pytorch/杭州日电量/industry_elec.py

import numpy as np
import pandas as pd
import torch
from torch import nn
import os


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))


if __name__ == '__main__':
    file_dir = r'C:\Users\鸽子\Desktop\浙江所有地市133行业数据（全）'
    for excel in os.listdir((file_dir)):
        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:]:
            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('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


            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)
            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())

            # 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'C:\Users\鸽子\Desktop\各地市8月行业电量预测\{excel[:2]}.txt', 'a', encoding='utf-8') as f:
                f.write(f'{excel[:2]}市{industry}行业月底偏差率:{round(target, 5)}\n')