补充9月数据

各地级市日电量模型/杭州.py

@@ -9,20 +9,52 @@ mpl.rcParams['font.sans-serif']=['kaiti']
 
 pd.set_option('display.width',None)
 
-data = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\杭州数据.xlsx',index_col='dtdate')
+def hf_season(x):
+    list1= []
+    for i in range(1,13):
+        if x.loc[f'2021-{i}'].mean() >= x.describe()['75%']:
+            list1.append(i)
+    return list1
+
+
+
+def season(x):
+    if str(x)[5:7] in ('06','07','08','12','01','02'):
+        return 1
+    else:
+        return 0
+def month(x):
+    if str(x)[5:7] in ('08','09','10','12','01','02'):
+        return 1
+    else:
+        return 0
+def normal(nd):
+    high = nd.describe()['75%'] + 1.5*(nd.describe()['75%']-nd.describe()['25%'])
+    low = nd.describe()['25%'] - 1.5*(nd.describe()['75%']-nd.describe()['25%'])
+    return nd[(nd<high)&(nd>low)]
+
+
+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)),data['售电量'])
 plt.show()
-print(data.head())
+
+# print(hf_season(data.loc['2021']['售电量']))
+
+data['month'] = data.index.strftime('%Y-%m-%d').str[6]
+data['month'] = data['month'].astype('int')
+data['season'] = data.index.map(season)
+print(data.head(50))
 
 df_eval = data.loc['2023-9']
 df_train = data.loc['2021-1':'2023-8']
 # df_train = df[500:850]
 print(len(df_eval),len(df_train),len(data))
 
+print(data.drop(columns='city_name').corr(method='pearson')['season'])
 
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量']]
+df_train = df_train[['tem_max','tem_min','24ST','rh','rh_max','prs','prs_max','prs_min','售电量','month','holiday','season']]
 
 
 # IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
@@ -33,14 +65,15 @@ df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量'
 # df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
 
 
-X = df_train[['tem_max','tem_min','holiday','24ST','rh','prs']]
+X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
 y = df_train['售电量']
+print(y.describe())
 # best_goal = 1
 # 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=216)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.15,random_state=209)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
@@ -53,13 +86,14 @@ eval_pred = model.predict(X_eval)
 
 result_eval = pd.DataFrame({'eval':df_eval['售电量'],'pred':eval_pred},index=df_eval['售电量'].index)
 # print(result_eval)
-# print((result_eval['eval'].sum()-result_eval['pred'].sum())/result_eval['eval'].sum())
+print((result_eval['eval'].sum()-result_eval['pred'].sum())/result_eval['eval'].sum())
 
 goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum()
-print(goal)
+print('goal:',goal)
 
 goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
-print(goal2)
+print('goal2:',goal2)
+print('r2:',r2_score(y_test,y_pred))
 # if abs(goal) < best_goal:
 #     best_goal = abs(goal)
 #     best_i['best_i'] = i
@@ -68,9 +102,9 @@ print(goal2)
 
 
 
-result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\杭州.csv')
+# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\杭州.csv')
-with open(r'C:\Users\user\Desktop\9月各地市日电量预测结果\偏差率.txt','a',encoding='utf-8') as f:
+# with open(r'C:\Users\user\Desktop\9月各地市日电量预测结果\偏差率.txt','a',encoding='utf-8') as f:
-    f.write(f'杭州月末3天偏差率：{round(goal,5)},9号-月底偏差率：{round(goal2,5)}\n')
+#     f.write(f'杭州月末3天偏差率：{round(goal,5)},9号-月底偏差率：{round(goal2,5)}\n')
 # # 保存模型
 # model.save_model('hangzhou.bin')
 # loaded_model = xgb.XGBRegressor()

文档处理.py

@@ -1,62 +1,62 @@
-import pandas as pd
+# import pandas as pd
-import os
+# import os
-import re
+# import re
-file_dir1 = r'C:\Users\鸽子\Desktop\一版结果\电压等级电量预测结果\偏差率'
+# file_dir1 = r'C:\Users\鸽子\Desktop\一版结果\电压等级电量预测结果\偏差率'
-file_dir2 = r'C:\Users\鸽子\Desktop\一版结果\电压等级电量预测结果\月底3天预测结果'
+# file_dir2 = r'C:\Users\鸽子\Desktop\一版结果\电压等级电量预测结果\月底3天预测结果'
-file_dir3 = r'C:\Users\鸽子\Desktop\一版结果\行业电量预测结果\偏差'
+# file_dir3 = r'C:\Users\鸽子\Desktop\一版结果\行业电量预测结果\偏差'
-import numpy as np
+# import numpy as np
-np.set_printoptions(threshold=np.inf)
+# np.set_printoptions(threshold=np.inf)
-
+#
-# print(os.listdir(file_dir3))
+# # print(os.listdir(file_dir3))
-# str1 = '丽水电压等级10kv以下月底偏差率:0.00229'
+# # str1 = '丽水电压等级10kv以下月底偏差率:0.00229'
-#
+# #
-# print(re.split('电压等级|月底偏差率:',str1))
+# # print(re.split('电压等级|月底偏差率:',str1))
-# with open(os.path.join(file_dir3,'9月底偏差率.txt'),'r',encoding='utf-8') as f:
+# # with open(os.path.join(file_dir3,'9月底偏差率.txt'),'r',encoding='utf-8') as f:
-#     lines = f.readlines()
+# #     lines = f.readlines()
-#     list_city = []
+# #     list_city = []
-#     list_industry = []
+# #     list_industry = []
-#     list_loss = []
+# #     list_loss = []
-#     for i in lines:
+# #     for i in lines:
-#         i = re.split(':|：|其中', i)
+# #         i = re.split(':|：|其中', i)
+# #         print(i)
+# #         list_city.append(i[0][:2])
+# #         list_industry.append(i[-2].replace(i[0][:2],''))
+# #         list_loss.append(i[-1][:-2])
+# # df_level = pd.DataFrame({'城市':list_city,'行业':list_industry,'偏差':list_loss})
+# # # df_level.to_csv(os.path.join(file_dir3,'9月底偏差率.csv'),encoding='gbk')
+# # print(df_level)
+# file_dir = r'C:\python-project\pytorch3\浙江行业电量\浙江所有地市133行业数据'
+# # print(os.listdir(file_dir))
+# dict1 = {}
+#
+# for file in os.listdir(file_dir):
+#
+#     df = pd.read_excel(os.path.join(file_dir,file),index_col=' stat_date ')
+#
+#     col_list = df.drop(columns=[i for i in df.columns if (df[i] == 0).sum() / len(df) >= 0.5]).columns
+#     dict1[file[:2]] = col_list
+#     print(dict1)
+#
+#     # print(len(df.drop(columns=[i for i in df.columns if (df[i] == 0).sum() / len(df) >= 0.5]).columns))
+#
+# read_path = r'C:\Users\鸽子\Desktop\一版结果\行业电量预测结果\月底预测结果'
+# list1 = []
+# for i in os.listdir(read_path):
 #     print(i)
-#         list_city.append(i[0][:2])
+#     data = pd.read_csv(os.path.join(read_path, i), sep='\t',header=None)
-#         list_industry.append(i[-2].replace(i[0][:2],''))
+#     data = data[data.columns[1:]]
-#         list_loss.append(i[-1][:-2])
+#
-# df_level = pd.DataFrame({'城市':list_city,'行业':list_industry,'偏差':list_loss})
+#
-# # df_level.to_csv(os.path.join(file_dir3,'9月底偏差率.csv'),encoding='gbk')
+#     for j,step in enumerate(range(0, len(data), 4)):
-# print(df_level)
+#         df = data.iloc[step+1:step + 4, :]
-file_dir = r'C:\python-project\pytorch3\浙江行业电量\浙江所有地市133行业数据'
+#         df.columns = ['预测值', '实际值', '偏差率']
-# print(os.listdir(file_dir))
+#         try:
-dict1 = {}
+#             df['行业'] = dict1[i[2:4]][j]
-
+#         except:
-for file in os.listdir(file_dir):
+#             pass
-
+#         df['城市'] = i[2:4]
-    df = pd.read_excel(os.path.join(file_dir,file),index_col=' stat_date ')
+#         list1.append(df)
-
+#         print(df)
-    col_list = df.drop(columns=[i for i in df.columns if (df[i] == 0).sum() / len(df) >= 0.5]).columns
+# df = pd.concat(list1,ignore_index=True)
-    dict1[file[:2]] = col_list
+# df.to_csv('各市行业电量预测结果.csv',encoding='gbk')
-    print(dict1)
+# print(df)
-
-    # print(len(df.drop(columns=[i for i in df.columns if (df[i] == 0).sum() / len(df) >= 0.5]).columns))
-
-read_path = r'C:\Users\鸽子\Desktop\一版结果\行业电量预测结果\月底预测结果'
-list1 = []
-for i in os.listdir(read_path):
-    print(i)
-    data = pd.read_csv(os.path.join(read_path, i), sep='\t',header=None)
-    data = data[data.columns[1:]]
-
-
-    for j,step in enumerate(range(0, len(data), 4)):
-        df = data.iloc[step+1:step + 4, :]
-        df.columns = ['预测值', '实际值', '偏差率']
-        try:
-            df['行业'] = dict1[i[2:4]][j]
-        except:
-            pass
-        df['城市'] = i[2:4]
-        list1.append(df)
-        print(df)
-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)

浙江行业电量/输出为3.py

@@ -147,6 +147,7 @@ def run(file_dir,excel):
         print(target)
         print(result_eight)
     final_df = pd.concat(list_app,ignore_index=True)
+    final_df.to_csv('市行业电量.csv',encoding='gbk')
     print(final_df)
 
         # result_eight.to_csv(f'./月底预测结果/9月{excel[:2]}.txt', sep='\t', mode='a')