输出预测结果

各地级市日电量模型/丽水.py

@@ -87,8 +87,8 @@ import numpy as np
 X_eval = np.array([
     [21,10,10,0,0],
     [21, 11, 10, 0, 0],
-    [18, 7, 10, 0, 0],
-    [17, 9, 10, 0, 0],
+    [20, 8, 10, 0, 0],
+    [20, 8, 10, 0, 0],
     [17, 10, 10, 0, 0]
 ])
 print(model.predict(X_eval))

各地级市日电量模型/台州.py

@@ -85,7 +85,7 @@ model.save_model('taizhou.bin')
 import numpy as np
 
 X_eval = np.array([
-    [19,11,10,0,0],
+    [19,11,10,1,0],
     [21, 7, 10, 0, 0],
     [19, 5, 10, 0, 0],
     [17, 8, 10, 0, 0],

各地级市日电量模型/绍兴.py

@@ -45,7 +45,7 @@ data = data.loc[normal(data['售电量']).index]
 # print(list0,list1,list2)
 data['season'] = data.index.map(season)
 
-df_eval = data.loc['2023-10']
+df_eval = data.loc['2023-11']
 # data = data.loc[:'2023-8']
 df_train = data[450:-1]
 # df_train = data[450:][:-3]
@@ -85,16 +85,16 @@ print(goal2)
 #     x = goal2
 # print(best_i,best_goal,x)
 print(result_eval)
-# 保存模型
-model.save_model('shaoxing.bin')
-loaded_model = xgb.XGBRegressor()
-loaded_model.load_model('shaoxing.bin')
+# # 保存模型
+# model.save_model('shaoxing.bin')
+# loaded_model = xgb.XGBRegressor()
+# loaded_model.load_model('shaoxing.bin')
 import numpy as np
 
 X_eval = np.array([
-    [17, 9, 10, 0, 0],
+    [16.2, 8.2, 10, 1, 0],
     [20, 6, 10, 0, 0],
-    [17, 5, 10, 0, 0],
+    [19, 7, 10, 0, 0],
     [16, 8, 10, 0, 0],
     [12, 7, 10, 0, 0]
 ])

文档处理.py

@@ -60,10 +60,31 @@
 # df = pd.concat(list1,ignore_index=True)
 # df.to_csv('各市行业电量预测结果.csv',encoding='gbk')
 # print(df)
+import os
+from openpyxl import Workbook
 import pandas as pd
-df = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江省11月分行业售电量预测v2.xlsx',sheet_name=1)
-print(df.head())
-print(df[df.columns[2:]].groupby(df['city_name']).sum().T)
-df2 = df[df.columns[2:]].groupby(df['city_name']).sum().T
-df2.to_excel(r'C:\Users\鸽子\Desktop\1.xlsx')
+# df = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江省11月分行业售电量预测v2.xlsx',sheet_name=1)
+# print(df.head())
+# print(df[df.columns[2:]].groupby(df['city_name']).sum().T)
+# df2 = df[df.columns[2:]].groupby(df['city_name']).sum().T
+# df2.to_excel(r'C:\Users\鸽子\Desktop\1.xlsx')
 
+file_dir = r'C:\Users\鸽子\Desktop\11月区县分压预测'
+for file in os.listdir(file_dir):
+    city = file[:-5]
+    wb = Workbook()
+    wb.save(fr'C:\Users\鸽子\Desktop\11月区县分压汇总\{city}.xlsx')
+
+for file in os.listdir(file_dir):
+    city = file[:-5]
+    excel_file = pd.ExcelFile(os.path.join(file_dir,file))
+    sheet_names = excel_file.sheet_names[1:]
+    for sheet in sheet_names:
+        df = excel_file.parse(sheet)
+        df_result = df[df.columns[1:]].sum()
+        df_result = pd.DataFrame(df_result)
+        df_result.columns = ['售电量']
+
+        with pd.ExcelWriter(fr'C:\Users\鸽子\Desktop\11月区县分压汇总\{city}.xlsx', mode='a', engine='openpyxl',
+                            if_sheet_exists='replace') as writer:
+            df_result.to_excel(writer, sheet_name=f'{sheet}')

浙江电压等级电量/区县分压/区县分压.py

@@ -9,47 +9,51 @@ pd.set_option('display.width',None)
 def normal(x):
     high = x.describe()['75%'] + 1.5*(x.describe()['75%']-x.describe()['25%'])
     low = x.describe()['25%'] - 1.5*(x.describe()['75%']-x.describe()['25%'])
-    return x[(x<=high)&(x>=low)]
+    return (x<=high)&(x>=low)
 
 
 df = pd.read_csv(r'C:\Users\鸽子\Desktop\浙江各区县数据(2).csv')
 df.columns = df.columns.map(lambda x:x.strip())
-df.drop(columns=['500kv(含330kv)及以上','220kv','110kv(含66kv)','20kv','power_sal'],inplace=True)
+df.dropna(subset=['city_name','county_name'],inplace=True)
+print(df.info())
 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')
-    for org in df_ct['org_name'].drop_duplicates():
-        if org.strip()[-4:] != '供电公司':
-            continue
-        df_org = df_ct[df_ct['org_name']==org]
-        df_org['1-10kv'] /= 10000
-        df_org['35kv'] /= 10000
-        df_org['0.4kv及以下'] /= 10000
-        s1 = df_org[['日期','0.4kv及以下']]
+list1 = []
+for city in df['city_name'].drop_duplicates():
+    wb = Workbook()
+    wb.save(fr'C:\Users\鸽子\Desktop\11月区县分压预测\{city}.xlsx')
+
+for org in df['county_name'].drop_duplicates():
+    if org.strip()[-4:] != '供电公司':
+        continue
+    df_org = df[df['county_name']==org]
+    city = df_org['city_name'].iloc[0]
+    df_result = pd.DataFrame({})
+    for level in df_org.columns[3:]:
+        s1 = df_org[['pt_date',level]]
         s1.replace(0,np.NaN,inplace=True)
         s1.dropna(how='any',inplace=True)
 
-        # plt.plot(range(len(s1)),s1['1-10kv'])
-        # plt.show()
-
         # 更改列名，更改为Prophet指定的列名ds和y
-        dd = s1.rename(columns={'日期':'ds','0.4kv及以下':'y'})
+        dd = s1.rename(columns={'pt_date':'ds',level:'y'})
+        dd['ds'] = dd['ds'].map(lambda x:x.strip())
         dd['ds'] = pd.to_datetime(dd['ds'])
+        dd.drop_duplicates(inplace=True)
+
+        # 划分数据，划分为训练集和验证集，预测的数据设置为未来4天
+        df_train = dd[(dd['ds']>='2023-01-01')&(dd['ds']<='2023-11-30')]
 
-        # 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']<='2023-07-31')][:-3]
-        df_train = df_train.loc[normal(df_train['y']).index]
-        if df_train.shape[0] <= 180:
+        # df_train = df_train.loc[normal(df_train['y']).index]
+        df_train['y'] = df_train['y'].where(normal(df_train['y']),other=np.nan).bfill()
+
+        if df_train.shape[0] <= 90:
             yc_org_list.append(org)
             continue
-        df_test = dd[(dd['ds']>='2022-01-01')&(dd['ds']<='2023-07-31')][-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
@@ -57,7 +61,7 @@ for city in df['市'].drop_duplicates():
 
         model.fit(df_train)
         # make_future_dataframe: 作用是告诉模型我们要预测多长时间，以及时间的周期是什么。生成一个时间戳
-        future = model.make_future_dataframe(periods=3, freq='D')
+        future = model.make_future_dataframe(periods=4, freq='D')
 
         # 进行预测，返回预测的结果forecast
         forecast = model.predict(future)
@@ -65,37 +69,43 @@ for city in df['市'].drop_duplicates():
         # 有：forecast['yhat']  = forecast['trend'] +  forecast['additive_terms'] 。
         # 因此：forecast['yhat']  = forecast['trend'] +forecast['weekly'] + forecast['yearly']。
         # 如果有节假日因素，那么就会有forecast['yhat']  = forecast['trend'] +forecast['weekly'] + forecast['yearly'] + forecast['holidays']。
-        # print(forecast)
 
         # 测试，把ds列，即data_series列设置为索引列
-        df_test = df_test.set_index('ds')
+        # df_test = df_test.set_index('ds')
 
         # 把预测到的数据取出ds列，预测值列yhat，同样把ds列设置为索引列。
-        forecast = forecast[['ds','yhat']].set_index('ds')
+        forecast = forecast[['ds','yhat']].set_index('ds').sort_index(ascending=True).loc['2023-11']
+
+        # 将预测列前25天替换为真实值
+        forecast.loc['2023-11'][:25] = dd.set_index('ds').loc['2023-11'][:25]
 
+        if len(forecast) < 334:
+            list1.append(org)
         # join:按照索引进行连接，
-        # dropna：能够找到DataFrame类型数据的空值（缺失值），将空值所在的行/列删除后，将新的DataFrame作为返回值返回。
-        df_all = forecast.join(dd.set_index('ds')).dropna()
-        df_all['org_name'] = org
-        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']]
+        forecast.columns = [level]
+
+        df_result = pd.concat([df_result,forecast],axis=1)
+
+        # df_all = forecast.join(dd.set_index('ds')).dropna()
+        # df_all['org_name'] = org
+        # 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['2023-7']
-            result['goal'] = (result['真实值'] - result['预测值'])[-3:].sum()/result['真实值'].sum()
-            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)
 
+        # result = df_all.loc['2023-7']
+        # result['goal'] = (result['真实值'] - result['预测值'])[-3:].sum()/result['真实值'].sum()
+        # 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\11月区县分压预测\{city}.xlsx',mode='a',engine='openpyxl',if_sheet_exists='replace') as writer:
+        df_result.to_excel(writer,sheet_name=f'{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
@@ -107,4 +117,3 @@ print(df['goal'].value_counts(bins=[-0.05,-0.01,-0.005,0, 0.005, 0.01, 0.02,0.05
 # plt.show()
 
 
-