岭回归

回归算法之岭回归

具有L2正则化的线性最小二乘法。岭回归是一种专用于共线性数据分析的有偏估计回归方法，实质上是一种改良的最小二乘估计法，通过放弃最小二乘法的无偏性，以损失部分信息、降低精度为代价获得回归系数更为符合实际、更可靠的回归方法，对病态数据的拟合要强于最小二乘法。当数据集中存在共线性的时候，岭回归就会有用。

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

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: NOne
    """
    # 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(
        "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)

    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"]))

    return None


if __name__ == "__main__":
    logistic()