|
|
import numpy as np
|
|
|
import pandas as pd
|
|
|
import matplotlib.pyplot as plt
|
|
|
import torch
|
|
|
from sklearn import preprocessing
|
|
|
from torch.utils.data import DataLoader,TensorDataset
|
|
|
|
|
|
|
|
|
|
|
|
data = pd.read_excel(r'C:\python-project\pytorch3\入模数据\杭州数据.xlsx',index_col='dtdate')
|
|
|
print(data.columns)
|
|
|
|
|
|
|
|
|
x = np.array(data.drop(columns=['售电量','city_name']).loc['2021-1':'2023-6'])
|
|
|
y = np.array(data['售电量'].loc['2021-1':'2023-6'])
|
|
|
|
|
|
# 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(np.array(x)) # fit：求出均值和标准差 transform：求解
|
|
|
|
|
|
# y归一化
|
|
|
min = np.min(y)
|
|
|
max = np.max(y)
|
|
|
y = (y - min)/(max - min)
|
|
|
|
|
|
x_eval = torch.from_numpy(data.drop(columns=['售电量','city_name']).loc['2023-7'].values).type(torch.float32)
|
|
|
y_eval = torch.from_numpy(data['售电量'].loc['2023-7'].values).type(torch.float32)
|
|
|
|
|
|
ds = TensorDataset(torch.from_numpy(x),torch.from_numpy(y))
|
|
|
dl = DataLoader(ds,batch_size=12,shuffle=True,drop_last=True)
|
|
|
|
|
|
|
|
|
# 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
|
|
|
|
|
|
hidden_size = 64
|
|
|
output_size =1
|
|
|
|
|
|
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, output_size)
|
|
|
).to(device)
|
|
|
cost = torch.nn.MSELoss().to(device)
|
|
|
optimizer = torch.optim.Adam(my_nn.parameters(), lr=0.0001)
|
|
|
|
|
|
# 训练网络
|
|
|
losses = []
|
|
|
for i in range(1000):
|
|
|
batch_loss = []
|
|
|
# 采用MINI-Batch的方法进行训练
|
|
|
for X,y in dl:
|
|
|
X,y = X.to(device).type(torch.float32),y.to(device).type(torch.float32)
|
|
|
|
|
|
prediction = my_nn(X)
|
|
|
loss = cost(y, 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(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()
|