|
|
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)
|
|
|
|
|
|
# 转为pytorch的tensor对象
|
|
|
train_x = torch.from_numpy(train_x)
|
|
|
train_y = torch.from_numpy(train_y)
|
|
|
|
|
|
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
|
|
|
|
|
|
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
|
|
print("cuda" if torch.cuda.is_available() else "cpu")
|
|
|
model.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("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)
|
|
|
|
|
|
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).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(1)
|
|
|
# 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)
|
|
|
|