波士顿房价预测

代码

import numpy as np
import matplotlib.pyplot as pltdef load_data():# 1.从文件导入数据datafile = 'D:\Python\PythonProject\sklearn\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)# 2.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])# 3.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train数据集的最大值，最小值，平均值maximums, minimums, avgs = training_data.max(axis=0), training_data.min(axis=0), \training_data.sum(axis=0) / training_data.shape[0]# 4.对数据进行归一化处理for i in range(feature_num):#print(maximums[i], minimums[i], avgs[i])data[:, i] = (data[:, i] - avgs[i]) / (maximums[i] - minimums[i])# 训练集和测试集的划分比例training_data = data[:offset]test_data = data[offset:]return training_data, test_dataclass 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)self.b = 0.def forward(self, x):z = np.dot(x, self.w) + self.breturn zdef loss(self, z, y):error = z - ynum_samples = error.shape[0]cost = error * errorcost = np.sum(cost) / num_samplesreturn costdef gradient(self, x, y):z = self.forward(x)N = x.shape[0]gradient_w = 1. / N * np.sum((z-y) * x, axis=0)gradient_w = gradient_w[:, np.newaxis]gradient_b = 1. / N * np.sum(z-y)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, training_data, num_epoches, batch_size=10, eta=0.01):n = len(training_data)losses = []for epoch_id in range(num_epoches):# 在每轮迭代开始之前，将训练数据的顺序随机的打乱，# 然后再按每次取batch_size条数据的方式取出np.random.shuffle(training_data)# 将训练数据进行拆分，每个mini_batch包含batch_size条的数据mini_batches = [training_data[k:k+batch_size] for k in range(0, n, batch_size)]for iter_id, mini_batch in enumerate(mini_batches):#print(self.w.shape)#print(self.b)x = mini_batch[:, :-1]y = mini_batch[:, -1:]a = self.forward(x)loss = self.loss(a, y)gradient_w, gradient_b = self.gradient(x, y)self.update(gradient_w, gradient_b, eta)losses.append(loss)print('Epoch {:3d} / iter {:3d}, loss = {:.4f}'.format(epoch_id, iter_id, loss))return losses# 获取数据
train_data, test_data = load_data()# 创建网络
net = Network(13)
# 启动训练
losses = net.train(train_data, num_epoches=50, batch_size=100, eta=0.1)# 画出损失函数的变化趋势
plot_x = np.arange(len(losses))
plot_y = np.array(losses)
plt.plot(plot_x, plot_y)
plt.show()# 输出模型在测试集上的分数和R²分数
x_test = test_data[:, :-1]
y_test = test_data[:, -1:]
score = net.loss(net.forward(x_test), y_test)

运行结果