7.逻辑回归实践

import pandas as pd
import numpy as np
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
def logistic():

    #读取数据
    data = pd.read_csv(‘venv/data/201706120039邱杰(处理好).csv‘)

    # 将列‘电梯情况‘进行条件的判断，替换为0、1
    data.loc[data[‘电梯情况‘] == ‘ 有‘, ‘电梯情况‘] = 1  # int 类型
    data.loc[data[‘电梯情况‘] == ‘暂无‘, ‘电梯情况‘] = 0

    # 提取列为‘面积‘、‘总价‘、‘室‘、‘厅‘为x
    data_x = data.iloc[:, [2, 3, 4, 5]]  # 提取到面积、总价、室、厅
    # 将x改为二维数组形式
    data_x = np.array(data_x)
    # 将列为‘电梯情况‘为y
    data_y = data.iloc[:, 10]
    # 将y改为一维数据形式
    data_y = np.array(data_y)



    #训练集分割
    x_train, x_text, y_train, y_text = train_test_split(data_x, data_y, test_size=0.2, random_state=10)

    # 3 进行标准化处置
    # 特征值和目标是是都必须进行标准化处理的（需要分别处理），实例化一个标注话API（X）
    std = StandardScaler()

    x_train = std.fit_transform(x_train)
    x_text = std.transform(x_text)

    #逻辑回归预测
    lg = LogisticRegression()
    lg.fit(x_train, y_train)
    print(lg.coef_)
    lg_predeit = lg.predict(x_text)
    print(‘准确率：‘,lg.score(x_text, y_text))
    print(‘召回率：‘,classification_report(y_text, lg_predeit,labels=[0,1], target_names=[‘无电梯‘,‘有电梯‘]))

if __name__ == ‘__main__‘:
    logistic()