mlessentials/Lab09/Exercise9.01/Exercise9_01.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.preprocessing import StandardScaler\n",
    "from sklearn.linear_model import LinearRegression\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": {
     "base_uri": "https://localhost:8080/",
     "height": 214
    },
    "colab_type": "code",
    "id": "YMQiyk9IoSTr",
    "outputId": "ecd53b58-0628-4d56-be59-c8effd01e6a5"
   },
   "outputs": [],
   "source": [
    "df.head()"
   ]
  },
  {
   "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": {
     "base_uri": "https://localhost:8080/",
     "height": 302
    },
    "colab_type": "code",
    "id": "sAKI1Aq8tkPF",
    "outputId": "64feb05f-deb8-4cc9-8850-af292d83a983"
   },
   "outputs": [],
   "source": [
    "df.describe()"
   ]
  },
  {
   "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": "14KemFv6t-PZ"
   },
   "outputs": [],
   "source": [
    "scaler = StandardScaler()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "P5gQ7yqBuIIw"
   },
   "outputs": [],
   "source": [
    "X_train = scaler.fit_transform(X_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "_Tq7gmTaud86"
   },
   "outputs": [],
   "source": [
    "X_test = scaler.transform(X_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "fDhW9UiFl-AE"
   },
   "outputs": [],
   "source": [
    "lr_model = LinearRegression()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 35
    },
    "colab_type": "code",
    "id": "A22jb3xUoZvX",
    "outputId": "66bc4c30-15d8-4598-f184-3a903b7274af"
   },
   "outputs": [],
   "source": [
    "lr_model.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "arae5xgLrlcO"
   },
   "outputs": [],
   "source": [
    "preds_train = lr_model.predict(X_train)\n",
    "preds_test = lr_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": "7715bc22-0359-45b2-e9af-8547279c44ca"
   },
   "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": "98b8f444-6382-4f47-d1ae-0a917fc1416a"
   },
   "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": "0de7ecbf-2bf8-4381-a474-7a11fdd33eae"
   },
   "outputs": [],
   "source": [
    "lr_model.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "qYJAfNV4s120"
   },
   "outputs": [],
   "source": [
    "coef_df = pd.DataFrame()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "_updjbMss5js"
   },
   "outputs": [],
   "source": [
    "coef_df['feature'] = df.columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "dN4nrheJtAAg"
   },
   "outputs": [],
   "source": [
    "coef_df['coefficient'] = lr_model.coef_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 194
    },
    "colab_type": "code",
    "id": "F7YMpWyFtE5B",
    "outputId": "eac4b816-30f1-4312-ca7d-6ac845940452"
   },
   "outputs": [],
   "source": [
    "coef_df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 702
    },
    "colab_type": "code",
    "id": "LxFxUajHs2Ge",
    "outputId": "c344d4df-8d73-4d31-8e5e-8b0e24a379d4"
   },
   "outputs": [],
   "source": [
    "alt.Chart(coef_df).mark_bar().encode(\n",
    "    x='coefficient',\n",
    "    y=\"feature\"\n",
    ")"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise9_01.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
}