from sklearn.linear_model import LinearRegression,SGDRegressor,Ridge,LogisticRegression from sklearn.model_selection import train_test_split from sklearn.preprocessing import StandardScaler from sklearn.metrics import mean_squared_error,classification_report import numpy as np import pandas as pd def logistic(): 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("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",names=column) print(data) data=data.replace(to_replace='?',value=np.nan)#缺失值进行处理 data=data.dropna() 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) lg = LogisticRegression(C=1.0) lg.fit(x_train, y_train) y_predict=lg.predict(x_test) print(lg.coef_) 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()