위스콘신_유방암_데이터_셋을_이용한_회귀_학습.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyMu+GjEdOB2udqR+ZeOAIyD",
      "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%9C%84%EC%8A%A4%EC%BD%98%EC%8B%A0_%EC%9C%A0%EB%B0%A9%EC%95%94_%EB%8D%B0%EC%9D%B4%ED%84%B0_%EC%85%8B%EC%9D%84_%EC%9D%B4%EC%9A%A9%ED%95%9C_%ED%9A%8C%EA%B7%80_%ED%95%99%EC%8A%B5.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#1. 위스콘신 유방암 데이터 셋 읽기"
      ],
      "metadata": {
        "id": "21aHarflpxRr"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "dmzfcoYzpu_Y"
      },
      "outputs": [],
      "source": [
        "from sklearn.datasets import load_breast_cancer\n",
        "\n",
        "cancer = load_breast_cancer()"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 표준화\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "\n",
        "scaler = StandardScaler()\n",
        "data_scaled = scaler.fit_transform(cancer.data)"
      ],
      "metadata": {
        "id": "6HynJz35p_BN"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# 훈련 / 검증 데이터 얻기\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "X_train, X_test, y_train, y_test = train_test_split(data_scaled, cancer.target, test_size = 0.3, random_state = 62)"
      ],
      "metadata": {
        "id": "ezVsbi18rP41"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# 모델 생성\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "\n",
        "lr_clf = LogisticRegression()\n",
        "lr_clf.fit(X_train, y_train)\n",
        "lr_preds = lr_clf.predict(X_test)\n",
        "lr_preds"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TIo37md-r7Sc",
        "outputId": "f5bf6202-4026-4eaf-a812-479fe80c65bf"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 0, 1, 0, 0, 0, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1,\n",
              "       1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1,\n",
              "       1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0,\n",
              "       1, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 0, 0,\n",
              "       1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0,\n",
              "       1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 1,\n",
              "       0, 0, 1, 1, 1, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1,\n",
              "       1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0])"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 지표 확인\n",
        "from sklearn.metrics import accuracy_score, roc_auc_score\n",
        "\n",
        "print('accuracy : {:0.3f}'.format(accuracy_score(y_test, lr_preds)))\n",
        "print('roc_auc: {:0.3f}'.format(roc_auc_score(y_test, lr_preds)))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3pov6c0XunXj",
        "outputId": "8e314af3-41e4-4c42-a5fa-419c08e397a5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "accuracy : 0.953\n",
            "roc_auc: 0.942\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 하이퍼 파라미터\n",
        "from sklearn.model_selection import GridSearchCV\n",
        "\n",
        "params = {'penalty':['l1', 'l2'], 'C':[0.01, 0.1, 1, 5, 10]}\n",
        "\n",
        "grid_clf = GridSearchCV(lr_clf, param_grid = params, scoring='accuracy', cv=5)\n",
        "grid_clf.fit(data_scaled, cancer.target)\n",
        "\n",
        "print('최적 하이퍼 파라미터:{0}, 최적 평균 정확도:{1:.3f}'.format(grid_clf.best_params_, grid_clf.best_score_))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "odbmvpIlr7Mq",
        "outputId": "08075140-146e-4287-de71-8d3a071d19e8"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "최적 하이퍼 파라미터:{'C': 1, 'penalty': 'l2'}, 최적 평균 정확도:0.981\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/model_selection/_validation.py:372: FitFailedWarning: \n",
            "25 fits failed out of a total of 50.\n",
            "The score on these train-test partitions for these parameters will be set to nan.\n",
            "If these failures are not expected, you can try to debug them by setting error_score='raise'.\n",
            "\n",
            "Below are more details about the failures:\n",
            "--------------------------------------------------------------------------------\n",
            "25 fits failed with the following error:\n",
            "Traceback (most recent call last):\n",
            "  File \"/usr/local/lib/python3.7/dist-packages/sklearn/model_selection/_validation.py\", line 680, in _fit_and_score\n",
            "    estimator.fit(X_train, y_train, **fit_params)\n",
            "  File \"/usr/local/lib/python3.7/dist-packages/sklearn/linear_model/_logistic.py\", line 1461, in fit\n",
            "    solver = _check_solver(self.solver, self.penalty, self.dual)\n",
            "  File \"/usr/local/lib/python3.7/dist-packages/sklearn/linear_model/_logistic.py\", line 449, in _check_solver\n",
            "    % (solver, penalty)\n",
            "ValueError: Solver lbfgs supports only 'l2' or 'none' penalties, got l1 penalty.\n",
            "\n",
            "  warnings.warn(some_fits_failed_message, FitFailedWarning)\n",
            "/usr/local/lib/python3.7/dist-packages/sklearn/model_selection/_search.py:972: UserWarning: One or more of the test scores are non-finite: [       nan 0.9490607         nan 0.97540755        nan 0.98068623\n",
            "        nan 0.97015991        nan 0.97015991]\n",
            "  category=UserWarning,\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 1. 파일 읽기"
      ],
      "metadata": {
        "id": "u2p6iD6EvRG1"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# 드라이버 로드\n",
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Ww9PoUHPvTUr",
        "outputId": "1ed3c643-4059-4b49-ba5e-3b8a55252972"
      },
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 타이타닉 정보 읽기\n",
        "import pandas as pd\n",
        "\n",
        "filepath = '/content/drive/MyDrive/2022_1_Study_AI/2022_1_Study_AI/data/titanic.csv'\n",
        "df_titanic = pd.read_csv(filepath)\n",
        "df_titanic.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 206
        },
        "id": "nO4yuRwuvU4d",
        "outputId": "9e91ea24-fa5d-462e-cb12-49db0bcfbf37"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   PassengerId  Survived  Pclass  \\\n",
              "0            1         0       3   \n",
              "1            2         1       1   \n",
              "2            3         1       3   \n",
              "3            4         1       1   \n",
              "4            5         0       3   \n",
              "\n",
              "                                                Name     Sex   Age  SibSp  \\\n",
              "0                            Braund, Mr. Owen Harris    male  22.0      1   \n",
              "1  Cumings, Mrs. John Bradley (Florence Briggs Th...  female  38.0      1   \n",
              "2                             Heikkinen, Miss. Laina  female  26.0      0   \n",
              "3       Futrelle, Mrs. Jacques Heath (Lily May Peel)  female  35.0      1   \n",
              "4                           Allen, Mr. William Henry    male  35.0      0   \n",
              "\n",
              "   Parch            Ticket     Fare Cabin Embarked  \n",
              "0      0         A/5 21171   7.2500   NaN        S  \n",
              "1      0          PC 17599  71.2833   C85        C  \n",
              "2      0  STON/O2. 3101282   7.9250   NaN        S  \n",
              "3      0            113803  53.1000  C123        S  \n",
              "4      0            373450   8.0500   NaN        S  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-59136f58-f66d-46f8-82fd-e4ac5092e574\">\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>PassengerId</th>\n",
              "      <th>Survived</th>\n",
              "      <th>Pclass</th>\n",
              "      <th>Name</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "      <th>SibSp</th>\n",
              "      <th>Parch</th>\n",
              "      <th>Ticket</th>\n",
              "      <th>Fare</th>\n",
              "      <th>Cabin</th>\n",
              "      <th>Embarked</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Braund, Mr. Owen Harris</td>\n",
              "      <td>male</td>\n",
              "      <td>22.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>A/5 21171</td>\n",
              "      <td>7.2500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>2</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Cumings, Mrs. John Bradley (Florence Briggs Th...</td>\n",
              "      <td>female</td>\n",
              "      <td>38.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>PC 17599</td>\n",
              "      <td>71.2833</td>\n",
              "      <td>C85</td>\n",
              "      <td>C</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>3</td>\n",
              "      <td>Heikkinen, Miss. Laina</td>\n",
              "      <td>female</td>\n",
              "      <td>26.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>STON/O2. 3101282</td>\n",
              "      <td>7.9250</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>4</td>\n",
              "      <td>1</td>\n",
              "      <td>1</td>\n",
              "      <td>Futrelle, Mrs. Jacques Heath (Lily May Peel)</td>\n",
              "      <td>female</td>\n",
              "      <td>35.0</td>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>113803</td>\n",
              "      <td>53.1000</td>\n",
              "      <td>C123</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>5</td>\n",
              "      <td>0</td>\n",
              "      <td>3</td>\n",
              "      <td>Allen, Mr. William Henry</td>\n",
              "      <td>male</td>\n",
              "      <td>35.0</td>\n",
              "      <td>0</td>\n",
              "      <td>0</td>\n",
              "      <td>373450</td>\n",
              "      <td>8.0500</td>\n",
              "      <td>NaN</td>\n",
              "      <td>S</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-59136f58-f66d-46f8-82fd-e4ac5092e574')\"\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-59136f58-f66d-46f8-82fd-e4ac5092e574 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-59136f58-f66d-46f8-82fd-e4ac5092e574');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "# 2. 데이터 추출"
      ],
      "metadata": {
        "id": "ytVS4tbaxeSX"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df_data = df_titanic[['Pclass', 'Sex', 'Age']]\n",
        "df_target = df_titanic['Survived']\n",
        "df_data.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ZeenA0UVxc_x",
        "outputId": "168d96a8-5848-403a-df96-587fd1b5f89c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 891 entries, 0 to 890\n",
            "Data columns (total 3 columns):\n",
            " #   Column  Non-Null Count  Dtype  \n",
            "---  ------  --------------  -----  \n",
            " 0   Pclass  891 non-null    int64  \n",
            " 1   Sex     891 non-null    object \n",
            " 2   Age     714 non-null    float64\n",
            "dtypes: float64(1), int64(1), object(1)\n",
            "memory usage: 21.0+ KB\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#3. 데이터 변환"
      ],
      "metadata": {
        "id": "H57u1_8DyKou"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "##3.1 결측치 처리"
      ],
      "metadata": {
        "id": "m3JMk8bgyNOl"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df_data['Age'].fillna(df_data['Age'].mean(), inplace=True)\n",
        "df_data.info()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "epgd317LyMrl",
        "outputId": "e6458e54-a25f-4512-febd-b70a285c4229"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "<class 'pandas.core.frame.DataFrame'>\n",
            "RangeIndex: 891 entries, 0 to 890\n",
            "Data columns (total 3 columns):\n",
            " #   Column  Non-Null Count  Dtype  \n",
            "---  ------  --------------  -----  \n",
            " 0   Pclass  891 non-null    int64  \n",
            " 1   Sex     891 non-null    object \n",
            " 2   Age     891 non-null    float64\n",
            "dtypes: float64(1), int64(1), object(1)\n",
            "memory usage: 21.0+ KB\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/pandas/core/generic.py:6392: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  return self._update_inplace(result)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "##3.2 문자열 변환"
      ],
      "metadata": {
        "id": "53y7Zpkd20KA"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn import preprocessing\n",
        "\n",
        "le = preprocessing.LabelEncoder()\n",
        "le = le.fit(df_data['Sex'])\n",
        "le.transform(df_data['Sex'])"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jMBjbF04yJtE",
        "outputId": "d270a33a-a81b-4e0b-c2d0-49d23efdb8e5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([1, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0, 1, 1,\n",
              "       0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0,\n",
              "       0, 1, 1, 0, 1, 0, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 1,\n",
              "       0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1,\n",
              "       0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0,\n",
              "       1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1,\n",
              "       0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 1,\n",
              "       1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1,\n",
              "       1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1,\n",
              "       0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 1, 0, 1,\n",
              "       1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 0,\n",
              "       1, 1, 1, 1, 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,\n",
              "       0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 1,\n",
              "       1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1, 0, 0,\n",
              "       1, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0,\n",
              "       0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1,\n",
              "       1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1,\n",
              "       0, 0, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 0, 0, 1,\n",
              "       0, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 0, 0, 0,\n",
              "       1, 0, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 1, 1, 0, 0, 0, 1, 1,\n",
              "       0, 1, 1, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1,\n",
              "       1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0,\n",
              "       1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1,\n",
              "       0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1, 0, 1, 1, 0, 1, 1, 0, 1,\n",
              "       1, 1, 0, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 1, 1, 1, 0, 1, 1, 1,\n",
              "       1, 1, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 0,\n",
              "       1, 0, 1, 1, 0, 0, 0, 1, 0, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0,\n",
              "       1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 1, 0,\n",
              "       1, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1,\n",
              "       0, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 0, 1, 0, 1, 0, 0, 1, 1, 0, 1, 1,\n",
              "       1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 0, 1,\n",
              "       1, 1, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 0, 1, 0, 1,\n",
              "       1, 1, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1,\n",
              "       0, 0, 1, 0, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 0,\n",
              "       1, 1, 0, 1, 1, 1, 0, 1, 1, 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 1, 1,\n",
              "       1, 1, 0, 1, 0, 1, 1, 0, 1, 0, 0, 0, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1,\n",
              "       0, 1, 1, 1, 0, 0, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 1, 0,\n",
              "       1, 1, 0, 1, 1, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0,\n",
              "       1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1,\n",
              "       0, 1, 1, 1, 0, 0, 1, 0, 0, 1, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 0,\n",
              "       0, 1, 0, 1, 1, 0, 1, 0, 0, 1, 1])"
            ]
          },
          "metadata": {},
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df_data['Sex'] = df_data['Sex'].map({'female':0, 'male':1})\n",
        "df_data.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 336
        },
        "id": "RHbvlrKY3SQn",
        "outputId": "b4f283f8-659b-4650-dd6f-2f76dd5c1913"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/ipykernel_launcher.py:1: SettingWithCopyWarning: \n",
            "A value is trying to be set on a copy of a slice from a DataFrame.\n",
            "Try using .loc[row_indexer,col_indexer] = value instead\n",
            "\n",
            "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
            "  \"\"\"Entry point for launching an IPython kernel.\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "   Pclass  Sex   Age\n",
              "0       3    1  22.0\n",
              "1       1    0  38.0\n",
              "2       3    0  26.0\n",
              "3       1    0  35.0\n",
              "4       3    1  35.0"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-cfd28083-c544-47a4-a30f-e9670d693967\">\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>Pclass</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>22.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>38.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>3</td>\n",
              "      <td>0</td>\n",
              "      <td>26.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>1</td>\n",
              "      <td>0</td>\n",
              "      <td>35.0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>3</td>\n",
              "      <td>1</td>\n",
              "      <td>35.0</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-cfd28083-c544-47a4-a30f-e9670d693967')\"\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-cfd28083-c544-47a4-a30f-e9670d693967 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-cfd28083-c544-47a4-a30f-e9670d693967');\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": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.preprocessing import StandardScaler\n",
        "\n",
        "scaler = StandardScaler()\n",
        "standard_scaled = scaler.fit_transform(df_data)"
      ],
      "metadata": {
        "id": "bSnYqpAm4V-i"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "#4. 모델 생성"
      ],
      "metadata": {
        "id": "_umH5RMP5N4i"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "##4.1 훈련 / 검증 데이터"
      ],
      "metadata": {
        "id": "gneHgHBN5Pb5"
      }
    },
    {
      "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(standard_scaled, df_target, test_size = 0.3, random_state = 62)"
      ],
      "metadata": {
        "id": "AnLPYRS05pWX"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "##4.2 모델 생성 및 학습"
      ],
      "metadata": {
        "id": "LD7LR4Mf5RHO"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.linear_model import LogisticRegression\n",
        "\n",
        "lr = LogisticRegression()\n",
        "lr.fit(X_train, y_train)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rErH2uMJ541d",
        "outputId": "61fad7cc-deaf-4558-94c1-9b354e2944da"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "LogisticRegression()"
            ]
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "##4.3 성능 평가"
      ],
      "metadata": {
        "id": "lPNG4wlC6DoR"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "lr.score(X_test, y_test)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "jZ3SEIvE6Fii",
        "outputId": "12ab7f64-f128-4681-85b8-0df11433fc40"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "0.7947761194029851"
            ]
          },
          "metadata": {},
          "execution_count": 24
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#5. 하이퍼 파라미터"
      ],
      "metadata": {
        "id": "eKiEtWAv6IqJ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import GridSearchCV\n",
        "lr = LogisticRegression()\n",
        "params = {'penalty':['l2'], 'C':[0.01, 0.1, 1, 5, 10]}\n",
        "\n",
        "grid_clf = GridSearchCV(lr, param_grid = params, scoring='accuracy', cv=5)\n",
        "grid_clf.fit(standard_scaled, df_target)\n",
        "\n",
        "print('최적 하이퍼 파라미터:{0}, 최적 평균 정확도:{1:.3f}'.format(grid_clf.best_params_, grid_clf.best_score_))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "MR9m44Ui6KvO",
        "outputId": "e720cadd-9a18-4f05-95d1-5d9037e31726"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "최적 하이퍼 파라미터:{'C': 5, 'penalty': 'l2'}, 최적 평균 정확도:0.788\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn.model_selection import GridSearchCV\n",
        "lr = LogisticRegression()\n",
        "# range(a, b, c)\n",
        "# a부터 b까지 리스트를 만들되 a는 포함하고 b는 불포함합니다. c를 적을 경우 c만큼을 건너뛴다고 생각하면 된다.\n",
        "\n",
        "c_list = range(2, 9, 1)\n",
        "params = {'penalty':['l2'], 'C':c_list}\n",
        "\n",
        "grid_clf = GridSearchCV(lr, param_grid = params, scoring='accuracy', cv=5)\n",
        "grid_clf.fit(standard_scaled, df_target)\n",
        "\n",
        "print('최적 하이퍼 파라미터:{0}, 최적 평균 정확도:{1:.3f}'.format(grid_clf.best_params_, grid_clf.best_score_))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "18JsPd7h-zst",
        "outputId": "8e672f2b-b452-4096-ba67-fb580b533857"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "최적 하이퍼 파라미터:{'C': 4, 'penalty': 'l2'}, 최적 평균 정확도:0.788\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "#6. 회귀 계수"
      ],
      "metadata": {
        "id": "QO_l25Zo_NYN"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "> 회귀 계수가 음수이면 데이터의 수치가 커질수록 결과가 작은 수일 확률이 높다. 반대로 양수가 되면 데이터의 수치가 커질수록 결과가 큰 수일 확률이 높다."
      ],
      "metadata": {
        "id": "OU0UUH56_QCt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# 하이퍼 파라미터 진행 후 최적의 모델 획득\n",
        "lr_best = grid_clf.best_estimator_\n",
        "# 회귀 계수 획득\n",
        "lr_best.coef_"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Y_vtjw28_Wsv",
        "outputId": "a28b1b7e-40e4-4254-e0c6-5842bcb85861"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([[-0.97279309, -1.24468592, -0.43228629]])"
            ]
          },
          "metadata": {},
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "result = pd.DataFrame(lr_best.coef_, columns=scaler.get_feature_names_out())\n",
        "result"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "W0P764cK_-7O",
        "outputId": "59c0008b-4078-40f8-d460-d3fb40cdd0f5"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "     Pclass       Sex       Age\n",
              "0 -0.972793 -1.244686 -0.432286"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-4094e2a7-a500-4c84-8fd6-367eae0ef3b1\">\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>Pclass</th>\n",
              "      <th>Sex</th>\n",
              "      <th>Age</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>-0.972793</td>\n",
              "      <td>-1.244686</td>\n",
              "      <td>-0.432286</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-4094e2a7-a500-4c84-8fd6-367eae0ef3b1')\"\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-4094e2a7-a500-4c84-8fd6-367eae0ef3b1 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-4094e2a7-a500-4c84-8fd6-367eae0ef3b1');\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": 39
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "> pclass는 1, 2, 3의 정보를 갖는다. 음수이므로 숫자가 클수록 작은 수의 결과를 얻을 확률이 높다. 즉, 3등급 자리일 경우 0(죽음)일 확률이 높다."
      ],
      "metadata": {
        "id": "0mMZ1IUgAI8j"
      }
    }
  ]
}