TPOT_implementation.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "e6405703dcaa4151851b40660a7efcd7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_47f7bcf548e247f4b387050d8a85142e",
              "IPY_MODEL_2f5ffa424a5b442e993b0e55e730454e",
              "IPY_MODEL_73459d1c0b6149f0b95db8c356ce70ce"
            ],
            "layout": "IPY_MODEL_79e593d920df4eaf8400aa2abf56dde8"
          }
        },
        "47f7bcf548e247f4b387050d8a85142e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_372906a8759c4f7ba808a134fdd9871d",
            "placeholder": "​",
            "style": "IPY_MODEL_4a38fa47caac42678f38616fcfa8be9e",
            "value": "Optimization Progress: 100%"
          }
        },
        "2f5ffa424a5b442e993b0e55e730454e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_88a63cb70bd44cc29a8b06d12e800bff",
            "max": 50,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_76264489d7cc497d8622d11cc0d0924c",
            "value": 50
          }
        },
        "73459d1c0b6149f0b95db8c356ce70ce": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_870301a53319460ba4a3ccbdcba53be3",
            "placeholder": "​",
            "style": "IPY_MODEL_a6a7c3ef7ca94271b5c3c3cb35b3038b",
            "value": " 50/50 [02:01&lt;00:00,  2.86s/pipeline]"
          }
        },
        "79e593d920df4eaf8400aa2abf56dde8": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": "hidden",
            "width": null
          }
        },
        "372906a8759c4f7ba808a134fdd9871d": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "4a38fa47caac42678f38616fcfa8be9e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "88a63cb70bd44cc29a8b06d12e800bff": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "76264489d7cc497d8622d11cc0d0924c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "870301a53319460ba4a3ccbdcba53be3": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "a6a7c3ef7ca94271b5c3c3cb35b3038b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "4d76f15f49674f178dfe6728d48f52b1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_5701480c7a334294af22961ee35171a5",
              "IPY_MODEL_017c150f16cf4a88a15c467a2f7ad159",
              "IPY_MODEL_e99e52b03b0f4d01b341746be5b20f72"
            ],
            "layout": "IPY_MODEL_a4ee7fc3d6ce45a7a48c281462cdd346"
          }
        },
        "5701480c7a334294af22961ee35171a5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_4edb480ce2e248c7a585876689d4ed99",
            "placeholder": "​",
            "style": "IPY_MODEL_3f96e43a75044298a1ce9064fed894f0",
            "value": "Optimization Progress: 100%"
          }
        },
        "017c150f16cf4a88a15c467a2f7ad159": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_c57e7614f03047929356a2a035e6cd22",
            "max": 60,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_cb855bee0d3e438fa726f0be22ea4136",
            "value": 60
          }
        },
        "e99e52b03b0f4d01b341746be5b20f72": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_a1925e061ad04fbcbc170d3338c1974c",
            "placeholder": "​",
            "style": "IPY_MODEL_a471e85a4a84439d82058dfc9daa936f",
            "value": " 60/60 [03:10&lt;00:00,  1.60s/pipeline]"
          }
        },
        "a4ee7fc3d6ce45a7a48c281462cdd346": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": "hidden",
            "width": null
          }
        },
        "4edb480ce2e248c7a585876689d4ed99": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3f96e43a75044298a1ce9064fed894f0": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "c57e7614f03047929356a2a035e6cd22": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "cb855bee0d3e438fa726f0be22ea4136": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "a1925e061ad04fbcbc170d3338c1974c": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "a471e85a4a84439d82058dfc9daa936f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "**TPOT installation**"
      ],
      "metadata": {
        "id": "uQ41-xvuHheG"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7cK79h1xHNq-",
        "outputId": "e2d325d9-ec1f-46cf-e70e-a23b81514823"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: tpot in /usr/local/lib/python3.10/dist-packages (0.12.2)\n",
            "Requirement already satisfied: numpy>=1.16.3 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.26.4)\n",
            "Requirement already satisfied: scipy>=1.3.1 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.13.1)\n",
            "Requirement already satisfied: scikit-learn>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.5.2)\n",
            "Requirement already satisfied: deap>=1.2 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.4.1)\n",
            "Requirement already satisfied: update-checker>=0.16 in /usr/local/lib/python3.10/dist-packages (from tpot) (0.18.0)\n",
            "Requirement already satisfied: tqdm>=4.36.1 in /usr/local/lib/python3.10/dist-packages (from tpot) (4.66.6)\n",
            "Requirement already satisfied: stopit>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.1.2)\n",
            "Requirement already satisfied: pandas>=0.24.2 in /usr/local/lib/python3.10/dist-packages (from tpot) (2.2.2)\n",
            "Requirement already satisfied: joblib>=0.13.2 in /usr/local/lib/python3.10/dist-packages (from tpot) (1.4.2)\n",
            "Requirement already satisfied: xgboost>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from tpot) (2.1.2)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->tpot) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->tpot) (2024.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->tpot) (2024.2)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=1.4.1->tpot) (3.5.0)\n",
            "Requirement already satisfied: requests>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from update-checker>=0.16->tpot) (2.32.3)\n",
            "Requirement already satisfied: nvidia-nccl-cu12 in /usr/local/lib/python3.10/dist-packages (from xgboost>=1.1.0->tpot) (2.23.4)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas>=0.24.2->tpot) (1.16.0)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (3.4.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (3.10)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (2.2.3)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->tpot) (2024.8.30)\n"
          ]
        }
      ],
      "source": [
        "pip install tpot"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Import TPOT packages and load Telecom Churn Dataset\n"
      ],
      "metadata": {
        "id": "b6GbAAbAHfUt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tpot import TPOTClassifier\n",
        "from sklearn.model_selection import train_test_split\n",
        "from __future__ import print_function\n",
        "import sys, tempfile, urllib, os\n",
        "import pandas as pd\n",
        "import numpy as np"
      ],
      "metadata": {
        "id": "e51V8bEjHzFc"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "BASE_DIR = '/tmp'\n",
        "OUTPUT_FILE = os.path.join(BASE_DIR, 'churn_data.csv')\n",
        "\n",
        "churn_data=urllib.request.urlretrieve('https://raw.githubusercontent.com/srivatsan88/YouTubeLI/master/dataset/WA_Fn-UseC_-Telco-Customer-Churn.csv', OUTPUT_FILE)"
      ],
      "metadata": {
        "id": "vWmYrxSZI-0d"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "churn_df = pd.read_csv(OUTPUT_FILE)"
      ],
      "metadata": {
        "id": "nonR2G4pJMFH"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "churn_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 342
        },
        "id": "yryijtC9JRnr",
        "outputId": "e85e1039-deb1-4360-cc3f-2d3b2dbc29d4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   customerID  gender  SeniorCitizen Partner Dependents  tenure PhoneService  \\\n",
              "0  7590-VHVEG  Female              0     Yes         No       1           No   \n",
              "1  5575-GNVDE    Male              0      No         No      34          Yes   \n",
              "2  3668-QPYBK    Male              0      No         No       2          Yes   \n",
              "3  7795-CFOCW    Male              0      No         No      45           No   \n",
              "4  9237-HQITU  Female              0      No         No       2          Yes   \n",
              "\n",
              "      MultipleLines InternetService OnlineSecurity  ... DeviceProtection  \\\n",
              "0  No phone service             DSL             No  ...               No   \n",
              "1                No             DSL            Yes  ...              Yes   \n",
              "2                No             DSL            Yes  ...               No   \n",
              "3  No phone service             DSL            Yes  ...              Yes   \n",
              "4                No     Fiber optic             No  ...               No   \n",
              "\n",
              "  TechSupport StreamingTV StreamingMovies        Contract PaperlessBilling  \\\n",
              "0          No          No              No  Month-to-month              Yes   \n",
              "1          No          No              No        One year               No   \n",
              "2          No          No              No  Month-to-month              Yes   \n",
              "3         Yes          No              No        One year               No   \n",
              "4          No          No              No  Month-to-month              Yes   \n",
              "\n",
              "               PaymentMethod MonthlyCharges  TotalCharges Churn  \n",
              "0           Electronic check          29.85         29.85    No  \n",
              "1               Mailed check          56.95        1889.5    No  \n",
              "2               Mailed check          53.85        108.15   Yes  \n",
              "3  Bank transfer (automatic)          42.30       1840.75    No  \n",
              "4           Electronic check          70.70        151.65   Yes  \n",
              "\n",
              "[5 rows x 21 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-3e0b9c23-f603-457d-b100-90c84461ad50\" 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>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>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>Churn</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>7590-VHVEG</td>\n",
              "      <td>Female</td>\n",
              "      <td>0</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>1</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>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>1</th>\n",
              "      <td>5575-GNVDE</td>\n",
              "      <td>Male</td>\n",
              "      <td>0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>34</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</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>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",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3668-QPYBK</td>\n",
              "      <td>Male</td>\n",
              "      <td>0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>2</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>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>3</th>\n",
              "      <td>7795-CFOCW</td>\n",
              "      <td>Male</td>\n",
              "      <td>0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>45</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>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>4</th>\n",
              "      <td>9237-HQITU</td>\n",
              "      <td>Female</td>\n",
              "      <td>0</td>\n",
              "      <td>No</td>\n",
              "      <td>No</td>\n",
              "      <td>2</td>\n",
              "      <td>Yes</td>\n",
              "      <td>No</td>\n",
              "      <td>Fiber optic</td>\n",
              "      <td>No</td>\n",
              "      <td>...</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",
              "  </tbody>\n",
              "</table>\n",
              "<p>5 rows × 21 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-3e0b9c23-f603-457d-b100-90c84461ad50')\"\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-3e0b9c23-f603-457d-b100-90c84461ad50 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-3e0b9c23-f603-457d-b100-90c84461ad50');\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-0c578812-dc6f-485d-99b3-78033a61a141\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-0c578812-dc6f-485d-99b3-78033a61a141')\"\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-0c578812-dc6f-485d-99b3-78033a61a141 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "churn_df"
            }
          },
          "metadata": {},
          "execution_count": 34
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print (\"Rows    :\" ,churn_df.shape[0])\n",
        "print (\"Columns :\" ,churn_df.shape[1])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Oxxa4tXEJbTl",
        "outputId": "acd5dde8-68bf-485b-b2c0-ac95adae31f1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Rows    : 7043\n",
            "Columns : 21\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Convert Categorical data to numerical encoding"
      ],
      "metadata": {
        "id": "djTNPHATJtqm"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.compose import make_column_transformer\n",
        "from sklearn.preprocessing import OrdinalEncoder\n",
        "\n",
        "# for simplicity we use this numerical encoding we can also do the onehotencoding\n",
        "\n",
        "categorical_columns = ['gender', 'Partner', 'Dependents', 'PhoneService', 'MultipleLines', 'InternetService', 'OnlineSecurity', 'OnlineBackup', 'DeviceProtection', 'TechSupport', 'StreamingTV', 'StreamingMovies', 'Contract', 'PaperlessBilling', 'PaymentMethod', 'Churn']\n",
        "column_trans = make_column_transformer((OrdinalEncoder(), categorical_columns))\n",
        "\n",
        "churn_transformed = column_trans.fit_transform(churn_df)\n"
      ],
      "metadata": {
        "id": "J-MVXZs-JykB"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "churn_df_trans = churn_df.copy()\n",
        "churn_df_trans = pd.DataFrame(churn_transformed, columns=categorical_columns)"
      ],
      "metadata": {
        "id": "r2TDKTPULo1U"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "churn_df.update(churn_df_trans)"
      ],
      "metadata": {
        "id": "_ciqkPKaL1S9"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "churn_df"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 600
        },
        "id": "_pnuyIEgL50s",
        "outputId": "fa467271-57ce-4403-a5c9-a1068429f450"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      customerID  gender  SeniorCitizen  Partner  Dependents  tenure  \\\n",
              "0     7590-VHVEG     0.0              0      1.0         0.0       1   \n",
              "1     5575-GNVDE     1.0              0      0.0         0.0      34   \n",
              "2     3668-QPYBK     1.0              0      0.0         0.0       2   \n",
              "3     7795-CFOCW     1.0              0      0.0         0.0      45   \n",
              "4     9237-HQITU     0.0              0      0.0         0.0       2   \n",
              "...          ...     ...            ...      ...         ...     ...   \n",
              "7038  6840-RESVB     1.0              0      1.0         1.0      24   \n",
              "7039  2234-XADUH     0.0              0      1.0         1.0      72   \n",
              "7040  4801-JZAZL     0.0              0      1.0         1.0      11   \n",
              "7041  8361-LTMKD     1.0              1      1.0         0.0       4   \n",
              "7042  3186-AJIEK     1.0              0      0.0         0.0      66   \n",
              "\n",
              "      PhoneService  MultipleLines  InternetService  OnlineSecurity  ...  \\\n",
              "0              0.0            1.0              0.0             0.0  ...   \n",
              "1              1.0            0.0              0.0             2.0  ...   \n",
              "2              1.0            0.0              0.0             2.0  ...   \n",
              "3              0.0            1.0              0.0             2.0  ...   \n",
              "4              1.0            0.0              1.0             0.0  ...   \n",
              "...            ...            ...              ...             ...  ...   \n",
              "7038           1.0            2.0              0.0             2.0  ...   \n",
              "7039           1.0            2.0              1.0             0.0  ...   \n",
              "7040           0.0            1.0              0.0             2.0  ...   \n",
              "7041           1.0            2.0              1.0             0.0  ...   \n",
              "7042           1.0            0.0              1.0             2.0  ...   \n",
              "\n",
              "      DeviceProtection  TechSupport  StreamingTV  StreamingMovies  Contract  \\\n",
              "0                  0.0          0.0          0.0              0.0       0.0   \n",
              "1                  2.0          0.0          0.0              0.0       1.0   \n",
              "2                  0.0          0.0          0.0              0.0       0.0   \n",
              "3                  2.0          2.0          0.0              0.0       1.0   \n",
              "4                  0.0          0.0          0.0              0.0       0.0   \n",
              "...                ...          ...          ...              ...       ...   \n",
              "7038               2.0          2.0          2.0              2.0       1.0   \n",
              "7039               2.0          0.0          2.0              2.0       1.0   \n",
              "7040               0.0          0.0          0.0              0.0       0.0   \n",
              "7041               0.0          0.0          0.0              0.0       0.0   \n",
              "7042               2.0          2.0          2.0              2.0       2.0   \n",
              "\n",
              "      PaperlessBilling  PaymentMethod  MonthlyCharges  TotalCharges Churn  \n",
              "0                  1.0            2.0           29.85         29.85   0.0  \n",
              "1                  0.0            3.0           56.95        1889.5   0.0  \n",
              "2                  1.0            3.0           53.85        108.15   1.0  \n",
              "3                  0.0            0.0           42.30       1840.75   0.0  \n",
              "4                  1.0            2.0           70.70        151.65   1.0  \n",
              "...                ...            ...             ...           ...   ...  \n",
              "7038               1.0            3.0           84.80        1990.5   0.0  \n",
              "7039               1.0            1.0          103.20        7362.9   0.0  \n",
              "7040               1.0            2.0           29.60        346.45   0.0  \n",
              "7041               1.0            3.0           74.40         306.6   1.0  \n",
              "7042               1.0            0.0          105.65        6844.5   0.0  \n",
              "\n",
              "[7043 rows x 21 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-c002bb1c-5dc4-426b-aa27-07b1379d882f\" 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>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>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>Churn</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>7590-VHVEG</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>29.85</td>\n",
              "      <td>29.85</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>5575-GNVDE</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>34</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>...</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>56.95</td>\n",
              "      <td>1889.5</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3668-QPYBK</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>53.85</td>\n",
              "      <td>108.15</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>7795-CFOCW</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>45</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>...</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>42.30</td>\n",
              "      <td>1840.75</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>9237-HQITU</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>70.70</td>\n",
              "      <td>151.65</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7038</th>\n",
              "      <td>6840-RESVB</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>24</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>...</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>84.80</td>\n",
              "      <td>1990.5</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7039</th>\n",
              "      <td>2234-XADUH</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>72</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>103.20</td>\n",
              "      <td>7362.9</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7040</th>\n",
              "      <td>4801-JZAZL</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>11</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>29.60</td>\n",
              "      <td>346.45</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7041</th>\n",
              "      <td>8361-LTMKD</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>4</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>...</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>74.40</td>\n",
              "      <td>306.6</td>\n",
              "      <td>1.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7042</th>\n",
              "      <td>3186-AJIEK</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>66</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>...</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>105.65</td>\n",
              "      <td>6844.5</td>\n",
              "      <td>0.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>7043 rows × 21 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c002bb1c-5dc4-426b-aa27-07b1379d882f')\"\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-c002bb1c-5dc4-426b-aa27-07b1379d882f 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-c002bb1c-5dc4-426b-aa27-07b1379d882f');\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-db2f3886-86fd-43bf-9ad4-4179d03df72c\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-db2f3886-86fd-43bf-9ad4-4179d03df72c')\"\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-db2f3886-86fd-43bf-9ad4-4179d03df72c button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "  <div id=\"id_8abbe4f0-7fef-45b7-8b3f-37d138904dcd\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('churn_df')\"\n",
              "            title=\"Generate code using this dataframe.\"\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",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_8abbe4f0-7fef-45b7-8b3f-37d138904dcd button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('churn_df');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "churn_df"
            }
          },
          "metadata": {},
          "execution_count": 72
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(churn_df.isnull().sum())"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SskDIIufL9Hl",
        "outputId": "fd172455-d293-4d4e-929d-2dd396285fe9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "customerID          0\n",
            "gender              0\n",
            "SeniorCitizen       0\n",
            "Partner             0\n",
            "Dependents          0\n",
            "tenure              0\n",
            "PhoneService        0\n",
            "MultipleLines       0\n",
            "InternetService     0\n",
            "OnlineSecurity      0\n",
            "OnlineBackup        0\n",
            "DeviceProtection    0\n",
            "TechSupport         0\n",
            "StreamingTV         0\n",
            "StreamingMovies     0\n",
            "Contract            0\n",
            "PaperlessBilling    0\n",
            "PaymentMethod       0\n",
            "MonthlyCharges      0\n",
            "TotalCharges        0\n",
            "Churn               0\n",
            "dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Optionally set the new pandas behavior\n",
        "pd.set_option('future.no_silent_downcasting', True)\n",
        "\n",
        "# Replace empty strings with NaN and check missing values\n",
        "missing_values = churn_df.replace(r'^\\s*$', np.nan, regex=True).isna().sum()\n",
        "print(missing_values)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5thQ0fLGM-6y",
        "outputId": "b9a011d0-768b-4884-b821-b04d764943bd"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "customerID          0\n",
            "gender              0\n",
            "SeniorCitizen       0\n",
            "Partner             0\n",
            "Dependents          0\n",
            "tenure              0\n",
            "PhoneService        0\n",
            "MultipleLines       0\n",
            "InternetService     0\n",
            "OnlineSecurity      0\n",
            "OnlineBackup        0\n",
            "DeviceProtection    0\n",
            "TechSupport         0\n",
            "StreamingTV         0\n",
            "StreamingMovies     0\n",
            "Contract            0\n",
            "PaperlessBilling    0\n",
            "PaymentMethod       0\n",
            "MonthlyCharges      0\n",
            "TotalCharges        0\n",
            "Churn               0\n",
            "dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "churn_df = churn_df.replace(r'^\\s*$', np.nan, regex=True)"
      ],
      "metadata": {
        "id": "KefiYkS1Nhzd"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Replace empty strings with NaN and check missing values\n",
        "missing_values = churn_df.replace(r'^\\s*$', np.nan, regex=True).isna().sum()\n",
        "print(missing_values)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CB6-HvVYN5YM",
        "outputId": "d306ee4c-8a56-45f0-cdad-3a63a0bfa4f5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "customerID          0\n",
            "gender              0\n",
            "SeniorCitizen       0\n",
            "Partner             0\n",
            "Dependents          0\n",
            "tenure              0\n",
            "PhoneService        0\n",
            "MultipleLines       0\n",
            "InternetService     0\n",
            "OnlineSecurity      0\n",
            "OnlineBackup        0\n",
            "DeviceProtection    0\n",
            "TechSupport         0\n",
            "StreamingTV         0\n",
            "StreamingMovies     0\n",
            "Contract            0\n",
            "PaperlessBilling    0\n",
            "PaymentMethod       0\n",
            "MonthlyCharges      0\n",
            "TotalCharges        0\n",
            "Churn               0\n",
            "dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(churn_df.dtypes)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yQnWKrpzOB9k",
        "outputId": "9132f47d-395e-43c7-da6f-640e99572075"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "customerID           object\n",
            "gender              float64\n",
            "SeniorCitizen         int64\n",
            "Partner             float64\n",
            "Dependents          float64\n",
            "tenure                int64\n",
            "PhoneService        float64\n",
            "MultipleLines       float64\n",
            "InternetService     float64\n",
            "OnlineSecurity      float64\n",
            "OnlineBackup        float64\n",
            "DeviceProtection    float64\n",
            "TechSupport         float64\n",
            "StreamingTV         float64\n",
            "StreamingMovies     float64\n",
            "Contract            float64\n",
            "PaperlessBilling    float64\n",
            "PaymentMethod       float64\n",
            "MonthlyCharges      float64\n",
            "TotalCharges        float64\n",
            "Churn               float64\n",
            "dtype: object\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Converting TotalCharges from object to numeric"
      ],
      "metadata": {
        "id": "9alPVx8VOzRJ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "churn_df.iloc[:, 19] = pd.to_numeric(churn_df.iloc[:, 19], errors='coerce')"
      ],
      "metadata": {
        "id": "-E5fDg15OJ0N"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.impute import SimpleImputer\n",
        "imp_median = SimpleImputer(missing_values=np.nan, strategy='median')"
      ],
      "metadata": {
        "id": "PXLx6A_lOX-f"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "churn_df.iloc[:, 19] = imp_median.fit_transform(churn_df.iloc[:, 19].values.reshape(-1, 1))"
      ],
      "metadata": {
        "id": "lGsXitLIOhcz"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Replace empty strings with NaN and check missing values\n",
        "missing_values = churn_df.replace(r'^\\s*$', np.nan, regex=True).isna().sum()\n",
        "print(missing_values)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YOX4Pyd0OnM-",
        "outputId": "77263636-c3eb-4064-d67c-88f74093658a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "customerID          0\n",
            "gender              0\n",
            "SeniorCitizen       0\n",
            "Partner             0\n",
            "Dependents          0\n",
            "tenure              0\n",
            "PhoneService        0\n",
            "MultipleLines       0\n",
            "InternetService     0\n",
            "OnlineSecurity      0\n",
            "OnlineBackup        0\n",
            "DeviceProtection    0\n",
            "TechSupport         0\n",
            "StreamingTV         0\n",
            "StreamingMovies     0\n",
            "Contract            0\n",
            "PaperlessBilling    0\n",
            "PaymentMethod       0\n",
            "MonthlyCharges      0\n",
            "TotalCharges        0\n",
            "Churn               0\n",
            "dtype: int64\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(churn_df.dtypes)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "IFtpNr7QO9Eh",
        "outputId": "a90e5de7-f5f0-4f86-87a0-f40e3b0d2eea"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "customerID           object\n",
            "gender              float64\n",
            "SeniorCitizen         int64\n",
            "Partner             float64\n",
            "Dependents          float64\n",
            "tenure                int64\n",
            "PhoneService        float64\n",
            "MultipleLines       float64\n",
            "InternetService     float64\n",
            "OnlineSecurity      float64\n",
            "OnlineBackup        float64\n",
            "DeviceProtection    float64\n",
            "TechSupport         float64\n",
            "StreamingTV         float64\n",
            "StreamingMovies     float64\n",
            "Contract            float64\n",
            "PaperlessBilling    float64\n",
            "PaymentMethod       float64\n",
            "MonthlyCharges      float64\n",
            "TotalCharges        float64\n",
            "Churn               float64\n",
            "dtype: object\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "churn_df_X = churn_df.drop(\"Churn\", axis=1)\n",
        "churn_df_X = churn_df_X.drop(\"customerID\", axis=1)\n",
        "churn_df_y = churn_df[\"Churn\"]"
      ],
      "metadata": {
        "id": "5bej843bRQP6"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_train, X_test, y_train, y_test = train_test_split(churn_df_X, churn_df_y, train_size=0.75, test_size=0.25)"
      ],
      "metadata": {
        "id": "5G8snBADYLvD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X_train"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 444
        },
        "id": "cVnDis7TYrxI",
        "outputId": "dd80e917-6b7b-40f7-9d98-85aaa386775c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      gender  SeniorCitizen  Partner  Dependents  tenure  PhoneService  \\\n",
              "3579     1.0              0      1.0         1.0      40           1.0   \n",
              "3102     0.0              0      0.0         0.0       5           1.0   \n",
              "1898     0.0              1      0.0         0.0       5           1.0   \n",
              "1438     0.0              0      0.0         0.0      40           1.0   \n",
              "6065     1.0              0      0.0         0.0      59           1.0   \n",
              "...      ...            ...      ...         ...     ...           ...   \n",
              "659      1.0              0      1.0         0.0      37           1.0   \n",
              "3144     1.0              0      0.0         0.0       6           1.0   \n",
              "3407     0.0              1      1.0         0.0      67           1.0   \n",
              "2428     1.0              0      0.0         1.0      38           1.0   \n",
              "255      0.0              0      1.0         1.0      67           0.0   \n",
              "\n",
              "      MultipleLines  InternetService  OnlineSecurity  OnlineBackup  \\\n",
              "3579            2.0              1.0             0.0           0.0   \n",
              "3102            0.0              0.0             2.0           0.0   \n",
              "1898            0.0              1.0             0.0           0.0   \n",
              "1438            0.0              0.0             0.0           0.0   \n",
              "6065            2.0              2.0             1.0           1.0   \n",
              "...             ...              ...             ...           ...   \n",
              "659             0.0              2.0             1.0           1.0   \n",
              "3144            0.0              2.0             1.0           1.0   \n",
              "3407            0.0              2.0             1.0           1.0   \n",
              "2428            2.0              1.0             0.0           0.0   \n",
              "255             1.0              0.0             0.0           2.0   \n",
              "\n",
              "      DeviceProtection  TechSupport  StreamingTV  StreamingMovies  Contract  \\\n",
              "3579               2.0          0.0          0.0              0.0       0.0   \n",
              "3102               0.0          2.0          0.0              0.0       0.0   \n",
              "1898               0.0          0.0          0.0              2.0       0.0   \n",
              "1438               2.0          0.0          0.0              0.0       1.0   \n",
              "6065               1.0          1.0          1.0              1.0       2.0   \n",
              "...                ...          ...          ...              ...       ...   \n",
              "659                1.0          1.0          1.0              1.0       0.0   \n",
              "3144               1.0          1.0          1.0              1.0       0.0   \n",
              "3407               1.0          1.0          1.0              1.0       2.0   \n",
              "2428               2.0          0.0          2.0              2.0       0.0   \n",
              "255                2.0          2.0          2.0              2.0       2.0   \n",
              "\n",
              "      PaperlessBilling  PaymentMethod  MonthlyCharges  TotalCharges  \n",
              "3579               1.0            2.0           81.20       3292.30  \n",
              "3102               0.0            2.0           54.20        308.25  \n",
              "1898               0.0            2.0           78.95        378.40  \n",
              "1438               1.0            3.0           50.25       2023.55  \n",
              "6065               0.0            3.0           25.00       1510.50  \n",
              "...                ...            ...             ...           ...  \n",
              "659                0.0            0.0           20.35        697.65  \n",
              "3144               0.0            3.0           18.95        110.15  \n",
              "3407               1.0            0.0           20.05       1263.05  \n",
              "2428               1.0            0.0           99.25       3777.15  \n",
              "255                1.0            2.0           59.55       4103.90  \n",
              "\n",
              "[5282 rows x 19 columns]"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-13202bfe-2364-41a7-b239-eec5608ef6bf\" 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>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",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>3579</th>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>40</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>81.20</td>\n",
              "      <td>3292.30</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3102</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>5</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>54.20</td>\n",
              "      <td>308.25</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1898</th>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>5</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>78.95</td>\n",
              "      <td>378.40</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1438</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>40</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>50.25</td>\n",
              "      <td>2023.55</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6065</th>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>59</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>25.00</td>\n",
              "      <td>1510.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>659</th>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>37</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>20.35</td>\n",
              "      <td>697.65</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3144</th>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>6</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>3.0</td>\n",
              "      <td>18.95</td>\n",
              "      <td>110.15</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3407</th>\n",
              "      <td>0.0</td>\n",
              "      <td>1</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>67</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>20.05</td>\n",
              "      <td>1263.05</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2428</th>\n",
              "      <td>1.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>38</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>99.25</td>\n",
              "      <td>3777.15</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>255</th>\n",
              "      <td>0.0</td>\n",
              "      <td>0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>67</td>\n",
              "      <td>0.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>0.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>1.0</td>\n",
              "      <td>2.0</td>\n",
              "      <td>59.55</td>\n",
              "      <td>4103.90</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>5282 rows × 19 columns</p>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-13202bfe-2364-41a7-b239-eec5608ef6bf')\"\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-13202bfe-2364-41a7-b239-eec5608ef6bf 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-13202bfe-2364-41a7-b239-eec5608ef6bf');\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-9729ecba-73cc-4595-8c7e-f952024718a2\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-9729ecba-73cc-4595-8c7e-f952024718a2')\"\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-9729ecba-73cc-4595-8c7e-f952024718a2 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "  <div id=\"id_c8d08d37-3f84-41bb-9520-c311eafeccb5\">\n",
              "    <style>\n",
              "      .colab-df-generate {\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-generate: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",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate: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",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('X_train')\"\n",
              "            title=\"Generate code using this dataframe.\"\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",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_c8d08d37-3f84-41bb-9520-c311eafeccb5 button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('X_train');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "X_train",
              "summary": "{\n  \"name\": \"X_train\",\n  \"rows\": 5282,\n  \"fields\": [\n    {\n      \"column\": \"gender\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.5000369775905428,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.0,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"SeniorCitizen\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0,\n        \"min\": 0,\n        \"max\": 1,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          1,\n          0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Partner\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.49971686858897635,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.0,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Dependents\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.45733611249074957,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.0,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"tenure\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 24,\n        \"min\": 0,\n        \"max\": 72,\n        \"num_unique_values\": 73,\n        \"samples\": [\n          67,\n          47\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"PhoneService\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.29563638024837124,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.0,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MultipleLines\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.9488453834436961,\n        \"min\": 0.0,\n        \"max\": 2.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          2.0,\n          0.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"InternetService\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.737080170220392,\n        \"min\": 0.0,\n        \"max\": 2.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          1.0,\n          0.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"OnlineSecurity\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8630054268682659,\n        \"min\": 0.0,\n        \"max\": 2.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0.0,\n          2.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"OnlineBackup\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.881376752916721,\n        \"min\": 0.0,\n        \"max\": 2.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0.0,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"DeviceProtection\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8829795851151968,\n        \"min\": 0.0,\n        \"max\": 2.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          2.0,\n          0.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"TechSupport\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8632738199614802,\n        \"min\": 0.0,\n        \"max\": 2.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0.0,\n          2.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"StreamingTV\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8866824109769142,\n        \"min\": 0.0,\n        \"max\": 2.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0.0,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"StreamingMovies\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8868997428290419,\n        \"min\": 0.0,\n        \"max\": 2.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0.0,\n          2.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Contract\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.8317676388331018,\n        \"min\": 0.0,\n        \"max\": 2.0,\n        \"num_unique_values\": 3,\n        \"samples\": [\n          0.0,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"PaperlessBilling\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.49213351486657625,\n        \"min\": 0.0,\n        \"max\": 1.0,\n        \"num_unique_values\": 2,\n        \"samples\": [\n          0.0,\n          1.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"PaymentMethod\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1.0624562011851393,\n        \"min\": 0.0,\n        \"max\": 3.0,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          3.0,\n          0.0\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"MonthlyCharges\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 29.997760063782863,\n        \"min\": 18.4,\n        \"max\": 118.75,\n        \"num_unique_values\": 1474,\n        \"samples\": [\n          61.2,\n          89.05\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"TotalCharges\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 2269.632252444759,\n        \"min\": 18.85,\n        \"max\": 8684.8,\n        \"num_unique_values\": 4965,\n        \"samples\": [\n          413.25,\n          1837.7\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 86
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "**Use TPOT Classifier to find the best model algorithm that fits the data. TPOT uses genetic algorithm based seac=rch internally**"
      ],
      "metadata": {
        "id": "1__MpXheZAIs"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# All AutoMl codes are very compute intensive so u just need to distribute the processing i.e. use multiple course from your CPU\n",
        "tpot = TPOTClassifier(generations=4, population_size=10, verbosity=3)\n",
        "tpot.fit(X_train, y_train)\n",
        "print(tpot.score(X_test, y_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402,
          "referenced_widgets": [
            "e6405703dcaa4151851b40660a7efcd7",
            "47f7bcf548e247f4b387050d8a85142e",
            "2f5ffa424a5b442e993b0e55e730454e",
            "73459d1c0b6149f0b95db8c356ce70ce",
            "79e593d920df4eaf8400aa2abf56dde8",
            "372906a8759c4f7ba808a134fdd9871d",
            "4a38fa47caac42678f38616fcfa8be9e",
            "88a63cb70bd44cc29a8b06d12e800bff",
            "76264489d7cc497d8622d11cc0d0924c",
            "870301a53319460ba4a3ccbdcba53be3",
            "a6a7c3ef7ca94271b5c3c3cb35b3038b"
          ]
        },
        "id": "e6rFwCwQY--A",
        "outputId": "177096e4-4938-4929-812f-1d4554f370b4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "32 operators have been imported by TPOT.\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Optimization Progress:   0%|          | 0/50 [00:00<?, ?pipeline/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "e6405703dcaa4151851b40660a7efcd7"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Generation 1 - Current Pareto front scores:\n",
            "\n",
            "-1\t0.7974285785957972\tXGBClassifier(input_matrix, XGBClassifier__learning_rate=0.1, XGBClassifier__max_depth=8, XGBClassifier__min_child_weight=15, XGBClassifier__n_estimators=100, XGBClassifier__n_jobs=1, XGBClassifier__subsample=0.9500000000000001, XGBClassifier__verbosity=0)\n",
            "\n",
            "Generation 2 - Current Pareto front scores:\n",
            "\n",
            "-1\t0.804242997620481\tXGBClassifier(input_matrix, XGBClassifier__learning_rate=0.1, XGBClassifier__max_depth=2, XGBClassifier__min_child_weight=10, XGBClassifier__n_estimators=100, XGBClassifier__n_jobs=1, XGBClassifier__subsample=0.4, XGBClassifier__verbosity=0)\n",
            "Pipeline encountered that has previously been evaluated during the optimization process. Using the score from the previous evaluation.\n",
            "\n",
            "Generation 3 - Current Pareto front scores:\n",
            "\n",
            "-1\t0.804242997620481\tXGBClassifier(input_matrix, XGBClassifier__learning_rate=0.1, XGBClassifier__max_depth=2, XGBClassifier__min_child_weight=10, XGBClassifier__n_estimators=100, XGBClassifier__n_jobs=1, XGBClassifier__subsample=0.4, XGBClassifier__verbosity=0)\n",
            "_pre_test decorator: _random_mutation_operator: num_test=0 Unsupported set of arguments: The combination of penalty='l1' and loss='hinge' is not supported, Parameters: penalty='l1', loss='hinge', dual=False.\n",
            "Pipeline encountered that has previously been evaluated during the optimization process. Using the score from the previous evaluation.\n",
            "\n",
            "Generation 4 - Current Pareto front scores:\n",
            "\n",
            "-1\t0.8046214271379835\tXGBClassifier(input_matrix, XGBClassifier__learning_rate=0.1, XGBClassifier__max_depth=2, XGBClassifier__min_child_weight=19, XGBClassifier__n_estimators=100, XGBClassifier__n_jobs=1, XGBClassifier__subsample=0.4, XGBClassifier__verbosity=0)\n",
            "0.807495741056218\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import multiprocessing\n",
        "\n",
        "if __name__ == '__main__':\n",
        "    multiprocessing.set_start_method('forkserver', force=True)\n",
        "    #n_jobs running n_jobs in parallel limited to number of course available in your system\n",
        "    tpot = TPOTClassifier(generations=2, population_size=20, verbosity=2, n_jobs=20, random_state=50)\n",
        "    tpot.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 141,
          "referenced_widgets": [
            "4d76f15f49674f178dfe6728d48f52b1",
            "5701480c7a334294af22961ee35171a5",
            "017c150f16cf4a88a15c467a2f7ad159",
            "e99e52b03b0f4d01b341746be5b20f72",
            "a4ee7fc3d6ce45a7a48c281462cdd346",
            "4edb480ce2e248c7a585876689d4ed99",
            "3f96e43a75044298a1ce9064fed894f0",
            "c57e7614f03047929356a2a035e6cd22",
            "cb855bee0d3e438fa726f0be22ea4136",
            "a1925e061ad04fbcbc170d3338c1974c",
            "a471e85a4a84439d82058dfc9daa936f"
          ]
        },
        "id": "E0dtLWIrZofB",
        "outputId": "51988aa4-0167-4c4c-e604-9fc0683bf62c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Optimization Progress:   0%|          | 0/60 [00:00<?, ?pipeline/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "4d76f15f49674f178dfe6728d48f52b1"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Generation 1 - Current best internal CV score: 0.8034843467790488\n",
            "\n",
            "Generation 2 - Current best internal CV score: 0.8038625971159084\n",
            "\n",
            "Best pipeline: ExtraTreesClassifier(ZeroCount(input_matrix), bootstrap=True, criterion=gini, max_features=0.55, min_samples_leaf=17, min_samples_split=11, n_estimators=100)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(tpot.score(X_test, y_test))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5dQ05kOsZ_RN",
        "outputId": "c771cfcf-53cb-49cb-e730-c994bb282cb4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.7995457126632595\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Model is not overfitting or something over here our test accuracy is higher than the cross validation accuracy"
      ],
      "metadata": {
        "id": "sFxFlQGM82F-"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "Export the scikit learn code for the best classifier and display the code"
      ],
      "metadata": {
        "id": "F60zZ4dTaG4H"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "tpot.export('tpot_churn_pipeline.py')"
      ],
      "metadata": {
        "id": "P_OKjjTuaGkJ"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!cat tpot_churn_pipeline.py"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "W81AqGeXaSvy",
        "outputId": "50bc9a19-e5b6-465c-8266-259501196492"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "import numpy as np\n",
            "import pandas as pd\n",
            "from sklearn.ensemble import ExtraTreesClassifier\n",
            "from sklearn.model_selection import train_test_split\n",
            "from sklearn.pipeline import make_pipeline\n",
            "from tpot.builtins import ZeroCount\n",
            "from tpot.export_utils import set_param_recursive\n",
            "\n",
            "# NOTE: Make sure that the outcome column is labeled 'target' in the data file\n",
            "tpot_data = pd.read_csv('PATH/TO/DATA/FILE', sep='COLUMN_SEPARATOR', dtype=np.float64)\n",
            "features = tpot_data.drop('target', axis=1)\n",
            "training_features, testing_features, training_target, testing_target = \\\n",
            "            train_test_split(features, tpot_data['target'], random_state=50)\n",
            "\n",
            "# Average CV score on the training set was: 0.8038625971159084\n",
            "exported_pipeline = make_pipeline(\n",
            "    ZeroCount(),\n",
            "    ExtraTreesClassifier(bootstrap=True, criterion=\"gini\", max_features=0.55, min_samples_leaf=17, min_samples_split=11, n_estimators=100)\n",
            ")\n",
            "# Fix random state for all the steps in exported pipeline\n",
            "set_param_recursive(exported_pipeline.steps, 'random_state', 50)\n",
            "\n",
            "exported_pipeline.fit(training_features, training_target)\n",
            "results = exported_pipeline.predict(testing_features)\n"
          ]
        }
      ]
    }
  ]
}