机器学习：numpy版本线性回归预测波士顿房价

数据链接

链接: https://pan.baidu.com/s/1uDG_2IZVZCn9kndZ_ZIGaA?pwd=nec2 提取码: nec2

导入数据

import numpy as np

path = 'Desktop/波士顿房价/trian.csv'

data = np.loadtxt(path, delimiter = ",", skiprows=1)
data.shape

划分数据

train = data[:int(data.shape[0]*0.8)]
test = data[int(data.shape[0]*0.8):]
print(train.shape, test.shape)
train_x = train[:,:-1]
train_y = train[:,13:]
test_x = test[:,:-1]
test_y = test[:,13:]
print(train_x.shape, train_y.shape)

模型

class Network:
    def __init__(self, num_weights):
        self.num_weights = num_weights
        self.w = np.random.rand(num_weights, 1)
       
        self.b = 0
        #前向计算
    def forward(self, x):
        z = np.dot(x, self.w) + self.b 
        return z
        #计算loss
    def loss(self, z, y):
        cost = (z-y)*(z-y)
        cost = np.mean(cost)
        return cost
        #计算梯度
    def gradient(self, z, y):
        w = (z-y)*train_x
        w = np.mean(w, axis = 0)
        w = np.array(w).reshape([13,1])
        b = z-y
        b = np.mean(b)
        return w, b
        #更新参数
    def update(self, gradient_w, gradient_b, eta):
        self.w = self.w - eta*gradient_w
        
        self.b = self.b - eta*gradient_b
        #训练
    def train(self, items, eta):
        for i in range(items):
            z = self.forward(train_x)
            loss = self.loss(z, train_y)
            gradient_w, gradient_b = self.gradient(z, train_y)
            self.update(gradient_w, gradient_b, eta)
            if i%100 ==0:
                test_loss = self.test()
                print('item:',i,'loss:', loss, 'test_loss:', test_loss)
          #测试
    def test(self):
        z = self.forward(test_x)
        loss = self.loss(z,test_y)
        return loss

    

net = Network(13)
net.train(1000000, eta= 6e-6)