[데이콘]와인품질분류.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "[데이콘]와인품질분류.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "toc_visible": true,
      "authorship_tag": "ABX9TyMFYNBxBOyFvhlQrkEN0TB7",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "47596c5b16964f149095767cb8f913b6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "IntProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_229e10840ed845dfad1db47054658a26",
            "_dom_classes": [],
            "description": "Processing: ",
            "_model_name": "IntProgressModel",
            "bar_style": "",
            "max": 3,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 3,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_6eeeaf30bb2341938bc5bc0c99b220da"
          }
        },
        "229e10840ed845dfad1db47054658a26": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "6eeeaf30bb2341938bc5bc0c99b220da": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "d4157d79a3fd48febe63236825488ef1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "TextModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "TextView",
            "style": "IPY_MODEL_7487f42744fc4135bde73555e3bffa75",
            "_dom_classes": [],
            "description": "",
            "_model_name": "TextModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": "Following data types have been inferred automatically, if they are correct press enter to continue or type 'quit' otherwise.",
            "_view_count": null,
            "disabled": false,
            "_view_module_version": "1.5.0",
            "continuous_update": true,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_881b782dc1af425dbdec343c92d901a7"
          }
        },
        "7487f42744fc4135bde73555e3bffa75": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "881b782dc1af425dbdec343c92d901a7": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": "100%",
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "88d9c55311b043bfa67d38e55a103719": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "IntProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_e3c0a7c6ce884646979590f3984f2ef8",
            "_dom_classes": [],
            "description": "Processing: ",
            "_model_name": "IntProgressModel",
            "bar_style": "",
            "max": 74,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 74,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_9745aa9eda9145d4bb0318421d90ce08"
          }
        },
        "e3c0a7c6ce884646979590f3984f2ef8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "9745aa9eda9145d4bb0318421d90ce08": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "fa76b1d30b214d6e90e80647392fddf4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "IntProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_8c97b7effd2040cbbc064f5b1f7a398d",
            "_dom_classes": [],
            "description": "Processing: ",
            "_model_name": "IntProgressModel",
            "bar_style": "",
            "max": 7,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 7,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_6f4465e520054989b6380c221fd577a8"
          }
        },
        "8c97b7effd2040cbbc064f5b1f7a398d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "6f4465e520054989b6380c221fd577a8": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "58bba3dd27b8480d804dc536bf80b9c8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "IntProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_c7dc9b986b9e46ddab94dfeab0d1ea1d",
            "_dom_classes": [],
            "description": "Processing: ",
            "_model_name": "IntProgressModel",
            "bar_style": "",
            "max": 7,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 7,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_3f292ae368fb44bb9dd1c4ea89dd734e"
          }
        },
        "c7dc9b986b9e46ddab94dfeab0d1ea1d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "3f292ae368fb44bb9dd1c4ea89dd734e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ea82de07133a4571b91ccfda0e2ff8d5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "IntProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_a8e7bdf07d044adfb0e5bfba90300ebc",
            "_dom_classes": [],
            "description": "Processing: ",
            "_model_name": "IntProgressModel",
            "bar_style": "",
            "max": 7,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 7,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_b01eedd6233f4a0eb2d64e27d5e811ec"
          }
        },
        "a8e7bdf07d044adfb0e5bfba90300ebc": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "b01eedd6233f4a0eb2d64e27d5e811ec": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "c3afe4bc02734bd0aed29b216287700e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "IntProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_11ff119b5c5c4594b7cc8c6ec1b5eff1",
            "_dom_classes": [],
            "description": "Processing: ",
            "_model_name": "IntProgressModel",
            "bar_style": "",
            "max": 6,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 6,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_437d4390be6f4ffaae07f11f4e6baa9c"
          }
        },
        "11ff119b5c5c4594b7cc8c6ec1b5eff1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "437d4390be6f4ffaae07f11f4e6baa9c": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/inrap8206/Dacon/blob/main/%5B%EB%8D%B0%EC%9D%B4%EC%BD%98%5D%EC%99%80%EC%9D%B8%ED%92%88%EC%A7%88%EB%B6%84%EB%A5%98.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DuhiPFjIS4lJ"
      },
      "source": [
        "## [데이콘] 와인품질분류\n",
        "- https://dacon.io/competitions/open/235610/overview/description"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "E6xftRkBVbKg"
      },
      "source": [
        "train = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/train.csv')\n",
        "print(train['quality'].value_counts())\n",
        "import seaborn as sns\n",
        "\n",
        "data = train.drop('index', axis=1)\n",
        "sns.set(style=\"ticks\", color_codes=True)\n",
        "g = sns.pairplot(data, hue=\"quality\", palette=\"husl\")"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "apVaeDSuwcd3"
      },
      "source": [
        "# Model Selection"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NZpZTyuJnsQK"
      },
      "source": [
        "## Manual"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6i5fKKbRv_vE",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "cf07a658-2397-4c67-c852-492c2cd04095"
      },
      "source": [
        "!pip install catboost"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting catboost\n",
            "  Downloading catboost-0.26.1-cp37-none-manylinux1_x86_64.whl (67.4 MB)\n",
            "\u001b[K     |████████████████████████████████| 67.4 MB 58 kB/s \n",
            "\u001b[?25hRequirement already satisfied: six in /usr/local/lib/python3.7/dist-packages (from catboost) (1.15.0)\n",
            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.7/dist-packages (from catboost) (3.2.2)\n",
            "Requirement already satisfied: scipy in /usr/local/lib/python3.7/dist-packages (from catboost) (1.4.1)\n",
            "Requirement already satisfied: plotly in /usr/local/lib/python3.7/dist-packages (from catboost) (4.4.1)\n",
            "Requirement already satisfied: graphviz in /usr/local/lib/python3.7/dist-packages (from catboost) (0.10.1)\n",
            "Requirement already satisfied: pandas>=0.24.0 in /usr/local/lib/python3.7/dist-packages (from catboost) (1.1.5)\n",
            "Requirement already satisfied: numpy>=1.16.0 in /usr/local/lib/python3.7/dist-packages (from catboost) (1.19.5)\n",
            "Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.24.0->catboost) (2.8.2)\n",
            "Requirement already satisfied: pytz>=2017.2 in /usr/local/lib/python3.7/dist-packages (from pandas>=0.24.0->catboost) (2018.9)\n",
            "Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib->catboost) (1.3.1)\n",
            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.7/dist-packages (from matplotlib->catboost) (0.10.0)\n",
            "Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.1 in /usr/local/lib/python3.7/dist-packages (from matplotlib->catboost) (2.4.7)\n",
            "Requirement already satisfied: retrying>=1.3.3 in /usr/local/lib/python3.7/dist-packages (from plotly->catboost) (1.3.3)\n",
            "Installing collected packages: catboost\n",
            "Successfully installed catboost-0.26.1\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 417
        },
        "id": "QoOTGj3mwfuk",
        "outputId": "a8695014-1a43-4510-9302-3192b26e0fbc"
      },
      "source": [
        "from sklearn.linear_model import RidgeClassifier, LogisticRegression  \n",
        "from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier, AdaBoostClassifier\n",
        "from sklearn.svm import SVC, LinearSVC\n",
        "from sklearn.neighbors import KNeighborsClassifier\n",
        "from sklearn.naive_bayes import GaussianNB\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from xgboost import XGBClassifier\n",
        "from lightgbm import LGBMClassifier\n",
        "from catboost import CatBoostClassifier\n",
        "from sklearn.model_selection import cross_val_score, KFold\n",
        "from sklearn.metrics import accuracy_score\n",
        "\n",
        "model_list = [RidgeClassifier(), LogisticRegression(), GaussianNB(), KNeighborsClassifier(n_neighbors=20), SVC(gamma = 0.01, C = 100, probability=True), \n",
        "              DecisionTreeClassifier(max_features=7 , max_depth=6,  min_samples_split=8), \n",
        "              RandomForestClassifier(random_state=2021), GradientBoostingClassifier(), AdaBoostClassifier(), XGBClassifier(), LGBMClassifier(), CatBoostClassifier(verbose=0)]\n",
        "scores = []\n",
        "\n",
        "for model in model_list:\n",
        "  score = cross_val_score(model, train, label, cv=5, scoring='accuracy')\n",
        "  scores.append(score.mean())\n",
        "\n",
        "\n",
        "model_test = pd.DataFrame({'model':model_list, 'score':scores})\n",
        "model_test.sort_values('score', ascending=False)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>model</th>\n",
              "      <th>score</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>RandomForestClassifier(bootstrap=True, ccp_alp...</td>\n",
              "      <td>0.675455</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>11</th>\n",
              "      <td>&lt;catboost.core.CatBoostClassifier object at 0x...</td>\n",
              "      <td>0.649624</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>10</th>\n",
              "      <td>LGBMClassifier(boosting_type='gbdt', class_wei...</td>\n",
              "      <td>0.633619</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>GradientBoostingClassifier(ccp_alpha=0.0, crit...</td>\n",
              "      <td>0.584135</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>XGBClassifier(base_score=0.5, booster='gbtree'...</td>\n",
              "      <td>0.578679</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>SVC(C=100, break_ties=False, cache_size=200, c...</td>\n",
              "      <td>0.563946</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>KNeighborsClassifier(algorithm='auto', leaf_si...</td>\n",
              "      <td>0.557393</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>LogisticRegression(C=1.0, class_weight=None, d...</td>\n",
              "      <td>0.545205</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>DecisionTreeClassifier(ccp_alpha=0.0, class_we...</td>\n",
              "      <td>0.533927</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>RidgeClassifier(alpha=1.0, class_weight=None, ...</td>\n",
              "      <td>0.531925</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>AdaBoostClassifier(algorithm='SAMME.R', base_e...</td>\n",
              "      <td>0.402040</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>GaussianNB(priors=None, var_smoothing=1e-09)</td>\n",
              "      <td>0.364752</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                model     score\n",
              "6   RandomForestClassifier(bootstrap=True, ccp_alp...  0.675455\n",
              "11  <catboost.core.CatBoostClassifier object at 0x...  0.649624\n",
              "10  LGBMClassifier(boosting_type='gbdt', class_wei...  0.633619\n",
              "7   GradientBoostingClassifier(ccp_alpha=0.0, crit...  0.584135\n",
              "9   XGBClassifier(base_score=0.5, booster='gbtree'...  0.578679\n",
              "4   SVC(C=100, break_ties=False, cache_size=200, c...  0.563946\n",
              "3   KNeighborsClassifier(algorithm='auto', leaf_si...  0.557393\n",
              "1   LogisticRegression(C=1.0, class_weight=None, d...  0.545205\n",
              "5   DecisionTreeClassifier(ccp_alpha=0.0, class_we...  0.533927\n",
              "0   RidgeClassifier(alpha=1.0, class_weight=None, ...  0.531925\n",
              "8   AdaBoostClassifier(algorithm='SAMME.R', base_e...  0.402040\n",
              "2        GaussianNB(priors=None, var_smoothing=1e-09)  0.364752"
            ]
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jBJ3YlfrnueU"
      },
      "source": [
        "## Pycatet"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dw3FDyyKnv_E"
      },
      "source": [
        "!pip install pycaret"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000,
          "referenced_widgets": [
            "47596c5b16964f149095767cb8f913b6",
            "229e10840ed845dfad1db47054658a26",
            "6eeeaf30bb2341938bc5bc0c99b220da",
            "d4157d79a3fd48febe63236825488ef1",
            "7487f42744fc4135bde73555e3bffa75",
            "881b782dc1af425dbdec343c92d901a7"
          ]
        },
        "id": "0mKXYsYPnyqd",
        "outputId": "bbcd2712-4d1d-40d1-d45a-0cdbfcd2798b"
      },
      "source": [
        "from pycaret.classification import *\n",
        "\n",
        "train = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/train.csv')\n",
        "setup_clf = setup(data=train, target='quality', session_id=2021, categorical_features=['type'], ignore_features=['index'])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Description</th>\n",
              "      <th>Value</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>session_id</td>\n",
              "      <td>2021</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Target</td>\n",
              "      <td>quality</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Target Type</td>\n",
              "      <td>Multiclass</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Label Encoded</td>\n",
              "      <td>3: 0, 4: 1, 5: 2, 6: 3, 7: 4, 8: 5, 9: 6</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Original Data</td>\n",
              "      <td>(5497, 14)</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>Missing Values</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>Numeric Features</td>\n",
              "      <td>11</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>Categorical Features</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>Ordinal Features</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>High Cardinality Features</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>10</th>\n",
              "      <td>High Cardinality Method</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>11</th>\n",
              "      <td>Transformed Train Set</td>\n",
              "      <td>(3847, 12)</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>12</th>\n",
              "      <td>Transformed Test Set</td>\n",
              "      <td>(1650, 12)</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>13</th>\n",
              "      <td>Shuffle Train-Test</td>\n",
              "      <td>True</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>14</th>\n",
              "      <td>Stratify Train-Test</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>15</th>\n",
              "      <td>Fold Generator</td>\n",
              "      <td>StratifiedKFold</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>16</th>\n",
              "      <td>Fold Number</td>\n",
              "      <td>10</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>17</th>\n",
              "      <td>CPU Jobs</td>\n",
              "      <td>-1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>18</th>\n",
              "      <td>Use GPU</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>19</th>\n",
              "      <td>Log Experiment</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>20</th>\n",
              "      <td>Experiment Name</td>\n",
              "      <td>clf-default-name</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>21</th>\n",
              "      <td>USI</td>\n",
              "      <td>dfb1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>22</th>\n",
              "      <td>Imputation Type</td>\n",
              "      <td>simple</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>23</th>\n",
              "      <td>Iterative Imputation Iteration</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>24</th>\n",
              "      <td>Numeric Imputer</td>\n",
              "      <td>mean</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>25</th>\n",
              "      <td>Iterative Imputation Numeric Model</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>26</th>\n",
              "      <td>Categorical Imputer</td>\n",
              "      <td>constant</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>27</th>\n",
              "      <td>Iterative Imputation Categorical Model</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>28</th>\n",
              "      <td>Unknown Categoricals Handling</td>\n",
              "      <td>least_frequent</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>29</th>\n",
              "      <td>Normalize</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>30</th>\n",
              "      <td>Normalize Method</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>31</th>\n",
              "      <td>Transformation</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>32</th>\n",
              "      <td>Transformation Method</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>33</th>\n",
              "      <td>PCA</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>34</th>\n",
              "      <td>PCA Method</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>35</th>\n",
              "      <td>PCA Components</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>36</th>\n",
              "      <td>Ignore Low Variance</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>37</th>\n",
              "      <td>Combine Rare Levels</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>38</th>\n",
              "      <td>Rare Level Threshold</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>39</th>\n",
              "      <td>Numeric Binning</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>40</th>\n",
              "      <td>Remove Outliers</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>41</th>\n",
              "      <td>Outliers Threshold</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>42</th>\n",
              "      <td>Remove Multicollinearity</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>43</th>\n",
              "      <td>Multicollinearity Threshold</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>44</th>\n",
              "      <td>Remove Perfect Collinearity</td>\n",
              "      <td>True</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>45</th>\n",
              "      <td>Clustering</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>46</th>\n",
              "      <td>Clustering Iteration</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>47</th>\n",
              "      <td>Polynomial Features</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>48</th>\n",
              "      <td>Polynomial Degree</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>49</th>\n",
              "      <td>Trignometry Features</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>50</th>\n",
              "      <td>Polynomial Threshold</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>51</th>\n",
              "      <td>Group Features</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>52</th>\n",
              "      <td>Feature Selection</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>53</th>\n",
              "      <td>Feature Selection Method</td>\n",
              "      <td>classic</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>54</th>\n",
              "      <td>Features Selection Threshold</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>55</th>\n",
              "      <td>Feature Interaction</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>56</th>\n",
              "      <td>Feature Ratio</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>57</th>\n",
              "      <td>Interaction Threshold</td>\n",
              "      <td>None</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>58</th>\n",
              "      <td>Fix Imbalance</td>\n",
              "      <td>False</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>59</th>\n",
              "      <td>Fix Imbalance Method</td>\n",
              "      <td>SMOTE</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                               Description                                     Value\n",
              "0                               session_id                                      2021\n",
              "1                                   Target                                   quality\n",
              "2                              Target Type                                Multiclass\n",
              "3                            Label Encoded  3: 0, 4: 1, 5: 2, 6: 3, 7: 4, 8: 5, 9: 6\n",
              "4                            Original Data                                (5497, 14)\n",
              "5                           Missing Values                                     False\n",
              "6                         Numeric Features                                        11\n",
              "7                     Categorical Features                                         1\n",
              "8                         Ordinal Features                                     False\n",
              "9                High Cardinality Features                                     False\n",
              "10                 High Cardinality Method                                      None\n",
              "11                   Transformed Train Set                                (3847, 12)\n",
              "12                    Transformed Test Set                                (1650, 12)\n",
              "13                      Shuffle Train-Test                                      True\n",
              "14                     Stratify Train-Test                                     False\n",
              "15                          Fold Generator                           StratifiedKFold\n",
              "16                             Fold Number                                        10\n",
              "17                                CPU Jobs                                        -1\n",
              "18                                 Use GPU                                     False\n",
              "19                          Log Experiment                                     False\n",
              "20                         Experiment Name                          clf-default-name\n",
              "21                                     USI                                      dfb1\n",
              "22                         Imputation Type                                    simple\n",
              "23          Iterative Imputation Iteration                                      None\n",
              "24                         Numeric Imputer                                      mean\n",
              "25      Iterative Imputation Numeric Model                                      None\n",
              "26                     Categorical Imputer                                  constant\n",
              "27  Iterative Imputation Categorical Model                                      None\n",
              "28           Unknown Categoricals Handling                            least_frequent\n",
              "29                               Normalize                                     False\n",
              "30                        Normalize Method                                      None\n",
              "31                          Transformation                                     False\n",
              "32                   Transformation Method                                      None\n",
              "33                                     PCA                                     False\n",
              "34                              PCA Method                                      None\n",
              "35                          PCA Components                                      None\n",
              "36                     Ignore Low Variance                                     False\n",
              "37                     Combine Rare Levels                                     False\n",
              "38                    Rare Level Threshold                                      None\n",
              "39                         Numeric Binning                                     False\n",
              "40                         Remove Outliers                                     False\n",
              "41                      Outliers Threshold                                      None\n",
              "42                Remove Multicollinearity                                     False\n",
              "43             Multicollinearity Threshold                                      None\n",
              "44             Remove Perfect Collinearity                                      True\n",
              "45                              Clustering                                     False\n",
              "46                    Clustering Iteration                                      None\n",
              "47                     Polynomial Features                                     False\n",
              "48                       Polynomial Degree                                      None\n",
              "49                    Trignometry Features                                     False\n",
              "50                    Polynomial Threshold                                      None\n",
              "51                          Group Features                                     False\n",
              "52                       Feature Selection                                     False\n",
              "53                Feature Selection Method                                   classic\n",
              "54            Features Selection Threshold                                      None\n",
              "55                     Feature Interaction                                     False\n",
              "56                           Feature Ratio                                     False\n",
              "57                   Interaction Threshold                                      None\n",
              "58                           Fix Imbalance                                     False\n",
              "59                    Fix Imbalance Method                                     SMOTE"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 478,
          "referenced_widgets": [
            "88d9c55311b043bfa67d38e55a103719",
            "e3c0a7c6ce884646979590f3984f2ef8",
            "9745aa9eda9145d4bb0318421d90ce08"
          ]
        },
        "id": "3pHjjr_ipcNB",
        "outputId": "ba45bc51-7b62-4885-ccd4-26add36e0da2"
      },
      "source": [
        "best_3 = compare_models(sort='Accuracy', n_select=3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Model</th>\n",
              "      <th>Accuracy</th>\n",
              "      <th>AUC</th>\n",
              "      <th>Recall</th>\n",
              "      <th>Prec.</th>\n",
              "      <th>F1</th>\n",
              "      <th>Kappa</th>\n",
              "      <th>MCC</th>\n",
              "      <th>TT (Sec)</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>rf</th>\n",
              "      <td>Random Forest Classifier</td>\n",
              "      <td>0.6387</td>\n",
              "      <td>0.3263</td>\n",
              "      <td>0.3540</td>\n",
              "      <td>0.6396</td>\n",
              "      <td>0.6221</td>\n",
              "      <td>0.4281</td>\n",
              "      <td>0.4346</td>\n",
              "      <td>0.921</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>et</th>\n",
              "      <td>Extra Trees Classifier</td>\n",
              "      <td>0.6356</td>\n",
              "      <td>0.3283</td>\n",
              "      <td>0.3624</td>\n",
              "      <td>0.6403</td>\n",
              "      <td>0.6213</td>\n",
              "      <td>0.4249</td>\n",
              "      <td>0.4306</td>\n",
              "      <td>0.718</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>lightgbm</th>\n",
              "      <td>Light Gradient Boosting Machine</td>\n",
              "      <td>0.6275</td>\n",
              "      <td>0.3128</td>\n",
              "      <td>0.3586</td>\n",
              "      <td>0.6232</td>\n",
              "      <td>0.6144</td>\n",
              "      <td>0.4179</td>\n",
              "      <td>0.4214</td>\n",
              "      <td>0.759</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>catboost</th>\n",
              "      <td>CatBoost Classifier</td>\n",
              "      <td>0.6215</td>\n",
              "      <td>0.3164</td>\n",
              "      <td>0.3586</td>\n",
              "      <td>0.6132</td>\n",
              "      <td>0.6094</td>\n",
              "      <td>0.4105</td>\n",
              "      <td>0.4133</td>\n",
              "      <td>15.498</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>gbc</th>\n",
              "      <td>Gradient Boosting Classifier</td>\n",
              "      <td>0.5737</td>\n",
              "      <td>0.3004</td>\n",
              "      <td>0.3072</td>\n",
              "      <td>0.5657</td>\n",
              "      <td>0.5555</td>\n",
              "      <td>0.3251</td>\n",
              "      <td>0.3314</td>\n",
              "      <td>4.265</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>dt</th>\n",
              "      <td>Decision Tree Classifier</td>\n",
              "      <td>0.5410</td>\n",
              "      <td>0.2591</td>\n",
              "      <td>0.3430</td>\n",
              "      <td>0.5442</td>\n",
              "      <td>0.5414</td>\n",
              "      <td>0.3176</td>\n",
              "      <td>0.3180</td>\n",
              "      <td>0.042</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>lda</th>\n",
              "      <td>Linear Discriminant Analysis</td>\n",
              "      <td>0.5378</td>\n",
              "      <td>0.2801</td>\n",
              "      <td>0.2571</td>\n",
              "      <td>0.5187</td>\n",
              "      <td>0.5122</td>\n",
              "      <td>0.2579</td>\n",
              "      <td>0.2659</td>\n",
              "      <td>0.024</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ridge</th>\n",
              "      <td>Ridge Classifier</td>\n",
              "      <td>0.5285</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.2130</td>\n",
              "      <td>0.4513</td>\n",
              "      <td>0.4596</td>\n",
              "      <td>0.2095</td>\n",
              "      <td>0.2288</td>\n",
              "      <td>0.017</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>lr</th>\n",
              "      <td>Logistic Regression</td>\n",
              "      <td>0.5256</td>\n",
              "      <td>0.2724</td>\n",
              "      <td>0.2187</td>\n",
              "      <td>0.4795</td>\n",
              "      <td>0.4748</td>\n",
              "      <td>0.2143</td>\n",
              "      <td>0.2292</td>\n",
              "      <td>1.845</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>qda</th>\n",
              "      <td>Quadratic Discriminant Analysis</td>\n",
              "      <td>0.4611</td>\n",
              "      <td>0.2719</td>\n",
              "      <td>0.3020</td>\n",
              "      <td>0.4869</td>\n",
              "      <td>0.4598</td>\n",
              "      <td>0.2338</td>\n",
              "      <td>0.2403</td>\n",
              "      <td>0.021</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>knn</th>\n",
              "      <td>K Neighbors Classifier</td>\n",
              "      <td>0.4580</td>\n",
              "      <td>0.2468</td>\n",
              "      <td>0.2383</td>\n",
              "      <td>0.4441</td>\n",
              "      <td>0.4441</td>\n",
              "      <td>0.1543</td>\n",
              "      <td>0.1557</td>\n",
              "      <td>0.125</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>ada</th>\n",
              "      <td>Ada Boost Classifier</td>\n",
              "      <td>0.4133</td>\n",
              "      <td>0.2108</td>\n",
              "      <td>0.2149</td>\n",
              "      <td>0.3771</td>\n",
              "      <td>0.3861</td>\n",
              "      <td>0.1080</td>\n",
              "      <td>0.1142</td>\n",
              "      <td>0.242</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>nb</th>\n",
              "      <td>Naive Bayes</td>\n",
              "      <td>0.3982</td>\n",
              "      <td>0.2524</td>\n",
              "      <td>0.2639</td>\n",
              "      <td>0.4368</td>\n",
              "      <td>0.4132</td>\n",
              "      <td>0.1464</td>\n",
              "      <td>0.1481</td>\n",
              "      <td>0.019</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>svm</th>\n",
              "      <td>SVM - Linear Kernel</td>\n",
              "      <td>0.3775</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.2006</td>\n",
              "      <td>0.3743</td>\n",
              "      <td>0.2953</td>\n",
              "      <td>0.1196</td>\n",
              "      <td>0.1637</td>\n",
              "      <td>0.130</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                    Model  Accuracy     AUC  Recall   Prec.  \\\n",
              "rf               Random Forest Classifier    0.6387  0.3263  0.3540  0.6396   \n",
              "et                 Extra Trees Classifier    0.6356  0.3283  0.3624  0.6403   \n",
              "lightgbm  Light Gradient Boosting Machine    0.6275  0.3128  0.3586  0.6232   \n",
              "catboost              CatBoost Classifier    0.6215  0.3164  0.3586  0.6132   \n",
              "gbc          Gradient Boosting Classifier    0.5737  0.3004  0.3072  0.5657   \n",
              "dt               Decision Tree Classifier    0.5410  0.2591  0.3430  0.5442   \n",
              "lda          Linear Discriminant Analysis    0.5378  0.2801  0.2571  0.5187   \n",
              "ridge                    Ridge Classifier    0.5285  0.0000  0.2130  0.4513   \n",
              "lr                    Logistic Regression    0.5256  0.2724  0.2187  0.4795   \n",
              "qda       Quadratic Discriminant Analysis    0.4611  0.2719  0.3020  0.4869   \n",
              "knn                K Neighbors Classifier    0.4580  0.2468  0.2383  0.4441   \n",
              "ada                  Ada Boost Classifier    0.4133  0.2108  0.2149  0.3771   \n",
              "nb                            Naive Bayes    0.3982  0.2524  0.2639  0.4368   \n",
              "svm                   SVM - Linear Kernel    0.3775  0.0000  0.2006  0.3743   \n",
              "\n",
              "              F1   Kappa     MCC  TT (Sec)  \n",
              "rf        0.6221  0.4281  0.4346     0.921  \n",
              "et        0.6213  0.4249  0.4306     0.718  \n",
              "lightgbm  0.6144  0.4179  0.4214     0.759  \n",
              "catboost  0.6094  0.4105  0.4133    15.498  \n",
              "gbc       0.5555  0.3251  0.3314     4.265  \n",
              "dt        0.5414  0.3176  0.3180     0.042  \n",
              "lda       0.5122  0.2579  0.2659     0.024  \n",
              "ridge     0.4596  0.2095  0.2288     0.017  \n",
              "lr        0.4748  0.2143  0.2292     1.845  \n",
              "qda       0.4598  0.2338  0.2403     0.021  \n",
              "knn       0.4441  0.1543  0.1557     0.125  \n",
              "ada       0.3861  0.1080  0.1142     0.242  \n",
              "nb        0.4132  0.1464  0.1481     0.019  \n",
              "svm       0.2953  0.1196  0.1637     0.130  "
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 821,
          "referenced_widgets": [
            "fa76b1d30b214d6e90e80647392fddf4",
            "8c97b7effd2040cbbc064f5b1f7a398d",
            "6f4465e520054989b6380c221fd577a8",
            "58bba3dd27b8480d804dc536bf80b9c8",
            "c7dc9b986b9e46ddab94dfeab0d1ea1d",
            "3f292ae368fb44bb9dd1c4ea89dd734e",
            "ea82de07133a4571b91ccfda0e2ff8d5",
            "a8e7bdf07d044adfb0e5bfba90300ebc",
            "b01eedd6233f4a0eb2d64e27d5e811ec"
          ]
        },
        "id": "w_cD1IGWszho",
        "outputId": "e5ad6fe1-a35a-49b8-a8c4-f3c04fb9c3cb"
      },
      "source": [
        "tuned_best_3 = [tune_model(i) for i in best_3]\n",
        "tuned_best_3"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Accuracy</th>\n",
              "      <th>AUC</th>\n",
              "      <th>Recall</th>\n",
              "      <th>Prec.</th>\n",
              "      <th>F1</th>\n",
              "      <th>Kappa</th>\n",
              "      <th>MCC</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.6130</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.3716</td>\n",
              "      <td>0.6082</td>\n",
              "      <td>0.5993</td>\n",
              "      <td>0.3915</td>\n",
              "      <td>0.3952</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.6026</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.3433</td>\n",
              "      <td>0.6045</td>\n",
              "      <td>0.5879</td>\n",
              "      <td>0.3737</td>\n",
              "      <td>0.3785</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.6104</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.3251</td>\n",
              "      <td>0.5989</td>\n",
              "      <td>0.5900</td>\n",
              "      <td>0.3859</td>\n",
              "      <td>0.3909</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.6052</td>\n",
              "      <td>0.7705</td>\n",
              "      <td>0.2747</td>\n",
              "      <td>0.5960</td>\n",
              "      <td>0.5843</td>\n",
              "      <td>0.3717</td>\n",
              "      <td>0.3783</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.5766</td>\n",
              "      <td>0.7690</td>\n",
              "      <td>0.2438</td>\n",
              "      <td>0.5367</td>\n",
              "      <td>0.5508</td>\n",
              "      <td>0.3262</td>\n",
              "      <td>0.3318</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>0.6130</td>\n",
              "      <td>0.7887</td>\n",
              "      <td>0.2729</td>\n",
              "      <td>0.5943</td>\n",
              "      <td>0.5896</td>\n",
              "      <td>0.3869</td>\n",
              "      <td>0.3918</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>0.6000</td>\n",
              "      <td>0.7697</td>\n",
              "      <td>0.2629</td>\n",
              "      <td>0.5672</td>\n",
              "      <td>0.5796</td>\n",
              "      <td>0.3706</td>\n",
              "      <td>0.3740</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>0.6198</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.3362</td>\n",
              "      <td>0.6098</td>\n",
              "      <td>0.6004</td>\n",
              "      <td>0.4054</td>\n",
              "      <td>0.4087</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>0.6042</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.3064</td>\n",
              "      <td>0.5821</td>\n",
              "      <td>0.5772</td>\n",
              "      <td>0.3654</td>\n",
              "      <td>0.3734</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>0.6562</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.3253</td>\n",
              "      <td>0.6103</td>\n",
              "      <td>0.6279</td>\n",
              "      <td>0.4539</td>\n",
              "      <td>0.4603</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Mean</th>\n",
              "      <td>0.6101</td>\n",
              "      <td>0.3098</td>\n",
              "      <td>0.3062</td>\n",
              "      <td>0.5908</td>\n",
              "      <td>0.5887</td>\n",
              "      <td>0.3831</td>\n",
              "      <td>0.3883</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>SD</th>\n",
              "      <td>0.0189</td>\n",
              "      <td>0.3795</td>\n",
              "      <td>0.0389</td>\n",
              "      <td>0.0221</td>\n",
              "      <td>0.0186</td>\n",
              "      <td>0.0309</td>\n",
              "      <td>0.0308</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "      Accuracy     AUC  Recall   Prec.      F1   Kappa     MCC\n",
              "0       0.6130  0.0000  0.3716  0.6082  0.5993  0.3915  0.3952\n",
              "1       0.6026  0.0000  0.3433  0.6045  0.5879  0.3737  0.3785\n",
              "2       0.6104  0.0000  0.3251  0.5989  0.5900  0.3859  0.3909\n",
              "3       0.6052  0.7705  0.2747  0.5960  0.5843  0.3717  0.3783\n",
              "4       0.5766  0.7690  0.2438  0.5367  0.5508  0.3262  0.3318\n",
              "5       0.6130  0.7887  0.2729  0.5943  0.5896  0.3869  0.3918\n",
              "6       0.6000  0.7697  0.2629  0.5672  0.5796  0.3706  0.3740\n",
              "7       0.6198  0.0000  0.3362  0.6098  0.6004  0.4054  0.4087\n",
              "8       0.6042  0.0000  0.3064  0.5821  0.5772  0.3654  0.3734\n",
              "9       0.6562  0.0000  0.3253  0.6103  0.6279  0.4539  0.4603\n",
              "Mean    0.6101  0.3098  0.3062  0.5908  0.5887  0.3831  0.3883\n",
              "SD      0.0189  0.3795  0.0389  0.0221  0.0186  0.0309  0.0308"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[RandomForestClassifier(bootstrap=True, ccp_alpha=0.0, class_weight={},\n",
              "                        criterion='entropy', max_depth=10, max_features='log2',\n",
              "                        max_leaf_nodes=None, max_samples=None,\n",
              "                        min_impurity_decrease=0.0005, min_impurity_split=None,\n",
              "                        min_samples_leaf=6, min_samples_split=5,\n",
              "                        min_weight_fraction_leaf=0.0, n_estimators=250,\n",
              "                        n_jobs=-1, oob_score=False, random_state=2021, verbose=0,\n",
              "                        warm_start=False),\n",
              " ExtraTreesClassifier(bootstrap=True, ccp_alpha=0.0, class_weight={},\n",
              "                      criterion='entropy', max_depth=10, max_features='log2',\n",
              "                      max_leaf_nodes=None, max_samples=None,\n",
              "                      min_impurity_decrease=0.0005, min_impurity_split=None,\n",
              "                      min_samples_leaf=6, min_samples_split=5,\n",
              "                      min_weight_fraction_leaf=0.0, n_estimators=250, n_jobs=-1,\n",
              "                      oob_score=False, random_state=2021, verbose=0,\n",
              "                      warm_start=False),\n",
              " LGBMClassifier(bagging_fraction=0.6, bagging_freq=6, boosting_type='gbdt',\n",
              "                class_weight=None, colsample_bytree=1.0, feature_fraction=0.8,\n",
              "                importance_type='split', learning_rate=0.05, max_depth=-1,\n",
              "                min_child_samples=16, min_child_weight=0.001, min_split_gain=0.3,\n",
              "                n_estimators=120, n_jobs=-1, num_leaves=150, objective=None,\n",
              "                random_state=2021, reg_alpha=1e-06, reg_lambda=10, silent=True,\n",
              "                subsample=1.0, subsample_for_bin=200000, subsample_freq=0)]"
            ]
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 417,
          "referenced_widgets": [
            "c3afe4bc02734bd0aed29b216287700e",
            "11ff119b5c5c4594b7cc8c6ec1b5eff1",
            "437d4390be6f4ffaae07f11f4e6baa9c"
          ]
        },
        "id": "lOFqHKfop00X",
        "outputId": "26bc68a3-ca31-4010-a0b5-f1863794c325"
      },
      "source": [
        "blender_best_3 = blend_models(estimator_list=tuned_best_3)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Accuracy</th>\n",
              "      <th>AUC</th>\n",
              "      <th>Recall</th>\n",
              "      <th>Prec.</th>\n",
              "      <th>F1</th>\n",
              "      <th>Kappa</th>\n",
              "      <th>MCC</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0.5974</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.3107</td>\n",
              "      <td>0.5941</td>\n",
              "      <td>0.5693</td>\n",
              "      <td>0.3480</td>\n",
              "      <td>0.3593</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>0.5896</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.2808</td>\n",
              "      <td>0.5577</td>\n",
              "      <td>0.5569</td>\n",
              "      <td>0.3335</td>\n",
              "      <td>0.3469</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>0.6182</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.3147</td>\n",
              "      <td>0.6237</td>\n",
              "      <td>0.5913</td>\n",
              "      <td>0.3800</td>\n",
              "      <td>0.3975</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>0.6182</td>\n",
              "      <td>0.7824</td>\n",
              "      <td>0.2663</td>\n",
              "      <td>0.6262</td>\n",
              "      <td>0.5883</td>\n",
              "      <td>0.3773</td>\n",
              "      <td>0.3950</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>0.5714</td>\n",
              "      <td>0.7732</td>\n",
              "      <td>0.2261</td>\n",
              "      <td>0.5384</td>\n",
              "      <td>0.5321</td>\n",
              "      <td>0.2981</td>\n",
              "      <td>0.3134</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>0.6208</td>\n",
              "      <td>0.7878</td>\n",
              "      <td>0.2687</td>\n",
              "      <td>0.6090</td>\n",
              "      <td>0.5921</td>\n",
              "      <td>0.3879</td>\n",
              "      <td>0.3996</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>0.5844</td>\n",
              "      <td>0.7661</td>\n",
              "      <td>0.2423</td>\n",
              "      <td>0.5590</td>\n",
              "      <td>0.5556</td>\n",
              "      <td>0.3272</td>\n",
              "      <td>0.3373</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>0.6172</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.2920</td>\n",
              "      <td>0.5803</td>\n",
              "      <td>0.5818</td>\n",
              "      <td>0.3801</td>\n",
              "      <td>0.3909</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>0.6016</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.2772</td>\n",
              "      <td>0.5626</td>\n",
              "      <td>0.5594</td>\n",
              "      <td>0.3485</td>\n",
              "      <td>0.3636</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>9</th>\n",
              "      <td>0.6562</td>\n",
              "      <td>0.0000</td>\n",
              "      <td>0.3166</td>\n",
              "      <td>0.6195</td>\n",
              "      <td>0.6232</td>\n",
              "      <td>0.4444</td>\n",
              "      <td>0.4575</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>Mean</th>\n",
              "      <td>0.6075</td>\n",
              "      <td>0.3109</td>\n",
              "      <td>0.2795</td>\n",
              "      <td>0.5871</td>\n",
              "      <td>0.5750</td>\n",
              "      <td>0.3625</td>\n",
              "      <td>0.3761</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>SD</th>\n",
              "      <td>0.0227</td>\n",
              "      <td>0.3809</td>\n",
              "      <td>0.0288</td>\n",
              "      <td>0.0302</td>\n",
              "      <td>0.0243</td>\n",
              "      <td>0.0385</td>\n",
              "      <td>0.0387</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "      Accuracy     AUC  Recall   Prec.      F1   Kappa     MCC\n",
              "0       0.5974  0.0000  0.3107  0.5941  0.5693  0.3480  0.3593\n",
              "1       0.5896  0.0000  0.2808  0.5577  0.5569  0.3335  0.3469\n",
              "2       0.6182  0.0000  0.3147  0.6237  0.5913  0.3800  0.3975\n",
              "3       0.6182  0.7824  0.2663  0.6262  0.5883  0.3773  0.3950\n",
              "4       0.5714  0.7732  0.2261  0.5384  0.5321  0.2981  0.3134\n",
              "5       0.6208  0.7878  0.2687  0.6090  0.5921  0.3879  0.3996\n",
              "6       0.5844  0.7661  0.2423  0.5590  0.5556  0.3272  0.3373\n",
              "7       0.6172  0.0000  0.2920  0.5803  0.5818  0.3801  0.3909\n",
              "8       0.6016  0.0000  0.2772  0.5626  0.5594  0.3485  0.3636\n",
              "9       0.6562  0.0000  0.3166  0.6195  0.6232  0.4444  0.4575\n",
              "Mean    0.6075  0.3109  0.2795  0.5871  0.5750  0.3625  0.3761\n",
              "SD      0.0227  0.3809  0.0288  0.0302  0.0243  0.0385  0.0387"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "qsSy8sAeqFae"
      },
      "source": [
        "test = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/test.csv')\n",
        "test['type'] = test['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "test.drop('index', axis=1, inplace=True)\n",
        "\n",
        "final_model = finalize_model(blender_best_3)\n",
        "prediction = predict_model(final_model, data=test)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 17
        },
        "id": "yZtGgbe7uSYC",
        "outputId": "653eb71f-9d69-444d-b26f-f4b8852c60e9"
      },
      "source": [
        "sub['quality'] = prediction['Label']\n",
        "sub.to_csv('wine_pycaret.csv', index=False)\n",
        "files.download('wine_pycaret.csv')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "download(\"download_448c7e8a-2548-4cf1-882f-1abef0024485\", \"wine_pycaret.csv\", 5904)"
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "neiLbQXznF6K"
      },
      "source": [
        "# Models"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "PaCGWqwPzWqr"
      },
      "source": [
        "## Baseline - RF"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Zz2Lr9gMvYKZ",
        "outputId": "6cdd9484-3fe0-4d7e-9702-e512eefdc5b2"
      },
      "source": [
        "import pandas as pd\n",
        "from google.colab import drive, files\n",
        "\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "train = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/train.csv')\n",
        "test = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/test.csv')\n",
        "sub = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/sample_submission.csv')\n",
        "\n",
        "# 변주형 범수 처리\n",
        "train['type'] = train['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "test['type'] = test['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "\n",
        "# 불필요 컬럼 삭제\n",
        "label = train['quality']\n",
        "train.drop(['index', 'quality'], axis=1, inplace=True)\n",
        "test.drop('index', axis=1, inplace=True)\n",
        "\n",
        "print('before : ', len(train))\n",
        "\n",
        "# SMOTE\n",
        "strategy = {3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8} #3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8   0.706 (표준화 미적용)\n",
        "from imblearn.over_sampling import SMOTE \n",
        "sm = SMOTE(random_state=2022, k_neighbors=1, sampling_strategy=strategy) #random_state=2022, k_neighbors=1, sampling_strategy=strategy\n",
        "train, label = sm.fit_resample(train, label)\n",
        "print('after : ', len(train))\n",
        "\n",
        "# # 피쳐 엔지니어링 (정제, 이상치처리, 파생변수 생성)\n",
        "# from sklearn.preprocessing import StandardScaler\n",
        "# sc = StandardScaler()\n",
        "\n",
        "# train = sc.fit_transform(train)\n",
        "# test = sc.transform(test)\n",
        "\n",
        "\n",
        "\n",
        "# 모델링\n",
        "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier\n",
        "from sklearn.neural_network import MLPClassifier\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "from sklearn.model_selection import cross_val_score\n",
        "\n",
        "\n",
        "model = RandomForestClassifier(random_state=2022, n_estimators=400, class_weight='balanced') #random_state=2022, n_estimators=400, class_weight='balanced'  0.706 (표준화 미적용)\n",
        "\n",
        "# # 교차검증\n",
        "# score = cross_val_score(model, train, label, cv=5, scoring='accuracy')\n",
        "\n",
        "# print(score)\n",
        "# print(score.mean())\n",
        "\n",
        "\n",
        "# 제출\n",
        "model.fit(train, label)\n",
        "preds = model.predict(test)\n",
        "sub.iloc[:,1] = preds\n",
        "sub.to_csv('wine.csv', index=False)\n",
        "files.download('wine.csv')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3aietf%3awg%3aoauth%3a2.0%3aoob&scope=email%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdocs.test%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.photos.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fpeopleapi.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fdrive.activity.readonly%20https%3a%2f%2fwww.googleapis.com%2fauth%2fexperimentsandconfigs%20https%3a%2f%2fwww.googleapis.com%2fauth%2fphotos.native&response_type=code\n",
            "\n",
            "Enter your authorization code:\n",
            "4/1AX4XfWiFhYUfdf308eHfQN---zZD7kHYnsjD9hG0HhKSzfvXmS6NEWticU8\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ibs_512JxzY0"
      },
      "source": [
        "## SVM"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 255
        },
        "id": "FFADugAIx2-b",
        "outputId": "f427cf18-c53f-45c2-8922-218718dc9775"
      },
      "source": [
        "import pandas as pd\n",
        "from google.colab import drive, files\n",
        "\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "train = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/train.csv')\n",
        "test = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/test.csv')\n",
        "sub = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/sample_submission.csv')\n",
        "\n",
        "# 변주형 범수 처리\n",
        "train['type'] = train['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "test['type'] = test['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "\n",
        "# 불필요 컬럼 삭제\n",
        "label = train['quality']\n",
        "train.drop(['index', 'quality'], axis=1, inplace=True)\n",
        "test.drop('index', axis=1, inplace=True)\n",
        "\n",
        "print('before : ', len(train))\n",
        "\n",
        "# SMOTE\n",
        "strategy = {3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8} #3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8   0.706 (표준화 미적용)\n",
        "from imblearn.over_sampling import SMOTE \n",
        "sm = SMOTE(random_state=2022, k_neighbors=1, sampling_strategy=strategy) #random_state=2022, k_neighbors=1, sampling_strategy=strategy\n",
        "train, label = sm.fit_resample(train, label)\n",
        "print('after : ', len(train))\n",
        "\n",
        "# 피쳐 엔지니어링 (정제, 이상치처리, 파생변수 생성)\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "sc = StandardScaler()\n",
        "\n",
        "train = sc.fit_transform(train)\n",
        "test = sc.transform(test)\n",
        "\n",
        "\n",
        "\n",
        "# 모델링\n",
        "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier\n",
        "from sklearn import svm\n",
        "from sklearn.model_selection import cross_val_score\n",
        "\n",
        "model = svm.SVC(decision_function_shape='ovo', C=3, gamma=1)\n",
        "\n",
        "# 교차검증\n",
        "score = cross_val_score(model, train, label, cv=5, scoring='accuracy')\n",
        "\n",
        "print(score)\n",
        "print(score.mean())\n",
        "\n",
        "\n",
        "# 제출\n",
        "model.fit(train, label)\n",
        "preds = model.predict(test)\n",
        "sub.iloc[:,1] = preds\n",
        "sub.to_csv('wine.csv', index=False)\n",
        "files.download('wine.csv')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n",
            "before :  5497\n",
            "after :  5616\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[0.64145907 0.66607302 0.61798753 0.63757792 0.67319679]\n",
            "0.6472588674844643\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "download(\"download_f6197c21-c26a-408d-b95c-a460b9e08019\", \"wine.csv\", 5904)"
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "R8icgggb0Xvj",
        "outputId": "e244b2fe-cf3d-405f-84b4-1749f1d0f39e"
      },
      "source": [
        "from sklearn.model_selection import GridSearchCV\n",
        "estimator = svm.SVC(decision_function_shape='ovo')\n",
        "# 구하고자 하는 parameter와 범위\n",
        "para_c = [ c for c in range(1, 15)]\n",
        "para_gamma = [gamma for gamma in range(1, 15)]\n",
        "param_grid = {\"C\": para_c,\n",
        "              \"gamma\": para_gamma}\n",
        "# 정확도가 높은 최적 parameter 찾기\n",
        "grid_svc = GridSearchCV(estimator, param_grid, scoring=\"accuracy\", n_jobs = -1)\n",
        "grid_svc.fit(train, label)\n",
        "print(\"best estimator model: \\n{}\".format(grid_svc.best_estimator_))\n",
        "print(\"\\nbest parameter: \\n{}\".format(grid_svc.best_params_))\n",
        "print(\"\\nbest score: \\n{}\".format(grid_svc.best_score_.round(3)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "best estimator model: \n",
            "SVC(C=3, break_ties=False, cache_size=200, class_weight=None, coef0=0.0,\n",
            "    decision_function_shape='ovo', degree=3, gamma=1, kernel='rbf', max_iter=-1,\n",
            "    probability=False, random_state=None, shrinking=True, tol=0.001,\n",
            "    verbose=False)\n",
            "\n",
            "best parameter: \n",
            "{'C': 3, 'gamma': 1}\n",
            "\n",
            "best score: \n",
            "0.647\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-jxaxc1sWime"
      },
      "source": [
        "## Gradient Boost"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cBuOqisj4o6W",
        "outputId": "a931bfae-9733-41e5-80e3-1bc3fcb62282"
      },
      "source": [
        "import pandas as pd\n",
        "from google.colab import drive, files\n",
        "\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "train = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/train.csv')\n",
        "test = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/test.csv')\n",
        "sub = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/sample_submission.csv')\n",
        "\n",
        "# 변주형 범수 처리\n",
        "train['type'] = train['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "test['type'] = test['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "\n",
        "# 불필요 컬럼 삭제\n",
        "label = train['quality']\n",
        "train.drop(['index', 'quality'], axis=1, inplace=True)\n",
        "test.drop('index', axis=1, inplace=True)\n",
        "\n",
        "print('before : ', len(train))\n",
        "\n",
        "# SMOTE\n",
        "strategy = {3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8} #3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8   0.706 (표준화 미적용)\n",
        "from imblearn.over_sampling import SMOTE \n",
        "sm = SMOTE(random_state=2022, k_neighbors=1, sampling_strategy=strategy) #random_state=2022, k_neighbors=1, sampling_strategy=strategy\n",
        "train, label = sm.fit_resample(train, label)\n",
        "print('after : ', len(train))\n",
        "\n",
        "# # 피쳐 엔지니어링 (정제, 이상치처리, 파생변수 생성)\n",
        "# from sklearn.preprocessing import StandardScaler\n",
        "# sc = StandardScaler()\n",
        "\n",
        "# train = sc.fit_transform(train)\n",
        "# test = sc.transform(test)\n",
        "\n",
        "\n",
        "\n",
        "# 모델링\n",
        "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier\n",
        "from sklearn import svm\n",
        "from sklearn.model_selection import cross_val_score\n",
        "\n",
        "model = GradientBoostingClassifier(min_samples_split = 10,\n",
        "                                   min_samples_leaf = 1,\n",
        "                                   max_depth = 5, \n",
        "                                   n_estimators = 200,\n",
        "                                   learning_rate = .1,\n",
        "                                   random_state=2021)\n",
        "\n",
        "# 교차검증\n",
        "score = cross_val_score(model, train, label, cv=5, scoring='accuracy')\n",
        "\n",
        "print(score)\n",
        "print(score.mean())\n",
        "\n",
        "\n",
        "# # 제출\n",
        "# model.fit(train, label)\n",
        "# preds = model.predict(test)\n",
        "# sub.iloc[:,1] = preds\n",
        "# sub.to_csv('wine.csv', index=False)\n",
        "# files.download('wine.csv')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n",
            "before :  5497\n",
            "after :  5616\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[0.64768683 0.66518255 0.63312556 0.64470169 0.66963491]\n",
            "0.6520663068864221\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "TOM2M4zsBYxV"
      },
      "source": [
        "## KNN"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Hk1dIAWRBaOu",
        "outputId": "e5ddd97f-b889-406f-c193-f34e4fac2e63"
      },
      "source": [
        "import pandas as pd\n",
        "from google.colab import drive, files\n",
        "\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "train = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/train.csv')\n",
        "test = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/test.csv')\n",
        "sub = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/sample_submission.csv')\n",
        "\n",
        "# 변주형 범수 처리\n",
        "train['type'] = train['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "test['type'] = test['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "\n",
        "# 불필요 컬럼 삭제\n",
        "label = train['quality']\n",
        "train.drop(['index', 'quality'], axis=1, inplace=True)\n",
        "test.drop('index', axis=1, inplace=True)\n",
        "\n",
        "print('before : ', len(train))\n",
        "\n",
        "# SMOTE\n",
        "strategy = {3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8} #3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8   0.706 (표준화 미적용)\n",
        "from imblearn.over_sampling import SMOTE \n",
        "sm = SMOTE(random_state=2022, k_neighbors=1, sampling_strategy=strategy) #random_state=2022, k_neighbors=1, sampling_strategy=strategy\n",
        "train, label = sm.fit_resample(train, label)\n",
        "print('after : ', len(train))\n",
        "\n",
        "# # 피쳐 엔지니어링 (정제, 이상치처리, 파생변수 생성)\n",
        "# from sklearn.preprocessing import StandardScaler\n",
        "# sc = StandardScaler()\n",
        "\n",
        "# train = sc.fit_transform(train)\n",
        "# test = sc.transform(test)\n",
        "\n",
        "\n",
        "\n",
        "# 모델링\n",
        "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier\n",
        "from sklearn.neighbors import KNeighborsClassifier\n",
        "from sklearn.model_selection import cross_val_score\n",
        "\n",
        "model = KNeighborsClassifier(n_neighbors = 7, weights = \"distance\", metric = \"manhattan\",)\n",
        "\n",
        "# 교차검증\n",
        "score = cross_val_score(model, train, label, cv=5, scoring='accuracy')\n",
        "\n",
        "print(score)\n",
        "print(score.mean())\n",
        "\n",
        "\n",
        "# # 제출\n",
        "# model.fit(train, label)\n",
        "# preds = model.predict(test)\n",
        "# sub.iloc[:,1] = preds\n",
        "# sub.to_csv('wine.csv', index=False)\n",
        "# files.download('wine.csv')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n",
            "before :  5497\n",
            "after :  5616\n",
            "[0.59252669 0.61709706 0.56366874 0.59839715 0.60463045]\n",
            "0.5952640201798056\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eKoNz0dAnPXt"
      },
      "source": [
        "# Ensemble - VotingClassifier"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "R2L8vDQQehJN",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 238
        },
        "outputId": "c6214022-5fdc-4684-a1fa-edb32205f6de"
      },
      "source": [
        "import pandas as pd\n",
        "from google.colab import drive, files\n",
        "\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "train = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/train.csv')\n",
        "test = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/test.csv')\n",
        "sub = pd.read_csv('./drive/My Drive/Colab Notebooks/빅분기 실기/연습_데이콘_와인품질분류/sample_submission.csv')\n",
        "\n",
        "# 변주형 범수 처리\n",
        "train['type'] = train['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "test['type'] = test['type'].map(lambda x : 1 if x == 'white' else 0)\n",
        "\n",
        "# 불필요 컬럼 삭제\n",
        "label = train['quality']\n",
        "train.drop(['index', 'quality'], axis=1, inplace=True)\n",
        "test.drop('index', axis=1, inplace=True)\n",
        "\n",
        "print('before : ', len(train))\n",
        "\n",
        "# SMOTE\n",
        "strategy = {3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8} #3:40, 4:240, 5:1788, 6:2416, 7:924, 8:200, 9:8   0.706 (표준화 미적용)\n",
        "from imblearn.over_sampling import SMOTE \n",
        "sm = SMOTE(random_state=2022, k_neighbors=1, sampling_strategy=strategy) #random_state=2022, k_neighbors=1, sampling_strategy=strategy\n",
        "train, label = sm.fit_resample(train, label)\n",
        "print('after : ', len(train))\n",
        "\n",
        "# 피쳐 엔지니어링 (정제, 이상치처리, 파생변수 생성)\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "sc = StandardScaler()\n",
        "\n",
        "train = sc.fit_transform(train)\n",
        "test = sc.transform(test)\n",
        "\n",
        "\n",
        "\n",
        "# 모델링\n",
        "from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier\n",
        "from sklearn import svm\n",
        "from sklearn.neighbors import KNeighborsClassifier\n",
        "\n",
        "from sklearn.ensemble import VotingClassifier\n",
        "\n",
        "voting_model = VotingClassifier(estimators=[ ('rf', RandomForestClassifier(random_state=2022, n_estimators=400, class_weight='balanced')),\n",
        "                                            ('svm',  svm.SVC(decision_function_shape='ovo', C=3, gamma=1, random_state=2022, probability=True)),\n",
        "                                            ('gb', GradientBoostingClassifier(min_samples_split = 10, min_samples_leaf = 1, max_depth = 5, n_estimators = 200, learning_rate = .1, random_state=2021)),\n",
        "                                            ('knn', KNeighborsClassifier(n_neighbors = 7, weights = \"distance\", metric = \"manhattan\"))], voting='soft', n_jobs=4)\n",
        "\n",
        "# 제출\n",
        "voting_model.fit(train, label)\n",
        "preds = voting_model.predict(test)\n",
        "sub.iloc[:,1] = preds\n",
        "sub.to_csv('wine_ensemble.csv', index=False)\n",
        "files.download('wine_ensemble.csv')"
      ],
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n",
            "before :  5497\n",
            "after :  5616\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/utils/deprecation.py:87: FutureWarning: Function safe_indexing is deprecated; safe_indexing is deprecated in version 0.22 and will be removed in version 0.24.\n",
            "  warnings.warn(msg, category=FutureWarning)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "\n",
              "    async function download(id, filename, size) {\n",
              "      if (!google.colab.kernel.accessAllowed) {\n",
              "        return;\n",
              "      }\n",
              "      const div = document.createElement('div');\n",
              "      const label = document.createElement('label');\n",
              "      label.textContent = `Downloading \"${filename}\": `;\n",
              "      div.appendChild(label);\n",
              "      const progress = document.createElement('progress');\n",
              "      progress.max = size;\n",
              "      div.appendChild(progress);\n",
              "      document.body.appendChild(div);\n",
              "\n",
              "      const buffers = [];\n",
              "      let downloaded = 0;\n",
              "\n",
              "      const channel = await google.colab.kernel.comms.open(id);\n",
              "      // Send a message to notify the kernel that we're ready.\n",
              "      channel.send({})\n",
              "\n",
              "      for await (const message of channel.messages) {\n",
              "        // Send a message to notify the kernel that we're ready.\n",
              "        channel.send({})\n",
              "        if (message.buffers) {\n",
              "          for (const buffer of message.buffers) {\n",
              "            buffers.push(buffer);\n",
              "            downloaded += buffer.byteLength;\n",
              "            progress.value = downloaded;\n",
              "          }\n",
              "        }\n",
              "      }\n",
              "      const blob = new Blob(buffers, {type: 'application/binary'});\n",
              "      const a = document.createElement('a');\n",
              "      a.href = window.URL.createObjectURL(blob);\n",
              "      a.download = filename;\n",
              "      div.appendChild(a);\n",
              "      a.click();\n",
              "      div.remove();\n",
              "    }\n",
              "  "
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "application/javascript": [
              "download(\"download_cf36cad4-5e89-4705-a2d2-efbfe77ceaba\", \"wine_ensemble.csv\", 5904)"
            ],
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GvCgKNfdnmfG"
      },
      "source": [
        "_"
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}