사이킷런(220218).ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyOJS4bCz+wGDCDcD5Db1cO/",
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/cnddlf/2022_1_Study_AI/blob/main/%EC%82%AC%EC%9D%B4%ED%82%B7%EB%9F%B0(220218).ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "id": "QeWjfWb7Wj0r",
        "outputId": "f720c3e9-a1ae-42af-f2cb-5826d8e732ad"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'1.0.2'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 1
        }
      ],
      "source": [
        "import sklearn\n",
        "# sklearn의 동작 유무 확인, 버전 확인\n",
        "sklearn.__version__"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.datasets import load_iris\n",
        "\n",
        "# iris 정보를 얻어오기\n",
        "iris = load_iris()\n",
        "iris\n",
        "# 타입 확인\n",
        "type(iris)\n",
        "# 가지고 있는 key 정보(내부 정보)\n",
        "iris.keys()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "p3A8WMwOW4a-",
        "outputId": "8c6f0824-4c66-4191-cbc9-b188303532d6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "dict_keys(['data', 'target', 'frame', 'target_names', 'DESCR', 'feature_names', 'filename', 'data_module'])"
            ]
          },
          "metadata": {},
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# print(iris['DESCR'])\n",
        "iris['data_module']"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "id": "f4Q_R_W0Xbu4",
        "outputId": "04f1d3b8-bd08-4533-8c6e-3558691857a6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'sklearn.datasets.data'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 3
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# iris_data = iris.data\n",
        "iris_data = iris['data']\n",
        "iris_data\n",
        "\n",
        "type(iris_data)\n",
        "# :의 왼쪽은 시작, 오른쪽은 끝, 없으면 0이 생략\n",
        "print(iris_data[:5])\n",
        "iris_data[1]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "PlDNxj3Ff5TJ",
        "outputId": "c83cda0c-9d80-4627-a7cb-1c154b677005"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[[5.1 3.5 1.4 0.2]\n",
            " [4.9 3.  1.4 0.2]\n",
            " [4.7 3.2 1.3 0.2]\n",
            " [4.6 3.1 1.5 0.2]\n",
            " [5.  3.6 1.4 0.2]]\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([4.9, 3. , 1.4, 0.2])"
            ]
          },
          "metadata": {},
          "execution_count": 4
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "iris_target = iris.target\n",
        "iris_target"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EHHwkoLNhZlk",
        "outputId": "91a3199e-82d6-4c30-f84d-dcd0213e6579"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
              "       0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
              "       0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
              "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,\n",
              "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
              "       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,\n",
              "       2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2])"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "iris_feature_names = iris.feature_names\n",
        "iris_feature_names"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aObLLEg7h2Vg",
        "outputId": "35dc2753-9fcf-444f-d381-732e70fd9864"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['sepal length (cm)',\n",
              " 'sepal width (cm)',\n",
              " 'petal length (cm)',\n",
              " 'petal width (cm)']"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "iris = load_iris()\n",
        "# data와 feature 정보로 dataframe 생성\n",
        "df_iris = pd.DataFrame(data=iris['data'], columns=iris['feature_names'])\n",
        "# 상위 5개의 데이터 확인\n",
        "df_iris.head()\n",
        "\n",
        "# 각 데이터별 결과 저장\n",
        "df_iris['label'] = iris['target']\n",
        "# 하위 5개의 데이터 확인\n",
        "df_iris.tail()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "UovPiS9okgrt",
        "outputId": "6c139b81-714c-4a54-f1ab-2a4763a27d8d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)  \\\n",
              "145                6.7               3.0                5.2               2.3   \n",
              "146                6.3               2.5                5.0               1.9   \n",
              "147                6.5               3.0                5.2               2.0   \n",
              "148                6.2               3.4                5.4               2.3   \n",
              "149                5.9               3.0                5.1               1.8   \n",
              "\n",
              "     label  \n",
              "145      2  \n",
              "146      2  \n",
              "147      2  \n",
              "148      2  \n",
              "149      2  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-c9528b42-550d-4fef-a8ad-c73be3e3add1\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>sepal length (cm)</th>\n",
              "      <th>sepal width (cm)</th>\n",
              "      <th>petal length (cm)</th>\n",
              "      <th>petal width (cm)</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>145</th>\n",
              "      <td>6.7</td>\n",
              "      <td>3.0</td>\n",
              "      <td>5.2</td>\n",
              "      <td>2.3</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>146</th>\n",
              "      <td>6.3</td>\n",
              "      <td>2.5</td>\n",
              "      <td>5.0</td>\n",
              "      <td>1.9</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>147</th>\n",
              "      <td>6.5</td>\n",
              "      <td>3.0</td>\n",
              "      <td>5.2</td>\n",
              "      <td>2.0</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>148</th>\n",
              "      <td>6.2</td>\n",
              "      <td>3.4</td>\n",
              "      <td>5.4</td>\n",
              "      <td>2.3</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>149</th>\n",
              "      <td>5.9</td>\n",
              "      <td>3.0</td>\n",
              "      <td>5.1</td>\n",
              "      <td>1.8</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-c9528b42-550d-4fef-a8ad-c73be3e3add1')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-c9528b42-550d-4fef-a8ad-c73be3e3add1 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-c9528b42-550d-4fef-a8ad-c73be3e3add1');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 7
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target)\n",
        "X_train[:5]\n",
        "\n",
        "print('전체 데이터 크기 : ', iris['data'].size)\n",
        "print('train 데이터의 기본 크기는 전체의 75% : ', X_train.size)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Jtsjs4g9k3Mp",
        "outputId": "70632859-717f-44b9-891e-80b38f2c0ed0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "전체 데이터 크기 :  600\n",
            "train 데이터의 기본 크기는 전체의 75% :  448\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "> 위의 코드를 실행할 때마다 다른 결과를 얻게 된다.\n",
        "\n",
        "```\n",
        "array([[5.6, 2.5, 3.9, 1.1],\n",
        "       [4.4, 2.9, 1.4, 0.2],\n",
        "       [5.5, 2.6, 4.4, 1.2],\n",
        "       [7.2, 3.2, 6. , 1.8],\n",
        "       [6.1, 2.6, 5.6, 1.4]])\n",
        "\n",
        "array([[5.1, 3.4, 1.5, 0.2],\n",
        "       [4.8, 3.4, 1.6, 0.2],\n",
        "       [5.8, 2.6, 4. , 1.2],\n",
        "       [5.7, 2.8, 4.1, 1.3],\n",
        "       [6.8, 2.8, 4.8, 1.4]])\n",
        "```\n"
      ],
      "metadata": {
        "id": "XGseh95PpSmi"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# 위와 같이 실행할때마다 다른 결과가 나타나는 것을 방지하기 위해 random_state 사용\n",
        "X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size=0.2, random_state=62)\n",
        "X_train[:5]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hyp7sQyjo2VQ",
        "outputId": "668852a9-5019-432d-a50b-4e86831143c1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[5.5, 2.3, 4. , 1.3],\n",
              "       [5.9, 3.2, 4.8, 1.8],\n",
              "       [5.8, 2.7, 5.1, 1.9],\n",
              "       [6.9, 3.2, 5.7, 2.3],\n",
              "       [5.8, 4. , 1.2, 0.2]])"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 처음부터 3번째 열까지, 모든 feature 정보까지 출력\n",
        "df_iris.iloc[:3, :4]"
      ],
      "metadata": {
        "id": "IpFjcn3EqFw0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 143
        },
        "outputId": "c46e363b-91df-4348-e856-bfaf874bb825"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)\n",
              "0                5.1               3.5                1.4               0.2\n",
              "1                4.9               3.0                1.4               0.2\n",
              "2                4.7               3.2                1.3               0.2"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-35ce5324-ddc4-4b94-90ba-0ef7b85a7921\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>sepal length (cm)</th>\n",
              "      <th>sepal width (cm)</th>\n",
              "      <th>petal length (cm)</th>\n",
              "      <th>petal width (cm)</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>5.1</td>\n",
              "      <td>3.5</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>4.9</td>\n",
              "      <td>3.0</td>\n",
              "      <td>1.4</td>\n",
              "      <td>0.2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>4.7</td>\n",
              "      <td>3.2</td>\n",
              "      <td>1.3</td>\n",
              "      <td>0.2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-35ce5324-ddc4-4b94-90ba-0ef7b85a7921')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-35ce5324-ddc4-4b94-90ba-0ef7b85a7921 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-35ce5324-ddc4-4b94-90ba-0ef7b85a7921');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_test_split(df_iris.iloc[:, :4], df_iris['label'])"
      ],
      "metadata": {
        "id": "vXTAy6R-rBpC",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "b739ae1c-7428-4742-a26e-0256f94e5c00"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[     sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)\n",
              " 84                 5.4               3.0                4.5               1.5\n",
              " 26                 5.0               3.4                1.6               0.4\n",
              " 52                 6.9               3.1                4.9               1.5\n",
              " 28                 5.2               3.4                1.4               0.2\n",
              " 69                 5.6               2.5                3.9               1.1\n",
              " ..                 ...               ...                ...               ...\n",
              " 40                 5.0               3.5                1.3               0.3\n",
              " 16                 5.4               3.9                1.3               0.4\n",
              " 116                6.5               3.0                5.5               1.8\n",
              " 60                 5.0               2.0                3.5               1.0\n",
              " 123                6.3               2.7                4.9               1.8\n",
              " \n",
              " [112 rows x 4 columns],\n",
              "      sepal length (cm)  sepal width (cm)  petal length (cm)  petal width (cm)\n",
              " 66                 5.6               3.0                4.5               1.5\n",
              " 102                7.1               3.0                5.9               2.1\n",
              " 101                5.8               2.7                5.1               1.9\n",
              " 11                 4.8               3.4                1.6               0.2\n",
              " 79                 5.7               2.6                3.5               1.0\n",
              " 114                5.8               2.8                5.1               2.4\n",
              " 85                 6.0               3.4                4.5               1.6\n",
              " 58                 6.6               2.9                4.6               1.3\n",
              " 105                7.6               3.0                6.6               2.1\n",
              " 34                 4.9               3.1                1.5               0.2\n",
              " 92                 5.8               2.6                4.0               1.2\n",
              " 117                7.7               3.8                6.7               2.2\n",
              " 113                5.7               2.5                5.0               2.0\n",
              " 138                6.0               3.0                4.8               1.8\n",
              " 46                 5.1               3.8                1.6               0.2\n",
              " 96                 5.7               2.9                4.2               1.3\n",
              " 71                 6.1               2.8                4.0               1.3\n",
              " 147                6.5               3.0                5.2               2.0\n",
              " 133                6.3               2.8                5.1               1.5\n",
              " 125                7.2               3.2                6.0               1.8\n",
              " 56                 6.3               3.3                4.7               1.6\n",
              " 24                 4.8               3.4                1.9               0.2\n",
              " 81                 5.5               2.4                3.7               1.0\n",
              " 27                 5.2               3.5                1.5               0.2\n",
              " 70                 5.9               3.2                4.8               1.8\n",
              " 108                6.7               2.5                5.8               1.8\n",
              " 6                  4.6               3.4                1.4               0.3\n",
              " 122                7.7               2.8                6.7               2.0\n",
              " 97                 6.2               2.9                4.3               1.3\n",
              " 134                6.1               2.6                5.6               1.4\n",
              " 61                 5.9               3.0                4.2               1.5\n",
              " 115                6.4               3.2                5.3               2.3\n",
              " 32                 5.2               4.1                1.5               0.1\n",
              " 139                6.9               3.1                5.4               2.1\n",
              " 93                 5.0               2.3                3.3               1.0\n",
              " 2                  4.7               3.2                1.3               0.2\n",
              " 148                6.2               3.4                5.4               2.3\n",
              " 145                6.7               3.0                5.2               2.3,\n",
              " 84     1\n",
              " 26     0\n",
              " 52     1\n",
              " 28     0\n",
              " 69     1\n",
              "       ..\n",
              " 40     0\n",
              " 16     0\n",
              " 116    2\n",
              " 60     1\n",
              " 123    2\n",
              " Name: label, Length: 112, dtype: int64,\n",
              " 66     1\n",
              " 102    2\n",
              " 101    2\n",
              " 11     0\n",
              " 79     1\n",
              " 114    2\n",
              " 85     1\n",
              " 58     1\n",
              " 105    2\n",
              " 34     0\n",
              " 92     1\n",
              " 117    2\n",
              " 113    2\n",
              " 138    2\n",
              " 46     0\n",
              " 96     1\n",
              " 71     1\n",
              " 147    2\n",
              " 133    2\n",
              " 125    2\n",
              " 56     1\n",
              " 24     0\n",
              " 81     1\n",
              " 27     0\n",
              " 70     1\n",
              " 108    2\n",
              " 6      0\n",
              " 122    2\n",
              " 97     1\n",
              " 134    2\n",
              " 61     1\n",
              " 115    2\n",
              " 32     0\n",
              " 139    2\n",
              " 93     1\n",
              " 2      0\n",
              " 148    2\n",
              " 145    2\n",
              " Name: label, dtype: int64]"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_iris_data = df_iris.drop('label', axis=1)\n",
        "df_iris_data\n",
        "\n",
        "df_iris_label = df_iris['label']\n",
        "df_iris_label"
      ],
      "metadata": {
        "id": "oPBCvqOLrsi5",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "7a8a7442-2911-469d-a9c8-eea6f67d6211"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0      0\n",
              "1      0\n",
              "2      0\n",
              "3      0\n",
              "4      0\n",
              "      ..\n",
              "145    2\n",
              "146    2\n",
              "147    2\n",
              "148    2\n",
              "149    2\n",
              "Name: label, Length: 150, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.tree import DecisionTreeClassifier\n",
        "\n",
        "# 모델 얻어오기\n",
        "df_clf = DecisionTreeClassifier()\n",
        "# 모델 생성\n",
        "df_clf.fit(X_train, y_train)\n",
        "\n",
        "DecisionTreeClassifier()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vo5u3ABPr9kt",
        "outputId": "c7ea5fed-f064-4c5e-b1d4-5be322e5c148"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "DecisionTreeClassifier()"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 검증데이터를 통해 예측 정보 얻기\n",
        "pred = df_clf.predict(X_test)\n",
        "# 예측 정보 출력\n",
        "print(pred)\n",
        "# 실 데이터 출력\n",
        "print(y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8CgvzFNO0SZ-",
        "outputId": "38ce6e54-b68a-4b53-f364-d0e650d7464c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[2 2 0 0 2 2 2 0 1 1 2 1 0 1 1 1 0 1 0 0 0 0 2 1 2 0 2 0 2 0]\n",
            "[2 2 0 0 2 1 2 0 1 1 2 2 0 1 1 1 0 1 0 0 0 0 2 1 2 0 2 0 2 0]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import accuracy_score\n",
        "\n",
        "print('예측 정확도 : {0: .4f}'.format(accuracy_score(y_test, pred)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_sD2rniQ0siM",
        "outputId": "b93d2c5f-4f2b-4c15-da2f-6e98750df69b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "예측 정확도 :  0.9333\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# iris 정보를 읽어 들이고 데이터와 타겟 정보를 각각 5개씩 출력하시오\n",
        "\n",
        "from sklearn.datasets import load_iris\n",
        "\n",
        "iris = load_iris()\n",
        "iris_data = iris['data']\n",
        "iris_label = iris['target']\n",
        "\n",
        "print(iris_data[:5])\n",
        "print(iris_label[:5])"
      ],
      "metadata": {
        "id": "AHCra_u9Pcd6",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ef5c5dbc-1759-4156-c63e-201496295417"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[[5.1 3.5 1.4 0.2]\n",
            " [4.9 3.  1.4 0.2]\n",
            " [4.7 3.2 1.3 0.2]\n",
            " [4.6 3.1 1.5 0.2]\n",
            " [5.  3.6 1.4 0.2]]\n",
            "[0 0 0 0 0]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.tree import DecisionTreeClassifier\n",
        "\n",
        "dt_clf = DecisionTreeClassifier"
      ],
      "metadata": {
        "id": "ZIPuibtdRmz7"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import KFold\n",
        "\n",
        "kfold = KFold(n_splits=5)"
      ],
      "metadata": {
        "id": "RP2TAvp3SSTU"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# shape이라는 것은 데이터의 모양을 보여준다.\n",
        "iris_data.shape\n",
        "# 행의 개수\n",
        "iris_data.shape[0]\n",
        "# 열(feature)의 개수\n",
        "iris_data.shape[1]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "SzxTFqbCSrQK",
        "outputId": "07f65256-2560-4386-cb04-d9c3097a17e4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "4"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "for train_idx, test_idx in kfold.split(iris_data):\n",
        "  print('train index')\n",
        "  print(train_idx)\n",
        "  print('test index')\n",
        "  print(test_idx)\n",
        "  print('='*50)"
      ],
      "metadata": {
        "id": "DvXg68TjTopD",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "433f4713-0121-4fa7-c7b9-848fceb97061"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "train index\n",
            "[ 30  31  32  33  34  35  36  37  38  39  40  41  42  43  44  45  46  47\n",
            "  48  49  50  51  52  53  54  55  56  57  58  59  60  61  62  63  64  65\n",
            "  66  67  68  69  70  71  72  73  74  75  76  77  78  79  80  81  82  83\n",
            "  84  85  86  87  88  89  90  91  92  93  94  95  96  97  98  99 100 101\n",
            " 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119\n",
            " 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137\n",
            " 138 139 140 141 142 143 144 145 146 147 148 149]\n",
            "test index\n",
            "[ 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23\n",
            " 24 25 26 27 28 29]\n",
            "==================================================\n",
            "train index\n",
            "[  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17\n",
            "  18  19  20  21  22  23  24  25  26  27  28  29  60  61  62  63  64  65\n",
            "  66  67  68  69  70  71  72  73  74  75  76  77  78  79  80  81  82  83\n",
            "  84  85  86  87  88  89  90  91  92  93  94  95  96  97  98  99 100 101\n",
            " 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119\n",
            " 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137\n",
            " 138 139 140 141 142 143 144 145 146 147 148 149]\n",
            "test index\n",
            "[30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53\n",
            " 54 55 56 57 58 59]\n",
            "==================================================\n",
            "train index\n",
            "[  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17\n",
            "  18  19  20  21  22  23  24  25  26  27  28  29  30  31  32  33  34  35\n",
            "  36  37  38  39  40  41  42  43  44  45  46  47  48  49  50  51  52  53\n",
            "  54  55  56  57  58  59  90  91  92  93  94  95  96  97  98  99 100 101\n",
            " 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119\n",
            " 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137\n",
            " 138 139 140 141 142 143 144 145 146 147 148 149]\n",
            "test index\n",
            "[60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83\n",
            " 84 85 86 87 88 89]\n",
            "==================================================\n",
            "train index\n",
            "[  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17\n",
            "  18  19  20  21  22  23  24  25  26  27  28  29  30  31  32  33  34  35\n",
            "  36  37  38  39  40  41  42  43  44  45  46  47  48  49  50  51  52  53\n",
            "  54  55  56  57  58  59  60  61  62  63  64  65  66  67  68  69  70  71\n",
            "  72  73  74  75  76  77  78  79  80  81  82  83  84  85  86  87  88  89\n",
            " 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137\n",
            " 138 139 140 141 142 143 144 145 146 147 148 149]\n",
            "test index\n",
            "[ 90  91  92  93  94  95  96  97  98  99 100 101 102 103 104 105 106 107\n",
            " 108 109 110 111 112 113 114 115 116 117 118 119]\n",
            "==================================================\n",
            "train index\n",
            "[  0   1   2   3   4   5   6   7   8   9  10  11  12  13  14  15  16  17\n",
            "  18  19  20  21  22  23  24  25  26  27  28  29  30  31  32  33  34  35\n",
            "  36  37  38  39  40  41  42  43  44  45  46  47  48  49  50  51  52  53\n",
            "  54  55  56  57  58  59  60  61  62  63  64  65  66  67  68  69  70  71\n",
            "  72  73  74  75  76  77  78  79  80  81  82  83  84  85  86  87  88  89\n",
            "  90  91  92  93  94  95  96  97  98  99 100 101 102 103 104 105 106 107\n",
            " 108 109 110 111 112 113 114 115 116 117 118 119]\n",
            "test index\n",
            "[120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137\n",
            " 138 139 140 141 142 143 144 145 146 147 148 149]\n",
            "==================================================\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.metrics import accuracy_score\n",
        "import numpy as np\n",
        "from sklearn.model_selection import StratifiedKFold\n",
        "\n",
        "dt_clf = DecisionTreeClassifier()\n",
        "kfold=StratifiedKFold(n_splits=3)\n",
        "\n",
        "\n",
        "cv_accuracy=[]\n",
        "n=iter = 1\n",
        "\n",
        "for train_idx, test_idx in kfold.split(iris_data, iris_label):\n",
        "  # 훈련용 데이터\n",
        "  X_train = iris_data[train_idx]\n",
        "  y_train = iris_label[train_idx]\n",
        "\n",
        "  # 검증 데이터\n",
        "  X_test = iris_data[test_idx]\n",
        "  y_test = iris_label[test_idx]\n",
        "\n",
        "  # 모델 학습\n",
        "  dt_clf.fit(X_train, y_train)\n",
        "  # 예측 출력\n",
        "  pred = dt_clf.predict(X_test)\n",
        "  # 정확도 출력\n",
        "  acc = round(accuracy_score(y_test, pred), 4)\n",
        "  print(acc)\n",
        "\n",
        "print('='*50)\n",
        "print(round(np.mean(cv_accuracy), 4))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fgL_Xge0WJJc",
        "outputId": "8dcbb5bc-975b-473b-927c-46222d4345ca"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "0.98\n",
            "0.94\n",
            "0.96\n",
            "==================================================\n",
            "nan\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/numpy/core/fromnumeric.py:3441: RuntimeWarning: Mean of empty slice.\n",
            "  out=out, **kwargs)\n",
            "/usr/local/lib/python3.7/dist-packages/numpy/core/_methods.py:189: RuntimeWarning: invalid value encountered in double_scalars\n",
            "  ret = ret.dtype.type(ret / rcount)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "x_test=[[3, 3, 1, 1]]\n",
        "dt_clf.predict(x_test)\n",
        "\n",
        "if pred[0]==1:\n",
        "  print('<p>setosa</p>')"
      ],
      "metadata": {
        "id": "8k1HZ7m4fo4a"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df_iris['label'].value_counts()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "EaRTtH2LgR71",
        "outputId": "69636980-052d-4421-d0b2-349e591221f4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0    50\n",
              "1    50\n",
              "2    50\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import StratifiedKFold\n",
        "kfold = StratifiedKFold(n_splits=3)\n",
        "\n",
        "kfold = KFold(n_splits=3)\n",
        "\n",
        "for train_idx, test_idx in kfold.split(iris_data):\n",
        "  y_train = df_iris['label'].iloc[train_idx]\n",
        "  y_test = df_iris['label'].iloc[test_idx]\n",
        "\n",
        "  print(y_train.value_counts())\n",
        "  print(y_test.value_counts())\n",
        "  print('='*50)\n",
        "\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "aL_JWhjsiAOs",
        "outputId": "5b0ebf7b-6a5e-41e7-d89b-a8da2942e8fc"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1    50\n",
            "2    50\n",
            "Name: label, dtype: int64\n",
            "0    50\n",
            "Name: label, dtype: int64\n",
            "==================================================\n",
            "0    50\n",
            "2    50\n",
            "Name: label, dtype: int64\n",
            "1    50\n",
            "Name: label, dtype: int64\n",
            "==================================================\n",
            "0    50\n",
            "1    50\n",
            "Name: label, dtype: int64\n",
            "2    50\n",
            "Name: label, dtype: int64\n",
            "==================================================\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import cross_val_score\n",
        "\n",
        "df_clf = DecisionTreeClassifier()\n",
        "scores = cross_val_score(dt_clf, X=iris_data, y=iris_label, scoring = 'accuracy', cv=3)\n",
        "scores"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "zDbOZXgqp4iS",
        "outputId": "32a206b4-cba3-403b-9f59-1974bbe6b2f4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0.98, 0.94, 1.  ])"
            ]
          },
          "metadata": {},
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "np.mean(scores)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vv3h-tssqu_v",
        "outputId": "36cadf07-f07a-4a19-c25f-2f2b06e42c48"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.9733333333333333"
            ]
          },
          "metadata": {},
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dt_clf2 = DecisionTreeClassifier()\n",
        "dt_clf2.fit(X_train, y_train)\n",
        "\n",
        "dt_clf.fit(X_train, y_train)\n",
        "\n",
        "pred1 = dt_clf.predict(X_test)\n",
        "pred2 = dt_clf2.predict(X_test)\n",
        "\n",
        "print(pred1)\n",
        "print(pred2)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UqC63Y_zq6sN",
        "outputId": "7aa5eefd-fc72-4fcf-cb73-c1f71511e168"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 1 0 0 1 0 1 0 0 1 0 1 0 0 1 1 1 1\n",
            " 1 1 1 1 1 1 1 1 1 1 1 1 1]\n",
            "[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 1 1 0 0 1 0 0 1 0 1 0 0 1 0 1 0 0 1 1 1 1\n",
            " 1 1 1 1 1 1 1 1 1 1 1 1 1]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "grid_param = {\n",
        "    'max_depth': [1, 2, 3],\n",
        "    'min_samples_split' : [2, 3, 4]\n",
        "}\n",
        "grid_param"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vzXsbeEos0jW",
        "outputId": "95f5a0f9-8f55-4c40-ac2e-ded4d273c2a0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'max_depth': [1, 2, 3], 'min_samples_split': [2, 3, 4]}"
            ]
          },
          "metadata": {},
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import GridSearchCV\n",
        "\n",
        "dt_clf = DecisionTreeClassifier()\n",
        "grid_dtree = GridSearchCV(dt_clf, param_grid=grid_param, cv=3, refit=True)\n"
      ],
      "metadata": {
        "id": "Iy2_s-qGskyD"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "grid_dtree.fit(X_train, y_train)"
      ],
      "metadata": {
        "id": "n6KuDFWewcx3",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "1ed3ec12-df71-4df8-8c42-d9ec09b32346"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "GridSearchCV(cv=3, estimator=DecisionTreeClassifier(),\n",
              "             param_grid={'max_depth': [1, 2, 3],\n",
              "                         'min_samples_split': [2, 3, 4]})"
            ]
          },
          "metadata": {},
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "scores_df = pd.DataFrame(grid_dtree.cv_results_)\n",
        "scores_df[['params', 'mean_test_score', 'rank_test_score', 'split0_test_score', 'split1_test_score', 'split2_test_score']]"
      ],
      "metadata": {
        "id": "gGkyF7ONwet6",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 332
        },
        "outputId": "d57a0321-2c9c-4be0-c315-90d1e829d7b4"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                     params  mean_test_score  rank_test_score  \\\n",
              "0  {'max_depth': 1, 'min_samples_split': 2}         0.681224                1   \n",
              "1  {'max_depth': 1, 'min_samples_split': 3}         0.681224                1   \n",
              "2  {'max_depth': 1, 'min_samples_split': 4}         0.681224                1   \n",
              "3  {'max_depth': 2, 'min_samples_split': 2}         0.681224                1   \n",
              "4  {'max_depth': 2, 'min_samples_split': 3}         0.681224                1   \n",
              "5  {'max_depth': 2, 'min_samples_split': 4}         0.681224                1   \n",
              "6  {'max_depth': 3, 'min_samples_split': 2}         0.681224                1   \n",
              "7  {'max_depth': 3, 'min_samples_split': 3}         0.681224                1   \n",
              "8  {'max_depth': 3, 'min_samples_split': 4}         0.681224                1   \n",
              "\n",
              "   split0_test_score  split1_test_score  split2_test_score  \n",
              "0           0.558824           0.969697           0.515152  \n",
              "1           0.558824           0.969697           0.515152  \n",
              "2           0.558824           0.969697           0.515152  \n",
              "3           0.558824           0.969697           0.515152  \n",
              "4           0.558824           0.969697           0.515152  \n",
              "5           0.558824           0.969697           0.515152  \n",
              "6           0.558824           0.969697           0.515152  \n",
              "7           0.558824           0.969697           0.515152  \n",
              "8           0.558824           0.969697           0.515152  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-00a7bab5-d60d-4d9a-ba58-3ae6b07d444d\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>params</th>\n",
              "      <th>mean_test_score</th>\n",
              "      <th>rank_test_score</th>\n",
              "      <th>split0_test_score</th>\n",
              "      <th>split1_test_score</th>\n",
              "      <th>split2_test_score</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>{'max_depth': 1, 'min_samples_split': 2}</td>\n",
              "      <td>0.681224</td>\n",
              "      <td>1</td>\n",
              "      <td>0.558824</td>\n",
              "      <td>0.969697</td>\n",
              "      <td>0.515152</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>{'max_depth': 1, 'min_samples_split': 3}</td>\n",
              "      <td>0.681224</td>\n",
              "      <td>1</td>\n",
              "      <td>0.558824</td>\n",
              "      <td>0.969697</td>\n",
              "      <td>0.515152</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>{'max_depth': 1, 'min_samples_split': 4}</td>\n",
              "      <td>0.681224</td>\n",
              "      <td>1</td>\n",
              "      <td>0.558824</td>\n",
              "      <td>0.969697</td>\n",
              "      <td>0.515152</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>{'max_depth': 2, 'min_samples_split': 2}</td>\n",
              "      <td>0.681224</td>\n",
              "      <td>1</td>\n",
              "      <td>0.558824</td>\n",
              "      <td>0.969697</td>\n",
              "      <td>0.515152</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>{'max_depth': 2, 'min_samples_split': 3}</td>\n",
              "      <td>0.681224</td>\n",
              "      <td>1</td>\n",
              "      <td>0.558824</td>\n",
              "      <td>0.969697</td>\n",
              "      <td>0.515152</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>5</th>\n",
              "      <td>{'max_depth': 2, 'min_samples_split': 4}</td>\n",
              "      <td>0.681224</td>\n",
              "      <td>1</td>\n",
              "      <td>0.558824</td>\n",
              "      <td>0.969697</td>\n",
              "      <td>0.515152</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6</th>\n",
              "      <td>{'max_depth': 3, 'min_samples_split': 2}</td>\n",
              "      <td>0.681224</td>\n",
              "      <td>1</td>\n",
              "      <td>0.558824</td>\n",
              "      <td>0.969697</td>\n",
              "      <td>0.515152</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7</th>\n",
              "      <td>{'max_depth': 3, 'min_samples_split': 3}</td>\n",
              "      <td>0.681224</td>\n",
              "      <td>1</td>\n",
              "      <td>0.558824</td>\n",
              "      <td>0.969697</td>\n",
              "      <td>0.515152</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>8</th>\n",
              "      <td>{'max_depth': 3, 'min_samples_split': 4}</td>\n",
              "      <td>0.681224</td>\n",
              "      <td>1</td>\n",
              "      <td>0.558824</td>\n",
              "      <td>0.969697</td>\n",
              "      <td>0.515152</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-00a7bab5-d60d-4d9a-ba58-3ae6b07d444d')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-00a7bab5-d60d-4d9a-ba58-3ae6b07d444d button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-00a7bab5-d60d-4d9a-ba58-3ae6b07d444d');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 31
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "grid_dtree.best_params_"
      ],
      "metadata": {
        "id": "vR-ygtGlwgu6",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "92a2049f-8de8-45f4-92e9-b08e41e4b8b0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'max_depth': 1, 'min_samples_split': 2}"
            ]
          },
          "metadata": {},
          "execution_count": 32
        }
      ]
    }
  ]
}