Merge remote-tracking branch 'origin/main'

.idea/misc.xml

@@ -1,4 +1,4 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="pytorch_gpu" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="C:\anaconda\envs\pytorch" project-jdk-type="Python SDK" />
 </project>

.idea/pytorch2.iml

@@ -2,7 +2,7 @@
 <module type="PYTHON_MODULE" version="4">
   <component name="NewModuleRootManager">
     <content url="file://$MODULE_DIR$" />
-    <orderEntry type="jdk" jdkName="pytorch_gpu" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="C:\anaconda\envs\pytorch" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

入模数据/1.py

@@ -1,120 +0,0 @@
-import xgboost as xgb
-import pandas as pd
-import os
-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 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]
-# for i in range(1,13):
-# plt.plot(range(len(data['售电量'][f'2022-{i}'])),data['售电量'][f'2022-{i}'])
-# plt.show()
-print(data['售电量']['2022-9'])
-plt.plot(range(len(data['售电量']['2022-7'])),data['售电量']['2022-7'])
-plt.plot(range(len(data['售电量']['2022-7']),len(data['售电量']['2022-7'])+len(data['售电量']['2023-7'])),data['售电量']['2023-7'])
-# plt.plot(range(len(data['售电量'][['2022-9','2023-9']])),data['售电量'][['2022-9','2023-9']])
-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.head(50))
-
-df_eval = data.loc['2023-7']
-df_train = data.loc['2021-1':'2023-6']
-# 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'])
-
-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%']
-# 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','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=0.15,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)
-
-# 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))
-    # 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\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:
-#     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()
-# loaded_model.load_model('hangzhou.bin')
-# model.predict(X_eval)
-

入模数据/金华.csv

@@ -1,32 +0,0 @@
-dtdate,eval,pred
-2023-08-01,4781.72,4638.4565
-2023-08-02,5264.18,4224.5635
-2023-08-03,5308.39,5036.8037
-2023-08-04,5531.27,5441.4995
-2023-08-05,5989.36,6265.5225
-2023-08-06,6373.8,5753.8174
-2023-08-07,5688.18,4972.277
-2023-08-08,5287.83,4424.5815
-2023-08-09,5560.11,4310.7837
-2023-08-10,5706.55,4657.085
-2023-08-11,5923.97,5702.3916
-2023-08-12,6238.88,5897.044
-2023-08-13,5961.14,4939.6694
-2023-08-14,5316.45,3566.0615
-2023-08-15,4802.99,3005.286
-2023-08-16,4908.05,3805.3303
-2023-08-17,4792.48,3044.6094
-2023-08-18,4380.25,3086.1318
-2023-08-19,4490.53,4237.0283
-2023-08-20,4577.54,3911.61
-2023-08-21,4784.33,4044.5312
-2023-08-22,4517.86,3943.1465
-2023-08-23,4327.74,4588.3257
-2023-08-24,4736.04,4383.0825
-2023-08-25,4981.34,4765.4146
-2023-08-26,4967.04,4744.9272
-2023-08-27,5044.84,4771.1987
-2023-08-28,4919.99,4644.142
-2023-08-29,3611.24,3359.0356
-2023-08-30,3184.04,3217.3503
-2023-08-31,3026.0,3217.8718

区域电量19年至今数据.py

@@ -12,10 +12,6 @@ mpl.rcParams['font.sans-serif']=['kaiti']
 pd.set_option('display.width',None)
 
 
-
-
-
-
 def season(x):
     if str(x)[5:7] in ['07', '08']:
         return 2

各地级市日电量模型/丽水.py

@@ -5,38 +5,55 @@ 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', '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)]
 
 
-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\丽水数据.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/丽水.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}'
+#     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 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['2023-9']
-df_train = data.loc['2021-1':'2023-8']
-# df_train = df[500:850]
+# 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 = 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)]
 
 
 X = df_train[['tem_max','tem_min','holiday','24ST','season']]
@@ -46,7 +63,8 @@ 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=0.15,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)
 
@@ -58,12 +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
@@ -73,7 +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')
+# 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['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))
-
-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'])
 
-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:
@@ -111,17 +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')
+
 
 
-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

浙江电压等级电量/test1.py

@@ -1,7 +1,18 @@
 import numpy as np
+import pandas as pd
 n1 = np.array([[1,1,1]])
 n2 = np.array([1,1,1]).reshape(1,-1)
 print(n2)
 n2 = np.array([]).reshape(3,-1)
 
-print(np.max([[1,2,3],[4,5,6]]))
+print(np.max([[1,2,3],[4,5,6]]))
+
+file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
+df = pd.read_csv(r'C:\Users\鸽子\Desktop\浙江省各地市日电量数据21-23年 .csv',encoding='gbk')
+df.columns = df.columns.map(lambda x:x.strip())
+for city in df['地市'].drop_duplicates():
+    df_city = df[df['地市']== city]
+    df_city['stat_date'] = pd.to_datetime(df_city['stat_date'],format='%Y/%m/%d')
+    df_city = df_city[df_city.columns[:-1]]
+    df_city['stat_date'] = df_city['stat_date'].astype('str')
+    df_city.to_excel(fr'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据\{city}.xlsx',index=False)

浙江电压等级电量/电压等级_输出为5.py

@@ -17,8 +17,8 @@ class LSTM_Regression(nn.Module):
         self.fc = nn.Linear(hidden_size, output_size)
 
     def forward(self, _x):
-        x, _ = self.lstm(_x)  # _x is input, size (seq_len, batch, input_size)   一批多少条样本  多少批样本  每一个样本的输入特征大小（10）
-        s, b, h = x.shape  # x is output, size (seq_len, batch, hidden_size)        经过lstm计算后输出为隐藏层大小
+        x, _ = self.lstm(_x)  # _x is input, size (seq_len, batch, input_size)
+        s, b, h = x.shape  # x is output, size (seq_len, batch, hidden_size)
         x = x.view(s * b, h)
         x = self.fc(x)
         x = x.view(s, b, -1)  # 把形状改回来
@@ -44,141 +44,117 @@ def data_preprocessing(data):
     data.sort_index(inplace=True)
     data = data.loc['2021-01':'2023-08']
     data.drop(columns=[i for i in data.columns if (data[i] == 0).sum() / len(data) >= 0.5], inplace=True)  # 去除0值列
-    data = data[data.values != 0]
+
     data = data.astype(float)
     for col in data.columns:
         data[col] = normal(data[col])
 
     return data
 
+# 拼接数据集
+file_dir = r'C:\Users\鸽子\Desktop\浙江各地市分电压日电量数据'
+excel = os.listdir(file_dir)[0]
+data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col='stat_date')
+data.drop(columns='地市',inplace=True)
+data = data_preprocessing(data)
 
-if __name__ == '__main__':
-    # 拼接数据集
-    file_dir = r'C:\Users\user\Desktop\浙江各地市分电压日电量数据'
-    excel = os.listdir(file_dir)[0]
+df = data[data.columns[0]]
+df.dropna(inplace = True)
+dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
 
-    data = pd.read_excel(os.path.join(file_dir, excel), sheet_name=0, index_col=' stat_date  ')
+for level in data.columns[1:]:
+    df = data[level]
+    df.dropna(inplace=True)
+    x, y = create_dataset(df, DAYS_FOR_TRAIN)
+    dataset_x = np.concatenate((dataset_x, x))
+    dataset_y = np.concatenate((dataset_y, y))
 
-    data = data_preprocessing(data)
 
-    df = data[data.columns[0]]
-    df.dropna(inplace = True)
-    dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
+for excel in os.listdir(file_dir)[1:]:
 
-    for level in data.columns[1:]:
+    data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col='stat_date')
+    data.drop(columns='地市', inplace=True)
+    data = data_preprocessing(data)
+
+    for level in data.columns:
         df = data[level]
         df.dropna(inplace=True)
-        x, y = create_dataset(df, DAYS_FOR_TRAIN)
-        dataset_x = np.concatenate((dataset_x, x))
-        dataset_y = np.concatenate((dataset_y, y))
-
-
-    for excel in os.listdir(file_dir)[1:]:
-        data = pd.read_excel(os.path.join(file_dir,excel), sheet_name=0,index_col=' stat_date  ')
-        data = data_preprocessing(data)
-
-        for level in data.columns:
-            df = data[level]
-            df.dropna(inplace=True)
-            x,y = create_dataset(df,DAYS_FOR_TRAIN)
-            dataset_x = np.concatenate((dataset_x,x))
-            dataset_y = np.concatenate((dataset_y,y))
-
-    print(dataset_x,dataset_y,dataset_x.shape,dataset_y.shape)
-
-    # 训练
-    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-
-    # 标准化到0~1
-    max_value = np.max(dataset_x)
-    min_value = np.min(dataset_x)
-    dataset_x = (dataset_x - min_value) / (max_value - min_value)
-    dataset_y = (dataset_y - min_value) / (max_value - min_value)
-
-    # 划分训练集和测试集
-    train_size = int(len(dataset_x)*0.7)
-
-    train_x = dataset_x[:train_size]
-    train_y = dataset_y[:train_size]
-
-    # 将数据改变形状，RNN 读入的数据维度是 (seq_size, batch_size, feature_size)
-    train_x = train_x.reshape(-1, 1, DAYS_FOR_TRAIN)
-    train_y = train_y.reshape(-1, 1, 5)
-
-    # 转为pytorch的tensor对象
-    train_x = torch.from_numpy(train_x).to(device).type(torch.float32)
-    train_y = torch.from_numpy(train_y).to(device).type(torch.float32)
-
-    model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=5, num_layers=2).to(device)  # 导入模型并设置模型的参数输入输出层、隐藏层等
-
-
-    train_loss = []
-    loss_function = nn.MSELoss()
-    optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
-
-    # for i in range(1500):
-    #     out = model(train_x)
-    #     loss = loss_function(out, train_y)
-    #     loss.backward()
-    #     optimizer.step()
-    #     optimizer.zero_grad()
-    #     train_loss.append(loss.item())
-    #     # print(loss)
-    # # 保存模型
-    # torch.save(model.state_dict(),'dy5.pth')
-
-
-    model.load_state_dict(torch.load('dy5.pth'))
-
-    # for test
-    model = model.eval()  # 转换成测试模式
-    # model.load_state_dict(torch.load(os.path.join(model_save_dir,model_file)))  # 读取参数
-    dataset_x = dataset_x.reshape(-1, 1, DAYS_FOR_TRAIN)  # (seq_size, batch_size, feature_size)
-    dataset_x = torch.from_numpy(dataset_x).to(device).type(torch.float32)
-
-    pred_test = model(dataset_x)  # 全量训练集
-
-    # 模型输出 (seq_size, batch_size, output_size)
-    pred_test = pred_test.view(-1)
-    pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))
-
-    # plt.plot(pred_test.reshape(-1), 'r', label='prediction')
-    # plt.plot(dataset_y.reshape(-1), 'b', label='real')
-    # plt.plot((train_size*5, train_size*5), (0, 1), 'g--')  # 分割线 左边是训练数据 右边是测试数据的输出
-    # plt.legend(loc='best')
-    # plt.show()
-
-
-
-
-
+        x,y = create_dataset(df,DAYS_FOR_TRAIN)
+        dataset_x = np.concatenate((dataset_x,x))
+        dataset_y = np.concatenate((dataset_y,y))
+
+print(dataset_x,dataset_y,dataset_x.shape,dataset_y.shape)
+
+# 训练
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# 标准化到0~1
+max_value = np.max(dataset_x)
+min_value = np.min(dataset_x)
+dataset_x = (dataset_x - min_value) / (max_value - min_value)
+dataset_y = (dataset_y - min_value) / (max_value - min_value)
+
+# 划分训练集和测试集
+train_size = int(len(dataset_x)*0.7)
+train_x = dataset_x[:train_size]
+train_y = dataset_y[:train_size]
+
+# 将数据改变形状，RNN 读入的数据维度是 (seq_size, batch_size, feature_size)
+train_x = train_x.reshape(-1, 1, DAYS_FOR_TRAIN)
+train_y = train_y.reshape(-1, 1, 5)
+
+# 转为pytorch的tensor对象
+train_x = torch.from_numpy(train_x).to(device).type(torch.float32)
+train_y = torch.from_numpy(train_y).to(device).type(torch.float32)
+
+model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=5, num_layers=2).to(device)  # 导入模型并设置模型的参数输入输出层、隐藏层等
+
+
+train_loss = []
+loss_function = nn.MSELoss()
+optimizer = torch.optim.Adam(model.parameters(), lr=0.005, betas=(0.9, 0.999), eps=1e-08, weight_decay=0)
+for i in range(1500):
+    out = model(train_x)
+    loss = loss_function(out, train_y)
+    loss.backward()
+    optimizer.step()
+    optimizer.zero_grad()
+    train_loss.append(loss.item())
+    print(loss)
+# 保存模型
+torch.save(model.state_dict(),'dy5.pth')
+
+# for test
+model = model.eval()  # 转换成测试模式
+# model.load_state_dict(torch.load(os.path.join(model_save_dir,model_file)))  # 读取参数
+dataset_x = dataset_x.reshape(-1, 1, DAYS_FOR_TRAIN)  # (seq_size, batch_size, feature_size)
+dataset_x = torch.from_numpy(dataset_x).to(device)
+
+pred_test = model(dataset_x)  # 全量训练集
+# 模型输出 (seq_size, batch_size, output_size)
+pred_test = pred_test.view(-1)
+pred_test = np.concatenate((np.zeros(DAYS_FOR_TRAIN), pred_test.cpu().detach().numpy()))
+
+plt.plot(pred_test, 'r', label='prediction')
+plt.plot(df, 'b', label='real')
+plt.plot((train_size, train_size), (0, 1), 'g--')  # 分割线 左边是训练数据 右边是测试数据的输出
+plt.legend(loc='best')
+plt.show()
 
 
 # 创建测试集
 # result_list = []
 # 以x为基础实际数据，滚动预测未来3天
-df_eval = pd.read_excel(r'C:\Users\user\Desktop\浙江各地市分电压日电量数据\杭州.xlsx',index_col=' stat_date  ')
-df_eval.columns = df_eval.columns.map(lambda x:x.strip())
-df_eval.index = pd.to_datetime(df_eval.index)
-
-x,y = create_dataset(df_eval.loc['2023-7']['10kv以下'],10)
-
-x = (x - min_value) / (max_value - min_value)
-x = x.reshape(-1,1,10)
-
-x = torch.from_numpy(x).type(torch.float32).to(device)
-pred = model(x)
+# x = torch.from_numpy(df[-14:-4]).to(device)
+# pred = model(x.reshape(-1,1,DAYS_FOR_TRAIN)).view(-1).detach().numpy()
 
 
 # 反归一化
-pred = pred * (max_value - min_value) + min_value
+# pred = pred * (max_value - min_value) + min_value
 # df = df * (max_value - min_value) + min_value
 
-print(pred,y)
-df = pd.DataFrame({'real':y.reshape(-1),'pred':pred.view(-1).cpu().detach().numpy()})
-df.to_csv('7月预测.csv',encoding='gbk')
-
-# 打印指标
+# print(pred)
+# # 打印指标
 # print(abs(pred - df[-3:]).mean() / df[-3:].mean())
 # result_eight = pd.DataFrame({'pred': np.round(pred,1),'real': df[-3:]})
 # target = (result_eight['pred'].sum() - result_eight['real'].sum()) / df[-31:].sum()