Skip to content

Instantly share code, notes, and snippets.

@domvwt

domvwt/vaex-catboost.ipynb

Created February 2, 2021 19:12
Show Gist options
  • Save domvwt/8dee71dcf26a721ce42464e0809b034e to your computer and use it in GitHub Desktop.
Save domvwt/8dee71dcf26a721ce42464e0809b034e to your computer and use it in GitHub Desktop.
Download ZIP
vaex-catboost.ipynb
Display the source blob
Display the rendered blob
Raw
vaex-catboost.ipynb
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"name": "vaex-catboost.ipynb",
"provenance": [],
"collapsed_sections": [],
"toc_visible": true,
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
}
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/gist/domvwt/8dee71dcf26a721ce42464e0809b034e/vaex-catboost.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ywOOu8YGu0Mj"
},
"source": [
"# Out-of-Core Gradient Boosting with Vaex and Catboost"
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "mM2JrQ4VpJaY",
"outputId": "38cc7c04-c096-4ad0-fab2-0f3d8ab19b5a"
},
"source": [
"%%shell\r\n",
"echo \"Setting up environment...\"\r\n",
"if [ ! -e \"data/yellow_tripdata_2019-12.csv\" ]\r\n",
" then \r\n",
" echo \"...Downloading data...\" \r\n",
" wget -q \\\r\n",
" https://nyc-tlc.s3.amazonaws.com/trip+data/yellow_tripdata_2019-{10..12}.csv \\\r\n",
" -P data/\r\n",
"fi\r\n",
"echo \"...Installing libraries...\"\r\n",
"pip install -Uqq vaex catboost optuna \"ipython>=7.0.0\" &> /dev/null\r\n",
"echo \"Setup Complete!\"\r\n",
"echo \"Runtime restart may be required to load new packages.\""
],
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"text": [
"Setting up environment...\n",
"...Installing libraries...\n",
"Setup Complete!\n",
"Runtime restart may be required to load new packages.\n"
],
"name": "stdout"
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
""
]
},
"metadata": {
"tags": []
},
"execution_count": 3
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "tO6_1lOhugqt"
},
"source": [
"import gc\n",
"import vaex as vx\n",
"import vaex.ml.catboost as cb\n",
"\n",
"from pathlib import Path"
],
"execution_count": 1,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "8Xulcfa3zyLa"
},
"source": [
"data_files = Path(\"data\").iterdir()"
],
"execution_count": 2,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "t13hPzuV0PfH",
"colab": {
"base_uri": "https://localhost:8080/"
},
"outputId": "2042d7f4-957f-4724-97ab-80f55646ab59"
},
"source": [
"# Vaex can read in multiple files and combine them\r\n",
"if not Path(\"data/taxi-data-combined.hdf5\").is_file():\r\n",
" for f in data_files:\r\n",
" df_temp = vx.from_csv(str(f), copy_index=False, convert=True)\r\n",
"\r\n",
" # Slight performance gains made by converting files and reloading as one \r\n",
" df00 = vx.open(\"data/*.hdf5\")\r\n",
" df00.export(\"data/taxi-data-combined.hdf5\")\r\n",
" \r\n",
"df00 = vx.open(\"data/taxi-data-combined.hdf5\")"
],
"execution_count": 3,
"outputs": [
{
"output_type": "stream",
"text": [
"/usr/local/lib/python3.6/dist-packages/IPython/core/interactiveshell.py:3343: DtypeWarning: Columns (6) have mixed types.Specify dtype option on import or set low_memory=False.\n",
" exec(code_obj, self.user_global_ns, self.user_ns)\n"
],
"name": "stderr"
}
]
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 885
},
"id": "4N3ft6K2l_CK",
"outputId": "1cdc67bb-8962-4000-f176-1f3d80bb0f3f"
},
"source": [
"# Very fast summary\r\n",
"df00.info()"
],
"execution_count": 4,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/html": [
"<style>.vaex-description pre {\n",
" max-width : 450px;\n",
" white-space : nowrap;\n",
" overflow : hidden;\n",
" text-overflow: ellipsis;\n",
" }\n",
"\n",
" .vex-description pre:hover {\n",
" max-width : initial;\n",
" white-space: pre;\n",
" }</style>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {
"tags": []
}
},
{
"output_type": "display_data",
"data": {
"text/html": [
"<div><h2>taxi-data-combined</h2> <b>rows</b>: 20,988,319</div><div><b>path</b>: <i>/content/data/taxi-data-combined.hdf5</i></div><div><b>Description</b>: file exported by vaex, by user root, on date 2021-02-02 19:11:58.646962, from source /has/no/path/arrays-/has/no/path/arrays-/has/no/path/arrays</div><h2>Columns:</h2><table class='table-striped'><thead><tr><th>column</th><th>type</th><th>unit</th><th>description</th><th>expression</th></tr></thead><tr><td>VendorID</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>tpep_pickup_datetime</td><td>str</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>tpep_dropoff_datetime</td><td>str</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>passenger_count</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>trip_distance</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>RatecodeID</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>store_and_fwd_flag</td><td>str</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>PULocationID</td><td>int64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>DOLocationID</td><td>int64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>payment_type</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>fare_amount</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>extra</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>mta_tax</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>tip_amount</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>tolls_amount</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>improvement_surcharge</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>total_amount</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr><tr><td>congestion_surcharge</td><td>float64</td><td></td><td ><pre></pre></td><td></td></tr></table><h2>Data:</h2><table>\n",
"<thead>\n",
"<tr><th># </th><th>VendorID </th><th>tpep_pickup_datetime </th><th>tpep_dropoff_datetime </th><th>passenger_count </th><th>trip_distance </th><th>RatecodeID </th><th>store_and_fwd_flag </th><th>PULocationID </th><th>DOLocationID </th><th>payment_type </th><th>fare_amount </th><th>extra </th><th>mta_tax </th><th>tip_amount </th><th>tolls_amount </th><th>improvement_surcharge </th><th>total_amount </th><th>congestion_surcharge </th></tr>\n",
"</thead>\n",
"<tbody>\n",
"<tr><td><i style='opacity: 0.6'>0</i> </td><td>1.0 </td><td>2019-10-01 00:19:55 </td><td>2019-10-01 00:23:57 </td><td>1.0 </td><td>0.4 </td><td>1.0 </td><td>N </td><td>48 </td><td>163 </td><td>2.0 </td><td>4.5 </td><td>3.0 </td><td>0.5 </td><td>0.0 </td><td>0.0 </td><td>0.3 </td><td>8.3 </td><td>2.5 </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>1</i> </td><td>1.0 </td><td>2019-10-01 00:40:19 </td><td>2019-10-01 00:55:17 </td><td>2.0 </td><td>4.3 </td><td>1.0 </td><td>N </td><td>144 </td><td>141 </td><td>1.0 </td><td>14.5 </td><td>3.0 </td><td>0.5 </td><td>2.0 </td><td>0.0 </td><td>0.3 </td><td>20.3 </td><td>2.5 </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>2</i> </td><td>1.0 </td><td>2019-10-01 00:06:52 </td><td>2019-10-01 00:21:23 </td><td>1.0 </td><td>5.0 </td><td>1.0 </td><td>N </td><td>137 </td><td>80 </td><td>1.0 </td><td>17.0 </td><td>3.0 </td><td>0.5 </td><td>5.2 </td><td>0.0 </td><td>0.3 </td><td>26.0 </td><td>2.5 </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>3</i> </td><td>2.0 </td><td>2019-10-01 00:36:08 </td><td>2019-10-01 00:36:15 </td><td>1.0 </td><td>0.0 </td><td>1.0 </td><td>N </td><td>25 </td><td>25 </td><td>4.0 </td><td>-2.5 </td><td>-0.5 </td><td>-0.5 </td><td>0.0 </td><td>0.0 </td><td>-0.3 </td><td>-3.8 </td><td>0.0 </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>4</i> </td><td>2.0 </td><td>2019-10-01 00:36:08 </td><td>2019-10-01 00:36:15 </td><td>1.0 </td><td>0.0 </td><td>1.0 </td><td>N </td><td>25 </td><td>25 </td><td>2.0 </td><td>2.5 </td><td>0.5 </td><td>0.5 </td><td>0.0 </td><td>0.0 </td><td>0.3 </td><td>3.8 </td><td>0.0 </td></tr>\n",
"<tr><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td><td>... </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>20,988,314</i></td><td>nan </td><td>2019-12-31 00:07:00 </td><td>2019-12-31 00:46:00 </td><td>nan </td><td>12.78 </td><td>nan </td><td>None </td><td>230 </td><td>72 </td><td>nan </td><td>32.32 </td><td>2.75 </td><td>0.5 </td><td>0.0 </td><td>6.12 </td><td>0.3 </td><td>41.99 </td><td>0.0 </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>20,988,315</i></td><td>nan </td><td>2019-12-31 00:20:00 </td><td>2019-12-31 00:47:00 </td><td>nan </td><td>18.52 </td><td>nan </td><td>None </td><td>219 </td><td>32 </td><td>nan </td><td>51.63 </td><td>2.75 </td><td>0.5 </td><td>0.0 </td><td>6.12 </td><td>0.3 </td><td>61.3 </td><td>0.0 </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>20,988,316</i></td><td>nan </td><td>2019-12-31 00:50:00 </td><td>2019-12-31 01:21:00 </td><td>nan </td><td>13.13 </td><td>nan </td><td>None </td><td>161 </td><td>76 </td><td>nan </td><td>38.02 </td><td>2.75 </td><td>0.5 </td><td>0.0 </td><td>6.12 </td><td>0.3 </td><td>47.69 </td><td>0.0 </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>20,988,317</i></td><td>nan </td><td>2019-12-31 00:38:19 </td><td>2019-12-31 01:19:37 </td><td>nan </td><td>14.51 </td><td>nan </td><td>None </td><td>230 </td><td>21 </td><td>nan </td><td>41.86 </td><td>2.75 </td><td>0.0 </td><td>0.0 </td><td>6.12 </td><td>0.3 </td><td>51.03 </td><td>0.0 </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>20,988,318</i></td><td>nan </td><td>2019-12-31 00:21:00 </td><td>2019-12-31 00:56:00 </td><td>nan </td><td>-17.16 </td><td>nan </td><td>None </td><td>193 </td><td>219 </td><td>nan </td><td>44.62 </td><td>2.75 </td><td>0.5 </td><td>0.0 </td><td>0.0 </td><td>0.3 </td><td>48.17 </td><td>0.0 </td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {
"tags": []
}
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "3TiEihMuvtxi"
},
"source": [
"# Efficient shuffle and train / test split\r\n",
"df_train, df_test = df00.sample(frac=1).ml.train_test_split(verbose=False)"
],
"execution_count": 5,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "-7vln7ogxvwJ"
},
"source": [
"target = \"tip_amount\"\r\n",
"features = [x for x in df00.get_column_names() if x != target]"
],
"execution_count": 6,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "co7rL9rJwIM6"
},
"source": [
"# Collect garbage because Python leaves trash everywhere\r\n",
"gc.collect()\r\n",
"\r\n",
"# Catboost model parameters\r\n",
"cbm_params = dict(\r\n",
" loss_function=\"MAE\",\r\n",
" early_stopping_rounds=10,\r\n",
" verbose=10,\r\n",
" used_ram_limit=\"8gb\"\r\n",
")\r\n",
"\r\n",
"# Vaex wrapper parameters\r\n",
"vcb_params = dict(\r\n",
" features=features,\r\n",
" target=target,\r\n",
" params=cbm_params\r\n",
") \r\n",
"\r\n",
"cbm = cb.CatBoostModel(**vcb_params)"
],
"execution_count": 7,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "TMO2QjHewgC5",
"outputId": "0e2242ef-4e2d-47ef-b2ba-874e957275e1"
},
"source": [
"# ~1.3hrs for 1000 iterations over 21 million records (on CPU only!)\r\n",
"cbm.fit(df_train, evals=[df_test])"
],
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"text": [
"0:\tlearn: 1.6928684\ttest: 1.7053601\tbest: 1.7053601 (0)\ttotal: 7.29s\tremaining: 2h 1m 23s\n",
"10:\tlearn: 1.4139167\ttest: 1.4291894\tbest: 1.4291894 (10)\ttotal: 1m 12s\tremaining: 1h 48m 22s\n",
"20:\tlearn: 1.2024777\ttest: 1.2196115\tbest: 1.2196115 (20)\ttotal: 2m 16s\tremaining: 1h 45m 53s\n",
"30:\tlearn: 1.0537415\ttest: 1.0723423\tbest: 1.0723423 (30)\ttotal: 3m 15s\tremaining: 1h 42m 4s\n",
"40:\tlearn: 0.9571214\ttest: 0.9773547\tbest: 0.9773547 (40)\ttotal: 4m 15s\tremaining: 1h 39m 46s\n",
"50:\tlearn: 0.8716443\ttest: 0.8923921\tbest: 0.8923921 (50)\ttotal: 5m 14s\tremaining: 1h 37m 37s\n",
"60:\tlearn: 0.8136729\ttest: 0.8348873\tbest: 0.8348873 (60)\ttotal: 6m 16s\tremaining: 1h 36m 33s\n",
"70:\tlearn: 0.7546232\ttest: 0.7754324\tbest: 0.7754324 (70)\ttotal: 7m 13s\tremaining: 1h 34m 32s\n",
"80:\tlearn: 0.7132797\ttest: 0.7339606\tbest: 0.7339606 (80)\ttotal: 8m 9s\tremaining: 1h 32m 31s\n",
"90:\tlearn: 0.6653240\ttest: 0.6850152\tbest: 0.6850152 (90)\ttotal: 9m 3s\tremaining: 1h 30m 28s\n",
"100:\tlearn: 0.6309959\ttest: 0.6501066\tbest: 0.6501066 (100)\ttotal: 9m 55s\tremaining: 1h 28m 20s\n",
"110:\tlearn: 0.5908915\ttest: 0.6087920\tbest: 0.6087920 (110)\ttotal: 10m 46s\tremaining: 1h 26m 15s\n",
"120:\tlearn: 0.5475404\ttest: 0.5639261\tbest: 0.5639261 (120)\ttotal: 11m 33s\tremaining: 1h 23m 59s\n",
"130:\tlearn: 0.5162067\ttest: 0.5315280\tbest: 0.5315280 (130)\ttotal: 12m 20s\tremaining: 1h 21m 54s\n",
"140:\tlearn: 0.4870182\ttest: 0.5014272\tbest: 0.5014272 (140)\ttotal: 13m 8s\tremaining: 1h 20m 5s\n",
"150:\tlearn: 0.4645559\ttest: 0.4782631\tbest: 0.4782631 (150)\ttotal: 13m 56s\tremaining: 1h 18m 21s\n",
"160:\tlearn: 0.4503989\ttest: 0.4636278\tbest: 0.4636278 (160)\ttotal: 14m 44s\tremaining: 1h 16m 48s\n",
"170:\tlearn: 0.4363300\ttest: 0.4491676\tbest: 0.4491676 (170)\ttotal: 15m 31s\tremaining: 1h 15m 18s\n",
"180:\tlearn: 0.4284812\ttest: 0.4410726\tbest: 0.4410726 (180)\ttotal: 16m 19s\tremaining: 1h 13m 51s\n",
"190:\tlearn: 0.4223071\ttest: 0.4347403\tbest: 0.4347403 (190)\ttotal: 17m 5s\tremaining: 1h 12m 21s\n",
"200:\tlearn: 0.4151820\ttest: 0.4274432\tbest: 0.4274432 (200)\ttotal: 17m 51s\tremaining: 1h 10m 59s\n",
"210:\tlearn: 0.4102676\ttest: 0.4223745\tbest: 0.4223745 (210)\ttotal: 18m 39s\tremaining: 1h 9m 47s\n",
"220:\tlearn: 0.4066448\ttest: 0.4186316\tbest: 0.4186316 (220)\ttotal: 19m 27s\tremaining: 1h 8m 35s\n",
"230:\tlearn: 0.4049713\ttest: 0.4169115\tbest: 0.4169115 (230)\ttotal: 20m 17s\tremaining: 1h 7m 33s\n",
"240:\tlearn: 0.4031656\ttest: 0.4150495\tbest: 0.4150495 (240)\ttotal: 21m 5s\tremaining: 1h 6m 25s\n",
"250:\tlearn: 0.4019513\ttest: 0.4138107\tbest: 0.4138107 (250)\ttotal: 21m 53s\tremaining: 1h 5m 18s\n",
"260:\tlearn: 0.3997633\ttest: 0.4115344\tbest: 0.4115344 (260)\ttotal: 22m 40s\tremaining: 1h 4m 12s\n",
"270:\tlearn: 0.3987803\ttest: 0.4105182\tbest: 0.4105182 (270)\ttotal: 23m 28s\tremaining: 1h 3m 9s\n",
"280:\tlearn: 0.3973583\ttest: 0.4090556\tbest: 0.4090556 (280)\ttotal: 24m 17s\tremaining: 1h 2m 10s\n",
"290:\tlearn: 0.3945904\ttest: 0.4062663\tbest: 0.4062663 (290)\ttotal: 25m 6s\tremaining: 1h 1m 9s\n",
"300:\tlearn: 0.3928638\ttest: 0.4044957\tbest: 0.4044957 (300)\ttotal: 25m 54s\tremaining: 1h 9s\n",
"310:\tlearn: 0.3915851\ttest: 0.4031730\tbest: 0.4031730 (310)\ttotal: 26m 42s\tremaining: 59m 9s\n",
"320:\tlearn: 0.3885112\ttest: 0.4001099\tbest: 0.4001099 (320)\ttotal: 27m 31s\tremaining: 58m 13s\n",
"330:\tlearn: 0.3875525\ttest: 0.3991172\tbest: 0.3991172 (330)\ttotal: 28m 17s\tremaining: 57m 11s\n",
"340:\tlearn: 0.3864145\ttest: 0.3979384\tbest: 0.3979384 (340)\ttotal: 29m 3s\tremaining: 56m 10s\n",
"350:\tlearn: 0.3845533\ttest: 0.3960163\tbest: 0.3960163 (350)\ttotal: 29m 54s\tremaining: 55m 17s\n",
"360:\tlearn: 0.3825845\ttest: 0.3939411\tbest: 0.3939411 (360)\ttotal: 30m 44s\tremaining: 54m 24s\n",
"370:\tlearn: 0.3806977\ttest: 0.3919765\tbest: 0.3919765 (370)\ttotal: 31m 32s\tremaining: 53m 28s\n",
"380:\tlearn: 0.3789194\ttest: 0.3901907\tbest: 0.3901907 (380)\ttotal: 32m 22s\tremaining: 52m 36s\n",
"390:\tlearn: 0.3776134\ttest: 0.3888039\tbest: 0.3888039 (390)\ttotal: 33m 13s\tremaining: 51m 45s\n",
"400:\tlearn: 0.3757225\ttest: 0.3868742\tbest: 0.3868742 (400)\ttotal: 34m 3s\tremaining: 50m 51s\n",
"410:\tlearn: 0.3744337\ttest: 0.3855392\tbest: 0.3855392 (410)\ttotal: 34m 54s\tremaining: 50m 1s\n",
"420:\tlearn: 0.3731948\ttest: 0.3842706\tbest: 0.3842706 (420)\ttotal: 35m 45s\tremaining: 49m 10s\n",
"430:\tlearn: 0.3720340\ttest: 0.3830637\tbest: 0.3830637 (430)\ttotal: 36m 35s\tremaining: 48m 18s\n",
"440:\tlearn: 0.3712737\ttest: 0.3822671\tbest: 0.3822671 (440)\ttotal: 37m 25s\tremaining: 47m 26s\n",
"450:\tlearn: 0.3693821\ttest: 0.3803382\tbest: 0.3803382 (450)\ttotal: 38m 15s\tremaining: 46m 33s\n",
"460:\tlearn: 0.3670183\ttest: 0.3778983\tbest: 0.3778983 (460)\ttotal: 39m 3s\tremaining: 45m 40s\n",
"470:\tlearn: 0.3657383\ttest: 0.3765788\tbest: 0.3765788 (470)\ttotal: 39m 57s\tremaining: 44m 53s\n",
"480:\tlearn: 0.3642693\ttest: 0.3750727\tbest: 0.3750727 (480)\ttotal: 40m 49s\tremaining: 44m 2s\n",
"490:\tlearn: 0.3633873\ttest: 0.3741619\tbest: 0.3741619 (490)\ttotal: 41m 40s\tremaining: 43m 11s\n",
"500:\tlearn: 0.3615285\ttest: 0.3722460\tbest: 0.3722460 (500)\ttotal: 42m 31s\tremaining: 42m 21s\n",
"510:\tlearn: 0.3606710\ttest: 0.3713726\tbest: 0.3713726 (510)\ttotal: 43m 24s\tremaining: 41m 31s\n",
"520:\tlearn: 0.3596970\ttest: 0.3703828\tbest: 0.3703828 (520)\ttotal: 44m 17s\tremaining: 40m 42s\n",
"530:\tlearn: 0.3592577\ttest: 0.3699641\tbest: 0.3699641 (530)\ttotal: 45m 5s\tremaining: 39m 49s\n",
"540:\tlearn: 0.3576823\ttest: 0.3683441\tbest: 0.3683441 (540)\ttotal: 45m 53s\tremaining: 38m 56s\n",
"550:\tlearn: 0.3569612\ttest: 0.3676098\tbest: 0.3676098 (550)\ttotal: 46m 41s\tremaining: 38m 2s\n",
"560:\tlearn: 0.3561434\ttest: 0.3667715\tbest: 0.3667715 (560)\ttotal: 47m 29s\tremaining: 37m 9s\n",
"570:\tlearn: 0.3553208\ttest: 0.3659301\tbest: 0.3659301 (570)\ttotal: 48m 17s\tremaining: 36m 16s\n",
"580:\tlearn: 0.3550750\ttest: 0.3656863\tbest: 0.3656863 (580)\ttotal: 49m 4s\tremaining: 35m 23s\n",
"590:\tlearn: 0.3546644\ttest: 0.3652726\tbest: 0.3652726 (590)\ttotal: 49m 50s\tremaining: 34m 29s\n",
"600:\tlearn: 0.3539238\ttest: 0.3645131\tbest: 0.3645131 (600)\ttotal: 50m 37s\tremaining: 33m 36s\n",
"610:\tlearn: 0.3532087\ttest: 0.3637667\tbest: 0.3637667 (610)\ttotal: 51m 23s\tremaining: 32m 43s\n",
"620:\tlearn: 0.3530105\ttest: 0.3635677\tbest: 0.3635677 (620)\ttotal: 52m 10s\tremaining: 31m 50s\n",
"630:\tlearn: 0.3524065\ttest: 0.3629561\tbest: 0.3629561 (630)\ttotal: 52m 59s\tremaining: 30m 59s\n",
"640:\tlearn: 0.3517995\ttest: 0.3623343\tbest: 0.3623343 (640)\ttotal: 53m 47s\tremaining: 30m 7s\n",
"650:\tlearn: 0.3515637\ttest: 0.3621173\tbest: 0.3621173 (650)\ttotal: 54m 37s\tremaining: 29m 17s\n",
"660:\tlearn: 0.3512135\ttest: 0.3617793\tbest: 0.3617793 (660)\ttotal: 55m 26s\tremaining: 28m 26s\n",
"670:\tlearn: 0.3509650\ttest: 0.3615207\tbest: 0.3615207 (670)\ttotal: 56m 16s\tremaining: 27m 35s\n",
"680:\tlearn: 0.3503143\ttest: 0.3608640\tbest: 0.3608640 (680)\ttotal: 57m 3s\tremaining: 26m 43s\n",
"690:\tlearn: 0.3470166\ttest: 0.3575298\tbest: 0.3575298 (690)\ttotal: 57m 49s\tremaining: 25m 51s\n",
"700:\tlearn: 0.3454248\ttest: 0.3559151\tbest: 0.3559151 (700)\ttotal: 58m 37s\tremaining: 25m\n",
"710:\tlearn: 0.3442789\ttest: 0.3547381\tbest: 0.3547381 (710)\ttotal: 59m 25s\tremaining: 24m 9s\n",
"720:\tlearn: 0.3432498\ttest: 0.3536738\tbest: 0.3536738 (720)\ttotal: 1h 13s\tremaining: 23m 18s\n",
"730:\tlearn: 0.3424126\ttest: 0.3528033\tbest: 0.3528033 (730)\ttotal: 1h 1m 5s\tremaining: 22m 28s\n",
"740:\tlearn: 0.3422675\ttest: 0.3526594\tbest: 0.3526594 (740)\ttotal: 1h 1m 53s\tremaining: 21m 37s\n",
"750:\tlearn: 0.3420059\ttest: 0.3523926\tbest: 0.3523926 (750)\ttotal: 1h 2m 40s\tremaining: 20m 46s\n",
"760:\tlearn: 0.3418179\ttest: 0.3522006\tbest: 0.3522006 (760)\ttotal: 1h 3m 28s\tremaining: 19m 55s\n",
"770:\tlearn: 0.3410647\ttest: 0.3514332\tbest: 0.3514332 (770)\ttotal: 1h 4m 13s\tremaining: 19m 4s\n",
"780:\tlearn: 0.3403482\ttest: 0.3506930\tbest: 0.3506930 (780)\ttotal: 1h 4m 59s\tremaining: 18m 13s\n",
"790:\tlearn: 0.3399770\ttest: 0.3502981\tbest: 0.3502981 (790)\ttotal: 1h 5m 47s\tremaining: 17m 22s\n",
"800:\tlearn: 0.3389604\ttest: 0.3492594\tbest: 0.3492594 (800)\ttotal: 1h 6m 35s\tremaining: 16m 32s\n",
"810:\tlearn: 0.3384936\ttest: 0.3487687\tbest: 0.3487687 (810)\ttotal: 1h 7m 21s\tremaining: 15m 41s\n",
"820:\tlearn: 0.3383249\ttest: 0.3485931\tbest: 0.3485931 (820)\ttotal: 1h 8m 7s\tremaining: 14m 51s\n",
"830:\tlearn: 0.3381256\ttest: 0.3483885\tbest: 0.3483885 (830)\ttotal: 1h 8m 53s\tremaining: 14m\n",
"840:\tlearn: 0.3378507\ttest: 0.3481054\tbest: 0.3481054 (840)\ttotal: 1h 9m 38s\tremaining: 13m 10s\n",
"850:\tlearn: 0.3376397\ttest: 0.3478904\tbest: 0.3478904 (850)\ttotal: 1h 10m 24s\tremaining: 12m 19s\n",
"860:\tlearn: 0.3374103\ttest: 0.3476592\tbest: 0.3476592 (860)\ttotal: 1h 11m 11s\tremaining: 11m 29s\n",
"870:\tlearn: 0.3370881\ttest: 0.3473417\tbest: 0.3473417 (870)\ttotal: 1h 11m 56s\tremaining: 10m 39s\n",
"880:\tlearn: 0.3367286\ttest: 0.3469834\tbest: 0.3469834 (880)\ttotal: 1h 12m 42s\tremaining: 9m 49s\n",
"890:\tlearn: 0.3361878\ttest: 0.3464304\tbest: 0.3464304 (890)\ttotal: 1h 13m 28s\tremaining: 8m 59s\n",
"900:\tlearn: 0.3361126\ttest: 0.3463604\tbest: 0.3463604 (900)\ttotal: 1h 14m 13s\tremaining: 8m 9s\n",
"910:\tlearn: 0.3357000\ttest: 0.3459066\tbest: 0.3459066 (910)\ttotal: 1h 15m\tremaining: 7m 19s\n",
"920:\tlearn: 0.3354891\ttest: 0.3456804\tbest: 0.3456804 (920)\ttotal: 1h 15m 47s\tremaining: 6m 30s\n",
"930:\tlearn: 0.3353045\ttest: 0.3454820\tbest: 0.3454820 (930)\ttotal: 1h 16m 34s\tremaining: 5m 40s\n",
"940:\tlearn: 0.3350048\ttest: 0.3451632\tbest: 0.3451632 (940)\ttotal: 1h 17m 21s\tremaining: 4m 50s\n",
"950:\tlearn: 0.3348775\ttest: 0.3450330\tbest: 0.3450330 (950)\ttotal: 1h 18m 8s\tremaining: 4m 1s\n",
"960:\tlearn: 0.3348215\ttest: 0.3449749\tbest: 0.3449749 (960)\ttotal: 1h 18m 54s\tremaining: 3m 12s\n",
"970:\tlearn: 0.3346815\ttest: 0.3448349\tbest: 0.3448349 (970)\ttotal: 1h 19m 40s\tremaining: 2m 22s\n",
"980:\tlearn: 0.3346708\ttest: 0.3448275\tbest: 0.3448275 (980)\ttotal: 1h 20m 26s\tremaining: 1m 33s\n",
"990:\tlearn: 0.3346314\ttest: 0.3447902\tbest: 0.3447902 (990)\ttotal: 1h 21m 12s\tremaining: 44.2s\n",
"999:\tlearn: 0.3345737\ttest: 0.3447316\tbest: 0.3447316 (999)\ttotal: 1h 21m 54s\tremaining: 0us\n",
"\n",
"bestTest = 0.3447316114\n",
"bestIteration = 999\n",
"\n"
],
"name": "stdout"
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "M0RmUPCUzNhP"
},
"source": [
""
],
"execution_count": null,
"outputs": []
}
]
}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment