mlessentials/Lab07/Exercise7.08/Exercise7_08.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "RRCLZIC_rtl4"
   },
   "source": [
    "# Randomized Search with Cross Validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "avRjeBTHrtl6"
   },
   "outputs": [],
   "source": [
    "# import libraries\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 266
    },
    "colab_type": "code",
    "id": "r7AT180zrtl_",
    "outputId": "4c755e98-711e-4230-9a6b-5c106927808f"
   },
   "outputs": [],
   "source": [
    "# data doesn't have headers, so let's create headers\n",
    "_headers = ['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safety', 'car']\n",
    "# read in cars dataset\n",
    "df = pd.read_csv('../Dataset/car.data', names=_headers, index_col=None)\n",
    "df.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 214
    },
    "colab_type": "code",
    "id": "JtepJmqyrtmE",
    "outputId": "ef50f2d7-2b5e-47da-a71f-64d64da0ad7d"
   },
   "outputs": [],
   "source": [
    "# encode categorical variables\n",
    "_df = pd.get_dummies(df, columns=['buying', 'maint', 'doors', 'persons', 'lug_boot', 'safety'])\n",
    "_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "9Ku1uPghrtmJ"
   },
   "outputs": [],
   "source": [
    "# separate features and labels DataFrames\n",
    "features = _df.drop(['car'], axis=1).values\n",
    "labels = _df[['car']].values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "U8qIrVjtrtmO"
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.model_selection import RandomizedSearchCV"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ICgnbVyHrtmT"
   },
   "outputs": [],
   "source": [
    "clf = RandomForestClassifier()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "jdmj0suprtmb"
   },
   "outputs": [],
   "source": [
    "params = {'n_estimators':[500, 1000, 2000], 'max_depth': np.arange(1, 8)}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "07xYf1qlrtmh"
   },
   "outputs": [],
   "source": [
    "clf_cv = RandomizedSearchCV(clf, param_distributions=params, cv=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 461
    },
    "colab_type": "code",
    "id": "IeCFXs-Irtml",
    "outputId": "20609e49-11b3-48f3-f12f-8ae95a7adbfc"
   },
   "outputs": [],
   "source": [
    "clf_cv.fit(features, labels.ravel())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "eclW-K0krtmr",
    "outputId": "8aeb220b-c3ae-4055-bca0-ee77e100e7be"
   },
   "outputs": [],
   "source": [
    "print(\"Tuned Random Forest Parameters: {}\".format(clf_cv.best_params_))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "LglPICW4rtmx",
    "outputId": "944898c0-ccac-4997-e9dc-b70978a9d4be"
   },
   "outputs": [],
   "source": [
    "print(\"Best score is {}\".format(clf_cv.best_score_))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 159
    },
    "colab_type": "code",
    "id": "7Vm-gC0Qrtm0",
    "outputId": "f7d7d68b-1773-472a-e9cc-0e22f3398260"
   },
   "outputs": [],
   "source": [
    "model = clf_cv.best_estimator_\n",
    "model"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "name": "Exercise7.08.ipynb",
   "provenance": []
  },
  "file_extension": ".py",
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "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": "3.8.6"
  },
  "mimetype": "text/x-python",
  "name": "python",
  "npconvert_exporter": "python",
  "pygments_lexer": "ipython3",
  "version": 3
 },
 "nbformat": 4,
 "nbformat_minor": 1
}