输出预测结果

文档处理.py

@@ -70,21 +70,41 @@ import pandas as pd
 # 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]
+#     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}')
+
+df = pd.read_excel('C:\python-project\p1031\浙江行业电量\浙江各地市行业电量数据\台州.xlsx').set_index('stat_date')
+print(df.columns)
+import matplotlib.pyplot as plt
+import matplotlib as mpl
+import matplotlib.dates as mdates
+date_rng = pd.date_range(start=df['4.有色金属矿采选业'].index[0], end=df['4.有色金属矿采选业'].index[-1], freq='D')
+mpl.rcParams['font.sans-serif']=['kaiti']
+print(df['4.有色金属矿采选业'][:-1])
+plt.figure(figsize=(10, 6))
+plt.plot(df['4.有色金属矿采选业'].index[:-1],df['4.有色金属矿采选业'][:-1])
 
-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']
+plt.title(f'4.有色金属矿采选业')
+plt.gcf().autofmt_xdate()
+plt.gca().xaxis.set_major_locator(mdates.DayLocator(interval=120))
 
-        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}')
+plt.xticks(rotation=45)
+plt.xlabel('时间')
+plt.ylabel('数值')
+plt.show()

浙江行业电量/prophet_行业电量.py

@@ -8,7 +8,7 @@ import numpy as np
 def normal(data):
     high = data.describe()['75%'] + 1.5 * (data.describe()['75%'] - data.describe()['25%'])
     low = data.describe()['25%'] - 1.5 * (data.describe()['75%'] - data.describe()['25%'])
-    return data[(data<=high)&(data>=low)]
+    return (data<=high)&(data>=low)
 
 
 file_dir = './浙江各地市行业电量数据'
@@ -18,14 +18,14 @@ for city in os.listdir(file_dir):
     df_city['stat_date'] = pd.to_datetime(df_city['stat_date'])
     list_goal = []
     list_industry = []
+    result_dict = {}
     for industry in df_city.columns[2:]:
         s1 = df_city[['stat_date', industry]]
-        s1 = s1[(s1['stat_date'] >= '2022-09-30') & (s1['stat_date'] <= '2023-10-31')]
-        s1 = s1.loc[normal(s1[industry]).index]
-        s1.rename(columns={'stat_date': 'ds', industry: 'y'}, inplace=True)
+        df_train = s1[(s1['stat_date'] >= '2022-09-30') & (s1['stat_date'] <= '2023-10-31')].sort_values(by='stat_date')
+        df_train.rename(columns={'stat_date': 'ds', industry: 'y'}, inplace=True)
 
-        df_train = s1[(s1['ds'] >= '2022-08-31') & (s1['ds'] <= '2023-10-31')].sort_values(by='ds')
-        df_test = s1[(s1['ds'] >= '2022-08-31') & (s1['ds'] <= '2023-10-31')].sort_values(by='ds')
+        df_train['y'] = df_train['y'].where(normal(df_train['y']), other=np.nan).fillna(method='ffill')
+        # df_test = s1[(s1['ds'] >= '2022-08-31') & (s1['ds'] <= '2023-10-31')].sort_values(by='ds')
 
         model = Prophet(yearly_seasonality=True, weekly_seasonality=True, daily_seasonality=True)
         model.add_country_holidays(country_name="CN")
@@ -33,9 +33,16 @@ for city in os.listdir(file_dir):
         future = model.make_future_dataframe(periods=3, freq='D')
 
         predict = model.predict(future)
-        predict = predict[['ds', 'yhat']].set_index('ds')
         print(city,industry)
-        print(predict.loc['2023-10'])
+
+        predict = predict[['ds', 'yhat']].set_index('ds').loc['2023-10'].rename(columns={'yhat':'售电量'})
+        df_train.rename(columns={'y':'售电量'},inplace=True)
+        result = pd.concat((df_train.set_index('ds').loc['2023-10'][:28],predict[-3:]))
+        result_dict[industry] = list(result['售电量'])
+
+
+    with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\行业电量v1130.xlsx',mode='a',if_sheet_exists='replace',engine='openpyxl') as writer:
+        pd.DataFrame(result_dict,index=pd.date_range(start=f'2023-10-01', end=f'2023-10-31', freq='D').strftime('%Y-%m-%d')).to_excel(writer,sheet_name=city)
 
         # df = predict.join(s1.set_index('ds')).loc['2023-8']
         # df['偏差率'] = (df['y'] - df['yhat']) / df['y']

浙江行业电量/行业电量_输出为3_步长为10.py

@@ -188,6 +188,8 @@ for city in df['city_name'].drop_duplicates():
     df1 = pd.concat((df_city.iloc[:27], df1))
     print(df_city)
     print(df1)
+
+
     with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\行业电量预测v1129.xlsx',mode='a',engine='openpyxl',if_sheet_exists='replace') as writer:
         df1.to_excel(writer,sheet_name=f'{city[4:6]}')
 print(time.time()-t1)