mlessentials/Lab09/Exercise9.03/Exercise9_03.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 mlxtend.evaluate import feature_importance_permutation\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": "01208cec-d18f-44b7-cd4f-daf356615b09"
   },
   "outputs": [],
   "source": [
    "rf_model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 159
    },
    "colab_type": "code",
    "id": "K3QQ305yvYWM",
    "outputId": "8e96b8dd-8d53-45ac-8d88-5394d777003d"
   },
   "outputs": [],
   "source": [
    "imp_vals, _ = feature_importance_permutation(predict_method=rf_model.predict, X=X_test.values, y=y_test.values, metric='r2', num_rounds=1, seed=2)\n",
    "imp_vals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "dNumrsgTwcTH"
   },
   "outputs": [],
   "source": [
    "varimp_df = pd.DataFrame({'feature': df.columns, 'importance': imp_vals})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 702
    },
    "colab_type": "code",
    "id": "0INCKVEIwkFB",
    "outputId": "efad98ad-4a5b-4e15-d5ae-2d3e4bd4ed08"
   },
   "outputs": [],
   "source": [
    "alt.Chart(varimp_df).mark_bar().encode(\n",
    "    x='importance',\n",
    "    y=\"feature\"\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise9_03.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
}