np.log(df['Appliances'] + 1e-5)
+        df = df.drop(columns=['Appliances'])
+        df = df.dropna(subset=self.columns_target).resample('10T').first()
+        
+        # Add time features 
+        time = df.index.to_series()
+        df["month"] = time.dt.month
+        df['day'] = time.dt.day
+        df['week'] = time.dt.isocalendar().week
+        df['hour'] = time.dt.hour
+        df['minute'] = time.dt.minute
+        df['dayofweek'] = time.dt.dayofweek
+        
+        return df
+
+class BejingPM25(RegressionForecastData):
+    """
+    See: http://archive.ics.uci.edu/ml/datasets/Beijing+PM2.5+Data
+    """
+    
+    columns_target = ['log_pm2.5']
+    columns_forecast = ['month', 'day', 'week', 'hour',
+       'minute', 'dayofweek']
+    
+    def download(self):
+        url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/00381/PRSA_data_2010.1.1-2014.12.31.csv'
+        
+        # download if needed
+        filename = '00381_BejingPM25.csv'
+        local_path = self.datasets_root/filename
+        if not local_path.exists():
+            download_url(url, self.datasets_root, filename)
+        df = pd.read_csv(local_path)
+        df.index = pd.to_datetime(df[['year', 'month', 'day', 'hour']]).dt.tz_localize('Asia/Shanghai')
+        df = df.drop(columns=['year', 'month', 'day', 'hour', 'No'])
+        
+        # log target
+        df['log_pm2.5'] = np.log(df['pm2.5'] + 1e-5)
+        df = df.drop(columns=['pm2.5'])
+        
+        df.dropna(subset=self.columns_target, inplace=True)
+        df = df.resample('1H').first()
+        
+        df['cbwd'] = df['cbwd'].fillna('none')
+        
+        
+        
+        # Add time features 
+        time = df.index.to_series()
+        df["month"] = time.dt.month
+        df['day'] = time.dt.day
+        df['week'] = time.dt.isocalendar().week
+        df['hour'] = time.dt.hour
+        df['minute'] = time.dt.minute
+        df['dayofweek'] = time.dt.dayofweek
+        
+#         df['log_pm2.5'] = np.log(df['pm2.5']+1e-5)
+        
+        return df
+
+def get_current_timeseries(
+        cache_folder=Path("../data/raw/IMOS_ANMN/"),
+        outfile=Path(
+            '../data/processed/currents/MOS_ANMN-WA_AETVZ_WATR20_FV01_WATR20-1909-Continental-194_currents.nc'
+        )):
+    """
+    Download Current data from the IMOS and pre-process.
+    """
+    if not outfile.exists():
+
+        files = [
+            "IMOS_ANMN-WA_AETVZ_20090715T080000Z_WATR20_FV01_WATR20-0907-Continental-194_END-20090716T181317Z_C-20191122T052830Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20100409T080000Z_WATR20_FV01_WATR20-1004-Continental-194_END-20100430T084500Z_C-20191122T053845Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20101222T080000Z_WATR20_FV01_WATR20-1012-Continental-194_END-20110518T051500Z_C-20200916T020035Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20110608T080000Z_WATR20_FV01_WATR20-1106-Continental-194_END-20111122T035000Z_C-20200916T025619Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20111221T060300Z_WATR20_FV01_WATR20-1112-Continental-194_END-20120704T050500Z_C-20200916T043212Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20120726T044000Z_WATR20_FV01_WATR20-1207-Continental-194_END-20130204T044000Z_C-20200916T032027Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20130221T080000Z_WATR20_FV01_WATR20-1302-Continental-194_END-20131003T035000Z_C-20180529T020609Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20131111T080000Z_WATR20_FV01_WATR20-1311-Continental-194_END-20140519T035000Z_C-20200114T033335Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20140710T080000Z_WATR20_FV01_WATR20-1407-Continental-194_END-20150121T021500Z_C-20180529T055902Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20150213T080000Z_WATR20_FV01_WATR20-1502-Continental-194_END-20150424T134002Z_C-20200114T035347Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20150914T080000Z_WATR20_FV01_WATR20-1509-Continental-194_END-20160331T043000Z_C-20180601T013623Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20160427T080000Z_WATR20_FV01_WATR20-1604-Continental-194_END-20160531T021800Z_C-20180531T071709Z.nc",
+            #     "IMOS_ANMN-WA_AETVZ_20170512T080000Z_WATR20_FV01_WATR20-1705-Continental-194_END-20170717T014558Z_C-20190805T004647Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20171204T080000Z_WATR20_FV01_WATR20-1712-Continental-194_END-20180618T030000Z_C-20180620T233149Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20180802T080000Z_WATR20_FV01_WATR20-1807-Continental-194_END-20190225T054500Z_C-20190227T001343Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20190307T080000Z_WATR20_FV01_WATR20-1903-Continental-194_END-20190911T003144Z_C-20200114T045053Z.nc",
+            "IMOS_ANMN-WA_AETVZ_20190926T080000Z_WATR20_FV01_WATR20-1909-Continental-194_END-20200326T030000Z_C-20200420T064334Z.nc",
+        ]
+        base = "http://thredds.aodn.org.au/thredds/fileServer/IMOS/ANMN/WA/WATR20/Velocity/"
+
+        # Download files
+        [download_url(base + f, cache_folder) for f in files]
+
+        # load and merge
+        xds = [xr.open_dataset(cache_folder / f) for f in files]
+        vars = [
+            'VCUR', 'UCUR', 'WCUR', 'TEMP', 'PRES_REL', 'DEPTH', 'ROLL',
+            'PITCH'
+        ]
+        xds2 = [x[vars].isel(HEIGHT_ABOVE_SENSOR=18) for x in xds]
+        xd = xr.concat(xds2, dim='TIME')
+        xd = xd.where(xd.DEPTH > 150)  # remove outliers
+
+        xd['TIME'] = xd['TIME'].dt.round('10T')
+        xd = xd.dropna(dim='TIME', subset=['VCUR', 'UCUR', 'WCUR'])
+
+        # Generate tidal freqs
+        t = xd.TIME.to_series()
+        df_eta = generate_tidal_periods(t)
+
+        # Add tidal freqs
+        xd = xd.merge(df_eta)
+
+        # Cache to nc
+        xd.to_netcdf(outfile)
+        print(
+            f'wrote "{outfile}" with size {outfile.stat().st_size*1e-6:2.2f} MB'
+        )
+    return outfile
+
+
+class IMOSCurrentsVel(RegressionForecastData):
+    """
+    
+    Current Speed at ANMN Two Rocks, WA, 204m mooring
+    
+    see:
+    - http://thredds.aodn.org.au/thredds/fileServer/IMOS/ANMN/WA/WATR20/Velocity/
+    from https://catalogue-imos.aodn.org.au/geonetwork/srv/api/records/ae86e2f5-eaaf-459e-a405-e654d85adb9c
+    and http://thredds.aodn.org.au/thredds/catalog/IMOS/ANMN/WA/WATR20/Velocity/catalog.html
+    And https://en.wikipedia.org/wiki/Theory_of_tides
+    """
+
+    columns_target = ['SPD']
+    columns_forecast = [
+        'M2', 'S2', 'N2', 'K2', 'K1', 'O1', 'P1', 'Q1', 'M4', 'M6', 'S4',
+        'MK3', 'MM', 'SSA', 'SA'
+    ]
+
+    def download(self):
+        outfile = self.datasets_root / 'MOS_ANMN-WA_AETVZ_WATR20_FV01_WATR20-1909-Continental-194_currents.nc'
+        get_current_timeseries(outfile=outfile)
+
+        # made in previous notebook
+        xd = xr.load_dataset(outfile)
+        df = xd.to_dataframe().drop(
+            columns=['HEIGHT_ABOVE_SENSOR', 'NOMINAL_DEPTH'])
+        df['SPD'] = np.sqrt(df.VCUR**2 + df.UCUR**2)
+        df.dropna(subset=self.columns_target, inplace=True)
+        df = df.resample('30T').first()
+
+        return df
diff --git a/seq2seq_time/data/dataset.py b/seq2seq_time/data/dataset.py
index fcea476..d297936 100644
--- a/seq2seq_time/data/dataset.py
+++ b/seq2seq_time/data/dataset.py
@@ -20,11 +20,11 @@ class Seq2SeqDataSet(torch.utils.data.Dataset):
     Returns x_past, y_past, x_future, etc.
     """
     
-    def __init__(self, df: pd.DataFrame, window_past=40, window_future=10, columns_target=['energy(kWh/hh)'], columns_blank=[],):
+    def __init__(self, df: pd.DataFrame, window_past=40, window_future=10, columns_target=['energy(kWh/hh)'], columns_past=[],):
         """
         Args:
         - df: DataFrame with time index, already scaled
-        - columns_blank: The columns we will blank, in the future
+        - columns_past: The columns we will blank, in the future
         """
         super().__init__()
         assert isinstance(df.index, pd.DatetimeIndex), 'should have a datetime index'
@@ -38,7 +38,7 @@ class Seq2SeqDataSet(torch.utils.data.Dataset):
         self.columns_target = columns_target
 
         # For speed
-        self._icol_blank = [df.drop(columns = columns_target).columns.tolist().index(n) for n in columns_blank]
+        self._icol_blank = [df.drop(columns = columns_target).columns.tolist().index(n) for n in columns_past]
         self._x = self.df.drop(columns = self.columns_target).values
         self._y = self.df[columns_target].values
 
@@ -64,6 +64,8 @@ class Seq2SeqDataSet(torch.utils.data.Dataset):
 
         # Stop it cheating by using future weather measurements. Fill in with last value
         x_future[:, self._icol_blank] = x_past[0, self._icol_blank]
+
+        # x_future[:, self._icol_blank] = 0
         return x_past, y_past, x_future, y_future
 
 
diff --git a/seq2seq_time/data/make_dataset.py b/seq2seq_time/data/make_dataset.py
deleted file mode 100644
index 96b377a..0000000
--- a/seq2seq_time/data/make_dataset.py
+++ /dev/null
@@ -1,30 +0,0 @@
-# -*- coding: utf-8 -*-
-import click
-import logging
-from pathlib import Path
-from dotenv import find_dotenv, load_dotenv
-
-
-@click.command()
-@click.argument('input_filepath', type=click.Path(exists=True))
-@click.argument('output_filepath', type=click.Path())
-def main(input_filepath, output_filepath):
-    """ Runs data processing scripts to turn raw data from (../raw) into
-        cleaned data ready to be analyzed (saved in ../processed).
-    """
-    logger = logging.getLogger(__name__)
-    logger.info('making final data set from raw data')
-
-
-if __name__ == '__main__':
-    log_fmt = '%(asctime)s - %(name)s - %(levelname)s - %(message)s'
-    logging.basicConfig(level=logging.INFO, format=log_fmt)
-
-    # not used in this stub but often useful for finding various files
-    project_dir = Path(__file__).resolve().parents[2]
-
-    # find .env automagically by walking up directories until it's found, then
-    # load up the .env entries as environment variables
-    load_dotenv(find_dotenv())
-
-    main()
diff --git a/seq2seq_time/data/tidal.py b/seq2seq_time/data/tidal.py
new file mode 100644
index 0000000..ed21e9e
--- /dev/null
+++ b/seq2seq_time/data/tidal.py
@@ -0,0 +1,43 @@
+import uptide
+import pandas as pd
+
+# https://en.wikipedia.org/wiki/Theory_of_tides#Harmonic_analysis
+default_tidal_constituents = [
+    'M2',
+    'S2',
+    'N2',
+    'K2',  # Semi-diurnal
+    'K1',
+    'O1',
+    'P1',
+    'Q1',  # Diurnal
+    'M4',
+    'M6',
+    'S4',
+    'MK3',  # Short period
+    'MM',
+    'SSA',
+    'SA'  # Long period
+]
+
+
+def generate_tidal_periods(t: pd.Series,
+                           constituents: list = default_tidal_constituents):
+    tide = uptide.Tides(constituents)
+    t0 = t[0]
+    td = t - t0
+    td = td.dt.total_seconds().to_numpy().astype(int)
+    tide.set_initial_time(t0)
+
+    # calc tides
+    amplitudes = np.ones_like(td)
+    phases = np.zeros_like(td)
+    eta = {}
+    for name, f, amplitude, omega, phase, phi, u in zip(
+            tide.constituents, tide.f, amplitudes, tide.omega, phases,
+            tide.phi, tide.u):
+        eta[name] = f * amplitude * np.cos(omega * td - phase + phi + u)
+    df_eta = pd.DataFrame(eta, index=t)
+    return df_eta
+
+
diff --git a/seq2seq_time/data/util.py b/seq2seq_time/data/util.py
new file mode 100644
index 0000000..ec44cb3
--- /dev/null
+++ b/seq2seq_time/data/util.py
@@ -0,0 +1,19 @@
+import sklearn
+from sklearn.preprocessing import StandardScaler, OrdinalEncoder
+from sklearn_pandas import DataFrameMapper
+
+def normalize_encode_dataframe(df, encoder=OrdinalEncoder):
+    """Normalise numeric data, encode categorical data."""
+    columns_input_numeric = list(df._get_numeric_data().columns)
+    columns_categorical = list(set(df.columns)-set(columns_input_numeric))
+    
+    transformers= [([n], StandardScaler()) for n in columns_input_numeric] + \
+                  [([n], encoder()) for n in columns_categorical]
+    scaler = DataFrameMapper(transformers, df_out=True)
+    df_norm = scaler.fit_transform(df)
+    return df_norm, scaler
+    
+def timeseries_split(df, test_fraction=0.2):
+    """Split timeseries data with test in the future"""
+    i = int(len(df)*test_fraction)
+    return df.iloc[:i], df.iloc[i:]