import numpy as np import pandas as pd import torch from torch import nn import os import time t1 = time.time() 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-5): dataset_x.append(data[i:(i + days_for_train)]) dataset_y.append(data[i + days_for_train:i + days_for_train+5]) # print(dataset_x,dataset_y) 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[(ndlow)] def data_preprocessing(data): data.columns = data.columns.map(lambda x: x.strip()) data.index = data.index.map(lambda x:str(x).strip()[:10]) data.index = pd.to_datetime(data.index,format='%Y-%m-%d') data.sort_index(inplace=True) data = data.loc['2021-01':'2023-08'] 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 data = data.astype(float) for col in data.columns: data[col] = normal(data[col]) return data # 拼接数据集 # file_dir = './浙江各地市行业电量数据' # excel = os.listdir(file_dir)[0] # data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col='stat_date') # data.drop(columns='地市',inplace=True) # data = data_preprocessing(data) # # df = data[data.columns[0]] # df.dropna(inplace = True) # dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN) # # for level in data.columns[1:]: # df = data[level] # df.dropna(inplace=True) # x, y = create_dataset(df, DAYS_FOR_TRAIN) # dataset_x = np.concatenate((dataset_x, x)) # dataset_y = np.concatenate((dataset_y, y)) # # # for excel in os.listdir(file_dir)[1:]: # # data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col='stat_date') # data.drop(columns='地市', inplace=True) # data = data_preprocessing(data) # # for level in data.columns: # df = data[level] # df.dropna(inplace=True) # x,y = create_dataset(df,DAYS_FOR_TRAIN) # dataset_x = np.concatenate((dataset_x,x)) # dataset_y = np.concatenate((dataset_y,y)) # # # print(dataset_x.shape,dataset_y.shape) # # 训练 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') # # # 标准化到0~1 # max_value = np.max(dataset_x) # min_value = np.min(dataset_x) # dataset_x = (dataset_x - min_value) / (max_value - min_value) # dataset_y = (dataset_y - min_value) / (max_value - min_value) # print('max_value:',max_value,'min_value:',min_value) # # 划分训练集和测试集 # train_size = int(len(dataset_x)*0.7) # 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, 5) # # # # 转为pytorch的tensor对象 # train_x = torch.from_numpy(train_x).to(device).type(torch.float32) # train_y = torch.from_numpy(train_y).to(device).type(torch.float32) # model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=5, 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(1500): # out = model(train_x) # loss = loss_function(out, train_y) # loss.backward() # optimizer.step() # optimizer.zero_grad() # train_loss.append(loss.item()) # if i % 100 == 0: # print(f'epoch {i+1}: loss:{loss}') # # # 保存/读取模型 # torch.save(model.state_dict(),'hy5.pth') # model.load_state_dict(torch.load('hy5.pth')) # # 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).type(torch.float32) # # 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.reshape(-1), 'r', label='prediction') # plt.plot(dataset_y.reshape(-1), 'b', label='real') # plt.plot((train_size*5, train_size*5), (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() model.load_state_dict(torch.load('hy5.pth',map_location=torch.device('cpu'))) max_value = 354024930.8 min_value = 0.0 # 创建测试集 file_dir = './浙江各地市行业电量数据' for excel in os.listdir(file_dir): df_city = pd.read_excel(os.path.join(file_dir,excel)) city = df_city['地市'].iloc[0] result_dict = {} for industry in df_city.columns[3:]: df_city[industry] = df_city[industry].astype('float') x, y = create_dataset(df_city[industry], 10) x = (x - min_value) / (max_value - min_value) x = x.reshape(-1, 1, 10) x = torch.from_numpy(x).type(torch.float32).to(device) pred = model(x).view(-1) pred = pred * (max_value - min_value) + min_value result = pred.detach().numpy()[-5:-2] result_dict[industry] = list(result) df = pd.DataFrame(result_dict,index=['2023-10-29','2023-10-30','2023-10-31']) # df.to_excel(fr'./行业电量预测29-31/{city}.xlsx') print(time.time()-t1) print(result_dict) # 反归一化 # pred = pred * (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({'pred': np.round(pred,1),'real': df[-3:]}) # target = (result_eight['pred'].sum() - result_eight['real'].sum()) / df[-31:].sum() # result_eight['loss_rate'] = round(target, 5) # result_eight['level'] = level # list_app.append(result_eight) # print(target) # print(result_eight) # final_df = pd.concat(list_app,ignore_index=True) # final_df.to_csv('市行业电量.csv',encoding='gbk') # print(final_df)