补充9月数据

各地级市日电量模型/杭州.py

@@ -37,8 +37,8 @@ def normal(nd):
 data = pd.read_excel(r'C:\python-project\pytorch3\入模数据\杭州数据.xlsx',index_col='dtdate')
 data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
 data = data.loc[normal(data['售电量']).index]
-plt.plot(range(len(data['售电量']['2021':'2022'])),data['售电量']['2021':'2022'])
-plt.show()
+# plt.plot(range(len(data['售电量']['2021':'2022'])),data['售电量']['2021':'2022'])
+# plt.show()
 
 # print(hf_season(data.loc['2021']['售电量']))
 
@@ -47,8 +47,8 @@ data['month'] = data['month'].astype('int')
 data['season'] = data.index.map(season)
 print(data.head(50))
 
-df_eval = data.loc['2023-7']
-df_train = data.loc['2021-1':'2023-6']
+df_eval = data.loc['2022-9':'2023-9']
+df_train = data.loc['2021-1':'2022-8']
 # df_train = df[500:850]
 print(len(df_eval),len(df_train),len(data))
 
@@ -73,7 +73,7 @@ print(y.describe())
 # best_i = {}
 # for i in range(400):
 
-x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.15,random_state=42)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=42)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
@@ -96,6 +96,8 @@ goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result
 print('goal2:',goal2)
 print(result_eval)
 print('r2:',r2_score(y_test,y_pred))
+
+# result_eval.to_csv('asda.csv',encoding='gbk')
     # if abs(goal) < best_goal:
     #     best_goal = abs(goal)
     #     best_i['best_i'] = i

浙江电压等级电量/电压等级_输出为3.py

@@ -38,6 +38,30 @@ def normal(nd):
     low = nd.describe()['25%'] - 1.5*(nd.describe()['75%']-nd.describe()['25%'])
     return nd[(nd<high)&(nd>low)]
 
+
+
+# def get_data():
+file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
+dataset_x = []
+for excel in os.listdir(file_dir):
+    data = pd.read_excel(os.path.join(file_dir,excel), 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)
+
+    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
+    print('len(data):', len(data))
+    list_app = []
+    for level in data.columns:
+        df = data[level]
+        df = df[df.values != 0]  # 去除0值行
+        df = normal(df)
+        df = df.astype('float32').values  # 转换数据类型
+        dataset_x create_dataset(df,DAYS_FOR_TRAIN)
+
+
 def run(file_dir,excel):
     device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 
@@ -53,8 +77,8 @@ def run(file_dir,excel):
     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))
     list_app = []
-    for industry in data.columns:
-        df = data[industry]
+    for level in data.columns:
+        df = data[level]
         df = df[df.values != 0]  # 去除0值行
         df = normal(df)
         df = df.astype('float32').values  # 转换数据类型
@@ -124,14 +148,6 @@ def run(file_dir,excel):
         pred = model(x.reshape(-1,1,DAYS_FOR_TRAIN)).view(-1).detach().numpy()
 
 
-        # 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 = pred * (max_value - min_value) + min_value
         df = df * (max_value - min_value) + min_value
@@ -155,11 +171,6 @@ def run(file_dir,excel):
         #     f.write(f'{excel[:2]}{industry}:{round(target, 5)}\n')
 
 if __name__ == '__main__':
-    file_dir = r'C:\Users\user\Desktop\浙江各地市分电压日电量数据'
+    file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
 
     run(file_dir,'杭州.xlsx')
-    # p = Pool(4)
-    # for excel in os.listdir(file_dir):
-    #     p.apply_async(func=run,args=(file_dir,excel))
-    # p.close()
-    # p.join()