模型调整

各地级市日电量模型/丽水.py

@@ -45,16 +45,12 @@ data = data.loc[normal(data['售电量']).index]
 
 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']]
-
-
+df_train = data[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']]
@@ -63,11 +59,9 @@ y = df_train['售电量']
 # best_i = {}
 # for i in range(200):
 
-
 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)
-
 y_pred = model.predict(x_test)
 result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
 
@@ -91,7 +85,7 @@ print(goal2)
 # 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

@@ -26,18 +26,18 @@ data = pd.read_excel(os.path.join(parent_dir,'入模数据/台州.xlsx'),index_c
 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)
+# 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)
 
@@ -50,11 +50,11 @@ 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']
-best_goal = 1
-best_i = {}
+# 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=163)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=158)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
@@ -78,7 +78,7 @@ print(goal2)
 # print(best_i,best_goal)
 
 # 保存模型
-model.save_model('taizhou.bin')
+# 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

@@ -42,9 +42,8 @@ data = data.loc[normal(data['售电量']).index]
 data['season'] = data.index.map(season)
 
 df_eval = data.loc['2023-08']
-df_train = data.iloc[500:850]
+df_train = data.iloc[450:900]
 # df_train = data.loc['2021-01':'2023-07']
-print(len(df_eval),len(df_train),len(data))
 
 
 
@@ -59,7 +58,7 @@ 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=42)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=158)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
@@ -84,7 +83,7 @@ print(result_eval)
 # print(best_i,best_goal,x)
 
 # 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

@@ -41,9 +41,9 @@ data = data.loc[normal(data['售电量']).index]
 
 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 = data.loc['2021-01':'2023-08']
+df_train = data[450:900]
+
 
 df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
@@ -55,7 +55,7 @@ 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=18)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=142)
 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)
@@ -80,7 +80,7 @@ print(goal2)
 # print(best_i,best_goal,x)
 
 # 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

@@ -50,12 +50,11 @@ data = data.loc[normal(data['售电量']).index]
 data['season'] = data.index.map(season)
 
 
-# df_train = df[500:850]
+df_train = data[500:850]
 
-df_train = data.loc['2021-01':'2023-08']
+# 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']
@@ -64,10 +63,9 @@ 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=0.2,random_state=142)
+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)
-
 y_pred = model.predict(x_test)
 result_test = pd.DataFrame({'test':y_test,'pred':y_pred},index=y_test.index)
 
@@ -98,7 +96,7 @@ print('r2:',r2_score(y_test,y_pred))
 # # 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')
@@ -108,8 +106,6 @@ model.save_model('hangzhou.bin')
 # df_hangzhou = df_eval[df_eval['city_name']=='金华市'].sort_values(by='dtdate')
 
 
-
-
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('hangzhou.bin')
 X_eval = np.array([[24.19,15.30,23,1,0],

各地级市日电量模型/温州.py

@@ -44,8 +44,8 @@ data['season'] = data.index.map(season)
 
 
 df_eval = data.loc['2023-9']
-# df_train = df[(df.index.str[:7]!='2023-08')&(df.index.str[:7]!='2023-09')]
-df_train = data[400:850]
+# df_train = data.loc['2021-1':'2023-8']
+df_train = data[450:900]
 
 
 df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
@@ -84,7 +84,7 @@ print(goal2)
 #     x = goal2
 # print(best_i,best_goal,x)
 # 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

@@ -45,7 +45,8 @@ data = data.loc[normal(data['售电量']).index]
 data['season'] = data.index.map(season)
 
 df_eval = data.loc['2023-9']
-df_train = data.loc['2021-1':'2023-8']
+# df_train = data.loc['2022-6':'2023-8']
+df_train = data[450:900]
 df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
 
 
@@ -53,7 +54,7 @@ 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=42)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=158)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
@@ -73,7 +74,7 @@ goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result
 print(goal2)
 
 # 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

@@ -43,8 +43,8 @@ data = data.loc[normal(data['售电量']).index]
 data['season'] = data.index.map(season)
 
 df_eval = data.loc['2023-9']
-df_train = data.loc['2021-1':'2023-8']
-# df_train = df[400:850]
+# df_train = data.loc['2021-1':'2023-8']
+df_train = data[450:900]
 print(len(df_eval),len(df_train),len(data))
 
 
@@ -86,7 +86,7 @@ print(goal2)
 # print(best_i,best_goal,x)
 
 # 保存模型
-model.save_model('shaoxing.bin')
+# model.save_model('shaoxing.bin')
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('shaoxing.bin')
 import numpy as np

各地级市日电量模型/舟山.py

@@ -43,7 +43,7 @@ data = data.loc[normal(data['售电量']).index]
 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 = 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']]
@@ -72,7 +72,7 @@ goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result
 print(goal2)
 
 
-model.save_model('zhoushan.bin')
+# model.save_model('zhoushan.bin')
 loaded_model = xgb.XGBRegressor()
 loaded_model.load_model('zhoushan.bin')
 import numpy as np

各地级市日电量模型/衢州.py

@@ -68,7 +68,7 @@ goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result
 print(goal2)
 
 # 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

各地级市日电量模型/金华.py

@@ -56,7 +56,7 @@ 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=42)
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.1,random_state=100)
 model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
 model.fit(x_train,y_train)
 
@@ -80,7 +80,7 @@ print(goal2)
     #     x = goal2
 
 # # 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