更新入模数据

各地级市日电量模型/丽水.py

@@ -6,48 +6,56 @@ from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 import matplotlib.pyplot as plt
 mpl.rcParams['font.sans-serif']=['kaiti']
+pd.set_option('display.width',None)
 
 def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
+    if str(x)[5:7] in ('01', '10', '11'):
+        return 0
+    elif str(x)[5:7] in ('02', '03', '04', '05', '06', '09', '12'):
         return 1
     else:
-        return 0
+        return 2
+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)]
+
 
 
-pd.set_option('display.width',None)
 parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
 data = pd.read_excel(os.path.join(parent_dir,'入模数据/丽水.xlsx'),index_col='dtdate')
 data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
-data['season'] = data.index.map(season)
-
-print(data.head())
-
-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))
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
-
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
+data = data.loc[normal(data['售电量']).index]
 
 # list2 = []
 # list0 = []
 # list1 = []
 # for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
-#     month_index = df.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
-#     if df.loc[month_index]['售电量'].mean() >= df['售电量'].describe()['75%']:
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     print(data.loc[month_index]['售电量'].max(),data['售电量'].describe()['75%'])
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
 #         list2.append(i)
-#     elif df.loc[month_index]['售电量'].mean() <= df['售电量'].describe()['25%']:
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
 #         list0.append(i)
 #     else:
 #         list1.append(i)
 # print(list0,list1,list2)
 
 
+
+data['season'] = data.index.map(season)
+
+print(data.head())
+
+df_eval = data.loc['2023-9']
+# df_train = data.loc['2021-1':'2023-8']
+df_train = data[500:850]
+print(len(df_eval),len(df_train),len(data))
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
+
+
+
+
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
 X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
 y = df_train['售电量']
@@ -56,7 +64,7 @@ y = df_train['售电量']
 # for i in range(200):
 
 
-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)
 
@@ -68,12 +76,12 @@ print(abs(y_test - y_pred).mean() / y_test.mean())
 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'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum())
+print(result_eval)
+
 goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum()
-print((result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum())
+print(goal)
 goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
+print(goal2)
     # if abs(goal) < best_goal:
     #     best_goal = abs(goal)
     #     best_i['best_i'] = i
@@ -83,7 +91,7 @@ goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result
 # 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'丽水月末3天偏差率：{goal},9号-月底偏差率：{goal2}')
 # # 保存模型
-# model.save_model('lishui.bin')
+model.save_model('lishui.bin')
 import numpy as np
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('lishui.bin')

各地级市日电量模型/台州.py

@@ -5,39 +5,47 @@ from sklearn.metrics import r2_score
 from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 import matplotlib.pyplot as plt
-
-def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
-        return 1
-    else:
-        return 0
 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\台州数据(1).xlsx',index_col='dtdate')
+def season(x):
+    if str(x)[5:7] in ('01', '02', '10', '11'):
+        return 0
+    elif str(x)[5:7] in ('03', '04', '05', '06', '09', '12'):
+        return 1
+    else:
+        return 2
+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)]
+
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/台州.xlsx'),index_col='dtdate')
 data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+data = data.loc[normal(data['售电量']).index]
+
+list2 = []
+list0 = []
+list1 = []
+for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+    month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+    if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+        list2.append(i)
+    elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+        list0.append(i)
+    else:
+        list1.append(i)
+print(list0,list1,list2)
+
 data['season'] = data.index.map(season)
-# plt.plot(range(len(data)),data['售电量'])
-# plt.show()
-print(data.head())
 
 df_eval = data.loc['2023-8']
-# df_train = data.loc['2021-1':'2023-7']
-df_train = data[500:850]
-print(len(df_eval),len(df_train),len(data))
-
 
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
-
-
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
+df_train = data[500:850]
 
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
 X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
@@ -60,22 +68,17 @@ 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'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum())
 goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum()
-print((result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum())
+print(goal)
 goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
+print(goal2)
 #     if abs(goal) < best_goal:
 #         best_goal = abs(goal)
 #         best_i['best_i'] = i
 # print(best_i,best_goal)
 
-
-#
-# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\台州.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:
-#     f.write(f'台州月末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('taizhou.bin')
+# 保存模型
+model.save_model('taizhou.bin')
 import numpy as np
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('taizhou.bin')

各地级市日电量模型/嘉兴.py

@@ -5,41 +5,50 @@ from sklearn.metrics import r2_score
 from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 import matplotlib.pyplot as plt
+mpl.rcParams['font.sans-serif']=['kaiti']
+pd.set_option('display.width',None)
+
 def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
+    if str(x)[5:7] in ('04', '10'):
+        return 0
+    elif str(x)[5:7] in ('01', '02', '03', '05', '06', '09', '11', '12'):
         return 1
     else:
-        return 0
-mpl.rcParams['font.sans-serif']=['kaiti']
+        return 2
 
+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)]
 
-pd.set_option('display.width',None)
 
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/嘉兴.xlsx'),index_col='dtdate')
+data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+data = data.loc[normal(data['售电量']).index]
 
-df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\嘉兴数据.xlsx')
-df['dtdate'] = pd.to_datetime(df['dtdate'],format='%Y-%m-%d').astype('string')
-df.set_index('dtdate',inplace=True)
-plt.plot(range(len(df)),df['售电量'])
-plt.show()
-print(df.head())
-df['season'] = df.index.map(season)
+# list2 = []
+# list0 = []
+# list1 = []
+# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+#         list2.append(i)
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+#         list0.append(i)
+#     else:
+#         list1.append(i)
+# print(list0,list1,list2)
+data['season'] = data.index.map(season)
 
-df_eval = df[df.index.str[:7]=='2023-08']
-# df_train = df[(df.index.str[:7]!='2023-08')&(df.index.str[:7]!='2023-09')]
-df_train = df[500:850]
-print(len(df_eval),len(df_train),len(df))
+df_eval = data.loc['2023-08']
+df_train = data.iloc[500:850]
+# df_train = data.loc['2021-01':'2023-07']
+print(len(df_eval),len(df_train),len(data))
 
 
 
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
-
-
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
 
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
@@ -50,7 +59,7 @@ y = df_train['售电量']
 # best_i = {}
 # for i in range(400):
 
-x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=272)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=42)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
@@ -61,14 +70,11 @@ result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
 # 指标打印
 print(abs(y_test - y_pred).mean() / y_test.mean())
 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)
-
 goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum()
-# print(goal)
-
 goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
 print(goal,goal2)
+print(result_eval)
 # print(goal2)
 #     if abs(goal) < best_goal :
 #         best_goal = abs(goal)
@@ -77,13 +83,8 @@ print(goal,goal2)
 #
 # print(best_i,best_goal,x)
 
-
-
-# result_eval.to_csv(r'C:\Users\user\Desktop\8月各地市日电量预测结果\嘉兴.csv')
-# with open(r'C:\Users\user\Desktop\8月各地市日电量预测结果\偏差率.txt','a',encoding='utf-8') as f:
-#     f.write(f'嘉兴月末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('jiaxing.bin')
+model.save_model('jiaxing.bin')
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('jiaxing.bin')
 import numpy as np

各地级市日电量模型/宁波.py

@@ -5,42 +5,47 @@ from sklearn.metrics import r2_score
 from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 import matplotlib.pyplot as plt
-def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
-        return 1
-    else:
-        return 0
 mpl.rcParams['font.sans-serif']=['kaiti']
-
-
 pd.set_option('display.width',None)
 
-
-df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\宁波数据.xlsx',index_col='dtdate')
-df.index = pd.to_datetime(df.index,format='%Y-%m-%d')
-df['season'] = df.index.map(season)
-plt.plot(range(len(df)),df['售电量'])
-plt.show()
-print(df.head())
-
-
-df_eval = df.loc['2023-09']
-df_train = df.loc['2021-01':'2023-08']
-# df_train = df[400:850]
-print(len(df_eval),len(df_train),len(df))
-
-
-
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
-
-
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
-
+def season(x):
+    if str(x)[5:7] in ('01', '04', '10'):
+        return 0
+    elif str(x)[5:7] in ('02', '03', '05', '06', '09', '11', '12'):
+        return 1
+    else:
+        return 2
+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)]
+
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/宁波.xlsx'),index_col='dtdate')
+data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+data = data.loc[normal(data['售电量']).index]
+
+# list2 = []
+# list0 = []
+# list1 = []
+# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+#         list2.append(i)
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+#         list0.append(i)
+#     else:
+#         list1.append(i)
+# print(list0,list1,list2)
+
+
+data['season'] = data.index.map(season)
+df_eval = data.loc['2023-09']
+df_train = data.loc['2021-01':'2023-08']
+# df_train = data[400:850]
+print(len(df_eval),len(df_train))
+
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
 X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
@@ -53,8 +58,6 @@ y = df_train['售电量']
 x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=18)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
-
-
 y_pred = model.predict(x_test)
 result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
 
@@ -76,12 +79,8 @@ print(goal2)
 #
 # print(best_i,best_goal,x)
 
-
-# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\宁波.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:
-#     f.write(f'宁波月末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('ningbo.bin')
+model.save_model('ningbo.bin')
 import numpy as np
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('ningbo.bin')

各地级市日电量模型/杭州.py

@@ -7,23 +7,15 @@ from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 import matplotlib.pyplot as plt
 mpl.rcParams['font.sans-serif']=['kaiti']
-
 pd.set_option('display.width',None)
 
-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'):
+    if str(x)[5:7] in ('04', '10'):
+        return 0
+    elif str(x)[5:7] in ('01', '02', '03', '05', '06', '09', '11', '12'):
         return 1
     else:
-        return 0
+        return 2
 def month(x):
     if str(x)[5:7] in ('08','09','10','12','01','02'):
         return 1
@@ -34,47 +26,45 @@ def normal(nd):
     low = nd.describe()['25%'] - 1.5*(nd.describe()['75%']-nd.describe()['25%'])
     return nd[(nd<high)&(nd>low)]
 
-
-data = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\杭州数据.xlsx',index_col='dtdate')
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/杭州.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()
-
-# 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.tail(50))
+# list2 = []
+# list0 = []
+# list1 = []
+# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+#         list2.append(i)
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+#         list0.append(i)
+#     else:
+#         list1.append(i)
+# print(list0,list1,list2)
 
-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))
 
-print(data.drop(columns='city_name').corr(method='pearson')['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)
 
-df_train = df_train[['tem_max','tem_min','24ST','rh','rh_max','prs','prs_max','prs_min','售电量','month','holiday','season']]
 
+# df_train = df[500:850]
 
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
+df_train = data.loc['2021-01':'2023-08']
+df_eval = data.loc['2023-9']
 
 
 X = df_train[['tem_max','tem_min','24ST','holiday','season']]
 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=0.2,random_state=42)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=142)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
@@ -83,20 +73,17 @@ result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
 
 # 指标打印
 print(abs(y_test - y_pred).mean() / y_test.mean())
-# 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['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:',goal)
-#
-# goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
-#
-# print('goal2:',goal2)
-# print(result_eval)
-# print('r2:',r2_score(y_test,y_pred))
+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)
+
+goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum()
+print('goal:',goal)
+
+goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
+
+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:
@@ -111,30 +98,17 @@ print(abs(y_test - y_pred).mean() / y_test.mean())
 # # 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')
 # 保存模型
-# model.save_model('hangzhou.bin')
+model.save_model('hangzhou.bin')
 
 # X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
-df_eval = pd.read_excel(r'C:\Users\user\Desktop\浙江气象1027.xlsx')
-df_eval.columns = df_eval.columns.map(lambda x:x.strip())
-df_eval = df_eval[['city_name','dtdate','tem_max','tem_min']]
-df_eval['city_name'] = df_eval['city_name'].map(lambda x:x.strip())
-df_hangzhou = df_eval[df_eval['city_name']=='金华市'].sort_values(by='dtdate')
+# df_eval = pd.read_excel(r'C:\Users\user\Desktop\浙江气象1027.xlsx')
+# df_eval.columns = df_eval.columns.map(lambda x:x.strip())
+# df_eval = df_eval[['city_name','dtdate','tem_max','tem_min']]
+# df_eval['city_name'] = df_eval['city_name'].map(lambda x:x.strip())
+# df_hangzhou = df_eval[df_eval['city_name']=='金华市'].sort_values(by='dtdate')
 
 
-# list2 = []
-# list0 = []
-# list1 = []
-# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
-#     month_index = df.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
-#     if df.loc[month_index]['售电量'].mean() >= df['售电量'].describe()['75%']:
-#         list2.append(i)
-#     elif df.loc[month_index]['售电量'].mean() <= df['售电量'].describe()['25%']:
-#         list0.append(i)
-#     else:
-#         list1.append(i)
-# print(list0,list1,list2)
 
-print(df_hangzhou)
 
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('hangzhou.bin')

各地级市日电量模型/温州.py

@@ -5,41 +5,50 @@ from sklearn.metrics import r2_score
 from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 import matplotlib.pyplot as plt
-def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
-        return 1
-    else:
-        return 0
 mpl.rcParams['font.sans-serif']=['kaiti']
-
-
 pd.set_option('display.width',None)
 
-
-df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\温州数据(1).xlsx',index_col='dtdate')
-df.index = pd.to_datetime(df.index,format='%Y-%m-%d')
-df['season'] = df.index.map(season)
-plt.plot(range(len(df)),df['售电量'])
-plt.show()
-print(df.head())
+def season(x):
+    if str(x)[5:7] in ('01', '02', '10'):
+        return 0
+    elif str(x)[5:7] in ('03', '04', '05', '06', '11', '12'):
+        return 1
+    else:
+        return 2
+
+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)]
+
+
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/温州.xlsx'),index_col='dtdate')
+data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+data = data.loc[normal(data['售电量']).index]
+
+# list2 = []
+# list0 = []
+# list1 = []
+# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+#         list2.append(i)
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+#         list0.append(i)
+#     else:
+#         list1.append(i)
+#
+# print(list0,list1,list2)
+data['season'] = data.index.map(season)
 
 
-df_eval = df.loc['2023-9']
+df_eval = data.loc['2023-9']
 # df_train = df[(df.index.str[:7]!='2023-08')&(df.index.str[:7]!='2023-09')]
-df_train = df[400:850]
-print(len(df_eval),len(df_train),len(df))
-
-
-
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
+df_train = data[400:850]
 
 
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
 
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
@@ -54,7 +63,6 @@ x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
-
 y_pred = model.predict(x_test)
 result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
 
@@ -69,18 +77,14 @@ print(goal)
 
 goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
 print(goal2)
+
 # if abs(goal) < best_goal :
 #     best_goal = abs(goal)
 #     best_i['best_i'] = i
 #     x = goal2
-
 # print(best_i,best_goal,x)
-
-# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\温州.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:
-#     f.write(f'温州月末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('wenzhou.bin')
+model.save_model('wenzhou.bin')
 
 loaded_model = xgb.XGBRegressor()
 

各地级市日电量模型/湖州.py

@@ -5,42 +5,55 @@ from sklearn.metrics import r2_score
 from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 mpl.rcParams['font.sans-serif']=['kaiti']
+pd.set_option('display.width',None)
 import random
 import matplotlib.pyplot as plt
+
 def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
+    if str(x)[5:7] in ('10'):
+        return 0
+    elif str(x)[5:7] in ('01', '02', '03', '04', '05', '06', '09', '11', '12'):
         return 1
     else:
-        return 0
-pd.set_option('display.width',None)
-
-
-df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\湖州数据.xlsx',index_col='dtdate')
-df.index = pd.to_datetime(df.index,format='%Y-%m-%d')
-df['season'] = df.index.map(season)
-print(df.head())
-
-df_eval = df.loc['2023-9']
-df_train = df.loc['2021-1':'2023-8']
-print(len(df_eval),len(df_train),len(df))
-
-
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
+        return 2
+
+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)]
+
+
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/湖州.xlsx'),index_col='dtdate')
+data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+data = data.loc[normal(data['售电量']).index]
+
+# list2 = []
+# list0 = []
+# list1 = []
+# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+#         list2.append(i)
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+#         list0.append(i)
+#     else:
+#         list1.append(i)
+#
+# print(list0,list1,list2)
 
+data['season'] = data.index.map(season)
 
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
+df_eval = data.loc['2023-9']
+df_train = data.loc['2021-1':'2023-8']
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
 
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
 X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
 y = df_train['售电量']
 
-x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=100)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=42)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
@@ -48,7 +61,6 @@ model.fit(x_train,y_train)
 y_pred = model.predict(x_test)
 result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
 
-
 # 指标打印
 print(abs(y_test - y_pred).mean() / y_test.mean())
 eval_pred = model.predict(X_eval)
@@ -57,19 +69,11 @@ result_eval = pd.DataFrame({'eval':df_eval['售电量'],'pred':eval_pred},index=
 
 goal = (result_eval['eval'][-3:].sum()-result_eval['pred'][-3:].sum())/result_eval['eval'].sum()
 print(goal)
-
 goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
 print(goal2)
 
-
-
-# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\湖州.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:
-#     f.write(f'湖州月末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('huzhou.bin')
+model.save_model('huzhou.bin')
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('huzhou.bin')
 import  numpy as np

各地级市日电量模型/绍兴.py

@@ -5,48 +5,57 @@ from sklearn.metrics import r2_score
 from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 import matplotlib.pyplot as plt
-def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
-        return 1
-    else:
-        return 0
 mpl.rcParams['font.sans-serif']=['kaiti']
-
-
 pd.set_option('display.width',None)
 
+def season(x):
+    if str(x)[5:7] in ('01', '02', '10', '11'):
+        return 0
+    elif str(x)[5:7] in ('03', '04', '05', '06', '09', '12'):
+        return 1
+    else:
+        return 2
+
+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)]
+
+
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/绍兴.xlsx'),index_col='dtdate')
+data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+data = data.loc[normal(data['售电量']).index]
+
+# list2 = []
+# list0 = []
+# list1 = []
+# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+#         list2.append(i)
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+#         list0.append(i)
+#     else:
+#         list1.append(i)
+#
+# print(list0,list1,list2)
+data['season'] = data.index.map(season)
 
-df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\绍兴数据(1).xlsx',index_col='dtdate')
-df.index = pd.to_datetime(df.index ,format='%Y-%m-%d')
-df['season'] = df.index.map(season)
-plt.plot(range(len(df)),df['售电量'])
-plt.show()
-print(df.head())
-
-
-df_eval = df.loc['2023-9']
-df_train = df.loc['2021-1':'2023-8']
+df_eval = data.loc['2023-9']
+df_train = data.loc['2021-1':'2023-8']
 # df_train = df[400:850]
-print(len(df_eval),len(df_train),len(df))
-
+print(len(df_eval),len(df_train),len(data))
 
 
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
 
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
-
 
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
 X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
 y = df_train['售电量']
 
-
 # best_goal = 1
 # best_i = {}
 # for i in range(400):
@@ -74,16 +83,8 @@ print(goal2)
 #     best_goal = abs(goal)
 #     best_i['best_i'] = i
 #     x = goal2
-
 # print(best_i,best_goal,x)
 
-
-
-# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\绍兴.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:
-#     f.write(f'绍兴月末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('shaoxing.bin')
 loaded_model = xgb.XGBRegressor()

各地级市日电量模型/舟山.py

@@ -5,49 +5,59 @@ from sklearn.metrics import r2_score
 from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 mpl.rcParams['font.sans-serif']=['kaiti']
+pd.set_option('display.width',None)
 import random
 import matplotlib.pyplot as plt
+
 def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
+    if str(x)[5:7] in ('01', '02', '03', '04', '05', '06', '09', '10', '11', '12'):
         return 1
     else:
-        return 0
-pd.set_option('display.width',None)
-
-
-df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\舟山数据(1).xlsx',index_col='dtdate')
-df.index = pd.to_datetime(df.index,format='%Y-%m-%d')
-df['season'] = df.index.map(season)
-print(df.head())
-
-df_eval = df.loc['2023-9']
-df_train = df.loc['2021-1':'2023-8']
-print(len(df_eval),len(df_train),len(df))
-
-
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
-
-
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
-
-
+        return 2
+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)]
+
+
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/舟山.xlsx'),index_col='dtdate')
+data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+data = data.loc[normal(data['售电量']).index]
+
+
+# list2 = []
+# list0 = []
+# list1 = []
+# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+#         list2.append(i)
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+#         list0.append(i)
+#     else:
+#         list1.append(i)
+# 
+# print(list0,list1,list2)
+
+data['season'] = data.index.map(season)
+df_eval = data.loc['2023-9']
+# df_train = data.loc['2021-1':'2023-8']
+df_train = data.iloc[500:850]
+
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
 X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
 y = df_train['售电量']
 
-x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=158)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=42)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
 
 y_pred = model.predict(x_test)
 result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
-# result_test.to_csv(r'C:\Users\鸽子\Desktop\test.csv',encoding='utf-8')
+
 
 # 指标打印
 print(abs(y_test - y_pred).mean() / y_test.mean())
@@ -61,9 +71,7 @@ print(goal)
 goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
 print(goal2)
 
-# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\舟山.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:
-#     f.write(f'舟山月末3天偏差率：{round(goal,5)},9号-月底偏差率：{round(goal2,5)}\n')
+
 model.save_model('zhoushan.bin')
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('zhoushan.bin')

各地级市日电量模型/衢州.py

@@ -5,46 +5,47 @@ from sklearn.metrics import r2_score
 from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 import matplotlib.pyplot as plt
+mpl.rcParams['font.sans-serif']=['kaiti']
+pd.set_option('display.width',None)
 def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
+    if str(x)[5:7] in ('01', '02'):
+        return 0
+    elif str(x)[5:7] in ('03', '04', '05', '06', '09', '10', '11', '12'):
         return 1
     else:
-        return 0
-
-mpl.rcParams['font.sans-serif']=['kaiti']
-
-
-pd.set_option('display.width',None)
+        return 2
 
+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)]
 
-df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\衢州数据.xlsx')
-df['dtdate'] = pd.to_datetime(df['dtdate'],format='%Y-%m-%d').astype('string')
-df.set_index('dtdate',inplace=True)
-df['season'] = df.index.map(season)
-plt.plot(range(len(df)),df['售电量'])
-plt.show()
-print(df.head())
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/衢州.xlsx'),index_col='dtdate')
+data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+data = data.loc[normal(data['售电量']).index]
 
-# df_eval = df[(df.index.str[:10]=='2023-08-29')|(df.index.str[:10]=='2023-08-30')|(df.index.str[:10]=='2023-08-31')]
+# list2 = []
+# list0 = []
+# list1 = []
+# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+#         list2.append(i)
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+#         list0.append(i)
+#     else:
+#         list1.append(i)
 #
-# df_train = df[(df.index.str[:7]!='2023-09')&(df.index.str!='2023-08-29')&(df.index.str!='2023-08-30')&(df.index.str!='2023-08-31')]
+# print(list0,list1,list2)
+data['season'] = data.index.map(season)
 
-df_eval = df[df.index.str[:7]=='2023-07']
-df_train = df[(df.index.str[:7]!='2023-08')&(df.index.str[:7]!='2023-09')]
-# df_train = df[450:900]
-# max_8,min_8 = df_eval['售电量'].max(),df_eval['售电量'].min()
 
-print(len(df_eval),len(df_train),len(df))
+df_eval = data.loc['2023-08']
+df_train = data.iloc[450:900]
 
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
-
-IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-high = df['售电量'].describe()['75%'] + 1.5*IQR
-low = df['售电量'].describe()['25%'] - 1.5*IQR
-print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-
-df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
 
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
 X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
@@ -66,17 +67,8 @@ print(goal)
 goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
 print(goal2)
 
-
-# print((result_eval['eval'].sum()-result_eval['pred'].sum())/result_eval['eval'].sum())
-# print((result_eval['eval'].sum()-(result_eval['eval'][:-3].sum()+result_eval['pred'][-3:].sum()))/result_eval['eval'].sum())
-# #
-# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\衢州.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:
-#     f.write(f'衢州月末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('quzhou.bin')
+model.save_model('quzhou.bin')
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('quzhou.bin')
 import numpy as np
@@ -89,22 +81,6 @@ X_eval = np.array([[24.0,15.6,23,0,0],
 print(model.predict(X_eval))
 
 
-# from sklearn.ensemble import RandomForestRegressor
-# from sklearn.metrics import mean_squared_error
-# rf = RandomForestRegressor(n_estimators=150,max_depth=6)
-#
-# # 在训练集上训练模型
-# rf.fit(x_train, y_train)
-#
-# # 在测试集上进行预测
-# y_pred = rf.predict(x_test)
-# eval_pred = rf.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['eval'][:-3].sum()+result_eval['pred'][-3:].sum()))/result_eval['eval'].sum())
-
-
 
 # import torch
 # from torch import nn

各地级市日电量模型/金华.py

@@ -5,43 +5,48 @@ from sklearn.metrics import r2_score
 from sklearn.model_selection import train_test_split
 import matplotlib as mpl
 import matplotlib.pyplot as plt
-def season(x):
-    if str(x)[5:7] in ('06','07','08','12','01','02'):
-        return 1
-    else:
-        return 0
 mpl.rcParams['font.sans-serif']=['kaiti']
-
-
 pd.set_option('display.width',None)
 
-
-df = pd.read_excel(r'C:\Users\user\PycharmProjects\pytorch2\入模数据\金华数据.xlsx')
-df['dtdate'] = pd.to_datetime(df['dtdate'],format='%Y-%m-%d').astype('string')
-df.set_index('dtdate',inplace=True)
-df['season'] = df.index.map(season)
-plt.plot(range(len(df)),df['售电量'])
-plt.show()
-print(df.head())
-
-
-df_eval = df[df.index.str[:7]=='2023-09']
-df_train = df[(df.index.str[:7]!='2023-08')&(df.index.str[:7]!='2023-09')]
-# df_train = df[500:850]
-print(len(df_eval),len(df_train),len(df))
-
-
-
-df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量','season']]
+def season(x):
+    if str(x)[5:7] in ('01', '02', '04', '10'):
+        return 0
+    elif str(x)[5:7] in ('03', '05', '06', '09', '11', '12'):
+        return 1
+    else:
+        return 2
+
+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)]
+
+parent_dir = os.path.abspath(os.path.join(os.getcwd(),os.pardir))
+data = pd.read_excel(os.path.join(parent_dir,'入模数据/金华.xlsx'),index_col='dtdate')
+data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+data = data.loc[normal(data['售电量']).index]
+
+# list2 = []
+# list0 = []
+# list1 = []
+# for i in ('01','02','03','04','05','06','07','08','09','10','11','12'):
+#     month_index = data.index.strftime('%Y-%m-%d').str[5:7] == f'{i}'
+#     if data.loc[month_index]['售电量'].mean() >= data['售电量'].describe()['75%']:
+#         list2.append(i)
+#     elif data.loc[month_index]['售电量'].mean() <= data['售电量'].describe()['25%']:
+#         list0.append(i)
+#     else:
+#         list1.append(i)
+#
+# print(list0,list1,list2)
+data['season'] = data.index.map(season)
 
 
-# IQR = df['售电量'].describe()['75%'] - df['售电量'].describe()['25%']
-# high = df['售电量'].describe()['75%'] + 1.5*IQR
-# low = df['售电量'].describe()['25%'] - 1.5*IQR
-# print('异常值数量：',len(df[(df['售电量'] >= high) | (df['售电量'] <= low)]))
-#
-# df_train = df_train[(df['售电量'] <= high) & (df['售电量'] >= low)]
+df_eval = data.loc['2023-09']
+# df_train = data.loc['2021-01':'2023-08']
+df_train = data.iloc[450:900]
 
+df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
 X_eval = df_eval[['tem_max','tem_min','holiday','24ST','season']]
@@ -51,11 +56,10 @@ y = df_train['售电量']
 # best_i = {}
 # for i in range(400):
 
-x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=142)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=42)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
-
 y_pred = model.predict(x_test)
 result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
 
@@ -75,13 +79,8 @@ print(goal2)
     #     best_i['best_i'] = i
     #     x = goal2
 
-# print(best_i,best_goal,x)
-# result_eval.to_csv(r'C:\Users\user\Desktop\9月各地市日电量预测结果\金华.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:
-#     f.write(f'金华月末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('jinhua.bin')
+model.save_model('jinhua.bin')
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('jinhua.bin')
 import numpy as np