逻辑回归模型——乳腺癌数据集

    # 导入数据集
    from sklearn import datasets
    import warnings
    warnings.filterwarnings('ignore')
    
    df = datasets.load_breast_cancer()
    
    X = df.data
    y = df.target
    X.shape    # 查看属性维度

    X  # 查看属性标签

    y  # 查看类别标签

    # 划分训练集和测试集
    from sklearn.model_selection import train_test_split
    
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=666)

    from sklearn.linear_model import LogisticRegression    # 导入逻辑回归模型
    from sklearn.preprocessing import StandardScaler     # 归一化
    from sklearn.preprocessing import PolynomialFeatures    # 生成多项式
    from sklearn.pipeline import Pipeline      # Pipeline管道
    
    # 直接用逻辑回归模型进行训练
    logr = LogisticRegression()
    logr.fit(X_train, y_train)   # 训练
    logr.score(X_test, y_test)   # 测试

    from sklearn.model_selection import GridSearchCV    # 网格搜索
    import numpy as np
    
    # 使用网格搜索和Pipeline管道进行参数调优
    pipe = Pipeline([
    ('Ploy', PolynomialFeatures()),
    ('Scaler', StandardScaler()),
    ('logr', LogisticRegression())
    ])
    
    param_grid = [{
    'Ploy__degree': [i for i in range(5)],
    'logr__C': [i for i in np.arange(0.01,0.11,10)],
    'logr__solver': ['liblinear']
    }]
    grid = GridSearchCV(pipe, param_grid=param_grid)
    
    grid.fit(X_train, y_train)

    grid.score(X_test, y_test)