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") 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(2) for excel in os.listdir((file_dir)): p.apply_async(func=to_data, args=(file_dir, excel)) p.close() p.join()