​

​

​

​

​

​

# 导入需要用到的package
import numpy as np
import json
import matplotlib.pyplot as pltdef load_data():# 从文件导入数据datafile = './work/housing.data'data = np.fromfile(datafile, sep=' ')# 每条数据包括14项，其中前面13项是影响因素，第14项是相应的房屋价格中位数feature_names = [ 'CRIM', 'ZN', 'INDUS', 'CHAS', 'NOX', 'RM', 'AGE', \'DIS', 'RAD', 'TAX', 'PTRATIO', 'B', 'LSTAT', 'MEDV' ]feature_num = len(feature_names)# 将原始数据进行Reshape，变成[N, 14]这样的形状data = data.reshape([data.shape[0] // feature_num, feature_num])# 将原数据集拆分成训练集和测试集# 这里使用80%的数据做训练，20%的数据做测试# 测试集和训练集必须是没有交集的ratio = 0.8offset = int(data.shape[0] * ratio)training_data = data[:offset]# 计算训练集的最大值，最小值（找的是每一列的极值）global maximums, minimums#maximums, minimums = data.max(axis=0), data.min(axis=0)maximums, minimums = training_data.max(axis=0), training_data.min(axis=0)#print("max:", maximums, "min:", minimums)# 对数据进行归一化处理，按列归一化处理for i in range(feature_num):data[:, i] = (data[:, i] - minimums[i]) / (maximums[i] - minimums[i])#print("归一化后的数据:\n", data)# 训练集和测试集的划分比例training_data = data[:offset]test_data = data[offset:]return training_data, test_data# 获取数据
training_data, test_data = load_data()
x = training_data[:, :-1] #所有行+所有列（除了最后一列）
y = training_data[:, -1:] #所有行+最后一列#w = [1, 2, 3] #shape = (3,)
#w = [[1], [2], [3]] #shape = (3,1)
#w = [[1,1], [2,2], [3,3]] #shape = (3,2)
#x = np.array(w)
# 查看数据
#print(x.shape)
#print(y.shape)class Network(object):def __init__(self, num_of_weights):# 随机产生w的初始值# 为了保持程序每次运行结果的一致性，# 此处设置固定的随机数种子np.random.seed(0)self.w = np.random.randn(num_of_weights, 1)#print("init self.w", self.w)self.b = 0.def forward(self, x):z = np.dot(x, self.w) + self.b #x是[404，13]的矩阵（404行，13列）, w是[13, 1]的矩阵（13行，1列），做点乘return zdef loss(self, z, y):error = z - y#print(error.shape)cost = error * errorcost = np.mean(cost)return costdef gradient(self, x, y):z = self.forward(x)gradient_w = (z-y)*x #梯度公式gradient_w = np.mean(gradient_w, axis=0) #对各列求均值gradient_w = gradient_w[:, np.newaxis]gradient_b = (z - y)gradient_b = np.mean(gradient_b)   return gradient_w, gradient_bdef update(self, gradient_w, gradient_b, eta = 0.01):self.w = self.w - eta * gradient_wself.b = self.b - eta * gradient_bdef train(self, x, y, iterations=100, eta=0.01):losses = []for i in range(iterations):z = self.forward(x)L = self.loss(z, y)gradient_w, gradient_b = self.gradient(x, y)self.update(gradient_w, gradient_b, eta)losses.append(L)if (i+1) % 10000 == 0:print('iter {}, loss {}'.format(i, L))return losses# 运行模式一：每次用所有数据进行训练
train_data, test_data = load_data()
x = train_data[:, :-1]
#print("x.shape:", x.shape)
y = train_data[:, -1:]
# 创建网络
net = Network(13)
num_iterations=100000
# 启动训练
losses = net.train(x,y, iterations=num_iterations, eta=0.01)# 画出损失函数的变化趋势
"""
plot_x = np.arange(num_iterations)
plot_y = np.array(losses)
plt.plot(plot_x, plot_y)
plt.show()
"""#对数据做反归一化处理
def restore_data(d):d = d* (maximums[-1] - minimums[-1]) + minimums[-1]return round(d,2)#用测试集做测试
print("测试集测试结果：")
x = test_data[:, :-1]
y = test_data[:, -1:]
z = net.forward(x)
print("样本数据", "\t", "预测数据")
print("-------------------------")
for i in range(x.shape[0]):print(restore_data(y[i][0]), "\t\t", restore_data(z[i][0]))