wehub-resource-sync
208 lines
7.0 KiB
Plaintext
208 lines
7.0 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Train Random Forest Estimator with H2O"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Checking whether there is an H2O instance running at http://localhost:54321..... not found.\n",
|
|
"Attempting to start a local H2O server...\n",
|
|
" Java Version: openjdk version \"1.8.0_181\"; OpenJDK Runtime Environment (build 1.8.0_181-8u181-b13-2~deb9u1-b13); OpenJDK 64-Bit Server VM (build 25.181-b13, mixed mode)\n",
|
|
" Starting server from /opt/conda/lib/python2.7/site-packages/h2o/backend/bin/h2o.jar\n",
|
|
" Ice root: /tmp/tmpz8qTmm\n",
|
|
" JVM stdout: /tmp/tmpz8qTmm/h2o_unknownUser_started_from_python.out\n",
|
|
" JVM stderr: /tmp/tmpz8qTmm/h2o_unknownUser_started_from_python.err\n",
|
|
" Server is running at http://127.0.0.1:54321\n",
|
|
"Connecting to H2O server at http://127.0.0.1:54321... successful.\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<div style=\"overflow:auto\"><table style=\"width:50%\"><tr><td>H2O cluster uptime:</td>\n",
|
|
"<td>01 secs</td></tr>\n",
|
|
"<tr><td>H2O cluster timezone:</td>\n",
|
|
"<td>Etc/UTC</td></tr>\n",
|
|
"<tr><td>H2O data parsing timezone:</td>\n",
|
|
"<td>UTC</td></tr>\n",
|
|
"<tr><td>H2O cluster version:</td>\n",
|
|
"<td>3.22.1.1</td></tr>\n",
|
|
"<tr><td>H2O cluster version age:</td>\n",
|
|
"<td>23 days </td></tr>\n",
|
|
"<tr><td>H2O cluster name:</td>\n",
|
|
"<td>H2O_from_python_unknownUser_ukj9f9</td></tr>\n",
|
|
"<tr><td>H2O cluster total nodes:</td>\n",
|
|
"<td>1</td></tr>\n",
|
|
"<tr><td>H2O cluster free memory:</td>\n",
|
|
"<td>3.042 Gb</td></tr>\n",
|
|
"<tr><td>H2O cluster total cores:</td>\n",
|
|
"<td>7</td></tr>\n",
|
|
"<tr><td>H2O cluster allowed cores:</td>\n",
|
|
"<td>7</td></tr>\n",
|
|
"<tr><td>H2O cluster status:</td>\n",
|
|
"<td>accepting new members, healthy</td></tr>\n",
|
|
"<tr><td>H2O connection url:</td>\n",
|
|
"<td>http://127.0.0.1:54321</td></tr>\n",
|
|
"<tr><td>H2O connection proxy:</td>\n",
|
|
"<td>None</td></tr>\n",
|
|
"<tr><td>H2O internal security:</td>\n",
|
|
"<td>False</td></tr>\n",
|
|
"<tr><td>H2O API Extensions:</td>\n",
|
|
"<td>XGBoost, Algos, AutoML, Core V3, Core V4</td></tr>\n",
|
|
"<tr><td>Python version:</td>\n",
|
|
"<td>2.7.15 final</td></tr></table></div>"
|
|
],
|
|
"text/plain": [
|
|
"-------------------------- ----------------------------------------\n",
|
|
"H2O cluster uptime: 01 secs\n",
|
|
"H2O cluster timezone: Etc/UTC\n",
|
|
"H2O data parsing timezone: UTC\n",
|
|
"H2O cluster version: 3.22.1.1\n",
|
|
"H2O cluster version age: 23 days\n",
|
|
"H2O cluster name: H2O_from_python_unknownUser_ukj9f9\n",
|
|
"H2O cluster total nodes: 1\n",
|
|
"H2O cluster free memory: 3.042 Gb\n",
|
|
"H2O cluster total cores: 7\n",
|
|
"H2O cluster allowed cores: 7\n",
|
|
"H2O cluster status: accepting new members, healthy\n",
|
|
"H2O connection url: http://127.0.0.1:54321\n",
|
|
"H2O connection proxy:\n",
|
|
"H2O internal security: False\n",
|
|
"H2O API Extensions: XGBoost, Algos, AutoML, Core V3, Core V4\n",
|
|
"Python version: 2.7.15 final\n",
|
|
"-------------------------- ----------------------------------------"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Parse progress: |█████████████████████████████████████████████████████████| 100%\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import h2o\n",
|
|
"from h2o.estimators.random_forest import H2ORandomForestEstimator\n",
|
|
"\n",
|
|
"import mlflow\n",
|
|
"import mlflow.h2o\n",
|
|
"\n",
|
|
"h2o.init()\n",
|
|
"\n",
|
|
"wine = h2o.import_file(path=\"wine-quality.csv\")\n",
|
|
"r = wine[\"quality\"].runif()\n",
|
|
"train = wine[r < 0.7]\n",
|
|
"test = wine[0.3 <= r]"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"def train_random_forest(ntrees):\n",
|
|
" with mlflow.start_run():\n",
|
|
" rf = H2ORandomForestEstimator(ntrees=ntrees)\n",
|
|
" train_cols = [n for n in wine.col_names if n != \"quality\"]\n",
|
|
" rf.train(train_cols, \"quality\", training_frame=train, validation_frame=test)\n",
|
|
"\n",
|
|
" mlflow.log_param(\"ntrees\", ntrees)\n",
|
|
"\n",
|
|
" mlflow.log_metric(\"rmse\", rf.rmse())\n",
|
|
" mlflow.log_metric(\"r2\", rf.r2())\n",
|
|
" mlflow.log_metric(\"mae\", rf.mae())\n",
|
|
"\n",
|
|
" mlflow.h2o.log_model(rf, name=\"model\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"drf Model Build progress: |███████████████████████████████████████████████| 100%\n",
|
|
"drf Model Build progress: |███████████████████████████████████████████████| 100%\n",
|
|
"drf Model Build progress: |███████████████████████████████████████████████| 100%\n",
|
|
"drf Model Build progress: |███████████████████████████████████████████████| 100%\n",
|
|
"drf Model Build progress: |███████████████████████████████████████████████| 100%\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"for ntrees in [10, 20, 50, 100, 200]:\n",
|
|
" train_random_forest(ntrees)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"import yaml"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"<function yaml.safe_dump>"
|
|
]
|
|
},
|
|
"execution_count": 5,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"yaml.safe_dump"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Python 2",
|
|
"language": "python",
|
|
"name": "python2"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 2
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython2",
|
|
"version": "2.7.15"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|