七、（4）逻辑回归——二分类法，预测乳腺癌数据

    # -*- coding: utf-8 -*-
    """
    Created on Sun May 26 21:34:29 2019
    
    @author: sun
    """
    
    from sklearn.linear_model import LogisticRegression
    from sklearn.model_selection import train_test_split
    from sklearn.preprocessing import StandardScaler
    from sklearn.metrics import classification_report
    from sklearn.externals import joblib
    import pandas as pd
    import numpy as np
    
    
    
    def logistic():
    """
    逻辑回归做二分类进行癌症预测（根据细胞的属性特征）
    
    """
    # 构造列标签名字,一共11个
    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']
    
    # 读取数据
    data = pd.read_csv(r"C:\Users\sun\Desktop\论文\算法代码\逻辑回归二分类\乳腺癌分类数据.csv",engine='python',names=column)
    
    #print(data)
    
    # 缺失值进行处理
    data = data.replace(to_replace='?', value=np.nan)
    
    data = data.dropna()
    
    # 进行数据的分割，1到10列为特征值，11列为目标值
    x_train, x_test, y_train, y_test = train_test_split(data[column[1:10]], data[column[10]], test_size=0.25)
    
    # 进行标准化处理
    std = StandardScaler()
    
    x_train = std.fit_transform(x_train)
    x_test = std.transform(x_test)
    
    # 逻辑回归预测
    lg = LogisticRegression(C=1.0)
    
    lg.fit(x_train, y_train)
    
    #print(lg.coef_)
    
    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"]))
    
      
       
    
    
    #保存训练好的模型
    joblib.dump(lg, "./lg.pkl")
    
    #加载模型，预测自己的数据
    model = joblib.load("./lg.pkl")
    
    # 读取数据，数据为相同格式下需要预测的数据。和前文七、（1）（2）的操作一样
    data = pd.read_csv(r"C:\Users\sun\Desktop\论文\算法代码\逻辑回归二分类\输入预测乳腺癌数据.csv",engine='python',names=column)
    
    xx_test= data[column[1:10]]  #获取特征值1 到 10 列，
    xx_test = std.transform(xx_test)
    
    yy_predict = model.predict(xx_test)
    
    print("保存的模型预测的结果：", yy_predict)
    
    if __name__ == "__main__":
    logistic()