逻辑回归预测癌症案列

逻辑回归（也会发生线性回归的过拟合）自带正则化。

优点：同岭回归一样可以解决过拟合问题。

from sklearn.datasets import load_boston
from sklearn.linear_model import LinearRegression, SGDRegressor, LogisticRegression
#LogisticRegressionCV属于交叉验证 LogisticRegression网格搜索
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error, classification_report
#分类模型评估里面sklearn.metrics   考虑召回率
from sklearn.linear_model import Ridge
import numpy as np
import pandas as pd

import joblib
def logis():
    """
    逻辑回归分类进行癌症预测（根据细胞属性特征）
    :return:None
    """
    #构造列标签名字
    column = ['Sample code number', 'Clump Thickness', 'Unidormity of Cell Size', 'Uniformity of Cell Shape', 'Marginal Adhesion', 'Single Epithelial Cell Size', 'Bare Nuclel', 'Bland Chromatin', 'Normal Nucleoli', 'Mitoses', 'Class']

    #读取数据
    data = pd.read_csv("http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data", names=column)

    print(data)

    #缺失值处理
    data = data.replace(to_replace='?', value=np.nan)
    data = data.dropna()

    #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)

    #j进行标准化处理
    std = StandardScaler()
    x_train = std.fit_transform(x_train)
    x_test - std.transform(x_test)

    #逻辑回归的预测()
    lg = LogisticRegression(C=1.0)
    lg.fit(x_train, y_train)   #进行训练，利用对数自然损值不断去求最小值，优化W值

    print(lg.coef_)                       #逻辑回归的权重参数
    y_predict = lg.predict(x_test)        #获取预测值
    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__":
    logis()