不用任何深度学习框架实现单神经元波士顿房价预测
数据集:housing.data
前十三列是十三种因素,最后一列房价
506行 14列
load_data()
def load_data():
# 从文件导入数据
datafile = './work/housing.data'
data = np.fromfile(datafile, sep=' ') #1维 (7084,)
# 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 = 0.8
offset = int(data.shape[0] * ratio)
training_data = data[:offset]
# 计算训练集的最大值,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]
# 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] - minimums[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_data
Net_work
import numpy as np
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)
self.b = 0.
def forward(self, x):
z = np.dot(x, self.w) + self.b
return z
def loss(self, z, y):
error = z - y
num_samples = error.shape[0]
cost = error * error
cost = np.sum(cost) / num_samples
return cost
def gradient(self, x, y): #一个神经元的梯度,很容易推
z = self.forward(x)
N = x.shape[0]
gradient_w = 1. / N * np.sum((z-y) * x, axis=0) #求梯度均值
gradient_w = gradient_w[:, np.newaxis]
gradient_b = 1. / N * np.sum(z-y)
return gradient_w, gradient_b
def update(self, gradient_w, gradient_b, eta = 0.01): #梯度方向函数增长最快,梯度的反方向使损失函数值减少最快
self.w = self.w - eta * gradient_w
self.b = self.b - eta * gradient_b
def train(self, training_data, num_epochs, batch_size=10, eta=0.01):
n = len(training_data)
losses = []
for epoch_id in range(num_epochs):
# 在每轮迭代开始之前,将训练数据的顺序随机打乱
# 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
开始训练
# 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_epochs=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()
版权声明:本文为qq_52766561原创文章,遵循 CC 4.0 BY-SA 版权协议,转载请附上原文出处链接和本声明。