使用python sklearn库逻辑回归建模实例

我学习的b站中机器学习的教程（线性回归和逻辑回归（点击学习））

此处csdn中含有上条链接中逻辑回归和线性回归的讲解实例代码

在视频学习中结合csdn文字版理解逻辑回归线性回归的教程理解教程（逻辑特别清楚）

癌症肿瘤良性、恶性预测 数据集获取

我张贴的代码的数据集下载为以下百度云链接

链接：https://pan.baidu.com/s/1dSGioVcbPKoJUS8ta7TteQ
提取码：h5jh
复制这段内容后打开百度网盘手机App，操作更方便哦
代码如下使用时提前进行相关库的下载和安装，同时更改代码中数据集的地址

import numpy.random
from sklearn.preprocessing import StandardScaler
from sklearn import preprocessing as pp
from sklearn.metrics import classification_report
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression, SGDRegressor, LogisticRegression



def logistic():
    path = r'D:\小美元\代码\ml-机器学习\data\breast-cancer-wisconsin.csv'#更改此处地址
    column = ['Sample code number', 'Clump Thickness', 'Uniformity of Cell Size', 'Uniformity of Cell Shape',
              'Marginal Adhesion', 'Single Epithelial Cell Size', 'Bare Nuclei', 'Bland Chromatin', 'Normal Nucleoli',
              'Mitoses', 'Class']

    data = pd.read_csv(path, names=column)
    print(data)
    # 缺失值进行数据处理
    data = data.replace(['?'],np.nan)
    print(data)
    data = data.dropna()  # 将空缺值删除
    # 进行数据的分割
    x_train, x_test, y_train, y_test = train_test_split(data[column[1:10]], data[column[10]], test_size=0.25)

    std = StandardScaler()# 数据标准化
    print('be4',x_train,x_test)
    x_train = std.fit_transform(x_train)
    x_test = std.transform(x_test)
    print('After',x_train, x_test)
    # 逻辑回归开始预测
    lg = LogisticRegression(C=1.0)
    lg.fit(x_train, y_train)
    print(lg.coef_)  # 十个特征值的参数
    y_predict = lg.predict(x_test)

    print("准确率：", lg.score(x_test, y_test))
    print("召回率：", classification_report(y_test, y_predict, labels=[2, 4], target_names=["良性", "恶性"]))

    return None


if __name__ == "__main__":
    logistic()

模型建立成功后模型准确率和召回率如下