pytorch/浙江行业电量/浙江全行业.py

import numpy as np
import pandas as pd
import torch
from torch import nn
from multiprocessing import Pool
import matplotlib.pyplot as plt
import os
os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
DAYS_FOR_TRAIN = 10
torch.manual_seed(42)
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 normal(nd):
    high = nd.describe()['75%'] + 1.5*(nd.describe()['75%']-nd.describe()['25%'])
    low = nd.describe()['25%'] - 1.5*(nd.describe()['75%']-nd.describe()['25%'])
    return nd[(nd<high)&(nd>low)]


device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

data = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江133行业日电量数据.xlsx', sheet_name=0,index_col=' stat_date ')

data.columns = data.columns.map(lambda x: x.strip())

data.index = pd.to_datetime(data.index,format='%Y%m%d')
data.sort_index(inplace=True)
# print(data.head())
data = data.loc['2021-01':'2023-09']

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))


df_result = pd.DataFrame({'预测值':[],'实际值':[],'偏差率':[],'行业':[]})
for industry in data.columns:
    df = data[industry]
    df = df[df.values != 0]  # 去除0值行
    df = normal(df)
    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) - 3
    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).to(device)
    train_y = torch.from_numpy(train_y).to(device)

    model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=1, num_layers=2).to(device)  # 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=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
    for i in range(2000):
        out = model(train_x)
        loss = loss_function(out, train_y)
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()
        train_loss.append(loss.item())
        # print(loss)
    # 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).to(device)

    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)
    pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))

    # plt.plot(pred_test, 'r', label='prediction')
    # plt.plot(df, 'b', label='real')
    # plt.plot((train_size, train_size), (0, 1), 'g--')  # 分割线 左边是训练数据 右边是测试数据的输出
    # plt.legend(loc='best')
    # plt.show()


    # 创建测试集
    result_list = []
    # 以x为基础实际数据，滚动预测未来3天
    x = torch.from_numpy(df[-14:-4]).to(device)
    for i in range(3):
        next_1_8 = x[1:]
        next_9 = model(x.reshape(-1,1,DAYS_FOR_TRAIN))
        # print(next_9,next_1_8)
        x = torch.concatenate((next_1_8, next_9.view(-1)))
        result_list.append(next_9.view(-1).item())


    # 反归一化
    pred = np.array(result_list) * (max_value - min_value) + min_value

    df = df * (max_value - min_value) + min_value


    # 打印指标
    # print(abs(pred - df[-3:]).mean() / df[-3:].mean())

    result_eight = pd.DataFrame({'预测值': np.round(pred,1),'实际值': df[-3:]})
    target = (result_eight['预测值'].sum() - result_eight['实际值'].sum()) / df[-31:].sum()
    result_eight['偏差率'] = round(target, 5)
    result_eight['行业'] = industry

    df_result = pd.concat((df_result,result_eight))
    print(df_result)


    # result_eight.to_csv(f'9月{excel[:2]}.txt', sep='\t', mode='a')
    # with open(fr'./偏差/9月底偏差率.txt', 'a', encoding='utf-8') as f:
    #     f.write(f'{excel[:2]}{industry}:{round(target, 5)}\n')