mlessentials/Lab09/Exercise9.02/Exercise9_02.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.metrics import mean_squared_error\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": "19bc9dc1-8be5-4e86-e046-b3f0db93036e"
   },
   "outputs": [],
   "source": [
    "rf_model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "8E5jQG-fCaMM"
   },
   "outputs": [],
   "source": [
    "preds_train = rf_model.predict(X_train)\n",
    "preds_test = rf_model.predict(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "0L0vYPIOri1M",
    "outputId": "7a89036f-2928-4de0-fccb-0af63f2e38e9"
   },
   "outputs": [],
   "source": [
    "train_mse = mean_squared_error(y_train, preds_train)\n",
    "train_mse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "4qIcCT_7rwrQ",
    "outputId": "cf6116e0-9bbf-482f-fa9a-201968438cb3"
   },
   "outputs": [],
   "source": [
    "test_mse = mean_squared_error(y_test, preds_test)\n",
    "test_mse"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 159
    },
    "colab_type": "code",
    "id": "lUuLmYo8r0JK",
    "outputId": "a54d81d3-1d5b-4491-9174-0640a1f80c41"
   },
   "outputs": [],
   "source": [
    "rf_model.feature_importances_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "qYJAfNV4s120"
   },
   "outputs": [],
   "source": [
    "varimp_df = pd.DataFrame()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "_updjbMss5js"
   },
   "outputs": [],
   "source": [
    "varimp_df['feature'] = df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "dN4nrheJtAAg"
   },
   "outputs": [],
   "source": [
    "varimp_df['importance'] = rf_model.feature_importances_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 194
    },
    "colab_type": "code",
    "id": "F7YMpWyFtE5B",
    "outputId": "1224b31e-30c1-4924-9ece-173490108b3f"
   },
   "outputs": [],
   "source": [
    "varimp_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 702
    },
    "colab_type": "code",
    "id": "LxFxUajHs2Ge",
    "outputId": "26b1ddd5-cada-460d-e10f-095e90db7d5c"
   },
   "outputs": [],
   "source": [
    "alt.Chart(varimp_df).mark_bar().encode(\n",
    "    x='importance',\n",
    "    y=\"feature\"\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise9_02.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
}