Churn-in-a-telecom-operator-colab.ipynb

churn-in-a-telecom-operator-colab.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "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": "3.8.2"
    },
    "colab": {
      "name": "Churn-in-a-telecom-operator-colab.ipynb",
      "provenance": [],
      "include_colab_link": true
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/gist/alonsosilvaallende/c67e50c1e2ec1227bc59457640f238a8/churn-in-a-telecom-operator-colab.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "IWUt4iKZJLIi"
      },
      "source": [
        "# Churn prediction in a telco\n",
        "\n",
        "Treselle Systems, a data consulting service, [analyzed customer churn data using logistic regression](http://www.treselle.com/blog/customer-churn-logistic-regression-with-r/).\n",
        "\n",
        "We will use that dataset to do our analysis. The dataset includes information about:\n",
        "\n",
        "+ Customers who left within the last month: the column is called Churn\n",
        "+ Services that each customer has signed up for: phone, multiple lines, internet, online security, online backup, device protection, tech support, and streaming TV and movies\n",
        "+ Customer account information: how long they've been a customer, contract, payment method, paperless billing, monthly charges, and total charges\n",
        "+ Demographic info about customers: gender, age range, and if they have partners and dependents"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "G9M17t2UJTfc"
      },
      "source": [
        "%pip install --quiet lifelines scikit-survival"
      ],
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "4eQkkBwbJLIl"
      },
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "plt.style.use('seaborn-v0_8-bright')"
      ],
      "execution_count": 2,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "ExecuteTime": {
          "end_time": "2020-01-09T22:37:18.227285Z",
          "start_time": "2020-01-09T22:37:18.131371Z"
        },
        "id": "So7R4TFbJLI5"
      },
      "source": [
        "churn_data = pd.read_csv(\n",
        "'https://raw.githubusercontent.com/treselle-systems/customer_churn_analysis/master/WA_Fn-UseC_-Telco-Customer-Churn.csv')"
      ],
      "execution_count": 3,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "ExecuteTime": {
          "end_time": "2020-01-09T22:37:18.287007Z",
          "start_time": "2020-01-09T22:37:18.264485Z"
        },
        "scrolled": false,
        "id": "S5CwX51iJLJM",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 707
        },
        "outputId": "0757e674-7ce2-417b-ecd6-294a549e1963"
      },
      "source": [
        "churn_data.head().T"
      ],
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                 0             1               2  \\\n",
              "customerID              7590-VHVEG    5575-GNVDE      3668-QPYBK   \n",
              "gender                      Female          Male            Male   \n",
              "SeniorCitizen                    0             0               0   \n",
              "Partner                        Yes            No              No   \n",
              "Dependents                      No            No              No   \n",
              "tenure                           1            34               2   \n",
              "PhoneService                    No           Yes             Yes   \n",
              "MultipleLines     No phone service            No              No   \n",
              "InternetService                DSL           DSL             DSL   \n",
              "OnlineSecurity                  No           Yes             Yes   \n",
              "OnlineBackup                   Yes            No             Yes   \n",
              "DeviceProtection                No           Yes              No   \n",
              "TechSupport                     No            No              No   \n",
              "StreamingTV                     No            No              No   \n",
              "StreamingMovies                 No            No              No   \n",
              "Contract            Month-to-month      One year  Month-to-month   \n",
              "PaperlessBilling               Yes            No             Yes   \n",
              "PaymentMethod     Electronic check  Mailed check    Mailed check   \n",
              "MonthlyCharges               29.85         56.95           53.85   \n",
              "TotalCharges                 29.85        1889.5          108.15   \n",
              "Churn                           No            No             Yes   \n",
              "\n",
              "                                          3                 4  \n",
              "customerID                       7795-CFOCW        9237-HQITU  \n",
              "gender                                 Male            Female  \n",
              "SeniorCitizen                             0                 0  \n",
              "Partner                                  No                No  \n",
              "Dependents                               No                No  \n",
              "tenure                                   45                 2  \n",
              "PhoneService                             No               Yes  \n",
              "MultipleLines              No phone service                No  \n",
              "InternetService                         DSL       Fiber optic  \n",
              "OnlineSecurity                          Yes                No  \n",
              "OnlineBackup                             No                No  \n",
              "DeviceProtection                        Yes                No  \n",
              "TechSupport                             Yes                No  \n",
              "StreamingTV                              No                No  \n",
              "StreamingMovies                          No                No  \n",
              "Contract                           One year    Month-to-month  \n",
              "PaperlessBilling                         No               Yes  \n",
              "PaymentMethod     Bank transfer (automatic)  Electronic check  \n",
              "MonthlyCharges                         42.3              70.7  \n",
              "TotalCharges                        1840.75            151.65  \n",
              "Churn                                    No               Yes  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-f897c59f-1fbc-4354-969c-52b6bdb4da02\" class=\"colab-df-container\">\n",
              "    <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>0</th>\n",
              "      <th>1</th>\n",
              "      <th>2</th>\n",
              "      <th>3</th>\n",
              "      <th>4</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>customerID</th>\n",
              "      <td>7590-VHVEG</td>\n",
              "      <td>5575-GNVDE</td>\n",
              "      <td>3668-QPYBK</td>\n",
              "      <td>7795-CFOCW</td>\n",
              "      <td>9237-HQITU</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>gender</th>\n",
              "      <td>Female</td>\n",
              "      <td>Male</td>\n",
              "      <td>Male</td>\n",
              "      <td>Male</td>\n",
              "      <td>Female</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>SeniorCitizen</th>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Partner</th>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Dependents</th>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>tenure</th>\n",
              "      <td>1</td>\n",
              "      <td>34</td>\n",
              "      <td>2</td>\n",
              "      <td>45</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PhoneService</th>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>MultipleLines</th>\n",
              "      <td>No phone service</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No phone service</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>InternetService</th>\n",
              "      <td>DSL</td>\n",
              "      <td>DSL</td>\n",
              "      <td>DSL</td>\n",
              "      <td>DSL</td>\n",
              "      <td>Fiber optic</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>OnlineSecurity</th>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Yes</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>OnlineBackup</th>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>DeviceProtection</th>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>TechSupport</th>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StreamingTV</th>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>StreamingMovies</th>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Contract</th>\n",
              "      <td>Month-to-month</td>\n",
              "      <td>One year</td>\n",
              "      <td>Month-to-month</td>\n",
              "      <td>One year</td>\n",
              "      <td>Month-to-month</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PaperlessBilling</th>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>PaymentMethod</th>\n",
              "      <td>Electronic check</td>\n",
              "      <td>Mailed check</td>\n",
              "      <td>Mailed check</td>\n",
              "      <td>Bank transfer (automatic)</td>\n",
              "      <td>Electronic check</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>MonthlyCharges</th>\n",
              "      <td>29.85</td>\n",
              "      <td>56.95</td>\n",
              "      <td>53.85</td>\n",
              "      <td>42.3</td>\n",
              "      <td>70.7</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>TotalCharges</th>\n",
              "      <td>29.85</td>\n",
              "      <td>1889.5</td>\n",
              "      <td>108.15</td>\n",
              "      <td>1840.75</td>\n",
              "      <td>151.65</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Churn</th>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Yes</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f897c59f-1fbc-4354-969c-52b6bdb4da02')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-f897c59f-1fbc-4354-969c-52b6bdb4da02 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-f897c59f-1fbc-4354-969c-52b6bdb4da02');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-fb7b5e7e-2988-4fe7-aa5b-f0613ed16a6d\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-fb7b5e7e-2988-4fe7-aa5b-f0613ed16a6d')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-fb7b5e7e-2988-4fe7-aa5b-f0613ed16a6d button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "churn_data"
            }
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "ExecuteTime": {
          "end_time": "2020-01-09T22:37:18.251731Z",
          "start_time": "2020-01-09T22:37:18.229450Z"
        },
        "id": "ku717ihdJLJe",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "deed513d-7efd-4b4b-b56b-82de954b6672"
      },
      "source": [
        "N = churn_data.shape[0]\n",
        "churned = len(churn_data.query(\"Churn == 'Yes'\"))\n",
        "notChurned = len(churn_data.query(\"Churn == 'No'\"))\n",
        "\n",
        "print(f'customers: {N}\\n')\n",
        "print(f\"customers who churned: {churned}\")\n",
        "print(f\"customers who haven't churned yet: {notChurned}\\n\")\n",
        "print(f'percentage of customers who churned: {100*churned/len(churn_data):.0f}%')\n",
        "print(f\"percentage of customers who haven't churned yet: {100*notChurned/len(churn_data):.0f}%\")"
      ],
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "customers: 7043\n",
            "\n",
            "customers who churned: 1869\n",
            "customers who haven't churned yet: 5174\n",
            "\n",
            "percentage of customers who churned: 27%\n",
            "percentage of customers who haven't churned yet: 73%\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "churn_data[\"Churn\"].unique()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GmZRZJMJME4F",
        "outputId": "b9226193-e47c-47d1-88bf-0acf67c907f3"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['No', 'Yes'], dtype=object)"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "ExecuteTime": {
          "end_time": "2020-01-09T22:37:18.305561Z",
          "start_time": "2020-01-09T22:37:18.288618Z"
        },
        "id": "WZgadAo6JLJp"
      },
      "source": [
        "churn_data['Churn'] = (churn_data['Churn'] == 'Yes')"
      ],
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "churn_data[\"Churn\"].unique()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BxK09LoeMPJw",
        "outputId": "74cd84af-fef7-4111-dec2-251b1291025b"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([False,  True])"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "ExecuteTime": {
          "end_time": "2020-01-09T22:37:18.262702Z",
          "start_time": "2020-01-09T22:37:18.254982Z"
        },
        "id": "CEv5C_L7JLJ2"
      },
      "source": [
        "# Drop customerID column\n",
        "churn_data = churn_data.drop('customerID', axis=1)\n",
        "\n",
        "# Drop TotalCharges column: otherwise together with MonthlyCharges you can deduce how many months you have been subscribed\n",
        "churn_data = churn_data.drop('TotalCharges', axis=1)"
      ],
      "execution_count": 9,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "ExecuteTime": {
          "end_time": "2020-01-09T22:37:18.691230Z",
          "start_time": "2020-01-09T22:37:18.307317Z"
        },
        "scrolled": false,
        "id": "Td3MQtORJLKB",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 641
        },
        "outputId": "f506fdcb-d7fc-4846-b544-e491a01fd9c6"
      },
      "source": [
        "from lifelines import KaplanMeierFitter\n",
        "\n",
        "kmf = KaplanMeierFitter()\n",
        "kmf.fit(churn_data['tenure'], churn_data['Churn'], label='Estimate for Average Customer')\n",
        "fig, ax = plt.subplots(figsize=(10,7))\n",
        "kmf.plot(ax=ax)\n",
        "ax.set_title('Kaplan-Meier Survival Curve - All Customers')\n",
        "ax.set_xlabel('Customer Tenure (Months)')\n",
        "ax.set_ylabel('Customer Survival Chance (%)')\n",
        "plt.show()"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x700 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OaQL73F8JLKQ"
      },
      "source": [
        "data = pd.DataFrame()\n",
        "data = kmf.survival_function_\n",
        "data['lower'] = kmf.confidence_interval_['Estimate for Average Customer_lower_0.95']\n",
        "data['upper'] = kmf.confidence_interval_['Estimate for Average Customer_upper_0.95']"
      ],
      "execution_count": 13,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8iBX5KruJLKK"
      },
      "source": [
        "import altair as alt"
      ],
      "execution_count": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "scrolled": true,
        "id": "iexNxw4lJLKd",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 385
        },
        "outputId": "2feda4ad-6ed2-4693-9fab-daa8a1ebdb53"
      },
      "source": [
        "label = alt.selection_single(\n",
        "    encodings=['x'], # limit selection to x-axis value\n",
        "    on='mouseover',  # select on mouseover events\n",
        "    nearest=True,    # select data point nearest the cursor\n",
        "    empty='none'     # empty selection includes no data points\n",
        ")\n",
        "\n",
        "base = alt.Chart(data.reset_index()).encode(\n",
        "    x=alt.X('timeline:Q', scale=alt.Scale(zero=False), axis=alt.Axis(title=\"Customer tenure (months)\"))\n",
        ")\n",
        "\n",
        "line = base.mark_line(point=False).encode(\n",
        "    y=alt.Y('Estimate for Average Customer', scale=alt.Scale(zero=False), axis=alt.Axis(title='Customer survival probability')),\n",
        "    color=alt.value('blue'),\n",
        "    tooltip = ['timeline', 'Estimate for Average Customer']\n",
        ")\n",
        "\n",
        "band = alt.Chart(data.reset_index()).mark_area(\n",
        "    opacity=0.5\n",
        ").encode(\n",
        "    x=alt.X('timeline:Q', scale=alt.Scale(zero=False)),\n",
        "    y='lower:Q',\n",
        "    y2='upper:Q'\n",
        ")\n",
        "\n",
        "alt.layer(\n",
        "    line, # base line chart\n",
        "    band,\n",
        "    alt.Chart().mark_rule(color='#aaa').encode(\n",
        "        x = alt.X('timeline:Q', scale=alt.Scale(zero=False), sort=None)\n",
        "    ).transform_filter(label),\n",
        "        # add circle marks for selected time points, hide unselected points\n",
        "    base.mark_circle(size=80).encode(\n",
        "        y=alt.Y('Estimate for Average Customer', scale=alt.Scale(zero=False), axis=alt.Axis(title='Customer survival probability')),\n",
        "        opacity=alt.condition(label, alt.value(1), alt.value(0))\n",
        "    ).add_selection(label),\n",
        "        # add white stroked text to provide a legible background for labels\n",
        "    base.mark_text(align='left', dx=5, dy=-5, stroke='white', strokeWidth=2).encode(\n",
        "        text='Estimate for Average Customer:Q'\n",
        "    ).transform_filter(label),\n",
        "        # add text labels for stock prices\n",
        "    base.mark_text(align='left', dx=5, dy=-5).encode(\n",
        "        text='Estimate for Average Customer:Q'\n",
        "    ).transform_filter(label),\n",
        "\n",
        "    data=data.reset_index()\n",
        ").properties(\n",
        "    title=f'Kaplan-Meier Survival Curve - All Customers',\n",
        "    width=600\n",
        ")"
      ],
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "\n",
              "<div id=\"altair-viz-f2e96f9921ee4d24bd3fa78fc3eb6a77\"></div>\n",
              "<script type=\"text/javascript\">\n",
              "  var VEGA_DEBUG = (typeof VEGA_DEBUG == \"undefined\") ? {} : VEGA_DEBUG;\n",
              "  (function(spec, embedOpt){\n",
              "    let outputDiv = document.currentScript.previousElementSibling;\n",
              "    if (outputDiv.id !== \"altair-viz-f2e96f9921ee4d24bd3fa78fc3eb6a77\") {\n",
              "      outputDiv = document.getElementById(\"altair-viz-f2e96f9921ee4d24bd3fa78fc3eb6a77\");\n",
              "    }\n",
              "    const paths = {\n",
              "      \"vega\": \"https://cdn.jsdelivr.net/npm//vega@5?noext\",\n",
              "      \"vega-lib\": \"https://cdn.jsdelivr.net/npm//vega-lib?noext\",\n",
              "      \"vega-lite\": \"https://cdn.jsdelivr.net/npm//[email protected]?noext\",\n",
              "      \"vega-embed\": \"https://cdn.jsdelivr.net/npm//vega-embed@6?noext\",\n",
              "    };\n",
              "\n",
              "    function maybeLoadScript(lib, version) {\n",
              "      var key = `${lib.replace(\"-\", \"\")}_version`;\n",
              "      return (VEGA_DEBUG[key] == version) ?\n",
              "        Promise.resolve(paths[lib]) :\n",
              "        new Promise(function(resolve, reject) {\n",
              "          var s = document.createElement('script');\n",
              "          document.getElementsByTagName(\"head\")[0].appendChild(s);\n",
              "          s.async = true;\n",
              "          s.onload = () => {\n",
              "            VEGA_DEBUG[key] = version;\n",
              "            return resolve(paths[lib]);\n",
              "          };\n",
              "          s.onerror = () => reject(`Error loading script: ${paths[lib]}`);\n",
              "          s.src = paths[lib];\n",
              "        });\n",
              "    }\n",
              "\n",
              "    function showError(err) {\n",
              "      outputDiv.innerHTML = `<div class=\"error\" style=\"color:red;\">${err}</div>`;\n",
              "      throw err;\n",
              "    }\n",
              "\n",
              "    function displayChart(vegaEmbed) {\n",
              "      vegaEmbed(outputDiv, spec, embedOpt)\n",
              "        .catch(err => showError(`Javascript Error: ${err.message}<br>This usually means there's a typo in your chart specification. See the javascript console for the full traceback.`));\n",
              "    }\n",
              "\n",
              "    if(typeof define === \"function\" && define.amd) {\n",
              "      requirejs.config({paths});\n",
              "      require([\"vega-embed\"], displayChart, err => showError(`Error loading script: ${err.message}`));\n",
              "    } else {\n",
              "      maybeLoadScript(\"vega\", \"5\")\n",
              "        .then(() => maybeLoadScript(\"vega-lite\", \"4.17.0\"))\n",
              "        .then(() => maybeLoadScript(\"vega-embed\", \"6\"))\n",
              "        .catch(showError)\n",
              "        .then(() => displayChart(vegaEmbed));\n",
              "    }\n",
              "  })({\"config\": {\"view\": {\"continuousWidth\": 400, \"continuousHeight\": 300}}, \"layer\": [{\"data\": {\"name\": \"data-dcd50d5b88127b75b77f518c21f916e9\"}, \"mark\": {\"type\": \"line\", \"point\": false}, \"encoding\": {\"color\": {\"value\": \"blue\"}, \"tooltip\": [{\"field\": \"timeline\", \"type\": \"quantitative\"}, {\"field\": \"Estimate for Average Customer\", \"type\": \"quantitative\"}], \"x\": {\"axis\": {\"title\": \"Customer tenure (months)\"}, \"field\": \"timeline\", \"scale\": {\"zero\": false}, \"type\": \"quantitative\"}, \"y\": {\"axis\": {\"title\": \"Customer survival probability\"}, \"field\": \"Estimate for Average Customer\", \"scale\": {\"zero\": false}, \"type\": \"quantitative\"}}}, {\"data\": {\"name\": \"data-dcd50d5b88127b75b77f518c21f916e9\"}, \"mark\": {\"type\": \"area\", \"opacity\": 0.5}, \"encoding\": {\"x\": {\"field\": \"timeline\", \"scale\": {\"zero\": false}, \"type\": \"quantitative\"}, \"y\": {\"field\": \"lower\", \"type\": \"quantitative\"}, \"y2\": {\"field\": \"upper\"}}}, {\"mark\": {\"type\": \"rule\", \"color\": \"#aaa\"}, \"encoding\": {\"x\": {\"field\": \"timeline\", \"scale\": {\"zero\": false}, \"sort\": null, \"type\": \"quantitative\"}}, \"transform\": [{\"filter\": {\"selection\": \"selector001\"}}]}, {\"data\": {\"name\": \"data-dcd50d5b88127b75b77f518c21f916e9\"}, \"mark\": {\"type\": \"circle\", \"size\": 80}, \"encoding\": {\"opacity\": {\"condition\": {\"value\": 1, \"selection\": \"selector001\"}, \"value\": 0}, \"x\": {\"axis\": {\"title\": \"Customer tenure (months)\"}, \"field\": \"timeline\", \"scale\": {\"zero\": false}, \"type\": \"quantitative\"}, \"y\": {\"axis\": {\"title\": \"Customer survival probability\"}, \"field\": \"Estimate for Average Customer\", \"scale\": {\"zero\": false}, \"type\": \"quantitative\"}}, \"selection\": {\"selector001\": {\"type\": \"single\", \"encodings\": [\"x\"], \"on\": \"mouseover\", \"nearest\": true, \"empty\": \"none\"}}}, {\"data\": {\"name\": \"data-dcd50d5b88127b75b77f518c21f916e9\"}, \"mark\": {\"type\": \"text\", \"align\": \"left\", \"dx\": 5, \"dy\": -5, \"stroke\": \"white\", \"strokeWidth\": 2}, \"encoding\": {\"text\": {\"field\": \"Estimate for Average Customer\", \"type\": \"quantitative\"}, \"x\": {\"axis\": {\"title\": \"Customer tenure (months)\"}, \"field\": \"timeline\", \"scale\": {\"zero\": false}, \"type\": \"quantitative\"}}, \"transform\": [{\"filter\": {\"selection\": \"selector001\"}}]}, {\"data\": {\"name\": \"data-dcd50d5b88127b75b77f518c21f916e9\"}, \"mark\": {\"type\": \"text\", \"align\": \"left\", \"dx\": 5, \"dy\": -5}, \"encoding\": {\"text\": {\"field\": \"Estimate for Average Customer\", \"type\": \"quantitative\"}, \"x\": {\"axis\": {\"title\": \"Customer tenure (months)\"}, \"field\": \"timeline\", \"scale\": {\"zero\": false}, \"type\": \"quantitative\"}}, \"transform\": [{\"filter\": {\"selection\": \"selector001\"}}]}], \"data\": {\"name\": \"data-dcd50d5b88127b75b77f518c21f916e9\"}, \"title\": \"Kaplan-Meier Survival Curve - All Customers\", \"width\": 600, \"$schema\": \"https://vega.github.io/schema/vega-lite/v4.17.0.json\", \"datasets\": {\"data-dcd50d5b88127b75b77f518c21f916e9\": [{\"timeline\": 0.0, \"Estimate for Average Customer\": 1.0, \"lower\": 1.0, \"upper\": 1.0}, {\"timeline\": 1.0, \"Estimate for Average Customer\": 0.9459613196814566, \"lower\": 0.9404183713158356, \"upper\": 0.9510021209572403}, {\"timeline\": 2.0, \"Estimate for Average Customer\": 0.9278349382636628, \"lower\": 0.9215059899590076, \"upper\": 0.9336721186843941}, {\"timeline\": 3.0, \"Estimate for Average Customer\": 0.9137245217943558, \"lower\": 0.9068570856457402, \"upper\": 0.9201081780961634}, {\"timeline\": 4.0, \"Estimate for Average Customer\": 0.9010445125469171, \"lower\": 0.8937333460911131, \"upper\": 0.9078789401526071}, {\"timeline\": 5.0, \"Estimate for Average Customer\": 0.8911105161984236, \"lower\": 0.8834732306073576, \"upper\": 0.8982764957239141}, {\"timeline\": 6.0, \"Estimate for Average Customer\": 0.8848262389332724, \"lower\": 0.8769910175693204, \"upper\": 0.8921935526017892}, {\"timeline\": 7.0, \"Estimate for Average Customer\": 0.8767129454802709, \"lower\": 0.8686302744761023, \"upper\": 0.8843320072393812}, {\"timeline\": 8.0, \"Estimate for Average Customer\": 0.8699329889878812, \"lower\": 0.8616495182497433, \"upper\": 0.8777563360010985}, {\"timeline\": 9.0, \"Estimate for Average Customer\": 0.862394006792432, \"lower\": 0.8538928337872115, \"upper\": 0.8704388125380358}, {\"timeline\": 10.0, \"Estimate for Average Customer\": 0.854915161098529, \"lower\": 0.8462039691721595, \"upper\": 0.8631736733837074}, {\"timeline\": 11.0, \"Estimate for Average Customer\": 0.8496909604294861, \"lower\": 0.8408359247763904, \"upper\": 0.8580958350839235}, {\"timeline\": 12.0, \"Estimate for Average Customer\": 0.8431995538158302, \"lower\": 0.834168685811462, \"upper\": 0.8517833206931235}, {\"timeline\": 13.0, \"Estimate for Average Customer\": 0.8366025632774321, \"lower\": 0.8273958732708122, \"upper\": 0.84536517439355}, {\"timeline\": 14.0, \"Estimate for Average Customer\": 0.8323737381892569, \"lower\": 0.8230555387776636, \"upper\": 0.841249734571825}, {\"timeline\": 15.0, \"Estimate for Average Customer\": 0.8257817372660968, \"lower\": 0.8162924499579037, \"upper\": 0.8348317518565246}, {\"timeline\": 16.0, \"Estimate for Average Customer\": 0.8207255621855252, \"lower\": 0.811106906401148, \"upper\": 0.8299071739485888}, {\"timeline\": 17.0, \"Estimate for Average Customer\": 0.8159762043807567, \"lower\": 0.8062374084341788, \"upper\": 0.82528003664297}, {\"timeline\": 18.0, \"Estimate for Average Customer\": 0.8115314860636578, \"lower\": 0.8016809173680022, \"upper\": 0.8209489863094623}, {\"timeline\": 19.0, \"Estimate for Average Customer\": 0.8079531388287515, \"lower\": 0.798012367175139, \"upper\": 0.8174622790431181}, {\"timeline\": 20.0, \"Estimate for Average Customer\": 0.8045199101935029, \"lower\": 0.7944926763694108, \"upper\": 0.8141168446808157}, {\"timeline\": 21.0, \"Estimate for Average Customer\": 0.8012361554580191, \"lower\": 0.7911262275701932, \"upper\": 0.8109170130349665}, {\"timeline\": 22.0, \"Estimate for Average Customer\": 0.7959622948540777, \"lower\": 0.7857205720282491, \"upper\": 0.8057769198289992}, {\"timeline\": 23.0, \"Estimate for Average Customer\": 0.7933831548159159, \"lower\": 0.7830768790035613, \"upper\": 0.8032632537959522}, {\"timeline\": 24.0, \"Estimate for Average Customer\": 0.7887363983705965, \"lower\": 0.7783129555299131, \"upper\": 0.798735202136176}, {\"timeline\": 25.0, \"Estimate for Average Customer\": 0.7840035684299431, \"lower\": 0.7734606163306005, \"upper\": 0.7941233735135383}, {\"timeline\": 26.0, \"Estimate for Average Customer\": 0.78087089567383, \"lower\": 0.7702488090051803, \"upper\": 0.791070790797879}, {\"timeline\": 27.0, \"Estimate for Average Customer\": 0.7781086312809701, \"lower\": 0.7674160577861241, \"upper\": 0.7883797833200772}, {\"timeline\": 28.0, \"Estimate for Average Customer\": 0.7755170954565537, \"lower\": 0.7647577267893169, \"upper\": 0.7858557012640619}, {\"timeline\": 29.0, \"Estimate for Average Customer\": 0.7722365662879559, \"lower\": 0.761392420324585, \"upper\": 0.7826607509843774}, {\"timeline\": 30.0, \"Estimate for Average Customer\": 0.7686799211927888, \"lower\": 0.7577433426203282, \"upper\": 0.7791973520011836}, {\"timeline\": 31.0, \"Estimate for Average Customer\": 0.7650647304993484, \"lower\": 0.7540337514754943, \"upper\": 0.7756773411800988}, {\"timeline\": 32.0, \"Estimate for Average Customer\": 0.7607086532205094, \"lower\": 0.7495639740543699, \"upper\": 0.7714358919002775}, {\"timeline\": 33.0, \"Estimate for Average Customer\": 0.7574498034209116, \"lower\": 0.7462199150029253, \"upper\": 0.7682629264281162}, {\"timeline\": 34.0, \"Estimate for Average Customer\": 0.7546129127713944, \"lower\": 0.7433083428939619, \"upper\": 0.7655012642310856}, {\"timeline\": 35.0, \"Estimate for Average Customer\": 0.7510069256125633, \"lower\": 0.7396066912924588, \"upper\": 0.7619915810379179}, {\"timeline\": 36.0, \"Estimate for Average Customer\": 0.7485454148763702, \"lower\": 0.7370785621208633, \"upper\": 0.7595970312942879}, {\"timeline\": 37.0, \"Estimate for Average Customer\": 0.7448039349619592, \"lower\": 0.7332355622236266, \"upper\": 0.7559575770131214}, {\"timeline\": 38.0, \"Estimate for Average Customer\": 0.7415060973752753, \"lower\": 0.7298477058195078, \"upper\": 0.7527501715335171}, {\"timeline\": 39.0, \"Estimate for Average Customer\": 0.7378977951982666, \"lower\": 0.7261404450815181, \"upper\": 0.7492412557752938}, {\"timeline\": 40.0, \"Estimate for Average Customer\": 0.7344973445291503, \"lower\": 0.7226464865355982, \"upper\": 0.7459347086154924}, {\"timeline\": 41.0, \"Estimate for Average Customer\": 0.7307675792685739, \"lower\": 0.718813324657747, \"upper\": 0.7423087300192401}, {\"timeline\": 42.0, \"Estimate for Average Customer\": 0.7269600816467797, \"lower\": 0.7148991560020901, \"upper\": 0.7386082428763483}, {\"timeline\": 43.0, \"Estimate for Average Customer\": 0.7228012711110432, \"lower\": 0.7106230187730818, \"upper\": 0.7345670985744338}, {\"timeline\": 44.0, \"Estimate for Average Customer\": 0.7211052180697188, \"lower\": 0.7088784590135658, \"upper\": 0.7329196547767036}, {\"timeline\": 45.0, \"Estimate for Average Customer\": 0.7193787091677161, \"lower\": 0.7071016548595497, \"upper\": 0.7312434901038949}, {\"timeline\": 46.0, \"Estimate for Average Customer\": 0.7158480161165857, \"lower\": 0.7034660682549528, \"upper\": 0.7278176757076321}, {\"timeline\": 47.0, \"Estimate for Average Customer\": 0.7116211615296467, \"lower\": 0.6991114342385604, \"upper\": 0.7237184770494878}, {\"timeline\": 48.0, \"Estimate for Average Customer\": 0.7088401843460741, \"lower\": 0.696245083070984, \"upper\": 0.7210227332102614}, {\"timeline\": 49.0, \"Estimate for Average Customer\": 0.7040913666751537, \"lower\": 0.6913482448254978, \"upper\": 0.7164216030931225}, {\"timeline\": 50.0, \"Estimate for Average Customer\": 0.7008511855123595, \"lower\": 0.6880058448875696, \"upper\": 0.7132833750752133}, {\"timeline\": 51.0, \"Estimate for Average Customer\": 0.6981876180614814, \"lower\": 0.685256130132329, \"upper\": 0.7107056284968808}, {\"timeline\": 52.0, \"Estimate for Average Customer\": 0.6954455950155849, \"lower\": 0.6824228100028451, \"upper\": 0.7080544290948518}, {\"timeline\": 53.0, \"Estimate for Average Customer\": 0.690470511556097, \"lower\": 0.6772766645524837, \"upper\": 0.7032492874895002}, {\"timeline\": 54.0, \"Estimate for Average Customer\": 0.6857136929815187, \"lower\": 0.6723539178814393, \"upper\": 0.6986572790007199}, {\"timeline\": 55.0, \"Estimate for Average Customer\": 0.6823209369414782, \"lower\": 0.668840380360719, \"upper\": 0.6953844208282612}, {\"timeline\": 56.0, \"Estimate for Average Customer\": 0.6784330683549172, \"lower\": 0.6648106650609784, \"upper\": 0.6916372461214441}, {\"timeline\": 57.0, \"Estimate for Average Customer\": 0.6751927910135208, \"lower\": 0.6614472891464104, \"upper\": 0.6885188721810138}, {\"timeline\": 58.0, \"Estimate for Average Customer\": 0.6705796725656021, \"lower\": 0.6566540260819743, \"upper\": 0.6840840058943622}, {\"timeline\": 59.0, \"Estimate for Average Customer\": 0.6671029147039528, \"lower\": 0.6530376784372129, \"upper\": 0.6807452682464185}, {\"timeline\": 60.0, \"Estimate for Average Customer\": 0.6644039143747397, \"lower\": 0.6502267928533968, \"upper\": 0.6781567791866754}, {\"timeline\": 61.0, \"Estimate for Average Customer\": 0.6606262091046632, \"lower\": 0.6462841968422708, \"upper\": 0.6745416370566342}, {\"timeline\": 62.0, \"Estimate for Average Customer\": 0.6581445178608437, \"lower\": 0.6436882696632222, \"upper\": 0.6721723630788525}, {\"timeline\": 63.0, \"Estimate for Average Customer\": 0.6560568270825379, \"lower\": 0.6414987023418927, \"upper\": 0.6701847193256479}, {\"timeline\": 64.0, \"Estimate for Average Customer\": 0.6538497393547579, \"lower\": 0.6391766092494745, \"upper\": 0.668090317858698}, {\"timeline\": 65.0, \"Estimate for Average Customer\": 0.6485434745628794, \"lower\": 0.6335747882063961, \"upper\": 0.6630731098587361}, {\"timeline\": 66.0, \"Estimate for Average Customer\": 0.640381746422204, \"lower\": 0.6249410515971489, \"upper\": 0.6553729251824221}, {\"timeline\": 67.0, \"Estimate for Average Customer\": 0.6335980414812913, \"lower\": 0.6177440126424799, \"upper\": 0.6489931821153638}, {\"timeline\": 68.0, \"Estimate for Average Customer\": 0.626857636784682, \"lower\": 0.6105561099292072, \"upper\": 0.6426893869172589}, {\"timeline\": 69.0, \"Estimate for Average Customer\": 0.6201353028781441, \"lower\": 0.6033383740719858, \"upper\": 0.6364493769082435}, {\"timeline\": 70.0, \"Estimate for Average Customer\": 0.6096568261782064, \"lower\": 0.5920089857499321, \"upper\": 0.6267982298776328}, {\"timeline\": 71.0, \"Estimate for Average Customer\": 0.6027809973115349, \"lower\": 0.5844705956903173, \"upper\": 0.6205645127398534}, {\"timeline\": 72.0, \"Estimate for Average Customer\": 0.5927901520522275, \"lower\": 0.5730628910042918, \"upper\": 0.6119362091926619}]}}, {\"mode\": \"vega-lite\"});\n",
              "</script>"
            ],
            "text/plain": [
              "alt.LayerChart(...)"
            ]
          },
          "metadata": {},
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from lifelines import KaplanMeierFitter\n",
        "kmf = KaplanMeierFitter()\n",
        "fig, ax = plt.subplots(figsize=(10,7))\n",
        "for r in churn_data['gender'].unique():\n",
        "    ix = churn_data['gender'] == r\n",
        "    kmf.fit(churn_data['tenure'].loc[ix], churn_data['Churn'].loc[ix], label=r)\n",
        "    # kmf.survival_function_.plot(ax=ax)\n",
        "    kmf.plot(ax=ax)\n",
        "# kmf.fit(churn_data['tenure'], churn_data['Churn'], label='Estimate for Average Customer')\n",
        "# kmf.plot(ax=ax)\n",
        "ax.set_title('Kaplan-Meier Survival Curve - All Customers')\n",
        "ax.set_xlabel('Customer Tenure (Months)')\n",
        "ax.set_ylabel('Customer Survival Chance (%)')\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 641
        },
        "id": "gDmUO9iWQbnH",
        "outputId": "a42c21ae-7b8e-4f69-979b-c4cde6f9ca81"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1000x700 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    }
  ]
}