更新电压lstm模型

.idea/misc.xml

@@ -1,4 +1,4 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="C:\anaconda\envs\pytorch" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="pytorch_gpu" project-jdk-type="Python SDK" />
 </project>

.idea/pytorch2.iml

@@ -2,7 +2,7 @@
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager">
     <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="C:\anaconda\envs\pytorch" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="pytorch_gpu" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

浙江电压等级电量/test1.py

@@ -9,26 +9,27 @@ 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)
-file_Dir = r'C:\Users\鸽子\Desktop\浙江各地市行业电量数据'
-for excel in os.listdir(file_Dir):
-    df1 = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江各地市日电量数据-27-28).xlsx',sheet_name=1)
-    df1.columns = df1.columns.map(lambda x:x.strip())
-    df2 = pd.read_excel(os.path.join(file_Dir,excel))
-    df2['地市'] = df2['地市'].map(lambda x:x.strip())
-    city = df2['地市'].iloc[0]
-    col_list = df2.columns
-    df1 = df1[col_list]
-    df1 = df1[(df1['stat_date']==20231028)&(df1['地市']==city)]
-    df1['stat_date'] = pd.to_datetime(df1['stat_date'],format='%Y%m%d')
-    df2 = pd.concat((df2,df1),ignore_index=True)
-    df2.to_excel(fr'C:\Users\鸽子\Desktop\浙江各地市行业电量数据\{city}.xlsx')
+file_dir = r'C:\Users\user\Desktop\浙江各地市分电压日电量数据'
+df = pd.read_excel(r'C:\Users\user\Desktop\浙江省各地市日电量及分压数据21-23年.xlsx',sheet_name=1)
+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'] = df_city['stat_date'].map(lambda x:x.strip())
+    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\user\Desktop\浙江各地市分电压日电量数据\{city}.xlsx',index=False)
+# file_Dir = r'C:\Users\鸽子\Desktop\浙江各地市行业电量数据'
+# for excel in os.listdir(file_Dir):
+#     df1 = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江各地市日电量数据-27-28).xlsx',sheet_name=1)
+#     df1.columns = df1.columns.map(lambda x:x.strip())
+#     df2 = pd.read_excel(os.path.join(file_Dir,excel))
+#     df2['地市'] = df2['地市'].map(lambda x:x.strip())
+#     city = df2['地市'].iloc[0]
+#     col_list = df2.columns
+#     df1 = df1[col_list]
+#     df1 = df1[(df1['stat_date']==20231028)&(df1['地市']==city)]
+#     df1['stat_date'] = pd.to_datetime(df1['stat_date'],format='%Y%m%d')
+#     df2 = pd.concat((df2,df1),ignore_index=True)
+#     df2.to_excel(fr'C:\Users\鸽子\Desktop\浙江各地市行业电量数据\{city}.xlsx')
 

浙江电压等级电量/电压等级_输出为5.py

@@ -5,7 +5,7 @@ from torch import nn
 from multiprocessing import Pool
 import matplotlib.pyplot as plt
 import os
-os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"
+os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"  # 解决OMP: Error #15: Initializing libiomp5md.dll, but found libiomp5md.dll already initialized.
 DAYS_FOR_TRAIN = 10
 torch.manual_seed(42)
 class LSTM_Regression(nn.Module):
@@ -52,120 +52,120 @@ def data_preprocessing(data):
     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]]
-# 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))
+file_dir = r'C:\Users\user\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]]
+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))
 
 
 
 # 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,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)
+
+# 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,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())
+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())
 
 # 保存模型
-# torch.save(model.state_dict(),'dy5.pth')
+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
-# 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 = 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()
 
 
 # 创建测试集
 
-max_value,min_value = 199482558.1,0.0
-model.load_state_dict(torch.load('dy5.pth',map_location=torch.device('cpu')))
-file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
-for excel in os.listdir(file_dir):
-    df_city = pd.read_excel(os.path.join(file_dir,excel))
-    df_city.drop(columns=[i for i in df_city.columns if (df_city[i] == 0).sum() / len(df_city) >= 0.5], inplace=True)
-
-    city = df_city['地市'].iloc[0]
-    result_dict = {}
-    for level in df_city.columns[2:]:
-        x, y = create_dataset(df_city[level], 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[level] = list(result)
-    df = pd.DataFrame(result_dict,index=['2023-10-29','2023-10-30','2023-10-31'])
-    df.to_excel(fr'C:\Users\鸽子\Desktop\分压电量预测29-31\{city}.xlsx')
-print(result_dict)
+# max_value,min_value = 192751288.47,0.0
+# model.load_state_dict(torch.load('dy5.pth',map_location=torch.device('cpu')))
+# file_dir = r'C:\Users\user\Desktop\浙江各地市分电压日电量数据'
+# for excel in os.listdir(file_dir):
+#     df_city = pd.read_excel(os.path.join(file_dir,excel))
+#     df_city.drop(columns=[i for i in df_city.columns if (df_city[i] == 0).sum() / len(df_city) >= 0.5], inplace=True)
+#
+#     city = df_city['地市'].iloc[0]
+#     result_dict = {}
+#     for level in df_city.columns[2:]:
+#         x, y = create_dataset(df_city[level], 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[level] = list(result)
+#     df = pd.DataFrame(result_dict,index=['2023-10-29','2023-10-30','2023-10-31'])
+#     df.to_excel(fr'C:\Users\鸽子\Desktop\分压电量预测29-31\{city}.xlsx')
+# print(result_dict)