pytorch/杭州日电量/industry_elec_cws.py

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)