{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "8UMFqsCD0xyF"
   },
   "outputs": [],
   "source": [
    "# Importing necessary packages\n",
    "import pandas as pd\n",
    "import altair as alt\n",
    "\n",
    "import warnings\n",
    "warnings.filterwarnings(\"ignore\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "HSXgY0ze09cY"
   },
   "outputs": [],
   "source": [
    "file_url = '../bank-full.csv'\n",
    "bankData = pd.read_csv(file_url, sep=\";\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "5SqiAWuMhase"
   },
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 323
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 2512,
     "status": "ok",
     "timestamp": 1573002258890,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "0va4ykVzhj2P",
    "outputId": "bc1d55b2-c36b-4bc7-e08c-2619e5c22014"
   },
   "outputs": [],
   "source": [
    "# Finding the data types\n",
    "bankData.dtypes"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "y4LHG0PWh-yr"
   },
   "outputs": [],
   "source": [
    "# Converting all the categorical variables to dummy variables\n",
    "bankCat = pd.get_dummies(bankData[['job','marital','education','default','housing','loan','contact','month','poutcome']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1094,
     "status": "ok",
     "timestamp": 1573002260021,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "XvvWurd4iCe1",
    "outputId": "e53521c2-2076-477c-f273-83578c2a7793"
   },
   "outputs": [],
   "source": [
    "bankCat.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 544,
     "status": "ok",
     "timestamp": 1573002260300,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "deGzAPEDiUNk",
    "outputId": "70bb6f3f-3a7f-45a3-c0d1-93658a900106"
   },
   "outputs": [],
   "source": [
    "# Seperating the numerical variables\n",
    "bankNum = bankData[['age','balance','day','duration','campaign','pdays','previous']]\n",
    "bankNum.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 275
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 772,
     "status": "ok",
     "timestamp": 1573002262056,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "-y6f9S1-icOZ",
    "outputId": "62f057c2-2275-4653-ebae-8b1e0edf51c9"
   },
   "outputs": [],
   "source": [
    "# Preparing the X variables\n",
    "X = pd.concat([bankCat, bankNum], axis=1)\n",
    "print(X.shape)\n",
    "# Preparing the Y variable\n",
    "Y = bankData['y']\n",
    "print(Y.shape)\n",
    "X.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "OwD0UzFnijwu"
   },
   "outputs": [],
   "source": [
    "# Splitting the data into train and test sets\n",
    "X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.3, random_state=123)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 156
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1265,
     "status": "ok",
     "timestamp": 1573002268433,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "qazFufwEiqYF",
    "outputId": "0b434c4b-d3e8-4847-e384-99815105658e"
   },
   "outputs": [],
   "source": [
    "# Defining the LogisticRegression function\n",
    "bankModel = LogisticRegression()\n",
    "bankModel.fit(X_train, y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 854,
     "status": "ok",
     "timestamp": 1573002270297,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "ccQefqFNi0dy",
    "outputId": "58c94307-8654-4e27-c9cd-65b5c339ab10"
   },
   "outputs": [],
   "source": [
    "pred = bankModel.predict(X_test)\n",
    "print('Accuracy of Logisticr regression model prediction on test set: {:.2f}'.format(bankModel.score(X_test, y_test)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 51
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1051,
     "status": "ok",
     "timestamp": 1573002272393,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "yrIBeRfyi9-L",
    "outputId": "5521a69d-272c-4106-c557-1539065fee1a"
   },
   "outputs": [],
   "source": [
    "# Confusion Matrix for the model\n",
    "from sklearn.metrics import confusion_matrix\n",
    "confusionMatrix = confusion_matrix(y_test, pred)\n",
    "print(confusionMatrix)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 170
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1048,
     "status": "ok",
     "timestamp": 1573002275023,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "9vLNwnEcjLOi",
    "outputId": "955e1709-2c0b-47cc-e8d5-a62704050f43"
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test, pred))"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Exercise3.06_updated.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
}