Logistic回归模型——Python

import collections
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt


# 1 创建数据集
Job_Dict = {
    '工作时间':[0.50,0.75,1.00,1.25,1.50,1.75,1.75,2.00,2.25,2.50,2.75,3.00,3.25,3.50,4.00,4.25,4.50,4.75,5.00,5.50],
    '是否升职':[0,0,0,0,0,0,1,0,1,0,1,0,1,0,1,1,1,1,1,1]
}
Job_OrderDict = collections.OrderedDict(Job_Dict)
Job_Df = pd.DataFrame(Job_OrderDict)
Job_Df.head()


# 2 准备数据

# 提取特征和标签
Job_X = Job_Df.loc[:,'工作时间']
Job_Y = Job_Df.loc[:,'是否升职']


# 3 分析数据

# 绘制散点图
plt.scatter(Job_X,Job_Y,color='blue',label='job data')
# 添加图标标签
plt.xlabel('Hours')
plt.ylabel('Pass')


# 4 建立逻辑回归模型

from sklearn.model_selection import train_test_split    # train_test_split（），随机划分训练集和测试集的函数

# （1）建立训练数据和测试数据
x_train,x_test,y_train,y_test = train_test_split(Job_X,Job_Y,train_size=.8)
# 输出数据的大小
print('原始数据特征：'