diff --git a/notebooks/01.0-mc-datasets.ipynb b/notebooks/01.0-mc-datasets.ipynb index 21e8050..187299a 100644 --- a/notebooks/01.0-mc-datasets.ipynb +++ b/notebooks/01.0-mc-datasets.ipynb @@ -1636,28 +1636,6 @@ "datasets" ] }, - { - "cell_type": "code", - "execution_count": 20, - "metadata": { - "ExecuteTime": { - "end_time": "2020-11-01T23:22:14.540113Z", - "start_time": "2020-11-01T23:22:14.490588Z" - } - }, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "columns_forecast ['holiday', 'month', 'day', 'week', 'hour', 'minute', 'dayofweek']\n", - "columns_past {'rain_1h', 'weather_main', 'clouds_all', 'temp', 'snow_1h', 'weather_description'}\n", - "columns_target ['traffic_volume']\n" - ] - } - ], - "source": [] - }, { "cell_type": "code", "execution_count": 23, @@ -3365,6 +3343,7 @@ " d = dataset(datasets_root)\n", " display(HTML(f\"

{dataset.__name__}

\"))\n", " print(d.__doc__)\n", + " print(f'{len(d)} rows at freq{d.index.freq.freqstr}')\n", " print('columns_forecast', d.columns_forecast)\n", " print('columns_past', d.columns_past)\n", " print('columns_target', d.columns_target)\n", @@ -3374,307 +3353,14 @@ }, { "cell_type": "code", - "execution_count": 7, + "execution_count": 25, "metadata": { "ExecuteTime": { - "end_time": "2020-11-01T08:32:56.793986Z", - "start_time": "2020-11-01T08:32:33.816269Z" + "end_time": "2020-11-01T23:37:29.680397Z", + "start_time": "2020-11-01T23:37:29.620610Z" } }, - "outputs": [ - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":DynamicMap []\n", - " :Overlay\n", - " .RGB.I :RGB [TIME,SPD] (R,G,B,A)\n", - " .RGB.II :RGB [TIME,SPD] (R,G,B,A)\n", - " .RGB.III :RGB [TIME,SPD] (R,G,B,A)" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "1001" - } - }, - "output_type": "display_data" - }, - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":DynamicMap []\n", - " :Overlay\n", - " .RGB.I :RGB [index,log_pm2.5] (R,G,B,A)\n", - " .RGB.II :RGB [index,log_pm2.5] (R,G,B,A)\n", - " .RGB.III :RGB [index,log_pm2.5] (R,G,B,A)" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "1458" - } - }, - "output_type": "display_data" - }, - { - "name": "stdout", - "output_type": "stream", - "text": [ - "Using downloaded and verified file: ../data/processed/gas-sensor-array-temperature-modulation.zip\n" - ] - }, - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":DynamicMap []\n", - " :Overlay\n", - " .RGB.I :RGB [Time (s),R1 (MOhm)] (R,G,B,A)\n", - " .RGB.II :RGB [Time (s),R1 (MOhm)] (R,G,B,A)\n", - " .RGB.III :RGB [Time (s),R1 (MOhm)] (R,G,B,A)" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "1915" - } - }, - "output_type": "display_data" - }, - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":DynamicMap []\n", - " :Overlay\n", - " .RGB.I :RGB [date,log_Appliances] (R,G,B,A)\n", - " .RGB.II :RGB [date,log_Appliances] (R,G,B,A)\n", - " .RGB.III :RGB [date,log_Appliances] (R,G,B,A)" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "2372" - } - }, - "output_type": "display_data" - }, - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":DynamicMap []\n", - " :Overlay\n", - " .RGB.I :RGB [date_time,traffic_volume] (R,G,B,A)\n", - " .RGB.II :RGB [date_time,traffic_volume] (R,G,B,A)\n", - " .RGB.III :RGB [date_time,traffic_volume] (R,G,B,A)" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "2829" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# View train, test, val splits\n", "l = hv.Layout()\n", @@ -4293,355 +3979,27 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 24, "metadata": { "ExecuteTime": { - "end_time": "2020-11-01T08:33:34.188872Z", - "start_time": "2020-11-01T08:33:13.520779Z" + "end_time": "2020-11-01T23:35:51.007327Z", + "start_time": "2020-11-01T23:35:50.946431Z" } }, - "outputs": [ - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":Layout\n", - " .Overlay.I :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [TIME] (tsp_days)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.II :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [TIME] (tsp_days)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.III :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [TIME] (tsp_days)\n", - " .VLine.Now :VLine [x,y]" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "34646" - } - }, - "output_type": "display_data" - }, - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":Layout\n", - " .Overlay.I :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [index] (week)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.II :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [index] (week)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.III :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [index] (week)\n", - " .VLine.Now :VLine [x,y]" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "43614" - } - }, - "output_type": "display_data" - }, - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":Layout\n", - " .Overlay.I :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [Time (s)] (tsp_days)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.II :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [Time (s)] (tsp_days)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.III :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [Time (s)] (tsp_days)\n", - " .VLine.Now :VLine [x,y]" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "49957" - } - }, - "output_type": "display_data" - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "BokehUserWarning: ColumnDataSource's columns must be of the same length. Current lengths: ('Press_mm_hg', 1), ('RH_1', 1), ('RH_2', 1), ('RH_3', 1), ('RH_4', 1), ('RH_5', 1), ('RH_6', 1), ('RH_7', 1), ('RH_8', 1), ('RH_9', 1), ('RH_out', 1), ('T1', 1), ('T2', 1), ('T3', 1), ('T4', 1), ('T5', 1), ('T6', 1), ('T7', 1), ('T8', 1), ('T9', 1), ('T_out', 1), ('Tdewpoint', 1), ('Visibility', 1), ('Windspeed', 1), ('color', 35), ('column', 35), ('date', 35), ('day', 1), ('dayofweek', 1), ('hour', 1), ('is_past', 1), ('lights', 1), ('line_width', 35), ('minute', 1), ('month', 1), ('muted_alpha', 35), ('rv1', 1), ('rv2', 1), ('tsp_days', 1), ('week', 1)\n", - "BokehUserWarning: ColumnDataSource's columns must be of the same length. Current lengths: ('Press_mm_hg', 1), ('RH_1', 1), ('RH_2', 1), ('RH_3', 1), ('RH_4', 1), ('RH_5', 1), ('RH_6', 1), ('RH_7', 1), ('RH_8', 1), ('RH_9', 1), ('RH_out', 1), ('T1', 1), ('T2', 1), ('T3', 1), ('T4', 1), ('T5', 1), ('T6', 1), ('T7', 1), ('T8', 1), ('T9', 1), ('T_out', 1), ('Tdewpoint', 1), ('Visibility', 1), ('Windspeed', 1), ('color', 35), ('column', 35), ('date', 35), ('day', 1), ('dayofweek', 1), ('hour', 1), ('is_past', 1), ('lights', 1), ('line_width', 35), ('minute', 1), ('month', 1), ('muted_alpha', 35), ('rv1', 1), ('rv2', 1), ('tsp_days', 1), ('week', 1)\n", - "BokehUserWarning: ColumnDataSource's columns must be of the same length. Current lengths: ('Press_mm_hg', 1), ('RH_1', 1), ('RH_2', 1), ('RH_3', 1), ('RH_4', 1), ('RH_5', 1), ('RH_6', 1), ('RH_7', 1), ('RH_8', 1), ('RH_9', 1), ('RH_out', 1), ('T1', 1), ('T2', 1), ('T3', 1), ('T4', 1), ('T5', 1), ('T6', 1), ('T7', 1), ('T8', 1), ('T9', 1), ('T_out', 1), ('Tdewpoint', 1), ('Visibility', 1), ('Windspeed', 1), ('color', 35), ('column', 35), ('date', 35), ('day', 1), ('dayofweek', 1), ('hour', 1), ('is_past', 1), ('lights', 1), ('line_width', 35), ('minute', 1), ('month', 1), ('muted_alpha', 35), ('rv1', 1), ('rv2', 1), ('tsp_days', 1), ('week', 1)\n" - ] - }, - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":Layout\n", - " .Overlay.I :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [date] (week)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.II :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [date] (week)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.III :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [date] (week)\n", - " .VLine.Now :VLine [x,y]" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "53660" - } - }, - "output_type": "display_data" - }, - { - "data": {}, - "metadata": {}, - "output_type": "display_data" - }, - { - "data": { - "application/vnd.holoviews_exec.v0+json": "", - "text/html": [ - "
\n", - "\n", - "\n", - "\n", - "\n", - "\n", - "
\n", - "
\n", - "" - ], - "text/plain": [ - ":Layout\n", - " .Overlay.I :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [date_time] (week)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.II :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [date_time] (week)\n", - " .VLine.Now :VLine [x,y]\n", - " .Overlay.III :Overlay\n", - " .NdOverlay.I :NdOverlay [column]\n", - " :Curve [date_time] (week)\n", - " .VLine.Now :VLine [x,y]" - ] - }, - "metadata": { - "application/vnd.holoviews_exec.v0+json": { - "id": "55569" - } - }, - "output_type": "display_data" - } - ], + "outputs": [], "source": [ "# View input columns\n", "for dataset in datasets:\n", " d = dataset(datasets_root)\n", " display(plot_batches_x(d))" ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] } ], "metadata": { diff --git a/notebooks/01.0-mc-datasets.py b/notebooks/01.0-mc-datasets.py index af9aec3..c4c309c 100644 --- a/notebooks/01.0-mc-datasets.py +++ b/notebooks/01.0-mc-datasets.py @@ -78,12 +78,11 @@ from seq2seq_time.data.data import IMOSCurrentsVel, AppliancesEnergyPrediction, datasets = [IMOSCurrentsVel, BejingPM25, GasSensor, AppliancesEnergyPrediction, MetroInterstateTraffic, ] datasets # - - - for dataset in datasets: d = dataset(datasets_root) display(HTML(f"

{dataset.__name__}

")) print(d.__doc__) + print(f'{len(d)} rows at freq{d.index.freq.freqstr}') print('columns_forecast', d.columns_forecast) print('columns_past', d.columns_past) print('columns_target', d.columns_target) @@ -177,3 +176,5 @@ ds_train, ds_val, ds_test = d.to_datasets(window_past=window_past, for dataset in datasets: d = dataset(datasets_root) display(plot_batches_x(d)) + +