EXPLORATION_1_3_load_breast_cancer.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "EXPLORATION 1-3 load_breast_cancer.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "authorship_tag": "ABX9TyMxtYsiEjY7WlYecj7LhizU",
      "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/Chabbbbbo/EXPLORATION/blob/main/EXPLORATION_1_3_load_breast_cancer.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ndjB-kVt7gcw",
        "outputId": "fcfbb9ff-6b9e-4312-a0cd-d3674536809c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['DESCR', 'data', 'data_module', 'feature_names', 'filename', 'frame', 'target', 'target_names']\n",
            "['malignant' 'benign']\n",
            ".. _breast_cancer_dataset:\n",
            "\n",
            "Breast cancer wisconsin (diagnostic) dataset\n",
            "--------------------------------------------\n",
            "\n",
            "**Data Set Characteristics:**\n",
            "\n",
            "    :Number of Instances: 569\n",
            "\n",
            "    :Number of Attributes: 30 numeric, predictive attributes and the class\n",
            "\n",
            "    :Attribute Information:\n",
            "        - radius (mean of distances from center to points on the perimeter)\n",
            "        - texture (standard deviation of gray-scale values)\n",
            "        - perimeter\n",
            "        - area\n",
            "        - smoothness (local variation in radius lengths)\n",
            "        - compactness (perimeter^2 / area - 1.0)\n",
            "        - concavity (severity of concave portions of the contour)\n",
            "        - concave points (number of concave portions of the contour)\n",
            "        - symmetry\n",
            "        - fractal dimension (\"coastline approximation\" - 1)\n",
            "\n",
            "        The mean, standard error, and \"worst\" or largest (mean of the three\n",
            "        worst/largest values) of these features were computed for each image,\n",
            "        resulting in 30 features.  For instance, field 0 is Mean Radius, field\n",
            "        10 is Radius SE, field 20 is Worst Radius.\n",
            "\n",
            "        - class:\n",
            "                - WDBC-Malignant\n",
            "                - WDBC-Benign\n",
            "\n",
            "    :Summary Statistics:\n",
            "\n",
            "    ===================================== ====== ======\n",
            "                                           Min    Max\n",
            "    ===================================== ====== ======\n",
            "    radius (mean):                        6.981  28.11\n",
            "    texture (mean):                       9.71   39.28\n",
            "    perimeter (mean):                     43.79  188.5\n",
            "    area (mean):                          143.5  2501.0\n",
            "    smoothness (mean):                    0.053  0.163\n",
            "    compactness (mean):                   0.019  0.345\n",
            "    concavity (mean):                     0.0    0.427\n",
            "    concave points (mean):                0.0    0.201\n",
            "    symmetry (mean):                      0.106  0.304\n",
            "    fractal dimension (mean):             0.05   0.097\n",
            "    radius (standard error):              0.112  2.873\n",
            "    texture (standard error):             0.36   4.885\n",
            "    perimeter (standard error):           0.757  21.98\n",
            "    area (standard error):                6.802  542.2\n",
            "    smoothness (standard error):          0.002  0.031\n",
            "    compactness (standard error):         0.002  0.135\n",
            "    concavity (standard error):           0.0    0.396\n",
            "    concave points (standard error):      0.0    0.053\n",
            "    symmetry (standard error):            0.008  0.079\n",
            "    fractal dimension (standard error):   0.001  0.03\n",
            "    radius (worst):                       7.93   36.04\n",
            "    texture (worst):                      12.02  49.54\n",
            "    perimeter (worst):                    50.41  251.2\n",
            "    area (worst):                         185.2  4254.0\n",
            "    smoothness (worst):                   0.071  0.223\n",
            "    compactness (worst):                  0.027  1.058\n",
            "    concavity (worst):                    0.0    1.252\n",
            "    concave points (worst):               0.0    0.291\n",
            "    symmetry (worst):                     0.156  0.664\n",
            "    fractal dimension (worst):            0.055  0.208\n",
            "    ===================================== ====== ======\n",
            "\n",
            "    :Missing Attribute Values: None\n",
            "\n",
            "    :Class Distribution: 212 - Malignant, 357 - Benign\n",
            "\n",
            "    :Creator:  Dr. William H. Wolberg, W. Nick Street, Olvi L. Mangasarian\n",
            "\n",
            "    :Donor: Nick Street\n",
            "\n",
            "    :Date: November, 1995\n",
            "\n",
            "This is a copy of UCI ML Breast Cancer Wisconsin (Diagnostic) datasets.\n",
            "https://goo.gl/U2Uwz2\n",
            "\n",
            "Features are computed from a digitized image of a fine needle\n",
            "aspirate (FNA) of a breast mass.  They describe\n",
            "characteristics of the cell nuclei present in the image.\n",
            "\n",
            "Separating plane described above was obtained using\n",
            "Multisurface Method-Tree (MSM-T) [K. P. Bennett, \"Decision Tree\n",
            "Construction Via Linear Programming.\" Proceedings of the 4th\n",
            "Midwest Artificial Intelligence and Cognitive Science Society,\n",
            "pp. 97-101, 1992], a classification method which uses linear\n",
            "programming to construct a decision tree.  Relevant features\n",
            "were selected using an exhaustive search in the space of 1-4\n",
            "features and 1-3 separating planes.\n",
            "\n",
            "The actual linear program used to obtain the separating plane\n",
            "in the 3-dimensional space is that described in:\n",
            "[K. P. Bennett and O. L. Mangasarian: \"Robust Linear\n",
            "Programming Discrimination of Two Linearly Inseparable Sets\",\n",
            "Optimization Methods and Software 1, 1992, 23-34].\n",
            "\n",
            "This database is also available through the UW CS ftp server:\n",
            "\n",
            "ftp ftp.cs.wisc.edu\n",
            "cd math-prog/cpo-dataset/machine-learn/WDBC/\n",
            "\n",
            ".. topic:: References\n",
            "\n",
            "   - W.N. Street, W.H. Wolberg and O.L. Mangasarian. Nuclear feature extraction \n",
            "     for breast tumor diagnosis. IS&T/SPIE 1993 International Symposium on \n",
            "     Electronic Imaging: Science and Technology, volume 1905, pages 861-870,\n",
            "     San Jose, CA, 1993.\n",
            "   - O.L. Mangasarian, W.N. Street and W.H. Wolberg. Breast cancer diagnosis and \n",
            "     prognosis via linear programming. Operations Research, 43(4), pages 570-577, \n",
            "     July-August 1995.\n",
            "   - W.H. Wolberg, W.N. Street, and O.L. Mangasarian. Machine learning techniques\n",
            "     to diagnose breast cancer from fine-needle aspirates. Cancer Letters 77 (1994) \n",
            "     163-171.\n"
          ]
        }
      ],
      "source": [
        "from sklearn.datasets import load_breast_cancer\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.metrics import classification_report\n",
        "\n",
        "#데이터 준비 및 정보확인\n",
        "cancer= load_breast_cancer()\n",
        "print(dir(cancer))\n",
        "\n",
        "#데이터 이해하기 \n",
        "cancer_data = cancer.data #Feature Data 저장\n",
        "cancer_label = cancer.target #Label Data 저장\n",
        "print(cancer.target_names) #Target Names 출력\n",
        "print(cancer.DESCR) #데이터 describe 해보기\n",
        "\n",
        "#Train, test 데이터 분리\n",
        "X_train, X_test, y_train, y_test = train_test_split(cancer_data, cancer_label, test_size=0.2, random_state=5)\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#1) Decision Tree\n",
        "from sklearn.tree import DecisionTreeClassifier\n",
        "decision_tree = DecisionTreeClassifier(random_state=32)\n",
        "decision_tree.fit(X_train, y_train)\n",
        "\n",
        "y_pred = decision_tree.predict(X_test)\n",
        "\n",
        "print(classification_report(y_test, y_pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "RifD65Ur8MG9",
        "outputId": "6bcdc67c-0f9d-4a43-9db7-59b37b9ab58f"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.94      0.92      0.93        48\n",
            "           1       0.94      0.95      0.95        66\n",
            "\n",
            "    accuracy                           0.94       114\n",
            "   macro avg       0.94      0.94      0.94       114\n",
            "weighted avg       0.94      0.94      0.94       114\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#2) Random Forest\n",
        "from sklearn.ensemble import RandomForestClassifier\n",
        "\n",
        "randomforest = RandomForestClassifier(random_state=32)\n",
        "randomforest.fit(X_train, y_train)\n",
        "\n",
        "y_pred = randomforest.predict(X_test)\n",
        "\n",
        "print(classification_report(y_test, y_pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "moFiPPCx8NNE",
        "outputId": "ca8f1d4d-3d21-499b-aaf6-8ef9edda13db"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       1.00      0.94      0.97        48\n",
            "           1       0.96      1.00      0.98        66\n",
            "\n",
            "    accuracy                           0.97       114\n",
            "   macro avg       0.98      0.97      0.97       114\n",
            "weighted avg       0.97      0.97      0.97       114\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#3) SVM\n",
        "from sklearn import svm\n",
        "svm_model = svm.SVC()\n",
        "\n",
        "svm_model.fit(X_train, y_train)\n",
        "y_pred = svm_model.predict(X_test)\n",
        "\n",
        "print(classification_report(y_test, y_pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "NwTZAd9P8NLu",
        "outputId": "41ab375e-bb32-42cf-b405-2249be4b4a83"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       1.00      0.85      0.92        48\n",
            "           1       0.90      1.00      0.95        66\n",
            "\n",
            "    accuracy                           0.94       114\n",
            "   macro avg       0.95      0.93      0.94       114\n",
            "weighted avg       0.94      0.94      0.94       114\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 4)SGD Classifier\n",
        "from sklearn.linear_model import SGDClassifier\n",
        "sgd_model = SGDClassifier()\n",
        "\n",
        "sgd_model.fit(X_train, y_train)\n",
        "y_pred = sgd_model.predict(X_test)\n",
        "\n",
        "print(classification_report(y_test, y_pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "c6iP0CHJ8M_1",
        "outputId": "a3dfa970-28f5-45ba-c9f1-62ec0bc5b748"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       0.88      0.92      0.90        48\n",
            "           1       0.94      0.91      0.92        66\n",
            "\n",
            "    accuracy                           0.91       114\n",
            "   macro avg       0.91      0.91      0.91       114\n",
            "weighted avg       0.91      0.91      0.91       114\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 5)Logistic Regression\n",
        "from sklearn.linear_model import LogisticRegression\n",
        "logistic_model = LogisticRegression()\n",
        "\n",
        "logistic_model.fit(X_train, y_train)\n",
        "y_pred = logistic_model.predict(X_test)\n",
        "\n",
        "print(classification_report(y_test, y_pred))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "CQUOt35l8Oz6",
        "outputId": "edc2b717-b102-44ac-a48b-20f6f6e09a07"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "              precision    recall  f1-score   support\n",
            "\n",
            "           0       1.00      0.90      0.95        48\n",
            "           1       0.93      1.00      0.96        66\n",
            "\n",
            "    accuracy                           0.96       114\n",
            "   macro avg       0.96      0.95      0.95       114\n",
            "weighted avg       0.96      0.96      0.96       114\n",
            "\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.7/dist-packages/sklearn/linear_model/_logistic.py:818: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
            "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
            "\n",
            "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
            "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
            "Please also refer to the documentation for alternative solver options:\n",
            "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
            "  extra_warning_msg=_LOGISTIC_SOLVER_CONVERGENCE_MSG,\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "#모델평가"
      ],
      "metadata": {
        "id": "PhEeyIMw8Mz7"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}