简单线性回归的实现（一元一次方程）

import numpy as np
#from matplotlib import pylab as pl
import matplotlib.pylab as pl
#线性回归
x = np.array([1,3,2,1,3])
y = np.array([14,24,18,17,27])
#定义回归函数
def fit(x,y):
    if len(x)!=len(y):
        return;
    numerator = 0;
    denominator = 0;
    x_mean = np.mean(x)#算数平均数
    y_mean = np.mean(y)
    for i in range(len(x)):
        numerator += (x[i] - x_mean) * (y[i] - y_mean)
        denominator += np.square(x[i] - x_mean)
    b1 = numerator / denominator
    b0 = y_mean - b1 * x_mean
    return b0 ,b1;

#定义预测函数
def predict(x,b0,b1):
    return b0 + b1 * x

#求取回归方程
b0 , b1 = fit(x,y)

#预测
x_test = np.array([1.2,8.5,4.6,7.9,6])
# print('xtest的长度是',len(x_test),x_test[2])
y_test = np.zeros((1,len(x_test)))
print("ssssss",len(y_test))
for i in range(len(x_test)):
    y_test[0][i] = predict(x_test[i],b0,b1)


if __name__ == '__main__':
    # print('Line is:y = %2.0fx + %2.0f'%(b1,b0))
    # for i in range(len(x_test)):
    #     print(y_test[0][i])

    #绘制图像
    xx = np.linspace(0,10)
    yy = b1 * xx + b0
    pl.plot(xx,yy)
    pl.scatter(x,y)
    pl.scatter(x_test,y_test[0])
    pl.show()