317_HyperParameter_Optimization_using_Genetic_algo.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "mount_file_id": "1AiOSIITKkWuxSSky6HqVYoU_NTH-wjff",
      "authorship_tag": "ABX9TyO4eKPyy/BD+V0RsNCks3mp",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "18e24619c11547e1903bdd4af0043dc7": {
          "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_eac1c64c75b24ee3b0bbc527b2a37e6e",
              "IPY_MODEL_b632233cc04c4cdb88ebacbaf1acbfbd",
              "IPY_MODEL_bb57f28ea99744a082e26e4e5ec423e2"
            ],
            "layout": "IPY_MODEL_40c1aff694a3440cb8a3a0998b2e0a6c"
          }
        },
        "eac1c64c75b24ee3b0bbc527b2a37e6e": {
          "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_510f9569fd6a46aaa261dc98558a412b",
            "placeholder": "​",
            "style": "IPY_MODEL_02629a9b139c4bf68b1b082ef9157291",
            "value": "Optimization Progress: 100%"
          }
        },
        "b632233cc04c4cdb88ebacbaf1acbfbd": {
          "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_17c5a2da79fd43c8aa53fc8dabf85935",
            "max": 170,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_64c36379573d469abf0f8e8a0356ab8f",
            "value": 170
          }
        },
        "bb57f28ea99744a082e26e4e5ec423e2": {
          "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_f2b0b456f6824b14986653b387bf94cb",
            "placeholder": "​",
            "style": "IPY_MODEL_b2386ab6f81f4e8c90f0e4fa1a78a61d",
            "value": " 170/170 [03:00&lt;00:00,  1.21s/pipeline]"
          }
        },
        "40c1aff694a3440cb8a3a0998b2e0a6c": {
          "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
          }
        },
        "510f9569fd6a46aaa261dc98558a412b": {
          "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
          }
        },
        "02629a9b139c4bf68b1b082ef9157291": {
          "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": ""
          }
        },
        "17c5a2da79fd43c8aa53fc8dabf85935": {
          "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
          }
        },
        "64c36379573d469abf0f8e8a0356ab8f": {
          "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": ""
          }
        },
        "f2b0b456f6824b14986653b387bf94cb": {
          "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
          }
        },
        "b2386ab6f81f4e8c90f0e4fa1a78a61d": {
          "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": ""
          }
        },
        "1a4140529ccb4134824bd8f039545b7f": {
          "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_ee3c07b7317a4ce3bec934c5645cce1a",
              "IPY_MODEL_8bf7f582202543e4bb6e2617df51c61b",
              "IPY_MODEL_ca4bbc4f05d94662bbd091f47aeb1bc9"
            ],
            "layout": "IPY_MODEL_6ec8a7db46b94a4392132dca65729e34"
          }
        },
        "ee3c07b7317a4ce3bec934c5645cce1a": {
          "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_722a5199b5674933b6d79f51ff4b52eb",
            "placeholder": "​",
            "style": "IPY_MODEL_6402ead328a84d55aa803dfd5e1b5318",
            "value": "Optimization Progress: 100%"
          }
        },
        "8bf7f582202543e4bb6e2617df51c61b": {
          "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_2302a9617e174e448c962b7323e9a375",
            "max": 300,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_23bb2ccfec2c4a2fa7ed5683d9635347",
            "value": 300
          }
        },
        "ca4bbc4f05d94662bbd091f47aeb1bc9": {
          "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_13dc18150d64424fb9699f23ac7250df",
            "placeholder": "​",
            "style": "IPY_MODEL_60eaddb7878f4c7482bfb3712d2681d2",
            "value": " 300/300 [14:56&lt;00:00,  2.78s/pipeline]"
          }
        },
        "6ec8a7db46b94a4392132dca65729e34": {
          "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
          }
        },
        "722a5199b5674933b6d79f51ff4b52eb": {
          "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
          }
        },
        "6402ead328a84d55aa803dfd5e1b5318": {
          "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": ""
          }
        },
        "2302a9617e174e448c962b7323e9a375": {
          "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
          }
        },
        "23bb2ccfec2c4a2fa7ed5683d9635347": {
          "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": ""
          }
        },
        "13dc18150d64424fb9699f23ac7250df": {
          "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
          }
        },
        "60eaddb7878f4c7482bfb3712d2681d2": {
          "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",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/bnsreenu/python_for_microscopists/blob/master/317_HyperParameter_Optimization_using_Genetic_algo.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "https://youtu.be/51sdLTNP1O8"
      ],
      "metadata": {
        "id": "tfC4F8376QBn"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        " **Hyperparameter optimization using Metaheuristic algorithms\n",
        "<br> such as the Genetic Algorithm <p>**\n",
        "\n",
        "In this example, we will use the same dataset (steel alloy strength) from the previous tutorial to fit and tune Random Forest Regressor. <br>\n",
        "The dataset can be downloaded from here: https://www.kaggle.com/datasets/fuarresvij/steel-test-data\n",
        "\n",
        "<p>\n",
        "The data set contains the elemental composition of different alloys and their respective yield and tensile strengths. A machine learning model can be trained on this data, allowing us to predict the strength of an alloy based on its chemical composition.\n"
      ],
      "metadata": {
        "id": "lMJa1wzQyU9T"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "ZqQG-mqqEPss"
      },
      "outputs": [],
      "source": [
        "#Read the csv file and capture data into a pandas dataframe\n",
        "import pandas as pd\n",
        "\n",
        "df = pd.read_csv(\"/content/drive/MyDrive/ColabNotebooks/data/steel_strength.csv\")"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Understand the data"
      ],
      "metadata": {
        "id": "ZovODOV2JNtq"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df.head()"
      ],
      "metadata": {
        "id": "t-m3yy0SE8o-",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 287
        },
        "outputId": "9ae5d1b8-31c2-476b-c221-30461d833c21"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                             formula     c    mn    si     cr  \\\n",
              "0  Fe0.620C0.000953Mn0.000521Si0.00102Cr0.000110N...  0.02  0.05  0.05   0.01   \n",
              "1  Fe0.623C0.00854Mn0.000104Si0.000203Cr0.147Ni0....  0.18  0.01  0.01  13.44   \n",
              "2  Fe0.625Mn0.000102Si0.000200Cr0.0936Ni0.129Mo0....  0.00  0.01  0.01   8.67   \n",
              "3  Fe0.634C0.000478Mn0.000523Si0.00102Cr0.000111N...  0.01  0.05  0.05   0.01   \n",
              "4  Fe0.636C0.000474Mn0.000518Si0.00101Cr0.000109N...  0.01  0.05  0.05   0.01   \n",
              "\n",
              "      ni    mo     v     n    nb     co     w    al    ti  yield strength  \\\n",
              "0  19.70  2.95  0.01  0.00  0.01  15.00  0.00  0.15  1.55          2411.5   \n",
              "1   0.01  3.01  0.46  0.04  0.01  19.46  2.35  0.04  0.00          1123.1   \n",
              "2  13.45  0.82  0.01  0.00  0.01  13.90  0.00  0.39  0.57          1736.3   \n",
              "3  17.70  3.95  0.01  0.00  0.01  15.00  0.00  0.13  1.47          2487.3   \n",
              "4  19.40  1.45  0.01  0.00  0.01  14.90  0.00  0.13  1.55          2249.6   \n",
              "\n",
              "   tensile strength  elongation  \n",
              "0            2473.5         7.0  \n",
              "1            1929.2         8.0  \n",
              "2            1871.8         NaN  \n",
              "3            2514.9         9.0  \n",
              "4            2315.0         8.5  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-dafadc32-9371-4039-a10b-035dbd1381dd\">\n",
              "    <div 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>formula</th>\n",
              "      <th>c</th>\n",
              "      <th>mn</th>\n",
              "      <th>si</th>\n",
              "      <th>cr</th>\n",
              "      <th>ni</th>\n",
              "      <th>mo</th>\n",
              "      <th>v</th>\n",
              "      <th>n</th>\n",
              "      <th>nb</th>\n",
              "      <th>co</th>\n",
              "      <th>w</th>\n",
              "      <th>al</th>\n",
              "      <th>ti</th>\n",
              "      <th>yield strength</th>\n",
              "      <th>tensile strength</th>\n",
              "      <th>elongation</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Fe0.620C0.000953Mn0.000521Si0.00102Cr0.000110N...</td>\n",
              "      <td>0.02</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.01</td>\n",
              "      <td>19.70</td>\n",
              "      <td>2.95</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>15.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.15</td>\n",
              "      <td>1.55</td>\n",
              "      <td>2411.5</td>\n",
              "      <td>2473.5</td>\n",
              "      <td>7.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Fe0.623C0.00854Mn0.000104Si0.000203Cr0.147Ni0....</td>\n",
              "      <td>0.18</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.01</td>\n",
              "      <td>13.44</td>\n",
              "      <td>0.01</td>\n",
              "      <td>3.01</td>\n",
              "      <td>0.46</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.01</td>\n",
              "      <td>19.46</td>\n",
              "      <td>2.35</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.00</td>\n",
              "      <td>1123.1</td>\n",
              "      <td>1929.2</td>\n",
              "      <td>8.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Fe0.625Mn0.000102Si0.000200Cr0.0936Ni0.129Mo0....</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.01</td>\n",
              "      <td>8.67</td>\n",
              "      <td>13.45</td>\n",
              "      <td>0.82</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>13.90</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.39</td>\n",
              "      <td>0.57</td>\n",
              "      <td>1736.3</td>\n",
              "      <td>1871.8</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Fe0.634C0.000478Mn0.000523Si0.00102Cr0.000111N...</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.01</td>\n",
              "      <td>17.70</td>\n",
              "      <td>3.95</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>15.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.13</td>\n",
              "      <td>1.47</td>\n",
              "      <td>2487.3</td>\n",
              "      <td>2514.9</td>\n",
              "      <td>9.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Fe0.636C0.000474Mn0.000518Si0.00101Cr0.000109N...</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.01</td>\n",
              "      <td>19.40</td>\n",
              "      <td>1.45</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>14.90</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.13</td>\n",
              "      <td>1.55</td>\n",
              "      <td>2249.6</td>\n",
              "      <td>2315.0</td>\n",
              "      <td>8.5</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-dafadc32-9371-4039-a10b-035dbd1381dd')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-dafadc32-9371-4039-a10b-035dbd1381dd 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-dafadc32-9371-4039-a10b-035dbd1381dd');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Check if there is any null data. There are a few missing from the elongation column but we will not use it for our exercise.\n",
        "df.isna().sum()"
      ],
      "metadata": {
        "id": "VVsnHGifPDMF",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "9786513d-25ed-47c2-c978-a2819054ca88"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "formula             0\n",
              "c                   0\n",
              "mn                  0\n",
              "si                  0\n",
              "cr                  0\n",
              "ni                  0\n",
              "mo                  0\n",
              "v                   0\n",
              "n                   0\n",
              "nb                  0\n",
              "co                  0\n",
              "w                   0\n",
              "al                  0\n",
              "ti                  0\n",
              "yield strength      0\n",
              "tensile strength    0\n",
              "elongation          9\n",
              "dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df.describe().T"
      ],
      "metadata": {
        "id": "ZtCxafObPI40",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 551
        },
        "outputId": "28d25286-f487-4731-91a7-bd7217432cd0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                  count         mean         std      min       25%       50%  \\\n",
              "c                 312.0     0.096442    0.109008     0.00     0.010     0.030   \n",
              "mn                312.0     0.146250    0.397102     0.01     0.010     0.010   \n",
              "si                312.0     0.221218    0.580796     0.01     0.010     0.010   \n",
              "cr                312.0     8.043830    5.426169     0.01     3.100     9.050   \n",
              "ni                312.0     8.184006    6.337055     0.01     0.960     8.500   \n",
              "mo                312.0     2.766090    1.832908     0.02     1.500     2.210   \n",
              "v                 312.0     0.183750    0.452462     0.00     0.010     0.010   \n",
              "n                 312.0     0.005545    0.018331     0.00     0.000     0.000   \n",
              "nb                312.0     0.035449    0.161537     0.00     0.010     0.010   \n",
              "co                312.0     7.008782    6.254431     0.01     0.010     7.085   \n",
              "w                 312.0     0.161282    0.920211     0.00     0.000     0.000   \n",
              "al                312.0     0.239135    0.340110     0.01     0.030     0.050   \n",
              "ti                312.0     0.310897    0.556593     0.00     0.000     0.030   \n",
              "yield strength    312.0  1420.998397  301.894169  1005.90  1219.475  1344.200   \n",
              "tensile strength  312.0  1641.653205  346.475179  1019.00  1338.125  1666.300   \n",
              "elongation        303.0    14.007261    5.095974     2.00    10.800    14.800   \n",
              "\n",
              "                        75%      max  \n",
              "c                    0.1825     0.43  \n",
              "mn                   0.0800     3.00  \n",
              "si                   0.1100     4.75  \n",
              "cr                  12.5200    17.50  \n",
              "ni                  12.1175    21.00  \n",
              "mo                   4.0900     9.67  \n",
              "v                    0.1275     4.32  \n",
              "n                    0.0000     0.15  \n",
              "nb                   0.0100     2.50  \n",
              "co                  13.4800    20.10  \n",
              "w                    0.0000     9.18  \n",
              "al                   0.3000     1.80  \n",
              "ti                   0.2325     2.50  \n",
              "yield strength    1576.0750  2510.30  \n",
              "tensile strength  1899.9500  2570.00  \n",
              "elongation          17.3000    35.00  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-edd23ffb-067c-457a-96cb-d1be84654d1c\">\n",
              "    <div 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>count</th>\n",
              "      <th>mean</th>\n",
              "      <th>std</th>\n",
              "      <th>min</th>\n",
              "      <th>25%</th>\n",
              "      <th>50%</th>\n",
              "      <th>75%</th>\n",
              "      <th>max</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>c</th>\n",
              "      <td>312.0</td>\n",
              "      <td>0.096442</td>\n",
              "      <td>0.109008</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.030</td>\n",
              "      <td>0.1825</td>\n",
              "      <td>0.43</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mn</th>\n",
              "      <td>312.0</td>\n",
              "      <td>0.146250</td>\n",
              "      <td>0.397102</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.0800</td>\n",
              "      <td>3.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>si</th>\n",
              "      <td>312.0</td>\n",
              "      <td>0.221218</td>\n",
              "      <td>0.580796</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.1100</td>\n",
              "      <td>4.75</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>cr</th>\n",
              "      <td>312.0</td>\n",
              "      <td>8.043830</td>\n",
              "      <td>5.426169</td>\n",
              "      <td>0.01</td>\n",
              "      <td>3.100</td>\n",
              "      <td>9.050</td>\n",
              "      <td>12.5200</td>\n",
              "      <td>17.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ni</th>\n",
              "      <td>312.0</td>\n",
              "      <td>8.184006</td>\n",
              "      <td>6.337055</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.960</td>\n",
              "      <td>8.500</td>\n",
              "      <td>12.1175</td>\n",
              "      <td>21.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>mo</th>\n",
              "      <td>312.0</td>\n",
              "      <td>2.766090</td>\n",
              "      <td>1.832908</td>\n",
              "      <td>0.02</td>\n",
              "      <td>1.500</td>\n",
              "      <td>2.210</td>\n",
              "      <td>4.0900</td>\n",
              "      <td>9.67</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>v</th>\n",
              "      <td>312.0</td>\n",
              "      <td>0.183750</td>\n",
              "      <td>0.452462</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.1275</td>\n",
              "      <td>4.32</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>n</th>\n",
              "      <td>312.0</td>\n",
              "      <td>0.005545</td>\n",
              "      <td>0.018331</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.15</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>nb</th>\n",
              "      <td>312.0</td>\n",
              "      <td>0.035449</td>\n",
              "      <td>0.161537</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.010</td>\n",
              "      <td>0.0100</td>\n",
              "      <td>2.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>co</th>\n",
              "      <td>312.0</td>\n",
              "      <td>7.008782</td>\n",
              "      <td>6.254431</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.010</td>\n",
              "      <td>7.085</td>\n",
              "      <td>13.4800</td>\n",
              "      <td>20.10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>w</th>\n",
              "      <td>312.0</td>\n",
              "      <td>0.161282</td>\n",
              "      <td>0.920211</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>9.18</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>al</th>\n",
              "      <td>312.0</td>\n",
              "      <td>0.239135</td>\n",
              "      <td>0.340110</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.030</td>\n",
              "      <td>0.050</td>\n",
              "      <td>0.3000</td>\n",
              "      <td>1.80</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ti</th>\n",
              "      <td>312.0</td>\n",
              "      <td>0.310897</td>\n",
              "      <td>0.556593</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.000</td>\n",
              "      <td>0.030</td>\n",
              "      <td>0.2325</td>\n",
              "      <td>2.50</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>yield strength</th>\n",
              "      <td>312.0</td>\n",
              "      <td>1420.998397</td>\n",
              "      <td>301.894169</td>\n",
              "      <td>1005.90</td>\n",
              "      <td>1219.475</td>\n",
              "      <td>1344.200</td>\n",
              "      <td>1576.0750</td>\n",
              "      <td>2510.30</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>tensile strength</th>\n",
              "      <td>312.0</td>\n",
              "      <td>1641.653205</td>\n",
              "      <td>346.475179</td>\n",
              "      <td>1019.00</td>\n",
              "      <td>1338.125</td>\n",
              "      <td>1666.300</td>\n",
              "      <td>1899.9500</td>\n",
              "      <td>2570.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>elongation</th>\n",
              "      <td>303.0</td>\n",
              "      <td>14.007261</td>\n",
              "      <td>5.095974</td>\n",
              "      <td>2.00</td>\n",
              "      <td>10.800</td>\n",
              "      <td>14.800</td>\n",
              "      <td>17.3000</td>\n",
              "      <td>35.00</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-edd23ffb-067c-457a-96cb-d1be84654d1c')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-edd23ffb-067c-457a-96cb-d1be84654d1c 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-edd23ffb-067c-457a-96cb-d1be84654d1c');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Assign all chemical composition columns to X"
      ],
      "metadata": {
        "id": "98zDAROAJc0s"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "X = df.drop(columns=[\"formula\", \"elongation\", \"tensile strength\", \"yield strength\"])"
      ],
      "metadata": {
        "id": "Q1-1j1XuOpDO"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "X.head()"
      ],
      "metadata": {
        "id": "VL_6K9OlOudk",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "outputId": "53611fce-ca09-47b6-ed89-49ac7745fd15"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "      c    mn    si     cr     ni    mo     v     n    nb     co     w    al  \\\n",
              "0  0.02  0.05  0.05   0.01  19.70  2.95  0.01  0.00  0.01  15.00  0.00  0.15   \n",
              "1  0.18  0.01  0.01  13.44   0.01  3.01  0.46  0.04  0.01  19.46  2.35  0.04   \n",
              "2  0.00  0.01  0.01   8.67  13.45  0.82  0.01  0.00  0.01  13.90  0.00  0.39   \n",
              "3  0.01  0.05  0.05   0.01  17.70  3.95  0.01  0.00  0.01  15.00  0.00  0.13   \n",
              "4  0.01  0.05  0.05   0.01  19.40  1.45  0.01  0.00  0.01  14.90  0.00  0.13   \n",
              "\n",
              "     ti  \n",
              "0  1.55  \n",
              "1  0.00  \n",
              "2  0.57  \n",
              "3  1.47  \n",
              "4  1.55  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-af07d62f-7e2a-4167-98f5-49380987708d\">\n",
              "    <div 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>c</th>\n",
              "      <th>mn</th>\n",
              "      <th>si</th>\n",
              "      <th>cr</th>\n",
              "      <th>ni</th>\n",
              "      <th>mo</th>\n",
              "      <th>v</th>\n",
              "      <th>n</th>\n",
              "      <th>nb</th>\n",
              "      <th>co</th>\n",
              "      <th>w</th>\n",
              "      <th>al</th>\n",
              "      <th>ti</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.02</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.01</td>\n",
              "      <td>19.70</td>\n",
              "      <td>2.95</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>15.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.15</td>\n",
              "      <td>1.55</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.18</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.01</td>\n",
              "      <td>13.44</td>\n",
              "      <td>0.01</td>\n",
              "      <td>3.01</td>\n",
              "      <td>0.46</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.01</td>\n",
              "      <td>19.46</td>\n",
              "      <td>2.35</td>\n",
              "      <td>0.04</td>\n",
              "      <td>0.00</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.01</td>\n",
              "      <td>8.67</td>\n",
              "      <td>13.45</td>\n",
              "      <td>0.82</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>13.90</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.39</td>\n",
              "      <td>0.57</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.01</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.01</td>\n",
              "      <td>17.70</td>\n",
              "      <td>3.95</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>15.00</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.13</td>\n",
              "      <td>1.47</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.01</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.05</td>\n",
              "      <td>0.01</td>\n",
              "      <td>19.40</td>\n",
              "      <td>1.45</td>\n",
              "      <td>0.01</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.01</td>\n",
              "      <td>14.90</td>\n",
              "      <td>0.00</td>\n",
              "      <td>0.13</td>\n",
              "      <td>1.55</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-af07d62f-7e2a-4167-98f5-49380987708d')\"\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 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\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",
              "    [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-af07d62f-7e2a-4167-98f5-49380987708d 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-af07d62f-7e2a-4167-98f5-49380987708d');\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",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Assign the yield strength column to y"
      ],
      "metadata": {
        "id": "45xTcFBjJjlN"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "y = df['yield strength']"
      ],
      "metadata": {
        "id": "Jtm-RMBtFEId"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Split data into train and test sets."
      ],
      "metadata": {
        "id": "3fcmZA_zJpCk"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "X_train, X_test, y_train, y_test = train_test_split(X,y,\n",
        "test_size=0.2, random_state = 42)"
      ],
      "metadata": {
        "id": "eQtHS8moFG6l"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Import the ML algorithm for regression - here, we will import the Random Forest Regressor from scikit-learn. <br>\n",
        "Please note that Colab comes with most of the required libraries. You need to make sure you install all the required libraries in case you are running the code locally."
      ],
      "metadata": {
        "id": "pZaXUaeGJsKI"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.ensemble import RandomForestRegressor"
      ],
      "metadata": {
        "id": "bHjMv9uAFI1F"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#Instantiate the model by defining the appropriate hyperparameters\n",
        "model = RandomForestRegressor(n_estimators=10, max_depth=10, max_features='log2', min_samples_split=10, min_samples_leaf=4)"
      ],
      "metadata": {
        "id": "VtfjhDL1FK78"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Are these the right hyperparameters? Well, this is the whole point of this exercise so we will soon find out."
      ],
      "metadata": {
        "id": "6-Fa4LgkKFk2"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "#Fit the model to our training data\n",
        "model.fit(X_train, y_train)"
      ],
      "metadata": {
        "id": "M94UWnSSFMRU",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 91
        },
        "outputId": "46b68556-40ab-4929-c6bc-a2815442c868"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "RandomForestRegressor(max_depth=10, max_features='log2', min_samples_leaf=4,\n",
              "                      min_samples_split=10, n_estimators=10)"
            ],
            "text/html": [
              "<style>#sk-container-id-1 {color: black;background-color: white;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestRegressor(max_depth=10, max_features=&#x27;log2&#x27;, min_samples_leaf=4,\n",
              "                      min_samples_split=10, n_estimators=10)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">RandomForestRegressor</label><div class=\"sk-toggleable__content\"><pre>RandomForestRegressor(max_depth=10, max_features=&#x27;log2&#x27;, min_samples_leaf=4,\n",
              "                      min_samples_split=10, n_estimators=10)</pre></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Test the model on our test data and check the RMSE values. We will later compare RMSE from this model to our optimized model."
      ],
      "metadata": {
        "id": "n7I5ZDPzKTip"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "y_pred = model.predict(X_test)"
      ],
      "metadata": {
        "id": "WhBZE5fhFO4e"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import mean_squared_error\n",
        "import numpy as np\n",
        "\n",
        "rmse_original_model = np.sqrt(mean_squared_error(y_test, y_pred))\n",
        "\n",
        "print(\"RMSE: \", rmse_original_model)"
      ],
      "metadata": {
        "id": "i5LKCSPxFQlz",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "d3cf2665-670e-4e91-9a15-5d57d4c9ed56"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "RMSE:  136.77210992979678\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#Hyperparameter optimization using Genetic Algorithm. <br>\n",
        "There are many python libraries for this task but we will use the TPOT library for this tutorial. <br>\n",
        "https://pypi.org/project/TPOT/\n",
        "<br>\n",
        "Please note that there are many approaches for hyperparameter tuning including bayesian and grid search approaches. They all offer different approaches but no clear winner."
      ],
      "metadata": {
        "id": "DpxnDXr_KiA7"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install TPOT"
      ],
      "metadata": {
        "id": "5hiy1-fshuzl",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "95d7e7af-c465-4aef-ceca-cfa0c2fe9a1f"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Collecting TPOT\n",
            "  Downloading TPOT-0.11.7-py3-none-any.whl (87 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.2/87.2 kB\u001b[0m \u001b[31m3.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: joblib>=0.13.2 in /usr/local/lib/python3.10/dist-packages (from TPOT) (1.2.0)\n",
            "Requirement already satisfied: numpy>=1.16.3 in /usr/local/lib/python3.10/dist-packages (from TPOT) (1.22.4)\n",
            "Requirement already satisfied: scikit-learn>=0.22.0 in /usr/local/lib/python3.10/dist-packages (from TPOT) (1.2.2)\n",
            "Collecting deap>=1.2\n",
            "  Downloading deap-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (139 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m139.9/139.9 kB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: tqdm>=4.36.1 in /usr/local/lib/python3.10/dist-packages (from TPOT) (4.65.0)\n",
            "Requirement already satisfied: xgboost>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from TPOT) (1.7.5)\n",
            "Requirement already satisfied: scipy>=1.3.1 in /usr/local/lib/python3.10/dist-packages (from TPOT) (1.10.1)\n",
            "Collecting stopit>=1.1.1\n",
            "  Downloading stopit-1.1.2.tar.gz (18 kB)\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "Requirement already satisfied: pandas>=0.24.2 in /usr/local/lib/python3.10/dist-packages (from TPOT) (1.5.3)\n",
            "Collecting update-checker>=0.16\n",
            "  Downloading update_checker-0.18.0-py3-none-any.whl (7.0 kB)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->TPOT) (2022.7.1)\n",
            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->TPOT) (2.8.2)\n",
            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.22.0->TPOT) (3.1.0)\n",
            "Requirement already satisfied: requests>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from update-checker>=0.16->TPOT) (2.27.1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas>=0.24.2->TPOT) (1.16.0)\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) (3.4)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->TPOT) (1.26.15)\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) (2022.12.7)\n",
            "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests>=2.3.0->update-checker>=0.16->TPOT) (2.0.12)\n",
            "Building wheels for collected packages: stopit\n",
            "  Building wheel for stopit (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for stopit: filename=stopit-1.1.2-py3-none-any.whl size=11954 sha256=af010248ac6cd808e1e26b4f0d3736258e803bf84850a131fe994edcf19f49a8\n",
            "  Stored in directory: /root/.cache/pip/wheels/af/f9/87/bf5b3d565c2a007b4dae9d8142dccc85a9f164e517062dd519\n",
            "Successfully built stopit\n",
            "Installing collected packages: stopit, deap, update-checker, TPOT\n",
            "Successfully installed TPOT-0.11.7 deap-1.3.3 stopit-1.1.2 update-checker-0.18.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tpot import TPOTRegressor"
      ],
      "metadata": {
        "id": "wfcno741h3Gl"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "#Define the grid of hyper parameters that we'd like to search\n",
        "params_grid = {'n_estimators': [20, 60, 100, 150],\n",
        "               'max_features': ['auto', 'sqrt','log2'],\n",
        "               'max_depth': [10, 50, 100, 200],\n",
        "               'min_samples_split': [2, 4, 8, 10],\n",
        "               'min_samples_leaf': [1, 2, 4, 6]}"
      ],
      "metadata": {
        "id": "B-jXGGN7ftyB"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Define the TPOT regressor object that performs the hyperparameter search using the Genetic ALgorithm approach."
      ],
      "metadata": {
        "id": "EF6OKcmCLPyS"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "tpot_regressor = TPOTRegressor(generations= 10, population_size= 50, offspring_size= 12,\n",
        "                                 verbosity= 2, early_stop= 12,\n",
        "                                 config_dict={'sklearn.ensemble.RandomForestRegressor': params_grid},\n",
        "                                 cv = 3, scoring = 'neg_mean_squared_error')\n"
      ],
      "metadata": {
        "id": "LnFkKtkc8dg7"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "Fit the TPOT regressor to our training data. This task may take a while based on the size of your data set."
      ],
      "metadata": {
        "id": "4Qy_upiWLbGT"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "tpot_regressor.fit(X_train,y_train)"
      ],
      "metadata": {
        "id": "GzZ9v6VPhWo0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 653,
          "referenced_widgets": [
            "18e24619c11547e1903bdd4af0043dc7",
            "eac1c64c75b24ee3b0bbc527b2a37e6e",
            "b632233cc04c4cdb88ebacbaf1acbfbd",
            "bb57f28ea99744a082e26e4e5ec423e2",
            "40c1aff694a3440cb8a3a0998b2e0a6c",
            "510f9569fd6a46aaa261dc98558a412b",
            "02629a9b139c4bf68b1b082ef9157291",
            "17c5a2da79fd43c8aa53fc8dabf85935",
            "64c36379573d469abf0f8e8a0356ab8f",
            "f2b0b456f6824b14986653b387bf94cb",
            "b2386ab6f81f4e8c90f0e4fa1a78a61d"
          ]
        },
        "outputId": "04ab7526-2fe2-4674-dba8-91df7cd42306"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Optimization Progress:   0%|          | 0/170 [00:00<?, ?pipeline/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "18e24619c11547e1903bdd4af0043dc7"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Generation 1 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Generation 2 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Generation 3 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Generation 4 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Generation 5 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Generation 6 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Generation 7 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Generation 8 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Generation 9 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Generation 10 - Current best internal CV score: -18818.887198181696\n",
            "\n",
            "Best pipeline: RandomForestRegressor(RandomForestRegressor(input_matrix, max_depth=50, max_features=log2, min_samples_leaf=2, min_samples_split=4, n_estimators=150), max_depth=50, max_features=log2, min_samples_leaf=1, min_samples_split=4, n_estimators=60)\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "TPOTRegressor(config_dict={'sklearn.ensemble.RandomForestRegressor': {'max_depth': [10,\n",
              "                                                                                    50,\n",
              "                                                                                    100,\n",
              "                                                                                    200],\n",
              "                                                                      'max_features': ['auto',\n",
              "                                                                                       'sqrt',\n",
              "                                                                                       'log2'],\n",
              "                                                                      'min_samples_leaf': [1,\n",
              "                                                                                           2,\n",
              "                                                                                           4,\n",
              "                                                                                           6],\n",
              "                                                                      'min_samples_split': [2,\n",
              "                                                                                            4,\n",
              "                                                                                            8,\n",
              "                                                                                            10],\n",
              "                                                                      'n_estimators': [20,\n",
              "                                                                                       60,\n",
              "                                                                                       100,\n",
              "                                                                                       150]}},\n",
              "              cv=3, early_stop=12, generations=10, offspring_size=12,\n",
              "              population_size=50, scoring='neg_mean_squared_error',\n",
              "              verbosity=2)"
            ],
            "text/html": [
              "<style>#sk-container-id-2 {color: black;background-color: white;}#sk-container-id-2 pre{padding: 0;}#sk-container-id-2 div.sk-toggleable {background-color: white;}#sk-container-id-2 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-2 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-2 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-2 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-2 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-2 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-2 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-2 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-2 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-2 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-2 div.sk-item {position: relative;z-index: 1;}#sk-container-id-2 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-2 div.sk-item::before, #sk-container-id-2 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-2 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-2 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-2 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-2 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-2 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-2 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-2 div.sk-label-container {text-align: center;}#sk-container-id-2 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-2 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>TPOTRegressor(config_dict={&#x27;sklearn.ensemble.RandomForestRegressor&#x27;: {&#x27;max_depth&#x27;: [10,\n",
              "                                                                                    50,\n",
              "                                                                                    100,\n",
              "                                                                                    200],\n",
              "                                                                      &#x27;max_features&#x27;: [&#x27;auto&#x27;,\n",
              "                                                                                       &#x27;sqrt&#x27;,\n",
              "                                                                                       &#x27;log2&#x27;],\n",
              "                                                                      &#x27;min_samples_leaf&#x27;: [1,\n",
              "                                                                                           2,\n",
              "                                                                                           4,\n",
              "                                                                                           6],\n",
              "                                                                      &#x27;min_samples_split&#x27;: [2,\n",
              "                                                                                            4,\n",
              "                                                                                            8,\n",
              "                                                                                            10],\n",
              "                                                                      &#x27;n_estimators&#x27;: [20,\n",
              "                                                                                       60,\n",
              "                                                                                       100,\n",
              "                                                                                       150]}},\n",
              "              cv=3, early_stop=12, generations=10, offspring_size=12,\n",
              "              population_size=50, scoring=&#x27;neg_mean_squared_error&#x27;,\n",
              "              verbosity=2)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">TPOTRegressor</label><div class=\"sk-toggleable__content\"><pre>TPOTRegressor(config_dict={&#x27;sklearn.ensemble.RandomForestRegressor&#x27;: {&#x27;max_depth&#x27;: [10,\n",
              "                                                                                    50,\n",
              "                                                                                    100,\n",
              "                                                                                    200],\n",
              "                                                                      &#x27;max_features&#x27;: [&#x27;auto&#x27;,\n",
              "                                                                                       &#x27;sqrt&#x27;,\n",
              "                                                                                       &#x27;log2&#x27;],\n",
              "                                                                      &#x27;min_samples_leaf&#x27;: [1,\n",
              "                                                                                           2,\n",
              "                                                                                           4,\n",
              "                                                                                           6],\n",
              "                                                                      &#x27;min_samples_split&#x27;: [2,\n",
              "                                                                                            4,\n",
              "                                                                                            8,\n",
              "                                                                                            10],\n",
              "                                                                      &#x27;n_estimators&#x27;: [20,\n",
              "                                                                                       60,\n",
              "                                                                                       100,\n",
              "                                                                                       150]}},\n",
              "              cv=3, early_stop=12, generations=10, offspring_size=12,\n",
              "              population_size=50, scoring=&#x27;neg_mean_squared_error&#x27;,\n",
              "              verbosity=2)</pre></div></div></div></div></div>"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "The hyperparameter search result can be exported as a ready to use python file with the best model parameters already defined."
      ],
      "metadata": {
        "id": "8S16NClQLlDs"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "print(tpot_regressor.export())"
      ],
      "metadata": {
        "id": "300ufYTPkNgp",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "92b4119f-33fc-4adc-a79c-25346794ed9c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "import numpy as np\n",
            "import pandas as pd\n",
            "from sklearn.ensemble import RandomForestRegressor\n",
            "from sklearn.model_selection import train_test_split\n",
            "from sklearn.pipeline import make_pipeline, make_union\n",
            "from tpot.builtins import StackingEstimator\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=None)\n",
            "\n",
            "# Average CV score on the training set was: -18818.887198181696\n",
            "exported_pipeline = make_pipeline(\n",
            "    StackingEstimator(estimator=RandomForestRegressor(max_depth=50, max_features=\"log2\", min_samples_leaf=2, min_samples_split=4, n_estimators=150)),\n",
            "    RandomForestRegressor(max_depth=50, max_features=\"log2\", min_samples_leaf=1, min_samples_split=4, n_estimators=60)\n",
            ")\n",
            "\n",
            "exported_pipeline.fit(training_features, training_target)\n",
            "results = exported_pipeline.predict(testing_features)\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Let us test the performance of our new model with tuned hyperparameters"
      ],
      "metadata": {
        "id": "v09hSL7HLwUB"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "tpot_pred = tpot_regressor.predict(X_test)"
      ],
      "metadata": {
        "id": "Wytxi9dOk9I6",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ec8d0598-823d-4cf4-dc74-cfdb26cdb3da"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/sklearn/base.py:439: UserWarning: X does not have valid feature names, but RandomForestRegressor was fitted with feature names\n",
            "  warnings.warn(\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Calculate and print RMSE for the optimized model (and for the original model)."
      ],
      "metadata": {
        "id": "UBik2jYXL13D"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "rmse_optimized_model = np.sqrt(mean_squared_error(y_test, tpot_pred))\n",
        "\n",
        "print(\"RMSE using the original model: \", rmse_original_model)\n",
        "print(\"RMSE using the optimized model: \", rmse_optimized_model)"
      ],
      "metadata": {
        "id": "yAn1lk8dlMNs",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "556ab1e9-3ebb-4afc-b68b-1327218c696b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "RMSE using the original model:  136.77210992979678\n",
            "RMSE using the optimized model:  104.1389767400783\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "The optimized model performs better!!!"
      ],
      "metadata": {
        "id": "XNoKiFwfT3gK"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "# Classification example <br>\n",
        "using the digits data set."
      ],
      "metadata": {
        "id": "WKQ8eQ0Jz0P1"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from tpot import TPOTClassifier\n",
        "from sklearn.datasets import load_digits\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "digits = load_digits()\n",
        "X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target,\n",
        "                                                    train_size=0.75, test_size=0.25, random_state=42)\n",
        "\n"
      ],
      "metadata": {
        "id": "mjdDKLsP0DSp"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "print(X_train.shape, y_train.shape)"
      ],
      "metadata": {
        "id": "Dxb6hC_v2KGa",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "4895de39-76a3-4eee-fd4e-7fc79f719d6a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(1347, 64) (1347,)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#Let us take the first 500 data points for fast experimentation.\n",
        "X_train = X_train[:500]\n",
        "y_train = y_train[:500]"
      ],
      "metadata": {
        "id": "STlc-SSR2TFb"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "tpot = TPOTClassifier(generations=5, population_size=50, verbosity=2, random_state=42)\n",
        "tpot.fit(X_train, y_train)\n",
        "print(tpot.score(X_test, y_test))\n",
        "tpot.export('tpot_digits_pipeline.py')"
      ],
      "metadata": {
        "id": "TnVfjJdq2I0y",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 297,
          "referenced_widgets": [
            "1a4140529ccb4134824bd8f039545b7f",
            "ee3c07b7317a4ce3bec934c5645cce1a",
            "8bf7f582202543e4bb6e2617df51c61b",
            "ca4bbc4f05d94662bbd091f47aeb1bc9",
            "6ec8a7db46b94a4392132dca65729e34",
            "722a5199b5674933b6d79f51ff4b52eb",
            "6402ead328a84d55aa803dfd5e1b5318",
            "2302a9617e174e448c962b7323e9a375",
            "23bb2ccfec2c4a2fa7ed5683d9635347",
            "13dc18150d64424fb9699f23ac7250df",
            "60eaddb7878f4c7482bfb3712d2681d2"
          ]
        },
        "outputId": "afc84435-04e3-4725-8065-9ff5c4681313"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Optimization Progress:   0%|          | 0/300 [00:00<?, ?pipeline/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "1a4140529ccb4134824bd8f039545b7f"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Generation 1 - Current best internal CV score: 0.962\n",
            "\n",
            "Generation 2 - Current best internal CV score: 0.966\n",
            "\n",
            "Generation 3 - Current best internal CV score: 0.968\n",
            "\n",
            "Generation 4 - Current best internal CV score: 0.968\n",
            "\n",
            "Generation 5 - Current best internal CV score: 0.974\n",
            "\n",
            "Best pipeline: KNeighborsClassifier(input_matrix, n_neighbors=3, p=2, weights=distance)\n",
            "0.98\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/sklearn/metrics/_scorer.py:794: FutureWarning: sklearn.metrics.SCORERS is deprecated and will be removed in v1.3. Please use sklearn.metrics.get_scorer_names to get a list of available scorers and sklearn.metrics.get_metric to get scorer.\n",
            "  warnings.warn(\n"
          ]
        }
      ]
    }
  ]
}