tft notebook

tft/tft.ipynb

@@ -0,0 +1,89 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "8c4e3b09",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a30ae052",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from estimator import TFTEstimator\n",
+    "from gluonts.dataset.repository.datasets import get_dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "0f3eb07d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset = get_dataset(\"electricity\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3efd0fbe",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "estimator = TFTEstimator(\n",
+    "    freq=dataset.metadata.freq,\n",
+    "    prediction_length=dataset.metadata.prediction_length,\n",
+    "\n",
+    "   \n",
+    "\n",
+    "    batch_size=128,\n",
+    "    num_batches_per_epoch=100,\n",
+    "    trainer_kwargs=dict(max_epochs=10, accelerator='auto'),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4c1a4f83",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "predictor = estimator.train(\n",
+    "    training_data=dataset.train,\n",
+    "    num_workers=16,\n",
+    "    shuffle_buffer_length=1024\n",
+    ")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}