{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [] }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" } }, "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "id": "KXYTwHCZp2d2" }, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt" ] }, { "cell_type": "code", "source": [ "df = pd.read_csv('/content/california_housing_train.csv')" ], "metadata": { "id": "DmTpVlHDqB09" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "df.head()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 226 }, "id": "2kH70XMWqByB", "outputId": "a4bcb79e-905a-4e12-baad-0c50adc10371" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", "0 -114.31 34.19 15.0 5612.0 1283.0 \n", "1 -114.47 34.40 19.0 7650.0 1901.0 \n", "2 -114.56 33.69 17.0 720.0 174.0 \n", "3 -114.57 33.64 14.0 1501.0 337.0 \n", "4 -114.57 33.57 20.0 1454.0 326.0 \n", "\n", " population households median_income median_house_value \n", "0 1015.0 472.0 1.4936 66900.0 \n", "1 1129.0 463.0 1.8200 80100.0 \n", "2 333.0 117.0 1.6509 85700.0 \n", "3 515.0 226.0 3.1917 73400.0 \n", "4 624.0 262.0 1.9250 65500.0 " ], "text/html": [ "\n", "
\n", "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
longitudelatitudehousing_median_agetotal_roomstotal_bedroomspopulationhouseholdsmedian_incomemedian_house_value
0-114.3134.1915.05612.01283.01015.0472.01.493666900.0
1-114.4734.4019.07650.01901.01129.0463.01.820080100.0
2-114.5633.6917.0720.0174.0333.0117.01.650985700.0
3-114.5733.6414.01501.0337.0515.0226.03.191773400.0
4-114.5733.5720.01454.0326.0624.0262.01.925065500.0
\n", "
\n", "
\n", "\n", "
\n", " \n", "\n", " \n", "\n", " \n", "
\n", "\n", "\n", "
\n", " \n", "\n", "\n", "\n", " \n", "
\n", "\n", "
\n", "
\n" ], "application/vnd.google.colaboratory.intrinsic+json": { "type": "dataframe", "variable_name": "df", "summary": "{\n \"name\": \"df\",\n \"rows\": 17000,\n \"fields\": [\n {\n \"column\": \"longitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.005166408426173,\n \"min\": -124.35,\n \"max\": -114.31,\n \"num_unique_values\": 827,\n \"samples\": [\n -117.56,\n -123.32,\n -118.26\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"latitude\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2.1373397946570734,\n \"min\": 32.54,\n \"max\": 41.95,\n \"num_unique_values\": 840,\n \"samples\": [\n 38.44,\n 40.79,\n 32.69\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"housing_median_age\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 12.586936981660335,\n \"min\": 1.0,\n \"max\": 52.0,\n \"num_unique_values\": 52,\n \"samples\": [\n 23.0,\n 52.0,\n 47.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_rooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 2179.947071452768,\n \"min\": 2.0,\n \"max\": 37937.0,\n \"num_unique_values\": 5533,\n \"samples\": [\n 3564.0,\n 6955.0,\n 5451.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"total_bedrooms\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 421.49945157986514,\n \"min\": 1.0,\n \"max\": 6445.0,\n \"num_unique_values\": 1848,\n \"samples\": [\n 729.0,\n 719.0,\n 2075.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"population\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1147.852959159525,\n \"min\": 3.0,\n \"max\": 35682.0,\n \"num_unique_values\": 3683,\n \"samples\": [\n 249.0,\n 1735.0,\n 235.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"households\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 384.52084085590013,\n \"min\": 1.0,\n \"max\": 6082.0,\n \"num_unique_values\": 1740,\n \"samples\": [\n 390.0,\n 1089.0,\n 1351.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_income\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 1.908156518379093,\n \"min\": 0.4999,\n \"max\": 15.0001,\n \"num_unique_values\": 11175,\n \"samples\": [\n 7.2655,\n 5.6293,\n 4.2262\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"median_house_value\",\n \"properties\": {\n \"dtype\": \"number\",\n \"std\": 115983.76438720913,\n \"min\": 14999.0,\n \"max\": 500001.0,\n \"num_unique_values\": 3694,\n \"samples\": [\n 162300.0,\n 346800.0,\n 116700.0\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}" } }, "metadata": {}, "execution_count": 32 } ] }, { "cell_type": "code", "source": [ "df['total_bedrooms'].fillna(df['total_bedrooms'].mean(),inplace=True)\n", "df.isna().sum()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 508 }, "id": "52BeZIIoqBvV", "outputId": "a1ac7984-91ef-4f7c-c700-1caa4ad62a96" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/tmp/ipython-input-33-3685529444.py:1: FutureWarning: A value is trying to be set on a copy of a DataFrame or Series through chained assignment using an inplace method.\n", "The behavior will change in pandas 3.0. This inplace method will never work because the intermediate object on which we are setting values always behaves as a copy.\n", "\n", "For example, when doing 'df[col].method(value, inplace=True)', try using 'df.method({col: value}, inplace=True)' or df[col] = df[col].method(value) instead, to perform the operation inplace on the original object.\n", "\n", "\n", " df['total_bedrooms'].fillna(df['total_bedrooms'].mean(),inplace=True)\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "longitude 0\n", "latitude 0\n", "housing_median_age 0\n", "total_rooms 0\n", "total_bedrooms 0\n", "population 0\n", "households 0\n", "median_income 0\n", "median_house_value 0\n", "dtype: int64" ], "text/html": [ "
\n", "\n", "\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
0
longitude0
latitude0
housing_median_age0
total_rooms0
total_bedrooms0
population0
households0
median_income0
median_house_value0
\n", "

" ] }, "metadata": {}, "execution_count": 33 } ] }, { "cell_type": "code", "source": [ "!pip install h2o" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yML2CxNewGyC", "outputId": "e040810b-cd82-41a4-e2ae-23d10d91e812" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Requirement already satisfied: h2o in /usr/local/lib/python3.11/dist-packages (3.46.0.7)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from h2o) (2.32.3)\n", "Requirement already satisfied: tabulate in /usr/local/lib/python3.11/dist-packages (from h2o) (0.9.0)\n", "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->h2o) (3.4.2)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->h2o) (3.10)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->h2o) (2.4.0)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->h2o) (2025.6.15)\n" ] } ] }, { "cell_type": "code", "source": [ "import h2o" ], "metadata": { "id": "LMX0k221qBsZ" }, "execution_count": null, "outputs": [] }, { "cell_type": "code", "source": [ "h2o.init()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 406 }, "id": "QPW4MIR1qBpH", "outputId": "9d4e9ff4-8511-4be9-c795-a34f63ce765d" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Checking whether there is an H2O instance running at http://localhost:54321. connected.\n", "Warning: Your H2O cluster version is (3 months and 9 days) old. There may be a newer version available.\n", "Please download and install the latest version from: https://h2o-release.s3.amazonaws.com/h2o/latest_stable.html\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "-------------------------- -----------------------------------------------------------------------------------------\n", "H2O_cluster_uptime: 32 mins 18 secs\n", "H2O_cluster_timezone: Etc/UTC\n", "H2O_data_parsing_timezone: UTC\n", "H2O_cluster_version: 3.46.0.7\n", "H2O_cluster_version_age: 3 months and 9 days\n", "H2O_cluster_name: H2O_from_python_unknownUser_cc3bvk\n", "H2O_cluster_total_nodes: 1\n", "H2O_cluster_free_memory: 2.950 Gb\n", "H2O_cluster_total_cores: 2\n", "H2O_cluster_allowed_cores: 2\n", "H2O_cluster_status: locked, healthy\n", "H2O_connection_url: http://localhost:54321\n", "H2O_connection_proxy: {\"http\": null, \"https\": null, \"colab_language_server\": \"/usr/colab/bin/language_service\"}\n", "H2O_internal_security: False\n", "Python_version: 3.11.13 final\n", "-------------------------- -----------------------------------------------------------------------------------------" ], "text/html": [ "\n", " \n", "
\n", " \n", " \n", " \n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
H2O_cluster_uptime:32 mins 18 secs
H2O_cluster_timezone:Etc/UTC
H2O_data_parsing_timezone:UTC
H2O_cluster_version:3.46.0.7
H2O_cluster_version_age:3 months and 9 days
H2O_cluster_name:H2O_from_python_unknownUser_cc3bvk
H2O_cluster_total_nodes:1
H2O_cluster_free_memory:2.950 Gb
H2O_cluster_total_cores:2
H2O_cluster_allowed_cores:2
H2O_cluster_status:locked, healthy
H2O_connection_url:http://localhost:54321
H2O_connection_proxy:{\"http\": null, \"https\": null, \"colab_language_server\": \"/usr/colab/bin/language_service\"}
H2O_internal_security:False
Python_version:3.11.13 final
\n", "
\n" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "train_df = h2o.H2OFrame(df)\n", "train_df.describe()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 709 }, "id": "gSWgdrOBy9sh", "outputId": "34867ad6-7a0c-480d-8420-cc693ed5bcc5" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Parse progress: |████████████████████████████████████████████████████████████████| (done) 100%\n" ] }, { "output_type": "display_data", "data": { "text/plain": [ "Rows:17000\n", "Cols:9\n" ], "text/html": [ "
Rows:17000\n",
              "Cols:9\n",
              "
" ] }, "metadata": {} }, { "output_type": "display_data", "data": { "text/plain": [ " longitude latitude housing_median_age total_rooms total_bedrooms population households median_income median_house_value\n", "------- ------------------ ----------------- -------------------- ------------------ ----------------- ----------------- ------------------ ------------------ --------------------\n", "type real real int int int int int real int\n", "mins -124.35 32.54 1.0 2.0 1.0 3.0 1.0 0.4999 14999.0\n", "mean -119.5621082352941 35.62522470588239 28.589352941176436 2643.6644117647143 539.4108235294095 1429.573941176477 501.2219411764718 3.8835781000000016 207300.9123529415\n", "maxs -114.31 41.95 52.0 37937.0 6445.0 35682.0 6082.0 15.0001 500001.0\n", "sigma 2.0051664084260357 2.137339794657087 12.586936981660406 2179.9470714527765 421.4994515798648 1147.852959159527 384.52084085590155 1.9081565183791034 115983.76438720895\n", "zeros 0 0 0 0 0 0 0 0 0\n", "missing 0 0 0 0 0 0 0 0 0\n", "0 -114.31 34.19 15.0 5612.0 1283.0 1015.0 472.0 1.4936 66900.0\n", "1 -114.47 34.4 19.0 7650.0 1901.0 1129.0 463.0 1.82 80100.0\n", "2 -114.56 33.69 17.0 720.0 174.0 333.0 117.0 1.6509 85700.0\n", "3 -114.57 33.64 14.0 1501.0 337.0 515.0 226.0 3.1917 73400.0\n", "4 -114.57 33.57 20.0 1454.0 326.0 624.0 262.0 1.925 65500.0\n", "5 -114.58 33.63 29.0 1387.0 236.0 671.0 239.0 3.3438 74000.0\n", "6 -114.58 33.61 25.0 2907.0 680.0 1841.0 633.0 2.6768 82400.0\n", "7 -114.59 34.83 41.0 812.0 168.0 375.0 158.0 1.7083 48500.0\n", "8 -114.59 33.61 34.0 4789.0 1175.0 3134.0 1056.0 2.1782 58400.0\n", "9 -114.6 34.83 46.0 1497.0 309.0 787.0 271.0 2.1908 48100.0\n", "[17000 rows x 9 columns]\n" ], "text/html": [ "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
longitude latitude housing_median_age total_rooms total_bedrooms population households median_income median_house_value
type real real int int int int int real int
mins -124.35 32.54 1.0 2.0 1.0 3.0 1.0 0.4999 14999.0
mean -119.562108235294135.6252247058823928.589352941176436 2643.6644117647143539.41082352940951429.573941176477501.2219411764718 3.8835781000000016207300.9123529415
maxs -114.31 41.95 52.0 37937.0 6445.0 35682.0 6082.0 15.0001 500001.0
sigma 2.00516640842603572.13733979465708712.586936981660406 2179.9470714527765421.49945157986481147.852959159527384.520840855901551.9081565183791034115983.76438720895
zeros 0 0 0 0 0 0 0 0 0
missing0 0 0 0 0 0 0 0 0
0 -114.31 34.19 15.0 5612.0 1283.0 1015.0 472.0 1.4936 66900.0
1 -114.47 34.4 19.0 7650.0 1901.0 1129.0 463.0 1.82 80100.0
2 -114.56 33.69 17.0 720.0 174.0 333.0 117.0 1.6509 85700.0
3 -114.57 33.64 14.0 1501.0 337.0 515.0 226.0 3.1917 73400.0
4 -114.57 33.57 20.0 1454.0 326.0 624.0 262.0 1.925 65500.0
5 -114.58 33.63 29.0 1387.0 236.0 671.0 239.0 3.3438 74000.0
6 -114.58 33.61 25.0 2907.0 680.0 1841.0 633.0 2.6768 82400.0
7 -114.59 34.83 41.0 812.0 168.0 375.0 158.0 1.7083 48500.0
8 -114.59 33.61 34.0 4789.0 1175.0 3134.0 1056.0 2.1782 58400.0
9 -114.6 34.83 46.0 1497.0 309.0 787.0 271.0 2.1908 48100.0 
[17000 rows x 9 columns]
" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "test = pd.read_csv('/content/california_housing_test.csv')\n", "test = h2o.H2OFrame(test)\n", "\n", "# Defining feature and label columns\n", "x = test.columns\n", "y = 'median_house_value'\n", "x.remove(y)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Ey38x0B-y9pQ", "outputId": "e1bccd62-1e9b-40df-ccbc-2ad49fa946e0" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Parse progress: |████████████████████████████████████████████████████████████████| (done) 100%\n" ] } ] }, { "cell_type": "code", "source": [ "# Import autoML from H2O\n", "from h2o.automl import H2OAutoML\n", "# callh20automl function\n", "aml = H2OAutoML(max_runtime_secs = 600,\n", " # exclude_algos =['DeepLearning'],\n", " seed = 1,\n", " # stopping_metric ='logloss',\n", " # sort_metric ='logloss',\n", " balance_classes = False,\n", " project_name ='Project_1'\n", ")\n", "# Train model and record time % time\n", "aml.train(x = x, y = y, training_frame = train_df)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "3bcm18Uny9l-", "outputId": "232690ca-152b-4fef-ac4e-04ddcee0d8cc" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "AutoML progress: |\n", "09:41:01.68: New models will be added to existing leaderboard Project_1@@median_house_value (leaderboard frame=null) with already 33 models.\n", "\n", "███████\n", "09:41:56.66: StackedEnsemble_BestOfFamily_5_AutoML_2_20250707_94101 [StackedEnsemble best_of_family_1 (built with AUTO metalearner, using top model from each algorithm type)] failed: water.exceptions.H2OIllegalArgumentException: Failed to find the xval predictions frame. . . Looks like keep_cross_validation_predictions wasn't set when building the models, or the frame was deleted.\n", "\n", "███████████\n", "09:43:47.916: StackedEnsemble_BestOfFamily_6_AutoML_2_20250707_94101 [StackedEnsemble best_of_family_2 (built with AUTO metalearner, using top model from each algorithm type)] failed: water.exceptions.H2OIllegalArgumentException: Failed to find the xval predictions frame. . . Looks like keep_cross_validation_predictions wasn't set when building the models, or the frame was deleted.\n", "09:43:47.939: StackedEnsemble_AllModels_4_AutoML_2_20250707_94101 [StackedEnsemble all_2 (built with AUTO metalearner, using all AutoML models)] failed: water.exceptions.H2OIllegalArgumentException: Failed to find the xval predictions frame. . . Looks like keep_cross_validation_predictions wasn't set when building the models, or the frame was deleted.\n", "\n", "███████████\n", "09:45:28.221: StackedEnsemble_BestOfFamily_7_AutoML_2_20250707_94101 [StackedEnsemble best_of_family_3 (built with AUTO metalearner, using top model from each algorithm type)] failed: water.exceptions.H2OIllegalArgumentException: Failed to find the xval predictions frame. . . Looks like keep_cross_validation_predictions wasn't set when building the models, or the frame was deleted.\n", "09:45:28.283: StackedEnsemble_AllModels_5_AutoML_2_20250707_94101 [StackedEnsemble all_3 (built with AUTO metalearner, using all AutoML models)] failed: water.exceptions.H2OIllegalArgumentException: Failed to find the xval predictions frame. . . Looks like keep_cross_validation_predictions wasn't set when building the models, or the frame was deleted.\n", "\n", "███████████████████████████████\n", "09:50:37.144: StackedEnsemble_AllModels_6_AutoML_2_20250707_94101 [StackedEnsemble all_4 (built with AUTO metalearner, using all AutoML models)] failed: water.exceptions.H2OIllegalArgumentException: Failed to find the xval predictions frame. . . Looks like keep_cross_validation_predictions wasn't set when building the models, or the frame was deleted.\n", "\n", "███| (done) 100%\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "Model Details\n", "=============\n", "H2OStackedEnsembleEstimator : Stacked Ensemble\n", "Model Key: StackedEnsemble_AllModels_3_AutoML_1_20250707_91158\n", "\n", "\n", "Model Summary for Stacked Ensemble: \n", "key value\n", "----------------------------------------- ----------------\n", "Stacking strategy cross_validation\n", "Number of base models (used / total) 11/26\n", "# GBM base models (used / total) 5/10\n", "# XGBoost base models (used / total) 6/10\n", "# DRF base models (used / total) 0/2\n", "# DeepLearning base models (used / total) 0/3\n", "# GLM base models (used / total) 0/1\n", "Metalearner algorithm GLM\n", "Metalearner fold assignment scheme Random\n", "Metalearner nfolds 5\n", "Metalearner fold_column\n", "Custom metalearner hyperparameters None\n", "\n", "ModelMetricsRegressionGLM: stackedensemble\n", "** Reported on train data. **\n", "\n", "MSE: 767473248.6093858\n", "RMSE: 27703.307539161924\n", "MAE: 18884.627811706105\n", "RMSLE: 0.1410694324080585\n", "Mean Residual Deviance: 767473248.6093858\n", "R^2: 0.9435628150737745\n", "Null degrees of freedom: 10056\n", "Residual degrees of freedom: 10045\n", "Null deviance: 136762522909302.33\n", "Residual deviance: 7718478461264.594\n", "AIC: 234318.8124810902\n", "\n", "ModelMetricsRegressionGLM: stackedensemble\n", "** Reported on cross-validation data. **\n", "\n", "MSE: 2013854660.997773\n", "RMSE: 44875.992033578186\n", "MAE: 29368.02054417076\n", "RMSLE: 0.22033689880319052\n", "Mean Residual Deviance: 2013854660.997773\n", "R^2: 0.8502870831954857\n", "Null degrees of freedom: 16999\n", "Residual degrees of freedom: 16988\n", "Null deviance: 228735799781891.16\n", "Residual deviance: 34235529236962.14\n", "AIC: 412466.2900218574\n", "\n", "Cross-Validation Metrics Summary: \n", " mean sd cv_1_valid cv_2_valid cv_3_valid cv_4_valid cv_5_valid\n", "---------------------- ----------- ----------- ------------ ------------ ------------ ------------ ------------\n", "aic 82510.9 1050.87 82634.8 82708.6 83850.7 82450.8 80909.6\n", "loglikelihood 0 0 0 0 0 0 0\n", "mae 29367.2 417.32 29427.2 29030.8 29377.6 30022 28978.7\n", "mean_residual_deviance 2.01404e+09 9.21073e+07 1.97099e+09 1.93002e+09 2.00108e+09 2.1708e+09 1.99732e+09\n", "mse 2.01404e+09 9.21073e+07 1.97099e+09 1.93002e+09 2.00108e+09 2.1708e+09 1.99732e+09\n", "null_deviance 4.57472e+13 1.49452e+12 4.47703e+13 4.54346e+13 4.60673e+13 4.81436e+13 4.432e+13\n", "r2 0.850252 0.00272747 0.849919 0.854655 0.849872 0.847121 0.849691\n", "residual_deviance 6.84711e+12 3.075e+11 6.71712e+12 6.58909e+12 6.91575e+12 7.35251e+12 6.66107e+12\n", "rmse 44868.9 1014.9 44395.8 43932 44733.5 46591.9 44691.4\n", "rmsle 0.220311 0.00378677 0.213761 0.223045 0.221418 0.222688 0.220643\n", "\n", "[tips]\n", "Use `model.explain()` to inspect the model.\n", "--\n", "Use `h2o.display.toggle_user_tips()` to switch on/off this section." ], "text/html": [ "
Model Details\n",
              "=============\n",
              "H2OStackedEnsembleEstimator : Stacked Ensemble\n",
              "Model Key: StackedEnsemble_AllModels_3_AutoML_1_20250707_91158\n",
              "
\n", "
\n", " \n", "
\n", " \n", " \n", " \n", "\n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
Model Summary for Stacked Ensemble:
keyvalue
Stacking strategycross_validation
Number of base models (used / total)11/26
# GBM base models (used / total)5/10
# XGBoost base models (used / total)6/10
# DRF base models (used / total)0/2
# DeepLearning base models (used / total)0/3
# GLM base models (used / total)0/1
Metalearner algorithmGLM
Metalearner fold assignment schemeRandom
Metalearner nfolds5
Metalearner fold_columnNone
Custom metalearner hyperparametersNone
\n", "
\n", "
\n", "
ModelMetricsRegressionGLM: stackedensemble\n",
              "** Reported on train data. **\n",
              "\n",
              "MSE: 767473248.6093858\n",
              "RMSE: 27703.307539161924\n",
              "MAE: 18884.627811706105\n",
              "RMSLE: 0.1410694324080585\n",
              "Mean Residual Deviance: 767473248.6093858\n",
              "R^2: 0.9435628150737745\n",
              "Null degrees of freedom: 10056\n",
              "Residual degrees of freedom: 10045\n",
              "Null deviance: 136762522909302.33\n",
              "Residual deviance: 7718478461264.594\n",
              "AIC: 234318.8124810902
\n", "
ModelMetricsRegressionGLM: stackedensemble\n",
              "** Reported on cross-validation data. **\n",
              "\n",
              "MSE: 2013854660.997773\n",
              "RMSE: 44875.992033578186\n",
              "MAE: 29368.02054417076\n",
              "RMSLE: 0.22033689880319052\n",
              "Mean Residual Deviance: 2013854660.997773\n",
              "R^2: 0.8502870831954857\n",
              "Null degrees of freedom: 16999\n",
              "Residual degrees of freedom: 16988\n",
              "Null deviance: 228735799781891.16\n",
              "Residual deviance: 34235529236962.14\n",
              "AIC: 412466.2900218574
\n", "
\n", " \n", "
\n", " \n", " \n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", " \n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
Cross-Validation Metrics Summary:
meansdcv_1_validcv_2_validcv_3_validcv_4_validcv_5_valid
aic82510.91050.867382634.8282708.5583850.69582450.8480909.586
loglikelihood0.00.00.00.00.00.00.0
mae29367.25417.320329427.2329030.7629377.59630022.028978.666
mean_residual_deviance2014042750.000000092107288.00000001970986110.00000001930019460.00000002001083900.00000002170802690.00000001997321600.0000000
mse2014042750.000000092107288.00000001970986110.00000001930019460.00000002001083900.00000002170802690.00000001997321600.0000000
null_deviance45747160000000.00000001494524490000.000000044770257000000.000000045434635000000.000000046067345000000.000000048143610000000.000000044319952000000.0000000
r20.85025150.00272750.84991860.85465480.84987190.84712140.8496908
residual_deviance6847105900000.0000000307499631000.00000006717120700000.00000006589086400000.00000006915745600000.00000007352509000000.00000006661067500000.0000000
rmse44868.9061014.904540044395.7943931.98444733.47746591.87544691.406
rmsle0.22031110.00378680.21376140.22304550.22141830.22268760.2206425
\n", "
\n", "
\n",
              "\n",
              "[tips]\n",
              "Use `model.explain()` to inspect the model.\n",
              "--\n",
              "Use `h2o.display.toggle_user_tips()` to switch on/off this section.
" ] }, "metadata": {}, "execution_count": 40 } ] }, { "cell_type": "code", "source": [ "lb = aml.leaderboard\n", "lb.head(rows = lb.nrows)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "VipY2dHBy9ig", "outputId": "92622f78-ad1b-4d06-9955-8a0046fe0b77" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "model_id rmse mse mae rmsle mean_residual_deviance\n", "------------------------------------------------------ -------- ----------- -------- ---------- ------------------------\n", "StackedEnsemble_AllModels_3_AutoML_1_20250707_91158 44876 2.01385e+09 29368 0.220337 2.01385e+09\n", "StackedEnsemble_AllModels_2_AutoML_1_20250707_91158 45093.1 2.03339e+09 29494.1 0.221225 2.03339e+09\n", "StackedEnsemble_AllModels_1_AutoML_1_20250707_91158 45093.8 2.03345e+09 29498.8 0.221259 2.03345e+09\n", "StackedEnsemble_BestOfFamily_2_AutoML_1_20250707_91158 45571.9 2.0768e+09 29913.2 0.224815 2.0768e+09\n", "StackedEnsemble_BestOfFamily_8_AutoML_2_20250707_94101 45789.1 2.09665e+09 30116.5 0.224983 2.09665e+09\n", "StackedEnsemble_BestOfFamily_4_AutoML_1_20250707_91158 45789.1 2.09665e+09 30116.5 0.224983 2.09665e+09\n", "StackedEnsemble_BestOfFamily_3_AutoML_1_20250707_91158 45934.1 2.10994e+09 30319.1 0.226491 2.10994e+09\n", "StackedEnsemble_BestOfFamily_1_AutoML_1_20250707_91158 46022 2.11802e+09 30492.5 0.228275 2.11802e+09\n", "GBM_9_AutoML_2_20250707_94101 46141.4 2.12903e+09 30517.2 0.227739 2.12903e+09\n", "GBM_4_AutoML_1_20250707_91158 46141.4 2.12903e+09 30517.2 0.227739 2.12903e+09\n", "GBM_3_AutoML_1_20250707_91158 46306.8 2.14432e+09 30633.4 0.227464 2.14432e+09\n", "GBM_8_AutoML_2_20250707_94101 46306.8 2.14432e+09 30633.4 0.227464 2.14432e+09\n", "GBM_7_AutoML_2_20250707_94101 46464 2.1589e+09 30839.8 0.229185 2.1589e+09\n", "GBM_2_AutoML_1_20250707_91158 46464 2.1589e+09 30839.8 0.229185 2.1589e+09\n", "GBM_1_AutoML_1_20250707_91158 46831 2.19314e+09 31360 0.233194 2.19314e+09\n", "GBM_6_AutoML_2_20250707_94101 46831 2.19314e+09 31360 0.233194 2.19314e+09\n", "GBM_5_AutoML_1_20250707_91158 47775.9 2.28254e+09 31747.6 0.235581 2.28254e+09\n", "GBM_10_AutoML_2_20250707_94101 47775.9 2.28254e+09 31747.6 0.235581 2.28254e+09\n", "XGBoost_grid_2_AutoML_2_20250707_94101_model_3 48661.2 2.36791e+09 32500.8 nan 2.36791e+09\n", "XGBoost_grid_1_AutoML_1_20250707_91158_model_3 48661.2 2.36791e+09 32500.8 nan 2.36791e+09\n", "GBM_grid_2_AutoML_2_20250707_94101_model_2 48845.4 2.38587e+09 33117.1 0.241984 2.38587e+09\n", "GBM_grid_1_AutoML_1_20250707_91158_model_2 48845.4 2.38587e+09 33117.1 0.241984 2.38587e+09\n", "GBM_grid_2_AutoML_2_20250707_94101_model_4 49145.5 2.41528e+09 33726.7 nan 2.41528e+09\n", "XGBoost_grid_1_AutoML_1_20250707_91158_model_1 49347.4 2.43517e+09 33408.7 nan 2.43517e+09\n", "XGBoost_grid_2_AutoML_2_20250707_94101_model_1 49347.4 2.43517e+09 33408.7 nan 2.43517e+09\n", "XGBoost_grid_2_AutoML_2_20250707_94101_model_7 49364.1 2.43681e+09 33474.8 0.247001 2.43681e+09\n", "GBM_grid_1_AutoML_1_20250707_91158_model_3 49375.4 2.43793e+09 33662.2 nan 2.43793e+09\n", "GBM_grid_2_AutoML_2_20250707_94101_model_3 49375.4 2.43793e+09 33662.2 nan 2.43793e+09\n", "GBM_grid_2_AutoML_2_20250707_94101_model_1 49443 2.44461e+09 34222.9 0.257013 2.44461e+09\n", "GBM_grid_1_AutoML_1_20250707_91158_model_1 49443 2.44461e+09 34222.9 0.257013 2.44461e+09\n", "XGBoost_3_AutoML_1_20250707_91158 49470.9 2.44737e+09 33486.9 0.249606 2.44737e+09\n", "XGBoost_6_AutoML_2_20250707_94101 49470.9 2.44737e+09 33486.9 0.249606 2.44737e+09\n", "GBM_grid_1_AutoML_1_20250707_91158_model_4 49645.4 2.46467e+09 34094.9 0.255603 2.46467e+09\n", "XGBoost_1_AutoML_1_20250707_91158 49711.4 2.47122e+09 33582.8 nan 2.47122e+09\n", "XGBoost_4_AutoML_2_20250707_94101 49711.4 2.47122e+09 33582.8 nan 2.47122e+09\n", "XGBoost_grid_2_AutoML_2_20250707_94101_model_2 49791.4 2.47918e+09 33386.9 0.249071 2.47918e+09\n", "XGBoost_grid_1_AutoML_1_20250707_91158_model_2 49791.4 2.47918e+09 33386.9 0.249071 2.47918e+09\n", "XGBoost_5_AutoML_2_20250707_94101 50075.6 2.50756e+09 33740 nan 2.50756e+09\n", "XGBoost_2_AutoML_1_20250707_91158 50075.6 2.50756e+09 33740 nan 2.50756e+09\n", "XGBoost_grid_1_AutoML_1_20250707_91158_model_4 50351.5 2.53527e+09 34061.7 nan 2.53527e+09\n", "XGBoost_grid_2_AutoML_2_20250707_94101_model_4 50351.5 2.53527e+09 34061.7 nan 2.53527e+09\n", "XGBoost_grid_1_AutoML_1_20250707_91158_model_7 50485.5 2.54878e+09 34303.9 0.249589 2.54878e+09\n", "XGBoost_grid_1_AutoML_1_20250707_91158_model_6 50588.4 2.55919e+09 34168 nan 2.55919e+09\n", "XGBoost_grid_2_AutoML_2_20250707_94101_model_6 50588.4 2.55919e+09 34168 nan 2.55919e+09\n", "XGBoost_grid_1_AutoML_1_20250707_91158_model_5 52010.1 2.70505e+09 36009.5 nan 2.70505e+09\n", "XGBoost_grid_2_AutoML_2_20250707_94101_model_5 52010.1 2.70505e+09 36009.5 nan 2.70505e+09\n", "XRT_2_AutoML_2_20250707_94101 52530.6 2.75947e+09 35845.1 0.25624 2.75947e+09\n", "XRT_1_AutoML_1_20250707_91158 52530.6 2.75947e+09 35845.1 0.25624 2.75947e+09\n", "DRF_2_AutoML_2_20250707_94101 52878.3 2.79611e+09 36044.2 0.258542 2.79611e+09\n", "DRF_1_AutoML_1_20250707_91158 52878.3 2.79611e+09 36044.2 0.258542 2.79611e+09\n", "GBM_grid_2_AutoML_2_20250707_94101_model_5 66208.9 4.38362e+09 49486 0.351629 4.38362e+09\n", "DeepLearning_2_AutoML_2_20250707_94101 67739.5 4.58864e+09 48003.7 0.347514 4.58864e+09\n", "DeepLearning_1_AutoML_1_20250707_91158 69136.7 4.77989e+09 48655.3 0.339401 4.77989e+09\n", "GBM_grid_1_AutoML_1_20250707_91158_model_5 82363.6 6.78376e+09 63158.9 0.435589 6.78376e+09\n", "DeepLearning_grid_3_AutoML_2_20250707_94101_model_1 89509.5 8.01194e+09 62642.8 nan 8.01194e+09\n", "DeepLearning_grid_1_AutoML_1_20250707_91158_model_1 90959.6 8.27365e+09 63825.9 nan 8.27365e+09\n", "DeepLearning_grid_1_AutoML_1_20250707_91158_model_2 96136 9.24213e+09 68575.4 nan 9.24213e+09\n", "GLM_2_AutoML_2_20250707_94101 115985 1.34525e+10 91648.3 0.592579 1.34525e+10\n", "GLM_1_AutoML_1_20250707_91158 115985 1.34525e+10 91648.3 0.592579 1.34525e+10\n", "XGBoost_grid_2_AutoML_2_20250707_94101_model_8 171184 2.9304e+10 146019 1.24439 2.9304e+10\n", "[60 rows x 6 columns]\n" ], "text/html": [ "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "
model_id rmse mse mae rmsle mean_residual_deviance
StackedEnsemble_AllModels_3_AutoML_1_20250707_91158 44876 2.01385e+09 29368 0.220337 2.01385e+09
StackedEnsemble_AllModels_2_AutoML_1_20250707_91158 45093.12.03339e+09 29494.1 0.221225 2.03339e+09
StackedEnsemble_AllModels_1_AutoML_1_20250707_91158 45093.82.03345e+09 29498.8 0.221259 2.03345e+09
StackedEnsemble_BestOfFamily_2_AutoML_1_20250707_91158 45571.92.0768e+09 29913.2 0.224815 2.0768e+09
StackedEnsemble_BestOfFamily_8_AutoML_2_20250707_94101 45789.12.09665e+09 30116.5 0.224983 2.09665e+09
StackedEnsemble_BestOfFamily_4_AutoML_1_20250707_91158 45789.12.09665e+09 30116.5 0.224983 2.09665e+09
StackedEnsemble_BestOfFamily_3_AutoML_1_20250707_91158 45934.12.10994e+09 30319.1 0.226491 2.10994e+09
StackedEnsemble_BestOfFamily_1_AutoML_1_20250707_91158 46022 2.11802e+09 30492.5 0.228275 2.11802e+09
GBM_9_AutoML_2_20250707_94101 46141.42.12903e+09 30517.2 0.227739 2.12903e+09
GBM_4_AutoML_1_20250707_91158 46141.42.12903e+09 30517.2 0.227739 2.12903e+09
GBM_3_AutoML_1_20250707_91158 46306.82.14432e+09 30633.4 0.227464 2.14432e+09
GBM_8_AutoML_2_20250707_94101 46306.82.14432e+09 30633.4 0.227464 2.14432e+09
GBM_7_AutoML_2_20250707_94101 46464 2.1589e+09 30839.8 0.229185 2.1589e+09
GBM_2_AutoML_1_20250707_91158 46464 2.1589e+09 30839.8 0.229185 2.1589e+09
GBM_1_AutoML_1_20250707_91158 46831 2.19314e+09 31360 0.233194 2.19314e+09
GBM_6_AutoML_2_20250707_94101 46831 2.19314e+09 31360 0.233194 2.19314e+09
GBM_5_AutoML_1_20250707_91158 47775.92.28254e+09 31747.6 0.235581 2.28254e+09
GBM_10_AutoML_2_20250707_94101 47775.92.28254e+09 31747.6 0.235581 2.28254e+09
XGBoost_grid_2_AutoML_2_20250707_94101_model_3 48661.22.36791e+09 32500.8nan 2.36791e+09
XGBoost_grid_1_AutoML_1_20250707_91158_model_3 48661.22.36791e+09 32500.8nan 2.36791e+09
GBM_grid_2_AutoML_2_20250707_94101_model_2 48845.42.38587e+09 33117.1 0.241984 2.38587e+09
GBM_grid_1_AutoML_1_20250707_91158_model_2 48845.42.38587e+09 33117.1 0.241984 2.38587e+09
GBM_grid_2_AutoML_2_20250707_94101_model_4 49145.52.41528e+09 33726.7nan 2.41528e+09
XGBoost_grid_1_AutoML_1_20250707_91158_model_1 49347.42.43517e+09 33408.7nan 2.43517e+09
XGBoost_grid_2_AutoML_2_20250707_94101_model_1 49347.42.43517e+09 33408.7nan 2.43517e+09
XGBoost_grid_2_AutoML_2_20250707_94101_model_7 49364.12.43681e+09 33474.8 0.247001 2.43681e+09
GBM_grid_1_AutoML_1_20250707_91158_model_3 49375.42.43793e+09 33662.2nan 2.43793e+09
GBM_grid_2_AutoML_2_20250707_94101_model_3 49375.42.43793e+09 33662.2nan 2.43793e+09
GBM_grid_2_AutoML_2_20250707_94101_model_1 49443 2.44461e+09 34222.9 0.257013 2.44461e+09
GBM_grid_1_AutoML_1_20250707_91158_model_1 49443 2.44461e+09 34222.9 0.257013 2.44461e+09
XGBoost_3_AutoML_1_20250707_91158 49470.92.44737e+09 33486.9 0.249606 2.44737e+09
XGBoost_6_AutoML_2_20250707_94101 49470.92.44737e+09 33486.9 0.249606 2.44737e+09
GBM_grid_1_AutoML_1_20250707_91158_model_4 49645.42.46467e+09 34094.9 0.255603 2.46467e+09
XGBoost_1_AutoML_1_20250707_91158 49711.42.47122e+09 33582.8nan 2.47122e+09
XGBoost_4_AutoML_2_20250707_94101 49711.42.47122e+09 33582.8nan 2.47122e+09
XGBoost_grid_2_AutoML_2_20250707_94101_model_2 49791.42.47918e+09 33386.9 0.249071 2.47918e+09
XGBoost_grid_1_AutoML_1_20250707_91158_model_2 49791.42.47918e+09 33386.9 0.249071 2.47918e+09
XGBoost_5_AutoML_2_20250707_94101 50075.62.50756e+09 33740 nan 2.50756e+09
XGBoost_2_AutoML_1_20250707_91158 50075.62.50756e+09 33740 nan 2.50756e+09
XGBoost_grid_1_AutoML_1_20250707_91158_model_4 50351.52.53527e+09 34061.7nan 2.53527e+09
XGBoost_grid_2_AutoML_2_20250707_94101_model_4 50351.52.53527e+09 34061.7nan 2.53527e+09
XGBoost_grid_1_AutoML_1_20250707_91158_model_7 50485.52.54878e+09 34303.9 0.249589 2.54878e+09
XGBoost_grid_1_AutoML_1_20250707_91158_model_6 50588.42.55919e+09 34168 nan 2.55919e+09
XGBoost_grid_2_AutoML_2_20250707_94101_model_6 50588.42.55919e+09 34168 nan 2.55919e+09
XGBoost_grid_1_AutoML_1_20250707_91158_model_5 52010.12.70505e+09 36009.5nan 2.70505e+09
XGBoost_grid_2_AutoML_2_20250707_94101_model_5 52010.12.70505e+09 36009.5nan 2.70505e+09
XRT_2_AutoML_2_20250707_94101 52530.62.75947e+09 35845.1 0.25624 2.75947e+09
XRT_1_AutoML_1_20250707_91158 52530.62.75947e+09 35845.1 0.25624 2.75947e+09
DRF_2_AutoML_2_20250707_94101 52878.32.79611e+09 36044.2 0.258542 2.79611e+09
DRF_1_AutoML_1_20250707_91158 52878.32.79611e+09 36044.2 0.258542 2.79611e+09
GBM_grid_2_AutoML_2_20250707_94101_model_5 66208.94.38362e+09 49486 0.351629 4.38362e+09
DeepLearning_2_AutoML_2_20250707_94101 67739.54.58864e+09 48003.7 0.347514 4.58864e+09
DeepLearning_1_AutoML_1_20250707_91158 69136.74.77989e+09 48655.3 0.339401 4.77989e+09
GBM_grid_1_AutoML_1_20250707_91158_model_5 82363.66.78376e+09 63158.9 0.435589 6.78376e+09
DeepLearning_grid_3_AutoML_2_20250707_94101_model_1 89509.58.01194e+09 62642.8nan 8.01194e+09
DeepLearning_grid_1_AutoML_1_20250707_91158_model_1 90959.68.27365e+09 63825.9nan 8.27365e+09
DeepLearning_grid_1_AutoML_1_20250707_91158_model_2 96136 9.24213e+09 68575.4nan 9.24213e+09
GLM_2_AutoML_2_20250707_94101 115985 1.34525e+10 91648.3 0.592579 1.34525e+10
GLM_1_AutoML_1_20250707_91158 115985 1.34525e+10 91648.3 0.592579 1.34525e+10
XGBoost_grid_2_AutoML_2_20250707_94101_model_8 171184 2.9304e+10 146019 1.24439 2.9304e+10 
[60 rows x 6 columns]
" ] }, "metadata": {}, "execution_count": 42 } ] }, { "cell_type": "code", "source": [ "# Get the top model of leaderboard\n", "se = aml.leader\n", "\n", "# Get the metalearner model of top model\n", "metalearner = h2o.get_model(se.metalearner()['name'])\n", "\n", "# Baselearner models :\n", "metalearner.varimp()" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "A3T7AO2kK7Xw", "outputId": "ab64692c-7e64-4ca3-9368-ba9c60f959c1" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.11/dist-packages/h2o/estimators/stackedensemble.py:965: H2ODeprecationWarning: The usage of stacked_ensemble.metalearner()['name'] will be deprecated. Metalearner now returns the metalearner object. If you need to get the 'name' please use stacked_ensemble.metalearner().model_id\n", " warnings.warn(\n" ] }, { "output_type": "execute_result", "data": { "text/plain": [ "[('GBM_3_AutoML_1_20250707_91158', 23234.78125, 1.0, 0.21439825598646953),\n", " ('GBM_4_AutoML_1_20250707_91158',\n", " 21459.20703125,\n", " 0.9235811949488442,\n", " 0.19801419745893173),\n", " ('XGBoost_grid_1_AutoML_1_20250707_91158_model_1',\n", " 16433.328125,\n", " 0.7072727712898094,\n", " 0.15163804867125227),\n", " ('XGBoost_1_AutoML_1_20250707_91158',\n", " 11521.1337890625,\n", " 0.49585720928887594,\n", " 0.10631092088985282),\n", " ('GBM_1_AutoML_1_20250707_91158',\n", " 10094.076171875,\n", " 0.43443818399947276,\n", " 0.09314278898341592),\n", " ('GBM_2_AutoML_1_20250707_91158',\n", " 10015.4267578125,\n", " 0.43105319779210316,\n", " 0.09241705384401762),\n", " ('GBM_grid_1_AutoML_1_20250707_91158_model_1',\n", " 4718.55029296875,\n", " 0.20308133062232941,\n", " 0.043540283108839034),\n", " ('XGBoost_grid_1_AutoML_1_20250707_91158_model_4',\n", " 3821.77587890625,\n", " 0.16448512416729769,\n", " 0.035265323757186516),\n", " ('XGBoost_2_AutoML_1_20250707_91158',\n", " 3534.77685546875,\n", " 0.1521329948164995,\n", " 0.0326170487666561),\n", " ('XGBoost_grid_1_AutoML_1_20250707_91158_model_3',\n", " 3403.84326171875,\n", " 0.14649775373799787,\n", " 0.031408862907362035),\n", " ('XGBoost_grid_1_AutoML_1_20250707_91158_model_5',\n", " 135.163330078125,\n", " 0.005817284381712223,\n", " 0.0012472156260164282),\n", " ('GBM_5_AutoML_1_20250707_91158', 0.0, 0.0, 0.0),\n", " ('GBM_grid_1_AutoML_1_20250707_91158_model_2', 0.0, 0.0, 0.0),\n", " ('GBM_grid_1_AutoML_1_20250707_91158_model_3', 0.0, 0.0, 0.0),\n", " ('XGBoost_3_AutoML_1_20250707_91158', 0.0, 0.0, 0.0),\n", " ('GBM_grid_1_AutoML_1_20250707_91158_model_4', 0.0, 0.0, 0.0),\n", " ('XGBoost_grid_1_AutoML_1_20250707_91158_model_2', 0.0, 0.0, 0.0),\n", " ('XGBoost_grid_1_AutoML_1_20250707_91158_model_7', 0.0, 0.0, 0.0),\n", " ('XGBoost_grid_1_AutoML_1_20250707_91158_model_6', 0.0, 0.0, 0.0),\n", " ('XRT_1_AutoML_1_20250707_91158', 0.0, 0.0, 0.0),\n", " ('DRF_1_AutoML_1_20250707_91158', 0.0, 0.0, 0.0),\n", " ('DeepLearning_1_AutoML_1_20250707_91158', 0.0, 0.0, 0.0),\n", " ('GBM_grid_1_AutoML_1_20250707_91158_model_5', 0.0, 0.0, 0.0),\n", " ('DeepLearning_grid_1_AutoML_1_20250707_91158_model_1', 0.0, 0.0, 0.0),\n", " ('DeepLearning_grid_1_AutoML_1_20250707_91158_model_2', 0.0, 0.0, 0.0),\n", " ('GLM_1_AutoML_1_20250707_91158', 0.0, 0.0, 0.0)]" ] }, "metadata": {}, "execution_count": 43 } ] }, { "cell_type": "code", "source": [ "# Get the best model from the AutoML run\n", "model = aml.leader\n", "\n", "# Evaluate the model on the test data\n", "performance = model.model_performance(test)\n", "\n", "# Print the performance metrics\n", "print(performance)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "suxyrUkvK7Kk", "outputId": "c483afd4-32bb-4a08-cbbe-d80b366196ef" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "ModelMetricsRegressionGLM: stackedensemble\n", "** Reported on test data. **\n", "\n", "MSE: 2082655548.9724505\n", "RMSE: 45636.121099108\n", "MAE: 29539.84376082709\n", "RMSLE: 0.2277528452878982\n", "Mean Residual Deviance: 2082655548.9724505\n", "R^2: 0.8371882128037335\n", "Null degrees of freedom: 2999\n", "Residual degrees of freedom: 2988\n", "Null deviance: 38381742925483.984\n", "Residual deviance: 6247966646917.352\n", "AIC: 72910.360067028\n" ] } ] }, { "cell_type": "code", "source": [ "model = h2o.get_model('StackedEnsemble_AllModels_3_AutoML_1_20250707_91158')\n", "model.model_performance(test)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 288 }, "id": "QYbQa9D4OeX3", "outputId": "660aa216-a501-4156-ecc9-b69c28a42cf0" }, "execution_count": null, "outputs": [ { "output_type": "execute_result", "data": { "text/plain": [ "ModelMetricsRegressionGLM: stackedensemble\n", "** Reported on test data. **\n", "\n", "MSE: 2082655548.9724505\n", "RMSE: 45636.121099108\n", "MAE: 29539.84376082709\n", "RMSLE: 0.2277528452878982\n", "Mean Residual Deviance: 2082655548.9724505\n", "R^2: 0.8371882128037335\n", "Null degrees of freedom: 2999\n", "Residual degrees of freedom: 2988\n", "Null deviance: 38381742925483.984\n", "Residual deviance: 6247966646917.352\n", "AIC: 72910.360067028" ], "text/html": [ "
ModelMetricsRegressionGLM: stackedensemble\n",
              "** Reported on test data. **\n",
              "\n",
              "MSE: 2082655548.9724505\n",
              "RMSE: 45636.121099108\n",
              "MAE: 29539.84376082709\n",
              "RMSLE: 0.2277528452878982\n",
              "Mean Residual Deviance: 2082655548.9724505\n",
              "R^2: 0.8371882128037335\n",
              "Null degrees of freedom: 2999\n",
              "Residual degrees of freedom: 2988\n",
              "Null deviance: 38381742925483.984\n",
              "Residual deviance: 6247966646917.352\n",
              "AIC: 72910.360067028
" ] }, "metadata": {}, "execution_count": 51 } ] }, { "cell_type": "code", "source": [ "base_models = model.base_models\n", "# Access one of the base models\n", "base_model = h2o.get_model(base_models[0])\n", "base_model.varimp_plot(num_of_features=9)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 739 }, "id": "fchMGEMRaRcu", "outputId": "7149e12f-38ed-47e1-e49a-ec0d6a5179de" }, "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "
" ], "image/png": "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\n" }, "metadata": {} }, { "output_type": "execute_result", "data": { "text/plain": [ "" ] }, "metadata": {}, "execution_count": 54 }, { "output_type": "display_data", "data": { "text/plain": [ "
" ] }, "metadata": {} } ] }, { "cell_type": "code", "source": [ "model_ids = [key for key in h2o.ls()['key'] if \"model\" in key.lower()]\n", "print(\"Model keys:\", model_ids)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "MaEE_GFrPGBF", "outputId": "51f51411-67de-4214-dc1e-2e6ae3859896" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Model keys: ['DeepLearning_grid_1_AutoML_1_20250707_91158_model_1', 'DeepLearning_grid_1_AutoML_1_20250707_91158_model_2', 'DeepLearning_grid_3_AutoML_2_20250707_94101_model_1', 'GBM_grid_1_AutoML_1_20250707_91158_model_1', 'GBM_grid_1_AutoML_1_20250707_91158_model_2', 'GBM_grid_1_AutoML_1_20250707_91158_model_3', 'GBM_grid_1_AutoML_1_20250707_91158_model_4', 'GBM_grid_1_AutoML_1_20250707_91158_model_5', 'GBM_grid_2_AutoML_2_20250707_94101_model_1', 'GBM_grid_2_AutoML_2_20250707_94101_model_2', 'GBM_grid_2_AutoML_2_20250707_94101_model_3', 'GBM_grid_2_AutoML_2_20250707_94101_model_4', 'GBM_grid_2_AutoML_2_20250707_94101_model_5', 'StackedEnsemble_AllModels_1_AutoML_1_20250707_91158', 'StackedEnsemble_AllModels_2_AutoML_1_20250707_91158', 'StackedEnsemble_AllModels_3_AutoML_1_20250707_91158', 'XGBoost_grid_1_AutoML_1_20250707_91158_model_1', 'XGBoost_grid_1_AutoML_1_20250707_91158_model_2', 'XGBoost_grid_1_AutoML_1_20250707_91158_model_3', 'XGBoost_grid_1_AutoML_1_20250707_91158_model_4', 'XGBoost_grid_1_AutoML_1_20250707_91158_model_5', 'XGBoost_grid_1_AutoML_1_20250707_91158_model_6', 'XGBoost_grid_1_AutoML_1_20250707_91158_model_7', 'XGBoost_grid_2_AutoML_2_20250707_94101_model_1', 'XGBoost_grid_2_AutoML_2_20250707_94101_model_2', 'XGBoost_grid_2_AutoML_2_20250707_94101_model_3', 'XGBoost_grid_2_AutoML_2_20250707_94101_model_4', 'XGBoost_grid_2_AutoML_2_20250707_94101_model_5', 'XGBoost_grid_2_AutoML_2_20250707_94101_model_6', 'XGBoost_grid_2_AutoML_2_20250707_94101_model_7', 'XGBoost_grid_2_AutoML_2_20250707_94101_model_8', 'levelone_training_StackedEnsemble_AllModels_1_AutoML_1_20250707_91158', 'levelone_training_StackedEnsemble_AllModels_2_AutoML_1_20250707_91158', 'levelone_training_StackedEnsemble_AllModels_3_AutoML_1_20250707_91158', 'metalearner_AUTO_StackedEnsemble_AllModels_1_AutoML_1_20250707_91158', 'metalearner_AUTO_StackedEnsemble_AllModels_2_AutoML_1_20250707_91158', 'metalearner_AUTO_StackedEnsemble_AllModels_3_AutoML_1_20250707_91158', 'modelmetrics_DRF_1_AutoML_1_20250707_91158@8809773276511986292_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_DRF_2_AutoML_2_20250707_94101@1433543472273281404_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_DeepLearning_1_AutoML_1_20250707_91158@3055007165537805416_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@-9121722699753449683', 'modelmetrics_DeepLearning_1_AutoML_1_20250707_91158@3055007165537805416_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_DeepLearning_2_AutoML_2_20250707_94101@1723428860597539000_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex.temporary.sample.58.82%@-9121722699753449683', 'modelmetrics_DeepLearning_2_AutoML_2_20250707_94101@1723428860597539000_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_DeepLearning_grid_1_AutoML_1_20250707_91158_model_1@931689185444217552_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@4288903748972694663', 'modelmetrics_DeepLearning_grid_1_AutoML_1_20250707_91158_model_1@931689185444217552_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_DeepLearning_grid_1_AutoML_1_20250707_91158_model_2@8385261208438086952_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@5921418155906320313', 'modelmetrics_DeepLearning_grid_1_AutoML_1_20250707_91158_model_2@8385261208438086952_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_DeepLearning_grid_3_AutoML_2_20250707_94101_model_1@7066114228727102044_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex.temporary.sample.58.82%@4288903748972694663', 'modelmetrics_DeepLearning_grid_3_AutoML_2_20250707_94101_model_1@7066114228727102044_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_10_AutoML_2_20250707_94101@-7823252752129038832_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_1_AutoML_1_20250707_91158@-1289769029863402260_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_2_AutoML_1_20250707_91158@-3904433776563313512_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_3_AutoML_1_20250707_91158@876239198614716560_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_4_AutoML_1_20250707_91158@4594879595482419456_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_5_AutoML_1_20250707_91158@-8847431910127972644_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_6_AutoML_2_20250707_94101@3184767699240190752_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_7_AutoML_2_20250707_94101@7663214038365827788_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_8_AutoML_2_20250707_94101@-3820576024255451452_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_9_AutoML_2_20250707_94101@3725757422776423988_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_grid_1_AutoML_1_20250707_91158_model_1@-5590630960911445216_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_grid_1_AutoML_1_20250707_91158_model_2@1580881568719762480_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_grid_1_AutoML_1_20250707_91158_model_3@-7536422631997967240_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_grid_1_AutoML_1_20250707_91158_model_4@-9165818860075557052_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_grid_1_AutoML_1_20250707_91158_model_5@5072946998659960104_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GBM_grid_2_AutoML_2_20250707_94101_model_1@-4830574072262078124_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_grid_2_AutoML_2_20250707_94101_model_2@8179405707021656676_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_grid_2_AutoML_2_20250707_94101_model_3@-7879292593258814804_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_grid_2_AutoML_2_20250707_94101_model_4@4476709469186623384_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GBM_grid_2_AutoML_2_20250707_94101_model_5@-698797995257808204_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_GLM_1_AutoML_1_20250707_91158@6921737403501183208_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_GLM_2_AutoML_2_20250707_94101@-831640194818126448_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_StackedEnsemble_AllModels_1_AutoML_1_20250707_91158@-3683039356614819396_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@2260175735545383275', 'modelmetrics_StackedEnsemble_AllModels_2_AutoML_1_20250707_91158@3606749139215043084_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@6425296141993263465', 'modelmetrics_StackedEnsemble_AllModels_3_AutoML_1_20250707_91158@-3587721952433344660_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@419931511102799360', 'modelmetrics_StackedEnsemble_AllModels_3_AutoML_1_20250707_91158@-3587721952433344660_on_Key_Frame__upload_99b751a6716a3daf5d5a2106e55e440b.hex@-5158700594373557672', 'modelmetrics_StackedEnsemble_AllModels_3_AutoML_1_20250707_91158@-3587721952433344660_on_Key_Frame__upload_9eed3d013ad823f1d5ab7bd469104502.hex@-5158700594373557672', 'modelmetrics_StackedEnsemble_BestOfFamily_1_AutoML_1_20250707_91158@2705715140868697116_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@-8872661092438102612', 'modelmetrics_StackedEnsemble_BestOfFamily_2_AutoML_1_20250707_91158@-8779655101252668740_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@-196771992635658664', 'modelmetrics_StackedEnsemble_BestOfFamily_3_AutoML_1_20250707_91158@-649844829921040288_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@-1421552436020262500', 'modelmetrics_StackedEnsemble_BestOfFamily_4_AutoML_1_20250707_91158@4297155048529344344_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex.temporary.sample.58.82%@-29231218504468640', 'modelmetrics_StackedEnsemble_BestOfFamily_8_AutoML_2_20250707_94101@-2320526121880729856_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex.temporary.sample.58.82%@-29231218504468640', 'modelmetrics_XGBoost_1_AutoML_1_20250707_91158@-5689558933265923240_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_2_AutoML_1_20250707_91158@6899590150996185980_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_3_AutoML_1_20250707_91158@-38798446915869796_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_4_AutoML_2_20250707_94101@-3949112535036441212_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_5_AutoML_2_20250707_94101@-4614740548366073432_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_6_AutoML_2_20250707_94101@-6860740851757410616_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_1_AutoML_1_20250707_91158_model_1@3578118541722759368_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_1_AutoML_1_20250707_91158_model_2@6434860691201655360_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_1_AutoML_1_20250707_91158_model_3@6747015288251156580_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_1_AutoML_1_20250707_91158_model_4@-1924558957737064816_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_1_AutoML_1_20250707_91158_model_5@-4846793152680732972_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_1_AutoML_1_20250707_91158_model_6@-3434113081075775852_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_1_AutoML_1_20250707_91158_model_7@-6719645223920875364_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_2_AutoML_2_20250707_94101_model_1@1553105980929784564_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_2_AutoML_2_20250707_94101_model_2@-3353140368847145620_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_2_AutoML_2_20250707_94101_model_3@5759467123673845136_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_2_AutoML_2_20250707_94101_model_4@5514389441462498492_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_2_AutoML_2_20250707_94101_model_5@-8613103863312572320_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_2_AutoML_2_20250707_94101_model_6@3899454868309813500_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_2_AutoML_2_20250707_94101_model_7@-488271450036587176_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XGBoost_grid_2_AutoML_2_20250707_94101_model_8@1964826731792511036_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_XRT_1_AutoML_1_20250707_91158@-7789801476782203664_on_AutoML_1_20250707_91158_training_Key_Frame__upload_ac0ee102296bc9e6aa4f16d9fd174e44.hex@5742864181011626912', 'modelmetrics_XRT_2_AutoML_2_20250707_94101@5904910436468322428_on_AutoML_2_20250707_94101_training_Key_Frame__upload_b5105239135e916a605bc013eee4851.hex@5742864181011626912', 'modelmetrics_metalearner_AUTO_StackedEnsemble_AllModels_1_AutoML_1_20250707_91158@-5294510782993423616_on_levelone_training_StackedEnsemble_AllModels_1_AutoML_1_20250707_91158@-7183972079879764516', 'modelmetrics_metalearner_AUTO_StackedEnsemble_AllModels_2_AutoML_1_20250707_91158@3827321718600575648_on_levelone_training_StackedEnsemble_AllModels_2_AutoML_1_20250707_91158@8550362939277114556', 'modelmetrics_metalearner_AUTO_StackedEnsemble_AllModels_3_AutoML_1_20250707_91158@1206798189852945196_on_levelone_training_StackedEnsemble_AllModels_3_AutoML_1_20250707_91158@6113654796526636082', 'modelmetrics_metalearner_AUTO_StackedEnsemble_BestOfFamily_1_AutoML_1_20250707_91158@5421700551273938488_on_levelone_training_StackedEnsemble_BestOfFamily_1_AutoML_1_20250707_91158@242762089531443664', 'modelmetrics_metalearner_AUTO_StackedEnsemble_BestOfFamily_2_AutoML_1_20250707_91158@-1670327779798875580_on_levelone_training_StackedEnsemble_BestOfFamily_2_AutoML_1_20250707_91158@-5074465575612763297', 'modelmetrics_metalearner_AUTO_StackedEnsemble_BestOfFamily_3_AutoML_1_20250707_91158@945330412307429220_on_levelone_training_StackedEnsemble_BestOfFamily_3_AutoML_1_20250707_91158@356023308171934172', 'modelmetrics_metalearner_AUTO_StackedEnsemble_BestOfFamily_4_AutoML_1_20250707_91158@-7910517244431495496_on_levelone_training_StackedEnsemble_BestOfFamily_4_AutoML_1_20250707_91158@7808240451217754928', 'modelmetrics_metalearner_AUTO_StackedEnsemble_BestOfFamily_8_AutoML_2_20250707_94101@-650364832519364528_on_levelone_training_StackedEnsemble_BestOfFamily_8_AutoML_2_20250707_94101@-4926499110542062384', 'transformation_8095_StackedEnsemble_AllModels_3_AutoML_1_20250707_91158_on_Key_Frame__upload_9eed3d013ad823f1d5ab7bd469104502.hex']\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.11/dist-packages/h2o/frame.py:1983: H2ODependencyWarning: Converting H2O frame to pandas dataframe using single-thread. For faster conversion using multi-thread, install polars and pyarrow and use it as pandas_df = h2o_df.as_data_frame(use_multi_thread=True)\n", "\n", " warnings.warn(\"Converting H2O frame to pandas dataframe using single-thread. For faster conversion using\"\n" ] } ] }, { "cell_type": "code", "source": [ "model_ids = h2o.ls()['key']\n", "print(model_ids)" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "GSVqNIGtZtxj", "outputId": "d08bdca1-a830-4fa1-c7e3-75d7159d44cc" }, "execution_count": null, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "0 AutoMLSession_Project_1@@median_house_value\n", "1 AutoML_1_20250707_91158_training_Key_Frame__up...\n", "2 AutoML_2_20250707_94101_training_Key_Frame__up...\n", "3 DRF_1_AutoML_1_20250707_91158\n", "4 DRF_2_AutoML_2_20250707_94101\n", " ... \n", "196 modelmetrics_metalearner_AUTO_StackedEnsemble_...\n", "197 modelmetrics_metalearner_AUTO_StackedEnsemble_...\n", "198 modelmetrics_metalearner_AUTO_StackedEnsemble_...\n", "199 py_4_sid_94bd\n", "200 transformation_8095_StackedEnsemble_AllModels_...\n", "Name: key, Length: 201, dtype: object\n" ] }, { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.11/dist-packages/h2o/frame.py:1983: H2ODependencyWarning: Converting H2O frame to pandas dataframe using single-thread. For faster conversion using multi-thread, install polars and pyarrow and use it as pandas_df = h2o_df.as_data_frame(use_multi_thread=True)\n", "\n", " warnings.warn(\"Converting H2O frame to pandas dataframe using single-thread. For faster conversion using\"\n" ] } ] }, { "cell_type": "code", "source": [ "model_path = h2o.save_model(model = model, path ='/content', force = True)" ], "metadata": { "id": "IBWh0BHkaRW-" }, "execution_count": null, "outputs": [] } ] }