机器学习-分类算法-逻辑回归13

逻辑回归是解决二分类问题的利器





数据来源：https://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/

逻辑回归在算法实现的时候有个判定是某个类别的概率，我们一般是根据样本数量的大小去判定。

from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import classification_report
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）
    :return: 
    """
    # 构造列标签名字
    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("file:///C:/Users/Administrator/Downloads/breast-cancer-wisconsin.data",names = column)
    print(data)

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

    # 进行数据分割(取出特征值，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)# 预测结果
    print("逻辑回归准确率:",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()