2019-08-04

import matplotlib.pyplot as plt
import numpy as np
from sklearn import linear_model

datasets_X = [] #尺寸
datasets_Y = [] #价格
fr = open(‘D:\python_source\Machine_study\mooc_data\回归/prices.txt‘, ‘r‘)
lines = fr.readlines()
for line in lines:
    items = line.strip().split(‘,‘) #转换为列表，以 ， 分隔
    datasets_X.append(int(items[0]))
    datasets_Y.append(int(items[1]))
length = len(datasets_X)
datasets_X = np.array(datasets_X).reshape([length, 1])#二维列表
#print(datasets_X)
datasets_Y = np.array(datasets_Y)

minX = min(datasets_X)
maxX = max(datasets_X)
X = np.arange(minX, maxX).reshape([-1, 1]) #以最大值和最小值为范围建立等差数列 2维列表 792-4399
#print(X)

linear = linear_model.LinearRegression()
linear.fit(datasets_X, datasets_Y) #拟合回归数据

print(‘Coefficients:‘, linear.coef_)#查看系数
print(‘intercept:‘, linear.intercept_)#查看截距

#可视化
plt.scatter(datasets_X, datasets_Y, color = ‘red‘)

plt.plot(X, linear.predict(X), color = ‘blue‘)
plt.xlabel(‘Area‘)
plt.ylabel(‘Price‘)
plt.show()