机器学习-分类算法之逻辑回归

1.逻辑回归（Logistics Regression）,简称LR。它的特点是能够使我们的特征输入集合转化为0和1这两类的概率。

2.良/恶性肿瘤预测：

from sklearn.linear_model.logistic import LogisticRegression
from sklearn.metrics.classification import classification_report
from sklearn.model_selection._split import train_test_split
from sklearn.preprocessing.data import StandardScaler

import numpy as np
import pandas as pd


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）
    
    #构造标签名字
    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("https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data",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
    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)
    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()

运行结果为：