{
 "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 numpy as np"
   ]
  },
  {
   "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": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 8374,
     "status": "ok",
     "timestamp": 1573003026166,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "ecnqNxm0TZay",
    "outputId": "515916d0-69e2-4b67-8da1-b11ebc7bb5d0"
   },
   "outputs": [],
   "source": [
    "# Normalising data\n",
    "from sklearn import preprocessing\n",
    "x = bankData[['balance']].values.astype(float)\n",
    "# Creating the scaling function\n",
    "minmaxScaler = preprocessing.MinMaxScaler()\n",
    "# Transforming the balance data by normalising it with minmaxScalre\n",
    "bankData['balanceTran'] = minmaxScaler.fit_transform(x)\n",
    "# Printing the head of the data\n",
    "bankData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "oISJ1v9sTg_S"
   },
   "outputs": [],
   "source": [
    "# Adding a small numerical constant to eliminate 0 values\n",
    "\n",
    "bankData['balanceTran'] = bankData['balanceTran'] + 0.00001"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 224
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1190,
     "status": "ok",
     "timestamp": 1573003030600,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "GsDGKLQzTy9O",
    "outputId": "d89e4bc9-09e9-4f54-d071-b2edc3784914"
   },
   "outputs": [],
   "source": [
    "# Let us transform values for loan data\n",
    "bankData['loanTran'] = 1\n",
    "# Giving a weight of 5 if there is no loan\n",
    "bankData.loc[bankData['loan'] == 'no', 'loanTran'] = 5\n",
    "bankData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 224
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1415,
     "status": "ok",
     "timestamp": 1573003040146,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "tPrwaWORT2wt",
    "outputId": "3687fb10-b25c-4ad4-d818-8f0ba4b6965c"
   },
   "outputs": [],
   "source": [
    "# Let us transform values for Housing data\n",
    "bankData['houseTran'] = 5\n",
    "# Giving a weight of 1 if the customer has a house\n",
    "bankData.loc[bankData['housing'] == 'no', 'houseTran'] = 1\n",
    "\n",
    "bankData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 224
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1023,
     "status": "ok",
     "timestamp": 1573003043755,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "C3a2zadTUGLq",
    "outputId": "ce60c876-3080-43c3-b3fa-8e44d17a123f"
   },
   "outputs": [],
   "source": [
    "# Let us now create the new variable which is a product of all these\n",
    "bankData['assetIndex'] = bankData['balanceTran'] * bankData['loanTran'] * bankData['houseTran']\n",
    "bankData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 34
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1199,
     "status": "ok",
     "timestamp": 1573003063439,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "I2eFF9GLUSn0",
    "outputId": "68c4ab47-ac24-4e42-9588-b6414d6826fd"
   },
   "outputs": [],
   "source": [
    "# Finding the quantile\n",
    "np.quantile(bankData['assetIndex'],[0.25,0.5,0.75])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 224
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1500,
     "status": "ok",
     "timestamp": 1573003081578,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "dklJXEaNUbf7",
    "outputId": "646550ac-4c22-494c-a792-fa8e5c7d9b97"
   },
   "outputs": [],
   "source": [
    "# Creating quantiles from the assetindex data\n",
    "bankData['assetClass'] = 'Quant1'\n",
    "\n",
    "bankData.loc[(bankData['assetIndex'] > 0.38) & (bankData['assetIndex'] < 0.57), 'assetClass'] = 'Quant2'\n",
    "\n",
    "bankData.loc[(bankData['assetIndex'] > 0.57) & (bankData['assetIndex'] < 1.9), 'assetClass'] = 'Quant3'\n",
    "\n",
    "bankData.loc[bankData['assetIndex'] > 1.9, 'assetClass'] = 'Quant4'\n",
    "\n",
    "bankData.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "JAt_inPjSo75"
   },
   "outputs": [],
   "source": [
    "# Calculating total of each asset class\n",
    "assetTot = bankData.groupby('assetClass')['y'].agg(assetTot='count').reset_index()\n",
    "# Calculating the category wise counts\n",
    "assetProp = bankData.groupby(['assetClass', 'y'])['y'].agg(assetCat='count').reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 297
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1143,
     "status": "ok",
     "timestamp": 1573003235697,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "tTGT5nBGSzgP",
    "outputId": "5a262e17-17ba-420e-ec7d-e9b470723f7f"
   },
   "outputs": [],
   "source": [
    "# Merging both the data frames\n",
    "assetComb = pd.merge(assetProp, assetTot, on=['assetClass'])\n",
    "assetComb['catProp'] = (assetComb.assetCat / assetComb.assetTot)*100\n",
    "assetComb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "iJG_qZRzlVc1"
   },
   "outputs": [],
   "source": [
    "# Categorical variables, removing loan and housing\n",
    "bankCat1 = pd.get_dummies(bankData[['job','marital','education','default','contact','month','poutcome']])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1007,
     "status": "ok",
     "timestamp": 1573003254182,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "N6j-jur1ljLP",
    "outputId": "567676f2-e3e5-48cf-8308-6a7276c09051"
   },
   "outputs": [],
   "source": [
    "bankNum1 = bankData[['age','day','duration','campaign','pdays','previous','assetIndex']]\n",
    "bankNum1.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "rhbHeJ3PlyiM"
   },
   "outputs": [],
   "source": [
    "# Normalise some of the numerical variables\n",
    "from sklearn import preprocessing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "zG-wd9qgl4xW"
   },
   "outputs": [],
   "source": [
    "# Creating the scaling function\n",
    "minmaxScaler = preprocessing.MinMaxScaler()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "3wDY6fPfmAki"
   },
   "outputs": [],
   "source": [
    "# Creating the transformation variables\n",
    "ageT1 = bankNum1[['age']].values.astype(float)\n",
    "dayT1 = bankNum1[['day']].values.astype(float)\n",
    "durT1 = bankNum1[['duration']].values.astype(float)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 323
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1121,
     "status": "ok",
     "timestamp": 1573003270320,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "5MT1CP24mDBx",
    "outputId": "628d9b83-87b0-476a-9331-6a09ed5eb071"
   },
   "outputs": [],
   "source": [
    "# Transforming the balance data by normalising it with minmaxScalre\n",
    "bankNum1['ageTran'] = minmaxScaler.fit_transform(ageT1)\n",
    "bankNum1['dayTran'] = minmaxScaler.fit_transform(dayT1)\n",
    "bankNum1['durTran'] = minmaxScaler.fit_transform(durT1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 204
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1345,
     "status": "ok",
     "timestamp": 1573003276269,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "L2LfnZDWmNJ3",
    "outputId": "6e72f0da-1dfc-4376-c9e5-c4a261e265f6"
   },
   "outputs": [],
   "source": [
    "# Let us create a new numerical variable by selecting the transformed variables\n",
    "bankNum2 = bankNum1[['ageTran','dayTran','durTran','campaign','pdays','previous','assetIndex']]\n",
    "\n",
    "# Printing the head of the data\n",
    "bankNum2.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 275
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1430,
     "status": "ok",
     "timestamp": 1573003278578,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "hD6suIpqmYTd",
    "outputId": "58fc69cb-ff8b-483e-8286-5b3f863a7f2f"
   },
   "outputs": [],
   "source": [
    "# Preparing the X variables\n",
    "X = pd.concat([bankCat1, bankNum2], 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": "4c7Jyxymmiaj"
   },
   "outputs": [],
   "source": [
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "# 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)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 156
    },
    "colab_type": "code",
    "executionInfo": {
     "elapsed": 1265,
     "status": "ok",
     "timestamp": 1573003281602,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "EVSGc5Lom2vj",
    "outputId": "28442c3a-4832-4df5-f84d-3d5ef637ed02"
   },
   "outputs": [],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "# 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": 838,
     "status": "ok",
     "timestamp": 1573003282951,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "GhFXSRnknr3p",
    "outputId": "e88952b2-01bc-497d-be39-8c2ad85f00bc"
   },
   "outputs": [],
   "source": [
    "pred = bankModel.predict(X_test)\n",
    "print('Accuracy of Logistic 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": 1127,
     "status": "ok",
     "timestamp": 1573003284105,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "DVBvXZJknuJ3",
    "outputId": "d865240b-fdbc-4526-bd3f-01b9e42792de"
   },
   "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": 1461,
     "status": "ok",
     "timestamp": 1573003287122,
     "user": {
      "displayName": "Anthony So",
      "photoUrl": "https://lh3.googleusercontent.com/a-/AAuE7mCYY-iGjUIqBSnlLoszfZTN7rU7FRNg05Rdt9Ii3A=s64",
      "userId": "11809607246124237079"
     },
     "user_tz": -660
    },
    "id": "BqcxgdLun0HY",
    "outputId": "2956690b-bee6-42db-826b-670f4c47d5ae"
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import classification_report\n",
    "print(classification_report(y_test, pred))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "Activity3.02_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
}