|
|
|
|
@ -3,6 +3,9 @@ import pandas as pd
|
|
|
|
|
import torch
|
|
|
|
|
from torch import nn
|
|
|
|
|
import os
|
|
|
|
|
import time
|
|
|
|
|
t1 = time.time()
|
|
|
|
|
|
|
|
|
|
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
|
|
|
|
|
DAYS_FOR_TRAIN = 10
|
|
|
|
|
torch.manual_seed(42)
|
|
|
|
|
@ -38,8 +41,7 @@ def normal(nd):
|
|
|
|
|
|
|
|
|
|
def data_preprocessing(data):
|
|
|
|
|
data.columns = data.columns.map(lambda x: x.strip())
|
|
|
|
|
data.index = data.index.map(lambda x:x.strip())
|
|
|
|
|
|
|
|
|
|
data.index = data.index.map(lambda x:str(x).strip()[:10])
|
|
|
|
|
data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
|
|
|
|
|
data.sort_index(inplace=True)
|
|
|
|
|
data = data.loc['2021-01':'2023-08']
|
|
|
|
|
@ -52,78 +54,78 @@ def data_preprocessing(data):
|
|
|
|
|
return data
|
|
|
|
|
|
|
|
|
|
# 拼接数据集
|
|
|
|
|
file_dir = r'C:\Users\user\Desktop\浙江各地市行业电量数据'
|
|
|
|
|
excel = os.listdir(file_dir)[0]
|
|
|
|
|
data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col='stat_date')
|
|
|
|
|
data.drop(columns='地市',inplace=True)
|
|
|
|
|
data = data_preprocessing(data)
|
|
|
|
|
|
|
|
|
|
df = data[data.columns[0]]
|
|
|
|
|
df.dropna(inplace = True)
|
|
|
|
|
dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
|
|
|
|
|
|
|
|
|
|
for level in data.columns[1:]:
|
|
|
|
|
df = data[level]
|
|
|
|
|
df.dropna(inplace=True)
|
|
|
|
|
x, y = create_dataset(df, DAYS_FOR_TRAIN)
|
|
|
|
|
dataset_x = np.concatenate((dataset_x, x))
|
|
|
|
|
dataset_y = np.concatenate((dataset_y, y))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
for excel in os.listdir(file_dir)[1:]:
|
|
|
|
|
|
|
|
|
|
data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col='stat_date')
|
|
|
|
|
data.drop(columns='地市', inplace=True)
|
|
|
|
|
data = data_preprocessing(data)
|
|
|
|
|
|
|
|
|
|
for level in data.columns:
|
|
|
|
|
df = data[level]
|
|
|
|
|
df.dropna(inplace=True)
|
|
|
|
|
x,y = create_dataset(df,DAYS_FOR_TRAIN)
|
|
|
|
|
dataset_x = np.concatenate((dataset_x,x))
|
|
|
|
|
dataset_y = np.concatenate((dataset_y,y))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
print(dataset_x.shape,dataset_y.shape)
|
|
|
|
|
# file_dir = './浙江各地市行业电量数据'
|
|
|
|
|
# excel = os.listdir(file_dir)[0]
|
|
|
|
|
# data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col='stat_date')
|
|
|
|
|
# data.drop(columns='地市',inplace=True)
|
|
|
|
|
# data = data_preprocessing(data)
|
|
|
|
|
#
|
|
|
|
|
# df = data[data.columns[0]]
|
|
|
|
|
# df.dropna(inplace = True)
|
|
|
|
|
# dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
|
|
|
|
|
#
|
|
|
|
|
# for level in data.columns[1:]:
|
|
|
|
|
# df = data[level]
|
|
|
|
|
# df.dropna(inplace=True)
|
|
|
|
|
# x, y = create_dataset(df, DAYS_FOR_TRAIN)
|
|
|
|
|
# dataset_x = np.concatenate((dataset_x, x))
|
|
|
|
|
# dataset_y = np.concatenate((dataset_y, y))
|
|
|
|
|
#
|
|
|
|
|
#
|
|
|
|
|
# for excel in os.listdir(file_dir)[1:]:
|
|
|
|
|
#
|
|
|
|
|
# data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col='stat_date')
|
|
|
|
|
# data.drop(columns='地市', inplace=True)
|
|
|
|
|
# data = data_preprocessing(data)
|
|
|
|
|
#
|
|
|
|
|
# for level in data.columns:
|
|
|
|
|
# df = data[level]
|
|
|
|
|
# df.dropna(inplace=True)
|
|
|
|
|
# x,y = create_dataset(df,DAYS_FOR_TRAIN)
|
|
|
|
|
# dataset_x = np.concatenate((dataset_x,x))
|
|
|
|
|
# dataset_y = np.concatenate((dataset_y,y))
|
|
|
|
|
#
|
|
|
|
|
#
|
|
|
|
|
# print(dataset_x.shape,dataset_y.shape)
|
|
|
|
|
# # 训练
|
|
|
|
|
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:',max_value,'min_value:',min_value)
|
|
|
|
|
# 划分训练集和测试集
|
|
|
|
|
train_size = int(len(dataset_x)*0.7)
|
|
|
|
|
train_x = dataset_x[:train_size]
|
|
|
|
|
train_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, DAYS_FOR_TRAIN)
|
|
|
|
|
train_y = train_y.reshape(-1, 1, 5)
|
|
|
|
|
|
|
|
|
|
# # 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)
|
|
|
|
|
|
|
|
|
|
# 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:',max_value,'min_value:',min_value)
|
|
|
|
|
# # 划分训练集和测试集
|
|
|
|
|
# train_size = int(len(dataset_x)*0.7)
|
|
|
|
|
# train_x = dataset_x[:train_size]
|
|
|
|
|
# train_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, DAYS_FOR_TRAIN)
|
|
|
|
|
# train_y = train_y.reshape(-1, 1, 5)
|
|
|
|
|
#
|
|
|
|
|
# # # 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)
|
|
|
|
|
#
|
|
|
|
|
model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=5, 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)
|
|
|
|
|
for i in range(1500):
|
|
|
|
|
out = model(train_x)
|
|
|
|
|
loss = loss_function(out, train_y)
|
|
|
|
|
loss.backward()
|
|
|
|
|
optimizer.step()
|
|
|
|
|
optimizer.zero_grad()
|
|
|
|
|
train_loss.append(loss.item())
|
|
|
|
|
if i % 100 == 0:
|
|
|
|
|
print(f'epoch {i+1}: loss:{loss}')
|
|
|
|
|
|
|
|
|
|
# 保存/读取模型
|
|
|
|
|
torch.save(model.state_dict(),'hy5.pth')
|
|
|
|
|
#
|
|
|
|
|
# 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)
|
|
|
|
|
# for i in range(1500):
|
|
|
|
|
# out = model(train_x)
|
|
|
|
|
# loss = loss_function(out, train_y)
|
|
|
|
|
# loss.backward()
|
|
|
|
|
# optimizer.step()
|
|
|
|
|
# optimizer.zero_grad()
|
|
|
|
|
# train_loss.append(loss.item())
|
|
|
|
|
# if i % 100 == 0:
|
|
|
|
|
# print(f'epoch {i+1}: loss:{loss}')
|
|
|
|
|
#
|
|
|
|
|
# # 保存/读取模型
|
|
|
|
|
# torch.save(model.state_dict(),'hy5.pth')
|
|
|
|
|
|
|
|
|
|
# model.load_state_dict(torch.load('hy5.pth'))
|
|
|
|
|
# # for test
|
|
|
|
|
@ -148,7 +150,7 @@ max_value = 354024930.8
|
|
|
|
|
min_value = 0.0
|
|
|
|
|
|
|
|
|
|
# 创建测试集
|
|
|
|
|
file_dir = r'C:\Users\鸽子\Desktop\浙江各地市行业电量数据'
|
|
|
|
|
file_dir = './浙江各地市行业电量数据'
|
|
|
|
|
for excel in os.listdir(file_dir):
|
|
|
|
|
df_city = pd.read_excel(os.path.join(file_dir,excel))
|
|
|
|
|
city = df_city['地市'].iloc[0]
|
|
|
|
|
@ -164,7 +166,8 @@ for excel in os.listdir(file_dir):
|
|
|
|
|
result = pred.detach().numpy()[-5:-2]
|
|
|
|
|
result_dict[industry] = list(result)
|
|
|
|
|
df = pd.DataFrame(result_dict,index=['2023-10-29','2023-10-30','2023-10-31'])
|
|
|
|
|
df.to_excel(fr'C:\Users\鸽子\Desktop\行业电量预测29-31\{city}.xlsx')
|
|
|
|
|
# df.to_excel(fr'./行业电量预测29-31/{city}.xlsx')
|
|
|
|
|
print(time.time()-t1)
|
|
|
|
|
print(result_dict)
|
|
|
|
|
|
|
|
|
|
# 反归一化
|
|
|
|
|
|
