|
|
import torch
|
|
|
import pandas as pd
|
|
|
import numpy as np
|
|
|
import matplotlib.pyplot as plt
|
|
|
from torch import nn
|
|
|
import os
|
|
|
from torch.utils.data import TensorDataset, DataLoader
|
|
|
import datetime
|
|
|
|
|
|
torch.manual_seed(42)
|
|
|
os.environ[
|
|
|
"KMP_DUPLICATE_LIB_OK"] = "TRUE" # 解决OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
|
|
|
pd.set_option('display.width', None)
|
|
|
|
|
|
|
|
|
class LSTM(nn.Module):
|
|
|
def __init__(self, input_size, hidden_size, output_size, num_layers=3):
|
|
|
super().__init__()
|
|
|
self.lstm = nn.LSTM(input_size, hidden_size, num_layers)
|
|
|
self.fc1 = nn.Linear(hidden_size, 64)
|
|
|
self.fc2 = nn.Linear(64, 128)
|
|
|
self.fc3 = nn.Linear(128, output_size)
|
|
|
self.ReLu = nn.ReLU()
|
|
|
self.dropout = nn.Dropout()
|
|
|
|
|
|
def forward(self, x):
|
|
|
output, _ = self.lstm(x)
|
|
|
s, b, h = output.shape
|
|
|
output = output.reshape(-1, h)
|
|
|
output = self.ReLu(self.fc1(output))
|
|
|
output = self.ReLu(self.fc2(output))
|
|
|
output = self.fc3(output)
|
|
|
return output
|
|
|
|
|
|
|
|
|
def normal(df):
|
|
|
drop_col = [x for x in df.columns if len(df[df[x]==0])/len(df) >= 0.5]
|
|
|
df.drop(columns=drop_col,inplace=True)
|
|
|
for col in df.columns:
|
|
|
try:
|
|
|
high = df[col].describe()['75%'] + 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
|
|
|
low = df[col].describe()['25%'] - 1.5 * (df[col].describe()['75%'] - df[col].describe()['25%'])
|
|
|
df[col] = df[col].map(lambda x: np.nan if (x >= high) | (x <= low) else x)
|
|
|
df[col] = df[col].fillna(method='ffill')
|
|
|
df[col] = df[col].fillna(method='bfill')
|
|
|
except:
|
|
|
pass
|
|
|
return df
|
|
|
|
|
|
def create_data(df_industry, industry):
|
|
|
dataset_x = []
|
|
|
dataset_y = []
|
|
|
# 按月份分组
|
|
|
grouped = df_industry.groupby(df_industry['stat_date'].dt.to_period('M'))
|
|
|
|
|
|
# 遍历每个月的数据
|
|
|
for name, group in grouped:
|
|
|
if len(group) == 31:
|
|
|
dataset_x.append(list(group[industry].values[1:28]))
|
|
|
dataset_y.append(list(group[industry].values[-3:]))
|
|
|
if len(group) == 30:
|
|
|
dataset_x.append(list(group[industry].values[:27]))
|
|
|
dataset_y.append(list(group[industry].values[-3:]))
|
|
|
if len(group) == 28:
|
|
|
fst = group[industry].values[0]
|
|
|
|
|
|
dataset_x.append([fst, fst, fst] + list(group[industry].values[1:25]))
|
|
|
dataset_y.append(list(group[industry].values[-3:]))
|
|
|
else:
|
|
|
fst = group[industry].values[0]
|
|
|
if len([fst, fst] + list(group[industry].values[1:26])) != 27:
|
|
|
break
|
|
|
dataset_x.append([fst, fst] + list(group[industry].values[1:26]))
|
|
|
dataset_y.append(list(group[industry].values[-3:]))
|
|
|
|
|
|
return np.array(dataset_x), np.array(dataset_y)
|
|
|
|
|
|
|
|
|
# 创建数据集
|
|
|
file_dir = './浙江各地市行业电量数据'
|
|
|
city1 = os.listdir(file_dir)[0]
|
|
|
df_city = pd.read_excel(os.path.join(file_dir, city1))
|
|
|
df_city = normal(df_city)
|
|
|
df_city = df_city.drop(columns='地市')
|
|
|
df_city[df_city.columns[1:]] /= 10000
|
|
|
df_city['stat_date'] = df_city['stat_date'].map(lambda x: str(x).strip()[:10])
|
|
|
df_city.stat_date = pd.to_datetime(df_city.stat_date)
|
|
|
|
|
|
|
|
|
|
|
|
industry = '全社会用电总计'
|
|
|
df_industry = df_city[['stat_date', industry]]
|
|
|
dataset_x, dataset_y = create_data(df_industry, industry)
|
|
|
|
|
|
|
|
|
for industry in df_city.columns[2:]:
|
|
|
df_level = df_city[['stat_date', industry]]
|
|
|
x, y = create_data(df_level, industry)
|
|
|
dataset_x = np.concatenate([dataset_x, x])
|
|
|
dataset_y = np.concatenate([dataset_y, y])
|
|
|
|
|
|
for excel in os.listdir(file_dir)[1:]:
|
|
|
df_city = pd.read_excel(os.path.join(file_dir, excel)).drop(columns='地市')
|
|
|
df_city = normal(df_city)
|
|
|
df_city[df_city.columns[1:]] /= 10000
|
|
|
df_city['stat_date'] = df_city['stat_date'].map(lambda x: str(x).strip()[:10])
|
|
|
df_city.stat_date = pd.to_datetime(df_city.stat_date)
|
|
|
for industry in df_city.columns[1:]:
|
|
|
df_level = df_city[['stat_date', industry]]
|
|
|
x, y = create_data(df_level, industry)
|
|
|
dataset_x = np.concatenate([dataset_x, x])
|
|
|
dataset_y = np.concatenate([dataset_y, y])
|
|
|
|
|
|
|
|
|
print(dataset_x.shape, dataset_y.shape)
|
|
|
|
|
|
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
|
|
# 标准化到0~1
|
|
|
max_value = np.max(dataset_x)
|
|
|
min_value = np.min(dataset_x)
|
|
|
dataset_x = (dataset_x - min_value) / (max_value - min_value)
|
|
|
dataset_y = (dataset_y - min_value) / (max_value - min_value)
|
|
|
|
|
|
print(max_value, min_value)
|
|
|
|
|
|
|
|
|
# 划分训练集和测试集
|
|
|
train_size = int(len(dataset_x) * 0.8)
|
|
|
train_x = dataset_x[:train_size]
|
|
|
train_y = dataset_y[:train_size]
|
|
|
eval_x = dataset_x[train_size:]
|
|
|
eval_y = dataset_y[train_size:]
|
|
|
|
|
|
# # 将数据改变形状，RNN 读入的数据维度是 (seq_size, batch_size, feature_size)
|
|
|
train_x = train_x.reshape(-1, 1, 27)
|
|
|
train_y = train_y.reshape(-1, 1, 3)
|
|
|
eval_x = eval_x.reshape(-1, 1, 27)
|
|
|
eval_y = eval_y.reshape(-1, 1, 3)
|
|
|
|
|
|
# # 转为pytorch的tensor对象
|
|
|
train_x = torch.from_numpy(train_x).to(device).type(torch.float32)
|
|
|
train_y = torch.from_numpy(train_y).to(device).type(torch.float32)
|
|
|
eval_x = torch.from_numpy(eval_x).to(device).type(torch.float32)
|
|
|
eval_y = torch.from_numpy(eval_y).to(device).type(torch.float32)
|
|
|
|
|
|
train_ds = TensorDataset(train_x, train_y)
|
|
|
train_dl = DataLoader(train_ds, batch_size=32, shuffle=True, drop_last=True)
|
|
|
eval_ds = TensorDataset(eval_x, eval_y)
|
|
|
eval_dl = DataLoader(eval_ds, batch_size=64, drop_last=True)
|
|
|
|
|
|
model = LSTM(27, 16, output_size=3, num_layers=3).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)
|
|
|
min_loss = 1
|
|
|
for i in range(10):
|
|
|
model.train()
|
|
|
for j, (x, y) in enumerate(train_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+1) % 100 == 0:
|
|
|
# print(f'epoch {i+1}/1500 loss:{round(loss.item(),5)}')
|
|
|
if (j + 1) % 10 == 0:
|
|
|
print(f'epoch {i + 1}/200 step {j + 1}/{len(train_dl)} loss:{loss}')
|
|
|
test_running_loss = 0
|
|
|
model.eval()
|
|
|
with torch.no_grad():
|
|
|
for x, y in eval_dl:
|
|
|
pred = model(eval_x)
|
|
|
loss = loss_function(pred, y)
|
|
|
test_running_loss += loss.item()
|
|
|
test_loss = test_running_loss / len(eval_dl)
|
|
|
if test_loss < min_loss:
|
|
|
min_loss = test_loss
|
|
|
best_model_weight = model.state_dict()
|
|
|
print(f'epoch {i + 1} test_loss:{test_loss}')
|
|
|
|
|
|
total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)
|
|
|
print(f"Total parameters in the LSTM model: {total_params}")
|
|
|
# 保存模型
|
|
|
torch.save(best_model_weight, 'dy3.pth')
|
|
|
|
|
|
# 读取模型
|
|
|
model = LSTM(27, 16, output_size=3, num_layers=3).to(device)
|
|
|
model.load_state_dict(torch.load('dy3.pth'))
|
|
|
# for test
|
|
|
|
|
|
dataset_x = dataset_x.reshape(-1, 1, 27) # (seq_size, batch_size, feature_size)
|
|
|
dataset_x = torch.from_numpy(dataset_x).to(device).type(torch.float32)
|
|
|
|
|
|
pred_test = model(dataset_x) # 全量训练集
|
|
|
# 模型输出 (seq_size, batch_size, output_size)
|
|
|
pred_test = pred_test.view(-1).cpu().detach().numpy()
|
|
|
|
|
|
plt.plot(pred_test.reshape(-1), 'r', label='prediction')
|
|
|
plt.plot(dataset_y.reshape(-1), 'b', label='real')
|
|
|
plt.plot((train_size * 3, train_size * 3), (0, 1), 'g--') # 分割线 左边是训练数据 右边是测试数据的输出
|
|
|
plt.legend(loc='best')
|
|
|
plt.show()
|