mlessentials/Lab09/Exercise9.04/Exercise9_04.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "RCQKxdZOjw_2"
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.ensemble import RandomForestRegressor\n",
    "from sklearn.inspection import plot_partial_dependence\n",
    "import altair as alt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "tm5mPWzJkRLO"
   },
   "outputs": [],
   "source": [
    "file_url = '../Dataset/phpYYZ4Qc.csv'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "FEC78ZbAj3Vb"
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(file_url)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "IxiwVfiJq8KL"
   },
   "outputs": [],
   "source": [
    "y = df.pop('rej')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "ifR4fTCIrJBe"
   },
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(df, y, test_size=0.3, random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "LF-qSSFXCaHa"
   },
   "outputs": [],
   "source": [
    "rf_model = RandomForestRegressor(random_state=1, n_estimators=50, max_depth=6, min_samples_leaf=60)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 141
    },
    "colab_type": "code",
    "id": "CB2JS9B2CaJ8",
    "outputId": "95d64032-9269-4d15-e669-495b9d2b574f"
   },
   "outputs": [],
   "source": [
    "rf_model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 297
    },
    "colab_type": "code",
    "id": "k5LP6Wv5KB4G",
    "outputId": "27606568-7ae5-4500-f636-6f83900f17a4"
   },
   "outputs": [],
   "source": [
    "plot_partial_dependence(rf_model, X_test, features=[df.columns.get_loc('a1pop')]) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 297
    },
    "colab_type": "code",
    "id": "8-TqPbvQJ7Hu",
    "outputId": "e7b0dc39-082f-4935-934a-a8a9bb84c8b9"
   },
   "outputs": [],
   "source": [
    "plot_partial_dependence(rf_model, X_test, features=[df.columns.get_loc('temp')]) "
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise9_04.ipynb",
   "provenance": []
  },
  "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}