|
|
import numpy as np
|
|
|
import pandas as pd
|
|
|
import torch
|
|
|
from torch import nn
|
|
|
from multiprocessing import Pool
|
|
|
import matplotlib.pyplot as plt
|
|
|
import os
|
|
|
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
|
|
|
DAYS_FOR_TRAIN = 10
|
|
|
torch.manual_seed(42)
|
|
|
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-3):
|
|
|
_x = data[i:(i + days_for_train)]
|
|
|
dataset_x.append(_x)
|
|
|
dataset_y.append(data[i + days_for_train:i + days_for_train+3])
|
|
|
return (np.array(dataset_x), np.array(dataset_y))
|
|
|
|
|
|
def normal(nd):
|
|
|
high = nd.describe()['75%'] + 1.5*(nd.describe()['75%']-nd.describe()['25%'])
|
|
|
low = nd.describe()['25%'] - 1.5*(nd.describe()['75%']-nd.describe()['25%'])
|
|
|
return nd[(nd<high)&(nd>low)]
|
|
|
|
|
|
def run(file_dir,excel):
|
|
|
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
|
|
|
|
|
data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col=' stat_date ')
|
|
|
|
|
|
data.columns = data.columns.map(lambda x: x.strip())
|
|
|
|
|
|
data.index = pd.to_datetime(data.index,format='%Y%m%d')
|
|
|
data.sort_index(inplace=True)
|
|
|
print(data.head())
|
|
|
data = data.loc['2021-01':'2023-09']
|
|
|
|
|
|
data.drop(columns=[i for i in data.columns if (data[i] == 0).sum() / len(data) >= 0.5], inplace=True) # 去除0值列
|
|
|
print('len(data):', len(data))
|
|
|
list_app = []
|
|
|
for industry in data.columns:
|
|
|
df = data[industry]
|
|
|
df = df[df.values != 0] # 去除0值行
|
|
|
df = normal(df)
|
|
|
df = df.astype('float32').values # 转换数据类型
|
|
|
|
|
|
|
|
|
# 标准化到0~1
|
|
|
max_value = np.max(df)
|
|
|
min_value = np.min(df)
|
|
|
df = (df - min_value) / (max_value - min_value)
|
|
|
|
|
|
dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
|
|
|
print('len(dataset_x:)', len(dataset_x))
|
|
|
|
|
|
# 划分训练集和测试集
|
|
|
train_size = len(dataset_x) - 3
|
|
|
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, 3)
|
|
|
|
|
|
# 转为pytorch的tensor对象
|
|
|
train_x = torch.from_numpy(train_x).to(device)
|
|
|
train_y = torch.from_numpy(train_y).to(device)
|
|
|
|
|
|
model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=3, 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(2500):
|
|
|
out = model(train_x)
|
|
|
loss = loss_function(out, train_y)
|
|
|
loss.backward()
|
|
|
optimizer.step()
|
|
|
optimizer.zero_grad()
|
|
|
train_loss.append(loss.item())
|
|
|
print(loss)
|
|
|
# 保存模型
|
|
|
# torch.save(model.state_dict(),save_filename)
|
|
|
# torch.save(model.state_dict(),os.path.join(model_save_dir,model_file))
|
|
|
|
|
|
# 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
|
|
|
dataset_x = dataset_x.reshape(-1, 1, DAYS_FOR_TRAIN) # (seq_size, batch_size, feature_size)
|
|
|
dataset_x = torch.from_numpy(dataset_x).to(device)
|
|
|
|
|
|
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)
|
|
|
pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))
|
|
|
|
|
|
# plt.plot(pred_test, 'r', label='prediction')
|
|
|
# plt.plot(df, 'b', label='real')
|
|
|
# plt.plot((train_size, train_size), (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()
|
|
|
|
|
|
|
|
|
# 创建测试集
|
|
|
# result_list = []
|
|
|
# 以x为基础实际数据，滚动预测未来3天
|
|
|
x = torch.from_numpy(df[-14:-4]).to(device)
|
|
|
pred = model(x.reshape(-1,1,DAYS_FOR_TRAIN)).view(-1).cpu().detach().numpy()
|
|
|
|
|
|
|
|
|
# for i in range(3):
|
|
|
# next_1_8 = x[1:]
|
|
|
# next_9 = model(x.reshape(-1,1,DAYS_FOR_TRAIN))
|
|
|
# # print(next_9,next_1_8)
|
|
|
# x = torch.concatenate((next_1_8, next_9.view(-1)))
|
|
|
# result_list.append(next_9.view(-1).item())
|
|
|
|
|
|
|
|
|
# 反归一化
|
|
|
pred = pred * (max_value - min_value) + min_value
|
|
|
df = df * (max_value - min_value) + min_value
|
|
|
|
|
|
print(pred)
|
|
|
# 打印指标
|
|
|
print(abs(pred - df[-3:]).mean() / df[-3:].mean())
|
|
|
result_eight = pd.DataFrame({'pred': np.round(pred,1),'real': df[-3:]})
|
|
|
target = (result_eight['pred'].sum() - result_eight['real'].sum()) / df[-31:].sum()
|
|
|
result_eight['loss_rate'] = round(target, 5)
|
|
|
result_eight['industry'] = industry
|
|
|
list_app.append(result_eight)
|
|
|
print(target)
|
|
|
print(result_eight)
|
|
|
final_df = pd.concat(list_app,ignore_index=True)
|
|
|
# final_df.to_csv('市行业电量.csv',encoding='gbk')
|
|
|
print(final_df)
|
|
|
|
|
|
# result_eight.to_csv(f'./月底预测结果/9月{excel[:2]}.txt', sep='\t', mode='a')
|
|
|
# with open(fr'./偏差/9月底偏差率.txt', 'a', encoding='utf-8') as f:
|
|
|
# f.write(f'{excel[:2]}{industry}:{round(target, 5)}\n')
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
file_dir = r'C:\Users\user\PycharmProjects\pytorch2\浙江行业电量\浙江所有地市133行业数据'
|
|
|
|
|
|
run(file_dir,'丽水133行业数据（全）.xlsx')
|
|
|
# p = Pool(4)
|
|
|
# for excel in os.listdir(file_dir):
|
|
|
# p.apply_async(func=run,args=(file_dir,excel))
|
|
|
# p.close()
|
|
|
# p.join() |