np实现线性回归

import numpy as np
import matplotlib.pyplot as plt
def load_data(path):
    data=np.loadtxt(path,delimiter=',',skiprows=1)
    #print(data.shape)
    #print(data)
    return data
def get_gradient(theta,x,y):
    m=x.shape[0]
    Y_estimate=np.dot(x,theta)
    assert (Y_estimate.shape==(m,))
    error=Y_estimate-y
    assert (error.shape==(m,))
    cost =1.0/(2*m)*np.sum(error**2)
    #grad=(1.0/m)*np.dot(x.T,error).reshape(-1)#(2,)
    grad = (1.0 / m) * np.dot(error,x) # (2,)
    return grad,cost

def gradient_descent(x,y,iterations,alpha):

    theta=np.random.randn(2)
    costs=[]
    for i in range(iterations):
        grad,cost=get_gradient(theta,x,y)
        new_theta=theta-alpha*grad
        if i%100==0:
            print('{} iterations cost={}'.format(i,cost))
            costs.append(cost)
        theta=new_theta
    return costs,theta
if __name__=='__main__':
    path='data/diabetes.csv'
    data=load_data(path)
    print(data.shape)
    data_x=data[:,0].reshape(-1,1)#(m,1)
    m=data_x.shape[0]
    #data_x 归一化处理
    average_data_x=np.mean(data_x)
    Stand_xvari=1.0/m*np.sqrt(np.sum(np.square(data_x-average_data_x)))
    # #print(average_data_x)
    datax_bn=(data_x-average_data_x)/Stand_xvari
    print(datax_bn.shape)
    #添加一列为1的向量 实际上就是乘以 theta 就是b
    data_x=np.hstack((np.ones_like(datax_bn),datax_bn))#(m,2)
    print(data_x.shape)
    data_y=data[:, 1]
    # data_y归一化处理
    average_data_y = np.mean(data_y)
    Stand_yvari = 1.0 / m * np.sqrt(np.sum(np.square(data_y - average_data_y)))
    # print(average_data_x)
    datay_bn = (data_y - average_data_y) / Stand_yvari
    print(datay_bn.shape)

    costs,theta=gradient_descent(data_x,datay_bn,iterations=50000,alpha=0.002)
    print(data_y.shape)

    #print(theta)
    y_predict=np.dot(data_x,theta)#theta[0]+theta[1]*data_x[:,1]
    print(y_predict.shape)
    plt.figure()
    #样本图
    print(data_x[:2])
    plt.scatter(data_x[:,1],datay_bn)
    plt.plot(data_x[:,1],y_predict)
    plt.show()