model_training/telco_model_training.ipynb

{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "id": "recent-format",
      "metadata": {
        "id": "recent-format"
      },
      "outputs": [],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "import xgboost\n",
        "from sklearn import model_selection\n",
        "from sklearn.metrics import accuracy_score, ConfusionMatrixDisplay, f1_score, precision_score\n",
        "from sklearn.preprocessing import LabelEncoder, MinMaxScaler"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "VqfmpVYlcZ4s",
      "metadata": {
        "id": "VqfmpVYlcZ4s"
      },
      "source": [
        "Reading from our CSV file (we have added an 'Error' header for the last column to make processing easier):"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "id": "A4W3EvjPcUIj",
      "metadata": {
        "id": "A4W3EvjPcUIj"
      },
      "outputs": [],
      "source": [
        "df = pd.read_csv('finantier_data_technical_test_dataset.csv')\n",
        "\n",
        "# Error column handling\n",
        "df['Error'].replace(np.nan, 'No', inplace = True)\n",
        "df['Error'].replace('error_error', np.nan, inplace = True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "id": "CGyWI7oPcXV9",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 322
        },
        "id": "CGyWI7oPcXV9",
        "outputId": "b0411d31-b56d-486f-c813-48c6ee90e2ec"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>customerID</th>\n",
              "      <th>gender</th>\n",
              "      <th>SeniorCitizen</th>\n",
              "      <th>Partner</th>\n",
              "      <th>Dependents</th>\n",
              "      <th>tenure</th>\n",
              "      <th>PhoneService</th>\n",
              "      <th>MultipleLines</th>\n",
              "      <th>InternetService</th>\n",
              "      <th>OnlineSecurity</th>\n",
              "      <th>...</th>\n",
              "      <th>TechSupport</th>\n",
              "      <th>StreamingTV</th>\n",
              "      <th>StreamingMovies</th>\n",
              "      <th>Contract</th>\n",
              "      <th>PaperlessBilling</th>\n",
              "      <th>PaymentMethod</th>\n",
              "      <th>MonthlyCharges</th>\n",
              "      <th>TotalCharges</th>\n",
              "      <th>Default</th>\n",
              "      <th>Error</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>4808-GHDJN</td>\n",
              "      <td>Female</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>...</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>7590-VHVEG</td>\n",
              "      <td>Female</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>1.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No phone service</td>\n",
              "      <td>DSL</td>\n",
              "      <td>No</td>\n",
              "      <td>...</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>Month-to-month</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Electronic check</td>\n",
              "      <td>29.85</td>\n",
              "      <td>29.85</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>5575-GNVDE</td>\n",
              "      <td>Male</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>34.0</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>DSL</td>\n",
              "      <td>Yes</td>\n",
              "      <td>...</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>One year</td>\n",
              "      <td>No</td>\n",
              "      <td>Mailed check</td>\n",
              "      <td>56.95</td>\n",
              "      <td>1889.5</td>\n",
              "      <td>No</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3668-QPYBK</td>\n",
              "      <td>Male</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>2.0</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>DSL</td>\n",
              "      <td>Yes</td>\n",
              "      <td>...</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>Month-to-month</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Mailed check</td>\n",
              "      <td>53.85</td>\n",
              "      <td>108.15</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>7795-CFOCW</td>\n",
              "      <td>Male</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>45.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No phone service</td>\n",
              "      <td>DSL</td>\n",
              "      <td>Yes</td>\n",
              "      <td>...</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>One year</td>\n",
              "      <td>No</td>\n",
              "      <td>Bank transfer (automatic)</td>\n",
              "      <td>42.30</td>\n",
              "      <td>1840.75</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 22 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "   customerID  gender  SeniorCitizen Partner Dependents  tenure PhoneService  \\\n",
              "0  4808-GHDJN  Female            NaN     NaN        NaN     NaN          NaN   \n",
              "1  7590-VHVEG  Female            0.0     Yes         No     1.0           No   \n",
              "2  5575-GNVDE    Male            0.0      No         No    34.0          Yes   \n",
              "3  3668-QPYBK    Male            0.0      No         No     2.0          Yes   \n",
              "4  7795-CFOCW    Male            0.0      No         No    45.0           No   \n",
              "\n",
              "      MultipleLines InternetService OnlineSecurity  ... TechSupport  \\\n",
              "0               NaN             NaN            NaN  ...         NaN   \n",
              "1  No phone service             DSL             No  ...          No   \n",
              "2                No             DSL            Yes  ...          No   \n",
              "3                No             DSL            Yes  ...          No   \n",
              "4  No phone service             DSL            Yes  ...         Yes   \n",
              "\n",
              "  StreamingTV StreamingMovies        Contract PaperlessBilling  \\\n",
              "0         NaN             NaN             NaN              NaN   \n",
              "1          No              No  Month-to-month              Yes   \n",
              "2          No              No        One year               No   \n",
              "3          No              No  Month-to-month              Yes   \n",
              "4          No              No        One year               No   \n",
              "\n",
              "               PaymentMethod MonthlyCharges TotalCharges  Default Error  \n",
              "0                        NaN            NaN          NaN      NaN   NaN  \n",
              "1           Electronic check          29.85        29.85       No    No  \n",
              "2               Mailed check          56.95       1889.5       No   NaN  \n",
              "3               Mailed check          53.85       108.15      Yes    No  \n",
              "4  Bank transfer (automatic)          42.30      1840.75       No    No  \n",
              "\n",
              "[5 rows x 22 columns]"
            ]
          },
          "execution_count": 3,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "WZBg5X9ochxu",
      "metadata": {
        "id": "WZBg5X9ochxu"
      },
      "source": [
        "Now we check the data types contained in the columns of our dataset:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "id": "qjN1FLL4cm12",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qjN1FLL4cm12",
        "outputId": "8fb5a7f2-6226-41b8-c5e4-461b30adb138"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "customerID           object\n",
              "gender               object\n",
              "SeniorCitizen       float64\n",
              "Partner              object\n",
              "Dependents           object\n",
              "tenure              float64\n",
              "PhoneService         object\n",
              "MultipleLines        object\n",
              "InternetService      object\n",
              "OnlineSecurity       object\n",
              "OnlineBackup         object\n",
              "DeviceProtection     object\n",
              "TechSupport          object\n",
              "StreamingTV          object\n",
              "StreamingMovies      object\n",
              "Contract             object\n",
              "PaperlessBilling     object\n",
              "PaymentMethod        object\n",
              "MonthlyCharges      float64\n",
              "TotalCharges         object\n",
              "Default              object\n",
              "Error                object\n",
              "dtype: object"
            ]
          },
          "execution_count": 4,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df.dtypes"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "pVCm2VJPcteB",
      "metadata": {
        "id": "pVCm2VJPcteB"
      },
      "source": [
        "Noticing that total charges is of type object (likely string), we need to convert it to float type (or any relevant numeric type) and then check for null values (if not TotalCharges would have been read as float in the first place):"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "id": "of6M5_YUcsFE",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "of6M5_YUcsFE",
        "outputId": "edaa0d52-0478-49d4-dea0-f6bea1c50b0d"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "customerID           4\n",
              "gender               4\n",
              "SeniorCitizen        5\n",
              "Partner              5\n",
              "Dependents           5\n",
              "tenure               5\n",
              "PhoneService         5\n",
              "MultipleLines        5\n",
              "InternetService      5\n",
              "OnlineSecurity       5\n",
              "OnlineBackup         5\n",
              "DeviceProtection     5\n",
              "TechSupport          5\n",
              "StreamingTV          5\n",
              "StreamingMovies      5\n",
              "Contract             5\n",
              "PaperlessBilling     5\n",
              "PaymentMethod        5\n",
              "MonthlyCharges       5\n",
              "TotalCharges        16\n",
              "Default              5\n",
              "Error                4\n",
              "dtype: int64"
            ]
          },
          "execution_count": 5,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df['TotalCharges'] = pd.to_numeric(df['TotalCharges'], errors = 'coerce')\n",
        "\n",
        "df.isnull().sum()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "_VxEFYqndwSZ",
      "metadata": {
        "id": "_VxEFYqndwSZ"
      },
      "source": [
        "We see multiple null values in each row, which we can easily remove using dropna function. We also need to remove the customerID and error columns as they are not relevant to our processing:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "id": "mojlmqJieA8q",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 357
        },
        "id": "mojlmqJieA8q",
        "outputId": "5cfd2250-bf02-4f9d-e1f8-254d8c0d026e"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>gender</th>\n",
              "      <th>SeniorCitizen</th>\n",
              "      <th>Partner</th>\n",
              "      <th>Dependents</th>\n",
              "      <th>tenure</th>\n",
              "      <th>PhoneService</th>\n",
              "      <th>MultipleLines</th>\n",
              "      <th>InternetService</th>\n",
              "      <th>OnlineSecurity</th>\n",
              "      <th>OnlineBackup</th>\n",
              "      <th>DeviceProtection</th>\n",
              "      <th>TechSupport</th>\n",
              "      <th>StreamingTV</th>\n",
              "      <th>StreamingMovies</th>\n",
              "      <th>Contract</th>\n",
              "      <th>PaperlessBilling</th>\n",
              "      <th>PaymentMethod</th>\n",
              "      <th>MonthlyCharges</th>\n",
              "      <th>TotalCharges</th>\n",
              "      <th>Default</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Female</td>\n",
              "      <td>0.0</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>1.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No phone service</td>\n",
              "      <td>DSL</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>Month-to-month</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Electronic check</td>\n",
              "      <td>29.85</td>\n",
              "      <td>29.85</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Male</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>2.0</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>DSL</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>Month-to-month</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Mailed check</td>\n",
              "      <td>53.85</td>\n",
              "      <td>108.15</td>\n",
              "      <td>Yes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Male</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>45.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No phone service</td>\n",
              "      <td>DSL</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>One year</td>\n",
              "      <td>No</td>\n",
              "      <td>Bank transfer (automatic)</td>\n",
              "      <td>42.30</td>\n",
              "      <td>1840.75</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>Female</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>2.0</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Fiber optic</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>Month-to-month</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Electronic check</td>\n",
              "      <td>70.70</td>\n",
              "      <td>151.65</td>\n",
              "      <td>Yes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>Female</td>\n",
              "      <td>0.0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>8.0</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Fiber optic</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Month-to-month</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Electronic check</td>\n",
              "      <td>99.65</td>\n",
              "      <td>820.50</td>\n",
              "      <td>Yes</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "   gender  SeniorCitizen Partner Dependents  tenure PhoneService  \\\n",
              "1  Female            0.0     Yes         No     1.0           No   \n",
              "3    Male            0.0      No         No     2.0          Yes   \n",
              "4    Male            0.0      No         No    45.0           No   \n",
              "5  Female            0.0      No         No     2.0          Yes   \n",
              "6  Female            0.0      No         No     8.0          Yes   \n",
              "\n",
              "      MultipleLines InternetService OnlineSecurity OnlineBackup  \\\n",
              "1  No phone service             DSL             No          Yes   \n",
              "3                No             DSL            Yes          Yes   \n",
              "4  No phone service             DSL            Yes           No   \n",
              "5                No     Fiber optic             No           No   \n",
              "6               Yes     Fiber optic             No           No   \n",
              "\n",
              "  DeviceProtection TechSupport StreamingTV StreamingMovies        Contract  \\\n",
              "1               No          No          No              No  Month-to-month   \n",
              "3               No          No          No              No  Month-to-month   \n",
              "4              Yes         Yes          No              No        One year   \n",
              "5               No          No          No              No  Month-to-month   \n",
              "6              Yes          No         Yes             Yes  Month-to-month   \n",
              "\n",
              "  PaperlessBilling              PaymentMethod  MonthlyCharges  TotalCharges  \\\n",
              "1              Yes           Electronic check           29.85         29.85   \n",
              "3              Yes               Mailed check           53.85        108.15   \n",
              "4               No  Bank transfer (automatic)           42.30       1840.75   \n",
              "5              Yes           Electronic check           70.70        151.65   \n",
              "6              Yes           Electronic check           99.65        820.50   \n",
              "\n",
              "  Default  \n",
              "1      No  \n",
              "3     Yes  \n",
              "4      No  \n",
              "5     Yes  \n",
              "6     Yes  "
            ]
          },
          "execution_count": 6,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# Remove all null values\n",
        "df.dropna(inplace = True)\n",
        "\n",
        "# Remove error and customerID column\n",
        "df.drop(labels = ['customerID', 'Error'], axis = 1, inplace = True)\n",
        "\n",
        "df.isnull().sum()\n",
        "df.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "C0tPH5iyeV5s",
      "metadata": {
        "id": "C0tPH5iyeV5s"
      },
      "source": [
        "Now we have no more null values and our irrelevant columns have been removed! Thus the data cleaning has been completed. We now need to perform data encoding on the various columns. We can label encode binary columns and use `pd.dummies()` function to one hot encode all the other columns."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "id": "S6qFSr8Ae8jg",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 305
        },
        "id": "S6qFSr8Ae8jg",
        "outputId": "826e874c-ed2c-4658-c7a7-83d38850664a"
      },
      "outputs": [
        {
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>gender</th>\n",
              "      <th>SeniorCitizen</th>\n",
              "      <th>Partner</th>\n",
              "      <th>Dependents</th>\n",
              "      <th>tenure</th>\n",
              "      <th>PhoneService</th>\n",
              "      <th>PaperlessBilling</th>\n",
              "      <th>MonthlyCharges</th>\n",
              "      <th>TotalCharges</th>\n",
              "      <th>Default</th>\n",
              "      <th>...</th>\n",
              "      <th>StreamingMovies_No</th>\n",
              "      <th>StreamingMovies_No internet service</th>\n",
              "      <th>StreamingMovies_Yes</th>\n",
              "      <th>Contract_Month-to-month</th>\n",
              "      <th>Contract_One year</th>\n",
              "      <th>Contract_Two year</th>\n",
              "      <th>PaymentMethod_Bank transfer (automatic)</th>\n",
              "      <th>PaymentMethod_Credit card (automatic)</th>\n",
              "      <th>PaymentMethod_Electronic check</th>\n",
              "      <th>PaymentMethod_Mailed check</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>29.85</td>\n",
              "      <td>29.85</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>53.85</td>\n",
              "      <td>108.15</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>45.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>42.30</td>\n",
              "      <td>1840.75</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>70.70</td>\n",
              "      <td>151.65</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>8.0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>99.65</td>\n",
              "      <td>820.50</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 41 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "   gender  SeniorCitizen  Partner  Dependents  tenure  PhoneService  \\\n",
              "1       0              0        1           0     1.0             0   \n",
              "3       1              0        0           0     2.0             1   \n",
              "4       1              0        0           0    45.0             0   \n",
              "5       0              0        0           0     2.0             1   \n",
              "6       0              0        0           0     8.0             1   \n",
              "\n",
              "   PaperlessBilling  MonthlyCharges  TotalCharges  Default  ...  \\\n",
              "1                 1           29.85         29.85        0  ...   \n",
              "3                 1           53.85        108.15        1  ...   \n",
              "4                 0           42.30       1840.75        0  ...   \n",
              "5                 1           70.70        151.65        1  ...   \n",
              "6                 1           99.65        820.50        1  ...   \n",
              "\n",
              "   StreamingMovies_No  StreamingMovies_No internet service  \\\n",
              "1                   1                                    0   \n",
              "3                   1                                    0   \n",
              "4                   1                                    0   \n",
              "5                   1                                    0   \n",
              "6                   0                                    0   \n",
              "\n",
              "   StreamingMovies_Yes  Contract_Month-to-month  Contract_One year  \\\n",
              "1                    0                        1                  0   \n",
              "3                    0                        1                  0   \n",
              "4                    0                        0                  1   \n",
              "5                    0                        1                  0   \n",
              "6                    1                        1                  0   \n",
              "\n",
              "   Contract_Two year  PaymentMethod_Bank transfer (automatic)  \\\n",
              "1                  0                                        0   \n",
              "3                  0                                        0   \n",
              "4                  0                                        1   \n",
              "5                  0                                        0   \n",
              "6                  0                                        0   \n",
              "\n",
              "   PaymentMethod_Credit card (automatic)  PaymentMethod_Electronic check  \\\n",
              "1                                      0                               1   \n",
              "3                                      0                               0   \n",
              "4                                      0                               0   \n",
              "5                                      0                               1   \n",
              "6                                      0                               1   \n",
              "\n",
              "   PaymentMethod_Mailed check  \n",
              "1                           0  \n",
              "3                           1  \n",
              "4                           0  \n",
              "5                           0  \n",
              "6                           0  \n",
              "\n",
              "[5 rows x 41 columns]"
            ]
          },
          "execution_count": 7,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "# We let not having defaulted be a value of 1 while defaulting be a value of 0\n",
        "# df['Default'] = df['Default'].map({'Yes': 0, 'No': 1})\n",
        "\n",
        "# Perform label encoding on binary columns\n",
        "to_label_encode = ['gender',\n",
        "                   'Partner',\n",
        "                   'Dependents',\n",
        "                   'PhoneService',\n",
        "                   'Default',\n",
        "                   'PaperlessBilling',\n",
        "                   'SeniorCitizen'\n",
        "                   ]\n",
        "\n",
        "df[to_label_encode] = df[to_label_encode].apply(LabelEncoder().fit_transform)\n",
        "\n",
        "df.head()\n",
        "\n",
        "# Perform one-hot encoding on the rest of our data\n",
        "\n",
        "df_dummies = pd.get_dummies(df)\n",
        "df_dummies.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "nQNUBg6-j_GX",
      "metadata": {
        "id": "nQNUBg6-j_GX"
      },
      "source": [
        "We now perform min-max scaling on our numerical columns to scale them between 1 and 0:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "id": "A872ZmMvkJhT",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 305
        },
        "id": "A872ZmMvkJhT",
        "outputId": "af542bd3-1a8a-4d81-ec9f-33e42e47da5d"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "tenure              72.00\n",
            "MonthlyCharges     118.75\n",
            "TotalCharges      8684.80\n",
            "dtype: float64\n"
          ]
        },
        {
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>gender</th>\n",
              "      <th>SeniorCitizen</th>\n",
              "      <th>Partner</th>\n",
              "      <th>Dependents</th>\n",
              "      <th>tenure</th>\n",
              "      <th>PhoneService</th>\n",
              "      <th>PaperlessBilling</th>\n",
              "      <th>MonthlyCharges</th>\n",
              "      <th>TotalCharges</th>\n",
              "      <th>Default</th>\n",
              "      <th>...</th>\n",
              "      <th>StreamingMovies_No</th>\n",
              "      <th>StreamingMovies_No internet service</th>\n",
              "      <th>StreamingMovies_Yes</th>\n",
              "      <th>Contract_Month-to-month</th>\n",
              "      <th>Contract_One year</th>\n",
              "      <th>Contract_Two year</th>\n",
              "      <th>PaymentMethod_Bank transfer (automatic)</th>\n",
              "      <th>PaymentMethod_Credit card (automatic)</th>\n",
              "      <th>PaymentMethod_Electronic check</th>\n",
              "      <th>PaymentMethod_Mailed check</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0.000000</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.115423</td>\n",
              "      <td>0.001275</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.014085</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0.354229</td>\n",
              "      <td>0.010310</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.619718</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.239303</td>\n",
              "      <td>0.210241</td>\n",
              "      <td>0</td>\n",
              "      <td>...</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.014085</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0.521891</td>\n",
              "      <td>0.015330</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.098592</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0.809950</td>\n",
              "      <td>0.092511</td>\n",
              "      <td>1</td>\n",
              "      <td>...</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 41 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "   gender  SeniorCitizen  Partner  Dependents    tenure  PhoneService  \\\n",
              "1       0              0        1           0  0.000000             0   \n",
              "3       1              0        0           0  0.014085             1   \n",
              "4       1              0        0           0  0.619718             0   \n",
              "5       0              0        0           0  0.014085             1   \n",
              "6       0              0        0           0  0.098592             1   \n",
              "\n",
              "   PaperlessBilling  MonthlyCharges  TotalCharges  Default  ...  \\\n",
              "1                 1        0.115423      0.001275        0  ...   \n",
              "3                 1        0.354229      0.010310        1  ...   \n",
              "4                 0        0.239303      0.210241        0  ...   \n",
              "5                 1        0.521891      0.015330        1  ...   \n",
              "6                 1        0.809950      0.092511        1  ...   \n",
              "\n",
              "   StreamingMovies_No  StreamingMovies_No internet service  \\\n",
              "1                   1                                    0   \n",
              "3                   1                                    0   \n",
              "4                   1                                    0   \n",
              "5                   1                                    0   \n",
              "6                   0                                    0   \n",
              "\n",
              "   StreamingMovies_Yes  Contract_Month-to-month  Contract_One year  \\\n",
              "1                    0                        1                  0   \n",
              "3                    0                        1                  0   \n",
              "4                    0                        0                  1   \n",
              "5                    0                        1                  0   \n",
              "6                    1                        1                  0   \n",
              "\n",
              "   Contract_Two year  PaymentMethod_Bank transfer (automatic)  \\\n",
              "1                  0                                        0   \n",
              "3                  0                                        0   \n",
              "4                  0                                        1   \n",
              "5                  0                                        0   \n",
              "6                  0                                        0   \n",
              "\n",
              "   PaymentMethod_Credit card (automatic)  PaymentMethod_Electronic check  \\\n",
              "1                                      0                               1   \n",
              "3                                      0                               0   \n",
              "4                                      0                               0   \n",
              "5                                      0                               1   \n",
              "6                                      0                               1   \n",
              "\n",
              "   PaymentMethod_Mailed check  \n",
              "1                           0  \n",
              "3                           1  \n",
              "4                           0  \n",
              "5                           0  \n",
              "6                           0  \n",
              "\n",
              "[5 rows x 41 columns]"
            ]
          },
          "execution_count": 8,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df_scaled = df_dummies\n",
        "\n",
        "features_mms = ['tenure', 'MonthlyCharges', 'TotalCharges']\n",
        "print(df[features_mms].apply(max))\n",
        "df_scaled[features_mms] = MinMaxScaler().fit_transform(df_scaled[features_mms])\n",
        "df_scaled.head()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "affac5c1",
      "metadata": {},
      "source": [
        "Now, we check all the column headers in our data (this will be useful when using our model for an API endpoint)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "id": "f80b569d",
      "metadata": {},
      "outputs": [
        {
          "data": {
            "text/plain": [
              "Index(['gender', 'SeniorCitizen', 'Partner', 'Dependents', 'tenure',\n",
              "       'PhoneService', 'PaperlessBilling', 'MonthlyCharges', 'TotalCharges',\n",
              "       'Default', 'MultipleLines_No', 'MultipleLines_No phone service',\n",
              "       'MultipleLines_Yes', 'InternetService_DSL',\n",
              "       'InternetService_Fiber optic', 'InternetService_No',\n",
              "       'OnlineSecurity_No', 'OnlineSecurity_No internet service',\n",
              "       'OnlineSecurity_Yes', 'OnlineBackup_No',\n",
              "       'OnlineBackup_No internet service', 'OnlineBackup_Yes',\n",
              "       'DeviceProtection_No', 'DeviceProtection_No internet service',\n",
              "       'DeviceProtection_Yes', 'TechSupport_No',\n",
              "       'TechSupport_No internet service', 'TechSupport_Yes', 'StreamingTV_No',\n",
              "       'StreamingTV_No internet service', 'StreamingTV_Yes',\n",
              "       'StreamingMovies_No', 'StreamingMovies_No internet service',\n",
              "       'StreamingMovies_Yes', 'Contract_Month-to-month', 'Contract_One year',\n",
              "       'Contract_Two year', 'PaymentMethod_Bank transfer (automatic)',\n",
              "       'PaymentMethod_Credit card (automatic)',\n",
              "       'PaymentMethod_Electronic check', 'PaymentMethod_Mailed check'],\n",
              "      dtype='object')"
            ]
          },
          "execution_count": 9,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "df_scaled.columns"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "irAmHyL4nKZN",
      "metadata": {
        "id": "irAmHyL4nKZN"
      },
      "source": [
        "We now need to check the skew of the data, which we can find using the average of the default column:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "id": "xJTOGiT1nQw6",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xJTOGiT1nQw6",
        "outputId": "7903b39c-2d4d-4d6a-9d11-782c88139aed"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "0.2658984208279983"
            ]
          },
          "execution_count": 10,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "sum(df_scaled['Default'])/len(df_scaled['Default'])"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "kPWzu5fEmYec",
      "metadata": {
        "id": "kPWzu5fEmYec"
      },
      "source": [
        "We see that our data is largely skewed towards people who do not default on their payments. We thus need to stratify our training/testing data as such. With our feature engineering complete, we can now split our testing and training data:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "id": "JzSDYGJnmYMe",
      "metadata": {
        "id": "JzSDYGJnmYMe"
      },
      "outputs": [],
      "source": [
        "# Applying sklearn's splitter\n",
        "\n",
        "X = df_scaled.drop(labels = 'Default', axis = 1).values\n",
        "y = df_scaled['Default'].values\n",
        "\n",
        "X_train, X_test, y_train, y_test = model_selection.train_test_split(X, y, test_size = 0.25, random_state = 0, stratify = y)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "zeHcbwjnok7X",
      "metadata": {
        "id": "zeHcbwjnok7X"
      },
      "source": [
        "Now we are ready to train our preliminary model. We are using XGBoost to train our data here, which although is a ML model that can handle tabular data, performs better than most deep learning models such as tabnet etc."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "id": "esWR9F_doyoh",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "esWR9F_doyoh",
        "outputId": "41db22e9-ab2b-429e-da62-53f9b44897f4"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n",
              "              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,\n",
              "              eval_metric='logloss', gamma=0, gpu_id=-1, importance_type=None,\n",
              "              interaction_constraints='', learning_rate=0.300000012,\n",
              "              max_delta_step=0, max_depth=6, min_child_weight=1, missing=nan,\n",
              "              monotone_constraints='()', n_estimators=100, n_jobs=-1,\n",
              "              num_parallel_tree=1, predictor='auto', random_state=0,\n",
              "              reg_alpha=0, reg_lambda=1, scale_pos_weight=2.7596291012838803,\n",
              "              subsample=1, tree_method='exact', use_label_encoder=False,\n",
              "              validate_parameters=1, verbosity=None)"
            ]
          },
          "execution_count": 12,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "cls_weight = (y_train.shape[0] - np.sum(y_train)) / np.sum(y_train)\n",
        "\n",
        "pre_xgb_clf = xgboost.XGBClassifier(eval_metric = 'logloss', use_label_encoder = False, random_state = 0, scale_pos_weight = cls_weight, n_jobs = -1)\n",
        "\n",
        "pre_xgb_clf.fit(X_train,\n",
        "            y_train)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "ea77DEkvrYyn",
      "metadata": {
        "id": "ea77DEkvrYyn"
      },
      "source": [
        "Great! We have a trained model - now let us look at the confusion matrix of how it performs on the test data as well as calculate its accuracy and f1-scores. Here, 1 refers to a prediction of not defaulter while 0 refers to a prediction of defaulter."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "id": "sBk-yOVAqvXg",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 348
        },
        "id": "sBk-yOVAqvXg",
        "outputId": "b3bbdb69-2c22-4557-cf24-f0b33a27ce5d"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "The resultant f1-score for defaulting is: 0.6068965517241379\n",
            "The resultant f1-score for not defaulting is: 0.8404638144742103\n",
            "The resultant accuracy is: 0.773037542662116\n",
            "The resultant precision is: 0.5620437956204379\n"
          ]
        }
      ],
      "source": [
        "y_pred = pre_xgb_clf.predict(X_test)\n",
        "\n",
        "ConfusionMatrixDisplay.from_predictions(y_test, y_pred, labels = [1,0])\n",
        "plt.show()\n",
        "\n",
        "pre_f_score = f1_score(y_test, y_pred)\n",
        "print(f\"The resultant f1-score for defaulting is: {pre_f_score}\")\n",
        "pre_f_score_def = f1_score(y_test, y_pred, pos_label=0)\n",
        "print(f\"The resultant f1-score for not defaulting is: {pre_f_score_def}\")\n",
        "pre_accuracy = accuracy_score(y_test, y_pred)\n",
        "print(f\"The resultant accuracy is: {pre_accuracy}\")\n",
        "pre_precision = precision_score(y_test,y_pred)\n",
        "print(f\"The resultant precision is: {pre_precision}\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "zANgHGRBwyDn",
      "metadata": {
        "id": "zANgHGRBwyDn"
      },
      "source": [
        "A f-score of 60.9% for predicting if a user will default. However, predicting whether the user will NOT default has a much btter f1-score of 84.0%. Our overall accuracy stands at about 77.3 and our precision at 56.2%. We will now try to optimise our parameters using cross validation and grid search techniques."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "id": "gl2LMccor9ni",
      "metadata": {
        "id": "gl2LMccor9ni"
      },
      "outputs": [],
      "source": [
        "# round_1 = {\n",
        "#     'max_depth' : [3,4,5],\n",
        "#     'learning_rate' : [0.1, 0.5 , 1],\n",
        "#     'gamma' : [0, 0.5, 1.0],\n",
        "#     'reg_lambda' : [10, 20, 50],\n",
        "# }\n",
        "\n",
        "# optimal_params = model_selection.GridSearchCV(\n",
        "#     estimator = xgboost.XGBClassifier(use_label_encoder = False,\n",
        "#                                       random_state = 0,\n",
        "#                                       scale_pos_weight = cls_weight,\n",
        "#                                       n_jobs = -1,\n",
        "#                                       eval_metric = 'logloss'),\n",
        "#     param_grid = round_1,\n",
        "#     scoring = 'roc_auc',\n",
        "#     verbose = 0,\n",
        "#     n_jobs = 10,\n",
        "#     cv = 3\n",
        "# )\n",
        "\n",
        "# optimal_params.fit(X_train, y_train)\n",
        "\n",
        "# print(optimal_params.best_params_)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "BqX2B_gQ53a5",
      "metadata": {
        "id": "BqX2B_gQ53a5"
      },
      "source": [
        "The optimal parameters given from the first run are:\n",
        "`{'gamma': 0.5, 'learning_rate': 0.1, 'max_depth': 3, 'reg_lambda': 50}`\n",
        "We now fine tune the parameters that returned on either extreme of our round 1 parameter options."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "id": "9SL2BMPj2Vxt",
      "metadata": {
        "id": "9SL2BMPj2Vxt"
      },
      "outputs": [],
      "source": [
        "# round_2 = {\n",
        "#     'max_depth' : [3],\n",
        "#     'learning_rate': [0.01, 0.05, 0.1],\n",
        "#     'gamma': [0.5],\n",
        "#     'reg_lambda': [50, 100, 200]\n",
        "# }\n",
        "\n",
        "# optimal_params = model_selection.GridSearchCV(\n",
        "#     estimator = xgboost.XGBClassifier(use_label_encoder = False,\n",
        "#                                       random_state = 0,\n",
        "#                                       scale_pos_weight = cls_weight,\n",
        "#                                       n_jobs = -1,\n",
        "#                                       eval_metric = 'logloss'),\n",
        "#     param_grid = round_1,\n",
        "#     scoring = 'roc_auc',\n",
        "#     verbose = 0,\n",
        "#     n_jobs = 10,\n",
        "#     cv = 3\n",
        "# )\n",
        "\n",
        "# optimal_params.fit(X_train, y_train)\n",
        "\n",
        "# print(optimal_params.best_params_)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "iNlN6bt8C487",
      "metadata": {
        "id": "iNlN6bt8C487"
      },
      "source": [
        "Our output from the second run gives the final optimised hyperparameters for our model:\n",
        "`{max_depth : 3, learning_rate : 0.1, gamma: 0.5, reg_lambda : 50}`"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "id": "W_FxbAEV4lFa",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "W_FxbAEV4lFa",
        "outputId": "f615585e-b21a-4d72-c277-0e566eb88a4a"
      },
      "outputs": [
        {
          "data": {
            "text/plain": [
              "XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,\n",
              "              colsample_bynode=1, colsample_bytree=1, enable_categorical=False,\n",
              "              eval_metric='logloss', gamma=0.5, gpu_id=-1, importance_type=None,\n",
              "              interaction_constraints='', learning_rate=0.1, max_delta_step=0,\n",
              "              max_depth=3, min_child_weight=1, missing=nan,\n",
              "              monotone_constraints='()', n_estimators=100, n_jobs=-1,\n",
              "              num_parallel_tree=1, predictor='auto', random_state=0,\n",
              "              reg_alpha=0, reg_lambda=50, scale_pos_weight=2.7596291012838803,\n",
              "              subsample=1, tree_method='exact', use_label_encoder=False,\n",
              "              validate_parameters=1, verbosity=None)"
            ]
          },
          "execution_count": 16,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "xgb_clf = xgboost.XGBClassifier(use_label_encoder = False,\n",
        "                                random_state = 0,\n",
        "                                scale_pos_weight = cls_weight,\n",
        "                                n_jobs = -1,\n",
        "                                gamma = 0.5,\n",
        "                                learning_rate = 0.1,\n",
        "                                max_depth = 3,\n",
        "                                reg_lambda = 50,\n",
        "                                eval_metric = 'logloss')\n",
        "\n",
        "xgb_clf.fit(X_train, y_train)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "suetHTzrC3_K",
      "metadata": {
        "id": "suetHTzrC3_K"
      },
      "source": [
        "With our final model, let us calculate the metrics."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 17,
      "id": "U6fk57sl6pDa",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 348
        },
        "id": "U6fk57sl6pDa",
        "outputId": "a2ff8aa1-a784-4511-c075-4e78564c848a"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 432x288 with 2 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "The resultant f1-score for defaulting is: 0.6272493573264782\n",
            "The resultant f1-score for not defaulting is: 0.8148148148148148\n",
            "The resultant accuracy is: 0.7525597269624573\n",
            "The resultant precision is: 0.5228571428571429\n"
          ]
        }
      ],
      "source": [
        "y_pred = xgb_clf.predict(X_test)\n",
        "\n",
        "ConfusionMatrixDisplay.from_predictions(y_test, y_pred, labels = [1,0])\n",
        "plt.show()\n",
        "\n",
        "f_score = f1_score(y_test, y_pred)\n",
        "print(f\"The resultant f1-score for defaulting is: {f_score}\")\n",
        "f_score_def = f1_score(y_test, y_pred, pos_label=0)\n",
        "print(f\"The resultant f1-score for not defaulting is: {f_score_def}\")\n",
        "accuracy = accuracy_score(y_test, y_pred)\n",
        "print(f\"The resultant accuracy is: {accuracy}\")\n",
        "precision = precision_score(y_test,y_pred)\n",
        "print(f\"The resultant precision is: {precision}\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "zpZLY4YDEJxN",
      "metadata": {
        "id": "zpZLY4YDEJxN"
      },
      "source": [
        "We can now compare to see how much our new model has improved!"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "id": "46Y--Gg1E0_r",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 507
        },
        "id": "46Y--Gg1E0_r",
        "outputId": "e30d56a5-cb68-49f6-f77f-e44dbe033c91"
      },
      "outputs": [
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 864x576 with 1 Axes>"
            ]
          },
          "metadata": {
            "needs_background": "light"
          },
          "output_type": "display_data"
        }
      ],
      "source": [
        "# set width of bar\n",
        "barWidth = 0.25\n",
        "fig = plt.subplots(figsize =(12, 8))\n",
        "\n",
        "pre_data = [pre_f_score, pre_f_score_def, pre_accuracy, pre_precision]\n",
        "data = [f_score, f_score_def, accuracy, precision]\n",
        "\n",
        "# Set position of bar on X axis\n",
        "br1 = np.arange(len(pre_data))\n",
        "br2 = [x + barWidth for x in br1]\n",
        " \n",
        "# Make the plot\n",
        "plt.bar(br1, pre_data, color ='b', width = barWidth,\n",
        "        edgecolor ='grey', label ='Preliminary Model')\n",
        "plt.bar(br2, data, color ='r', width = barWidth, label ='Optimised Model')\n",
        " \n",
        "# Adding Xticks\n",
        "plt.xlabel('Metric', fontweight ='bold', fontsize = 15)\n",
        "plt.ylabel('Score', fontweight ='bold', fontsize = 15)\n",
        "plt.xticks([r + barWidth/2 for r in range(len(pre_data))],\n",
        "        ['f_score_def', 'f_score_no_def', 'accuracy', 'precision'])\n",
        "\n",
        "# Adjust the y-axis to zoom in on the relevant area\n",
        "ax = plt.gca()\n",
        "ax.set_ylim([0.45,0.85])\n",
        "\n",
        "plt.legend()\n",
        "plt.show()\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "id": "IAcS6MwtIXBP",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IAcS6MwtIXBP",
        "outputId": "8305c90e-8593-41da-e90f-792bb29c8114"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "The increase in f1-score for defaulters is 3.3535872867492573%\n",
            "The increase in f1-score for not defaulting is -3.0517672763153243%\n",
            "The increase in accuracy is -2.649006622516553%\n",
            "The increase in precision is -6.972170686456389%\n"
          ]
        }
      ],
      "source": [
        "# Calculate percentage increase from base model\n",
        "f_score_inc = (f_score - pre_f_score)/pre_f_score\n",
        "f_score_def_inc = (f_score_def - pre_f_score_def)/pre_f_score_def\n",
        "accuracy_inc = (accuracy - pre_accuracy)/pre_accuracy\n",
        "precision_inc = (precision - pre_precision)/pre_precision\n",
        "\n",
        "print(f\"The increase in f1-score for defaulters is {f_score_inc*100}%\")\n",
        "print(f\"The increase in f1-score for not defaulting is {f_score_def_inc*100}%\")\n",
        "print(f\"The increase in accuracy is {accuracy_inc*100}%\")\n",
        "print(f\"The increase in precision is {precision_inc*100}%\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "SiMBfRtwHugb",
      "metadata": {
        "id": "SiMBfRtwHugb"
      },
      "source": [
        "We can see that while our f1-score for predicting if a user will default on their telco payment has increased slightly, it has come at the cost of the other metrics. While our f1-score for defaulting improved by 3.35%, the f1-score for not defaulting decreased by 3.05%, the accuracy dropped by 2.64% and the precision dropped by 6.97%. Depending on the metric we are targetting, we can choose the relevant model as such."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "46KCzty-JZ9p",
      "metadata": {
        "id": "46KCzty-JZ9p"
      },
      "source": [
        "Finally, we can save our model!"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "id": "j8pASkimJdKA",
      "metadata": {
        "id": "j8pASkimJdKA"
      },
      "outputs": [],
      "source": [
        "import pickle\n",
        "pickle.dump(pre_xgb_clf, open(\"preliminary_telco_default_model.json\", \"wb\"))\n",
        "pickle.dump(xgb_clf, open(\"telco_default_model.json\", \"wb\"))"
      ]
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "collapsed_sections": [],
      "name": "Model Training.py.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": "3.9.10"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}