|
|
import numpy as np
|
|
|
import pandas as pd
|
|
|
import torch
|
|
|
from torch import nn
|
|
|
import os
|
|
|
import matplotlib.pyplot as plt
|
|
|
from sklearn.preprocessing import MinMaxScaler
|
|
|
from torch.utils.data import DataLoader,TensorDataset
|
|
|
|
|
|
class LSTM_Regression(nn.Module):
|
|
|
def __init__(self, input_size, hidden_size, output_size=1, num_layers=2):
|
|
|
super().__init__()
|
|
|
|
|
|
self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
|
|
|
self.fc = nn.Linear(hidden_size, output_size)
|
|
|
|
|
|
def forward(self, _x):
|
|
|
x, _ = self.lstm(_x) # _x is input, size (seq_len, batch, input_size)
|
|
|
s, b, h = x.shape # x is output, size (seq_len, batch, hidden_size)
|
|
|
x = x.view(s * b, h)
|
|
|
x = self.fc(x)
|
|
|
x = x.view(s, b, -1) # 把形状改回来
|
|
|
return x
|
|
|
|
|
|
|
|
|
def create_dataset(data, days_for_train=5) -> (np.array, np.array):
|
|
|
dataset_x, dataset_y = [], []
|
|
|
for i in range(len(data) - days_for_train):
|
|
|
_x = data[i:(i + days_for_train)]
|
|
|
dataset_x.append(_x)
|
|
|
dataset_y.append(data[i + days_for_train])
|
|
|
return (np.array(dataset_x), np.array(dataset_y))
|
|
|
|
|
|
|
|
|
def inverse_transform_col(scaler,y,n_col):
|
|
|
'''scaler是对包含多个feature的X拟合的,y对应其中一个feature,n_col为y在X中对应的列编号.返回y的反归一化结果'''
|
|
|
y = y.copy()
|
|
|
y -= scaler.min_[n_col]
|
|
|
y /= scaler.scale_[n_col]
|
|
|
return y
|
|
|
|
|
|
|
|
|
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
|
|
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)
|
|
|
data.columns = data.columns.map(lambda x: x.strip())
|
|
|
data.drop(columns='city_name',inplace=True)
|
|
|
# 标准化到0~1
|
|
|
scaler = MinMaxScaler()
|
|
|
df_normalized = pd.DataFrame(scaler.fit_transform(data), columns=data.columns,index=data.index).astype(float)
|
|
|
|
|
|
# 划分训练集和测试集
|
|
|
x_all = df_normalized.drop(columns='售电量').loc['2021-1':'2023-9']
|
|
|
y_all = df_normalized['售电量'].loc['2021-1':'2023-9']
|
|
|
|
|
|
x_train = df_normalized.drop(columns='售电量').loc['2021-1':'2023-8']
|
|
|
y_train = df_normalized['售电量'].loc['2021-1':'2023-8']
|
|
|
|
|
|
eval = df_normalized.loc['2023-9']
|
|
|
x_eval = eval.drop(columns='售电量')
|
|
|
y_eval = eval['售电量']
|
|
|
|
|
|
|
|
|
|
|
|
# 将数据改变形状，RNN 读入的数据维度是 (seq_size, batch_size, feature_size)
|
|
|
|
|
|
x_train = np.array(x_train.values).reshape(-1, 1, 13)
|
|
|
y_train = np.array(y_train.values).reshape(-1, 1, 1)
|
|
|
|
|
|
# 转为pytorch的tensor对象
|
|
|
x_train = torch.from_numpy(x_train).to(device).type(torch.float32)
|
|
|
y_train = torch.from_numpy(y_train).to(device).type(torch.float32)
|
|
|
|
|
|
x_eval = torch.from_numpy(x_eval.values).to(device).type(torch.float32)
|
|
|
|
|
|
model = LSTM_Regression(13, 16, output_size=1, num_layers=2).to(device) # 导入模型并设置模型的参数输入输出层、隐藏层等
|
|
|
|
|
|
train_loss = []
|
|
|
loss_function = nn.MSELoss()
|
|
|
optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
|
|
|
|
|
|
ds = TensorDataset(x_train,y_train)
|
|
|
dl = DataLoader(ds,batch_size=3,shuffle=True)
|
|
|
|
|
|
|
|
|
for i in range(300):
|
|
|
for j,(x,y) in enumerate(dl):
|
|
|
x,y = x.to(device),y.to(device)
|
|
|
out = model(x)
|
|
|
loss = loss_function(out, y)
|
|
|
loss.backward()
|
|
|
optimizer.step()
|
|
|
optimizer.zero_grad()
|
|
|
train_loss.append(loss.item())
|
|
|
if i%100 == 0:
|
|
|
print(f'epoch:{i+1} 第{j}次loss:{loss}')
|
|
|
|
|
|
# 保存模型
|
|
|
torch.save(model.state_dict(),'lstm.pth')
|
|
|
# torch.save(model.state_dict(),os.path.join(model_save_dir,model_file))
|
|
|
|
|
|
model.load_state_dict(torch.load('lstm.pth'))
|
|
|
# for test
|
|
|
model = model.eval() # 转换成测试模式
|
|
|
# model.load_state_dict(torch.load(os.path.join(model_save_dir,model_file))) # 读取参数
|
|
|
|
|
|
x_eval = x_eval.reshape(-1, 1, 13) # (seq_size, batch_size, feature_size)
|
|
|
|
|
|
|
|
|
pred_test = model(x_eval) # 全量训练集
|
|
|
|
|
|
# 模型输出 (seq_size, batch_size, output_size)
|
|
|
pred_test = pred_test.view(-1).cpu().data.numpy()
|
|
|
print(x_eval.shape,pred_test.shape)
|
|
|
|
|
|
# 反归一化
|
|
|
|
|
|
pred_test = inverse_transform_col(scaler,pred_test,-1)
|
|
|
pred_test = pred_test.reshape(-1)
|
|
|
|
|
|
y_eval = inverse_transform_col(scaler,y_eval,-1)
|
|
|
# 打印指标
|
|
|
print(abs(pred_test - y_eval).mean() /y_eval.mean())
|
|
|
result_eight = pd.DataFrame({'pred_test': pred_test, 'real': y_eval})
|
|
|
target = (result_eight['pred_test'][-3:].sum() - result_eight['real'][-3:].sum()) / result_eight[
|
|
|
'real'].sum()
|
|
|
print(result_eight)
|
|
|
print(target)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|