输出预测结果

浙江电压等级电量/区县分压/xgb_区县.py

@@ -15,29 +15,38 @@ df = pd.read_csv('区县400v入模数据.csv',encoding='gbk',index_col='dtdate')
 df.index = pd.to_datetime(df.index)
 print(df.head())
 
-# org_name = df['org_name'].values[0]
-org_name = ' 国网温岭市供电公司 '
-data = df[df['org_name']==org_name]
-data = data.loc[normal(data['0.4kv及以下']).index]
-print(data)
-X = data.drop(columns=['city_name','org_name','0.4kv及以下'])
-x = X.loc['2022-1':'2023-7']
-x_eval = X.loc['2023-8']
-y = data['0.4kv及以下'].loc['2022-1':'2023-7']
-y_eval = data['0.4kv及以下'].loc['2023-8']
-plt.plot(range(len(y)),y)
-plt.show()
-
-x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state=42)
-
-model = xgb.XGBRegressor(max_depth=6,learning_rate=0.05,n_estimators=150)
-model.fit(x_train,y_train)
-
-pred = model.predict(x_test)
-print(r2_score(pred,y_test))
-
-predict = model.predict(x_eval)
-result = pd.DataFrame({'real':y_eval,'pred':predict},index=y_eval.index)
-print(result)
-print((result['real'][-3:]-result['pred'][-3:]).sum()/result['real'].sum())
-
+list_org = []
+list_fl = []
+list_sc = []
+for org_name in df['org_name'].drop_duplicates():
+    data = df[df['org_name']==org_name]
+    if org_name.strip()[-4:] != '供电公司':
+        continue
+    data = data.loc[normal(data['0.4kv及以下']).index]
+    X = data.drop(columns=['city_name','org_name','0.4kv及以下'])
+    x = X.loc['2022-1':'2023-7'][:-3]
+    x_eval = X.loc['2023-7']
+    y = data['0.4kv及以下'].loc['2022-1':'2023-7'][:-3]
+    y_eval = data['0.4kv及以下'].loc['2023-7']
+    # plt.plot(range(len(y)),y)
+    # plt.show()
+
+    x_train,x_test,y_train,y_test = train_test_split(x,y,test_size=0.3,random_state=42)
+
+    model = xgb.XGBRegressor(max_depth=6,learning_rate=0.05,n_estimators=150)
+    model.fit(x_train,y_train)
+
+    pred = model.predict(x_test)
+    # print(org_name)
+    list_org.append(org_name)
+    # print(r2_score(pred,y_test))
+    list_sc.append(r2_score(pred,y_test))
+    predict = model.predict(x_eval)
+    result = pd.DataFrame({'real':y_eval,'pred':predict},index=y_eval.index)
+    # print(result)
+    # print((result['real'][-3:]-result['pred'][-3:]).sum()/result['real'].sum())
+    list_fl.append((result['real'][-3:]-result['pred'][-3:]).sum()/result['real'].sum())
+
+df = pd.DataFrame({'org':list_org,'sc':list_sc,'goal':list_fl})
+print(df)
+print(df['goal'].value_counts(bins=[-0.05,-0.01,-0.005,0, 0.005, 0.01, 0.02,0.05],sort=False))

浙江电压等级电量/区县分压/区县分压.py

@@ -19,10 +19,12 @@ print(df.columns)
 
 print(dict(zip(df.columns,[(df[x]==0).sum()/len(df) for x in df.columns])))
 yc_org_list = []
+list_fl = []
+list_org = []
 for city in df['市'].drop_duplicates():
     df_ct = df[df['市']==city]
-    wb = Workbook()
-    wb.save(fr'C:\Users\鸽子\Desktop\9月0.4kv区县预测\{city}.xlsx')
+    # wb = Workbook()
+    # wb.save(fr'C:\Users\鸽子\Desktop\9月0.4kv区县预测\{city}.xlsx')
     for org in df_ct['org_name'].drop_duplicates():
         if org.strip()[-4:] != '供电公司':
             continue
@@ -42,12 +44,12 @@ for city in df['市'].drop_duplicates():
         dd['ds'] = pd.to_datetime(dd['ds'])
 
         # 划分数据，划分为训练集和验证集，预测的数据设置为未来3天
-        df_train = dd[(dd['ds']>='2022-01-01')&(dd['ds']<='2023-09-30')][:-3]
+        df_train = dd[(dd['ds']>='2022-01-01')&(dd['ds']<='2023-07-31')][:-3]
         df_train = df_train.loc[normal(df_train['y']).index]
         if df_train.shape[0] <= 180:
             yc_org_list.append(org)
             continue
-        df_test = dd[(dd['ds']>='2022-01-01')&(dd['ds']<='2023-09-30')][-3:]
+        df_test = dd[(dd['ds']>='2022-01-01')&(dd['ds']<='2023-07-31')][-3:]
         # 数据的变动会受到季节、周、天的影响，存在一定的规律性，因此我们将这三个参数设置为True
         model = Prophet(yearly_seasonality=True, weekly_seasonality=True, daily_seasonality=True)
         # 采用中国的假期模式，其余参数均保持默认
@@ -78,15 +80,22 @@ for city in df['市'].drop_duplicates():
         df_all['偏差率'] = (df_all['y'] - df_all['yhat'])/df_all['y']
         df_all.rename(columns={'y':'真实值','yhat':'预测值'},inplace=True)
         df_all = df_all[['org_name','真实值','预测值','偏差率']]
+
+        list_org.append(org)
         try:
-            result = df_all.loc['2023-9']
+            result = df_all.loc['2023-7']
             result['goal'] = (result['真实值'] - result['预测值'])[-3:].sum()/result['真实值'].sum()
-            with pd.ExcelWriter(fr'C:\Users\鸽子\Desktop\9月0.4kv区县预测\{city}.xlsx',mode='a',engine='openpyxl',if_sheet_exists='replace') as writer:
-                result.to_excel(writer,sheet_name=f'{org}')
+            list_fl.append((result['真实值'] - result['预测值'])[-3:].sum()/result['真实值'].sum())
+
+            # with pd.ExcelWriter(fr'C:\Users\鸽子\Desktop\9月0.4kv区县预测\{city}.xlsx',mode='a',engine='openpyxl',if_sheet_exists='replace') as writer:
+            #     result.to_excel(writer,sheet_name=f'{org}')
         except:
             yc_org_list.append(org)
 
-print(yc_org_list)
+df = pd.DataFrame({'org':list_org,'goal':list_fl})
+print(df)
+print(df['goal'].value_counts(bins=[-0.05,-0.01,-0.005,0, 0.005, 0.01, 0.02,0.05],sort=False))
+# print(yc_org_list)
     # # 创建一个ExcelWriter对象
     # with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\output.xlsx',mode='a',if_sheet_exists='replace') as writer:
     #     # 将不同的子文件写入同一个Excel文件的不同工作表

浙江电压等级电量/电压等级_输出为5.py

@@ -165,6 +165,7 @@ for excel in os.listdir(file_dir):
     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[1:]:
         x, y = create_dataset(df_city[level], 10)

浙江行业电量/prophet_行业电量.py

@@ -0,0 +1,9 @@
+from prophet import Prophet
+import pandas as pd
+import os
+import datetime
+
+file_dir = './浙江各地市行业电量数据'
+city = os.listdir(file_dir)[0]
+df_city = pd.read_excel(os.path.join(file_dir,city))
+print(df_city.columns)