|
|
import numpy as np
|
|
|
import pandas as pd
|
|
|
import matplotlib.pyplot as plt
|
|
|
import torch
|
|
|
from sklearn import preprocessing
|
|
|
|
|
|
data = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\杭州数据.xlsx',index_col='dtdate')
|
|
|
print(data.columns)
|
|
|
|
|
|
|
|
|
y = np.array(data['售电量']) # 制作标签，用于比对训练结果
|
|
|
x = data.drop(columns=['售电量','city_name']) # 在特征数据集中去掉label
|
|
|
# df.drop(label, axis=0)
|
|
|
# label：要删除的列或者行，如果要删除多个，传入列表
|
|
|
# axis:轴的方向，0为行，1为列，默认为0
|
|
|
fea_train = np.array(x) # 转换为ndarray格式
|
|
|
|
|
|
# 数据标准化操作：(x-均值μ) / 标准差σ ，使数据关于原点对称，提升训练效率
|
|
|
input_features = preprocessing.StandardScaler().fit_transform(fea_train) # fit：求出均值和标准差 transform：求解
|
|
|
|
|
|
# y归一化 防止梯度爆炸
|
|
|
y = (y - np.min(y))/(np.max(y) - np.min(y))
|
|
|
print(y)
|
|
|
|
|
|
# 设定神经网络的输入参数、隐藏层神经元、输出参数的个数
|
|
|
input_size = input_features.shape[1] # 设定输入特征个数
|
|
|
# np.shape[1]
|
|
|
# 0为行，1为列，默认为0
|
|
|
# 在此表格中因为每行为各样本的值，每列为不同的特征分类，所以此处0表示样本数，1表示特征数
|
|
|
hidden_size = 64 # 设定隐藏层包含64个神经元
|
|
|
output_size = 1 # 设定输出特征个数为1
|
|
|
batch_size = 32 # 每一批迭代的特征数量
|
|
|
|
|
|
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") # 选择使用GPU训练
|
|
|
|
|
|
my_nn = torch.nn.Sequential(
|
|
|
torch.nn.Linear(input_size, hidden_size).to(device), # 输入层 → 第一层
|
|
|
torch.nn.ReLU().to(device),
|
|
|
torch.nn.Linear(hidden_size, hidden_size).to(device), # 第一层 → 第二层
|
|
|
torch.nn.ReLU().to(device),
|
|
|
torch.nn.Linear(hidden_size, hidden_size).to(device), # 第二层 → 第三层
|
|
|
torch.nn.ReLU().to(device),
|
|
|
torch.nn.Linear(hidden_size, hidden_size).to(device), # 第三层 → 第四层
|
|
|
torch.nn.ReLU().to(device),
|
|
|
torch.nn.Linear(hidden_size, output_size).to(device) # 第四层 → 输出层
|
|
|
).to(device)
|
|
|
cost = torch.nn.MSELoss().to(device)
|
|
|
optimizer = torch.optim.Adam(my_nn.parameters(), lr=0.001)
|
|
|
|
|
|
# 训练网络
|
|
|
losses = []
|
|
|
for i in range(300):
|
|
|
batch_loss = []
|
|
|
# 采用MINI-Batch的方法进行训练
|
|
|
for start in range(0, len(input_features), batch_size):
|
|
|
end = start + batch_size if start + batch_size < len(input_features) else len(input_features)
|
|
|
x_train = torch.tensor(input_features[start:end], dtype=torch.float32, requires_grad=True).to(device)
|
|
|
y_train = torch.tensor(y[start:end], dtype=torch.float32, requires_grad=True).to(device)
|
|
|
prediction = my_nn(x_train)
|
|
|
loss = cost(y_train, prediction)
|
|
|
optimizer.zero_grad()
|
|
|
loss.backward(retain_graph=True)
|
|
|
optimizer.step()
|
|
|
batch_loss.append(loss.data.cpu().numpy())
|
|
|
|
|
|
if i % 10 == 0:
|
|
|
losses.append(np.mean(batch_loss))
|
|
|
print(losses)
|
|
|
print(i, np.mean(batch_loss))
|
|
|
|
|
|
# 保存模型
|
|
|
# torch.save(my_nn, 'BP.pt')
|
|
|
|
|
|
# 绘制图像
|
|
|
dev_x = [i * 10 for i in range(20)]
|
|
|
plt.xlabel('step count')
|
|
|
plt.ylabel('loss')
|
|
|
plt.xlim((0, 200))
|
|
|
plt.ylim((0, 1000))
|
|
|
plt.plot(dev_x, losses)
|
|
|
plt.show()
|