更新入模数据

浙江电压等级电量/test1.py

@@ -1,7 +1,18 @@
 import numpy as np
+import pandas as pd
 n1 = np.array([[1,1,1]])
 n2 = np.array([1,1,1]).reshape(1,-1)
 print(n2)
 n2 = np.array([]).reshape(3,-1)
 
 print(np.max([[1,2,3],[4,5,6]]))
+
+file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
+df = pd.read_csv(r'C:\Users\鸽子\Desktop\浙江省各地市日电量数据21-23年 .csv',encoding='gbk')
+df.columns = df.columns.map(lambda x:x.strip())
+for city in df['地市'].drop_duplicates():
+    df_city = df[df['地市']== city]
+    df_city['stat_date'] = pd.to_datetime(df_city['stat_date'],format='%Y/%m/%d')
+    df_city = df_city[df_city.columns[:-1]]
+    df_city['stat_date'] = df_city['stat_date'].astype('str')
+    df_city.to_excel(fr'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据\{city}.xlsx',index=False)

浙江电压等级电量/电压等级_输出为5.py

@@ -44,20 +44,18 @@ def data_preprocessing(data):
     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[data.values != 0]
+
     data = data.astype(float)
     for col in data.columns:
         data[col] = normal(data[col])
 
     return data
 
-
 # 拼接数据集
 file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
 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]]
@@ -73,7 +71,9 @@ for level in data.columns[1:]:
 
 
 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:
@@ -95,7 +95,7 @@ dataset_x = (dataset_x - min_value) / (max_value - min_value)
 dataset_y = (dataset_y - min_value) / (max_value - min_value)
 
 # 划分训练集和测试集
-train_size = len(dataset_x)*0.7
+train_size = int(len(dataset_x)*0.7)
 train_x = dataset_x[:train_size]
 train_y = dataset_y[:train_size]
 
@@ -104,10 +104,10 @@ 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)
-train_y = torch.from_numpy(train_y).to(device)
+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=3, 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
+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 = []
@@ -120,11 +120,10 @@ for i in range(1500):
     optimizer.step()
     optimizer.zero_grad()
     train_loss.append(loss.item())
-    # print(loss)
+    print(loss)
 # 保存模型
 torch.save(model.state_dict(),'dy5.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