You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

156 lines
5.5 KiB
Python

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

import time
import numpy as np
import pandas as pd
import torch
from torch import nn
import os
from multiprocessing import Process, Pool
DAYS_FOR_TRAIN = 9
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 to_data(file_dir, excel):
data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0)
data.columns = data.columns.map(lambda x: x.strip())
data.sort_values(by='stat_date', ascending=True)
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))
for industry in data.columns[1:]:
c = time.time()
df = data[['stat_date', industry]]
df = df[df[industry] != 0] # 去除0值行
df['stat_date'] = pd.to_datetime(df['stat_date'], format='%Y%m%d', errors='coerce').astype('string')
df.set_index('stat_date', inplace=True)
df = df[(df.index.str[:6] != '202309') & (df.index.str[:6] != '202310')]
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("========")
print('len(dataset_x:)', len(dataset_x))
# 划分训练集和测试集
train_size = len(dataset_x) - 31
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, 1)
# 使用GPU
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
# 转为pytorch的tensor对象
train_x = torch.from_numpy(train_x)
train_y = torch.from_numpy(train_y)
train_x = train_x.cuda()
train_y = train_y.cuda()
model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=1, num_layers=2) # 导入模型并设置模型的参数输入输出层、隐藏层等
# 使用GPU
print("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
# train_x.to(device)
# train_y.to(device)
train_loss = []
loss_function = nn.MSELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=0.001, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
a = time.time()
print(industry, "行业加载时间", a - c)
for i in range(1200):
out = model(train_x)
loss = loss_function(out, train_y)
loss.backward()
optimizer.step()
optimizer.zero_grad()
train_loss.append(loss.item())
b = time.time()
print(excel, industry, '训练用时', b - a)
# 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)
dataset_x = dataset_x.cuda()
pred_test = model(dataset_x) # 全量训练集
# 模型输出 (seq_size, batch_size, output_size)
pred_test = pred_test.cpu()
pred_test = pred_test.view(-1).data.numpy()
pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test))
assert len(pred_test) == len(df)
# 反归一化
pred_test = pred_test * (max_value - min_value) + min_value
df = df * (max_value - min_value) + min_value
pred_test = pred_test.reshape(-1)
df = df.reshape(-1)
# 打印指标
print(abs(pred_test[-31:] - df[-31:]).mean() / df[-31:].mean())
result_eight = pd.DataFrame({'pred_test': pred_test[-31:], 'real': df[-31:]})
target = (result_eight['pred_test'][-3:].sum() - result_eight['real'][-3:].sum()) / result_eight[
'real'].sum()
# print(target)
with open(fr'.\cws_to_data\{excel[:2]}.txt', 'a', encoding='utf-8') as f:
tmp_data = {'city': excel[:2], 'industry': industry, "month_deviation_rate": round(target, 5)}
f.write(str(tmp_data) + "\n")
print("========")
if __name__ == '__main__':
file_dir = r'./浙江所有地市133行业数据'
p = Pool(4)
for excel in os.listdir((file_dir)):
p.apply_async(func=to_data, args=(file_dir, excel))
p.close()
p.join()
# for excel in os.listdir((file_dir)):
# to_data(file_dir, excel)