train_random_forest.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Train sklearn RF model on Boston dataset and predict"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup Environment"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install -q -U pip\n",
    "!pip install -q scikit-learn==0.24.1\n",
    "!pip install -q joblib"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import logging\n",
    "import joblib\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from sklearn.datasets import load_boston\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "logging.basicConfig(level=logging.INFO)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prepare data\n",
    "We load the Boston dataset from sklearn and split it into train and test sets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# we use the Boston housing dataset \n",
    "data = load_boston()\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(data.data, data.target, test_size=0.25, random_state=42)\n",
    "\n",
    "trainX = pd.DataFrame(X_train, columns=data.feature_names)\n",
    "trainX['target'] = y_train\n",
    "\n",
    "testX = pd.DataFrame(X_test, columns=data.feature_names)\n",
    "testX['target'] = y_test"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def generate_model(filename, n_estimators, min_samples_leaf):\n",
    "    logging.info('preparing train and test datasets')\n",
    "    features = 'CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX PTRATIO B LSTAT'\n",
    "    X_train = trainX[features.split()]\n",
    "    X_test = testX[features.split()]\n",
    "    y_train = trainX['target']\n",
    "    y_test = testX['target']\n",
    "\n",
    "    # TRAIN\n",
    "    logging.info('training model')\n",
    "    model = RandomForestRegressor(\n",
    "        n_estimators=n_estimators,\n",
    "        min_samples_leaf=min_samples_leaf,\n",
    "        n_jobs=-1\n",
    "    )\n",
    "\n",
    "    model.fit(X_train, y_train)\n",
    "\n",
    "    # ABS ERROR AND COUPLE PERF METRICS\n",
    "    logging.info('evaluating model')\n",
    "    abs_err = np.abs(model.predict(X_test) - y_test)\n",
    "\n",
    "    for q in [10, 50, 90]:\n",
    "        logging.info(f'AE-at-{q}th-percentile: {np.percentile(a=abs_err, q=q)}')\n",
    "\n",
    "    # SAVE MODEL\n",
    "    logging.info(f'saving model binary: {filename}.pkl')\n",
    "    joblib.dump(model, f'{filename}.pkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# train model\n",
    "generate_model('random_forest', 100, 3)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Predict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def model_predict(filename, data):\n",
    "    # LOAD MODEL\n",
    "    model = joblib.load(filename)\n",
    "    # PREDICT\n",
    "    predictions = model.predict([data])\n",
    "    logging.info(f'predictions: {predictions}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load test data and predict on first row\n",
    "features = 'CRIM ZN INDUS CHAS NOX RM AGE DIS RAD TAX PTRATIO B LSTAT'\n",
    "X_test = testX[features.split()]\n",
    "\n",
    "model_predict('random_forest.pkl', X_test.iloc[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_python3",
   "language": "python",
   "name": "conda_python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}