1

杭州日电量/industry_elec.py

@@ -0,0 +1,123 @@
+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')
+
+
+
+