1

各地级市日电量模型/丽水.py

@@ -0,0 +1,67 @@
+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)
+
+data = pd.read_excel(r'C:\Users\鸽子\Desktop\入模数据\丽水数据.xlsx',index_col='dtdate')
+data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+
+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 = 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']]
+
+
+# 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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+y = df_train['售电量']
+
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.15,random_state=100)
+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)
+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()
+goal = 1
+
+
+# result_eval.to_csv(r'C:\Users\鸽子\Desktop\各地市日电量预测结果\丽水.csv')
+
+# 保存模型
+# model.save_model('lishui.bin')
+# loaded_model = xgb.XGBRegressor()
+# loaded_model.load_model('lishui.bin')
+# model.predict(X_eval)
+

各地级市日电量模型/台州.py

@@ -0,0 +1,68 @@
+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)
+
+
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\入模数据\台州数据(1).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_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[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']]
+
+
+# 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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+y = df_train['售电量']
+
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=100)
+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)
+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\鸽子\Desktop\各地市日电量预测结果\台州.csv')
+
+# 保存模型
+model.save_model('taizhou.bin')
+loaded_model = xgb.XGBRegressor()
+loaded_model.load_model('taizhou.bin')
+model.predict(X_eval)
+

各地级市日电量模型/嘉兴.py

@@ -0,0 +1,67 @@
+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)
+
+
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\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_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_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量']]
+
+
+# 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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+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)
+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)
+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\鸽子\Desktop\各地市日电量预测结果\嘉兴.csv')
+
+# 保存模型
+model.save_model('jiaxing.bin')
+loaded_model = xgb.XGBRegressor()
+loaded_model.load_model('jiaxing.bin')
+model.predict(X_eval)
+

各地级市日电量模型/宁波.py

@@ -0,0 +1,68 @@
+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)
+
+
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\入模数据\宁波数据.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_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[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']]
+
+
+# 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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+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)
+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)
+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\鸽子\Desktop\各地市日电量预测结果\宁波.csv')
+
+# 保存模型
+model.save_model('ningbo.bin')
+loaded_model = xgb.XGBRegressor()
+loaded_model.load_model('ningbo.bin')
+model.predict(X_eval)
+

各地级市日电量模型/温州.py

@@ -0,0 +1,68 @@
+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)
+
+
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\入模数据\温州数据(1).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_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[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']]
+
+
+# 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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+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)
+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)
+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\鸽子\Desktop\各地市日电量预测结果\温州.csv')
+
+# 保存模型
+model.save_model('wenzhou.bin')
+loaded_model = xgb.XGBRegressor()
+loaded_model.load_model('wenzhou.bin')
+model.predict(X_eval)
+

各地级市日电量模型/湖州.py

@@ -0,0 +1,63 @@
+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
+mpl.rcParams['font.sans-serif']=['kaiti']
+import random
+import matplotlib.pyplot as plt
+
+pd.set_option('display.width',None)
+
+
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\入模数据\湖州数据.xlsx')
+df['dtdate'] = pd.to_datetime(df['dtdate'],format='%Y-%m-%d').astype('string')
+df.set_index('dtdate',inplace=True)
+print(df.head())
+
+df_eval = df[df.index.str[:7]=='2023-08']
+df_train = df[(df.index.str[:7]!='2023-08')&(df.index.str[:7]!='2023-09')]
+print(len(df_eval),len(df_train),len(df))
+
+
+df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量']]
+
+
+# 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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+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)
+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())
+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())
+result_eval.to_csv(r'C:\Users\鸽子\Desktop\各地市日电量预测结果\湖州.csv')
+
+print((result_eval['eval'].sum()-(result_eval['eval'][:-3].sum()+result_eval['pred'][-3:].sum()))/result_eval['eval'].sum())
+
+model.save_model('huzhou.bin')
+loaded_model = xgb.XGBRegressor()
+loaded_model.load_model('huzhou.bin')
+model.predict(X_eval)
+

各地级市日电量模型/绍兴.py

@@ -0,0 +1,68 @@
+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)
+
+
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\入模数据\绍兴数据(1).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_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[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']]
+
+
+# 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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+y = df_train['售电量']
+
+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)
+
+# 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)
+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\鸽子\Desktop\各地市日电量预测结果\绍兴.csv')
+
+# 保存模型
+model.save_model('shaoxing.bin')
+loaded_model = xgb.XGBRegressor()
+loaded_model.load_model('shaoxing.bin')
+model.predict(X_eval)
+

各地级市日电量模型/舟山.py

@@ -0,0 +1,63 @@
+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
+mpl.rcParams['font.sans-serif']=['kaiti']
+import random
+import matplotlib.pyplot as plt
+
+pd.set_option('display.width',None)
+
+
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\入模数据\舟山数据(1).xlsx')
+df['dtdate'] = pd.to_datetime(df['dtdate'],format='%Y-%m-%d').astype('string')
+df.set_index('dtdate',inplace=True)
+print(df.head())
+
+df_eval = df[df.index.str[:7]=='2023-08']
+df_train = df[(df.index.str[:7]!='2023-08')&(df.index.str[:7]!='2023-09')]
+print(len(df_eval),len(df_train),len(df))
+
+
+df_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量']]
+
+
+# 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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+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)
+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())
+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())
+result_eval.to_csv(r'C:\Users\鸽子\Desktop\各地市日电量预测结果\舟山.csv')
+
+print((result_eval['eval'].sum()-(result_eval['eval'][:-3].sum()+result_eval['pred'][-3:].sum()))/result_eval['eval'].sum())
+
+model.save_model('zhoushan.bin')
+loaded_model = xgb.XGBRegressor()
+loaded_model.load_model('zhoushan.bin')
+model.predict(X_eval)
+

各地级市日电量模型/衢州.py

@@ -0,0 +1,143 @@
+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)
+
+
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\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)
+plt.plot(range(len(df)),df['售电量'])
+plt.show()
+print(df.head())
+
+df_eval = df[(df.index.str[:10]=='2023-08-29')|(df.index.str[:10]=='2023-08-30')|(df.index.str[:10]=='2023-08-31')]
+
+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')]
+# 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_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量']]
+
+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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+y = df_train['售电量']
+
+x_train,x_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=102)
+model = xgb.XGBRegressor(max_depth=6, learning_rate=0.1, 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)
+target = (result_eval['eval'].sum()-result_eval['pred'].sum())/ df[df.index.str[:7]=='2023-08']['售电量'].sum()
+print(target)
+
+
+
+# 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\鸽子\Desktop\各地市日电量预测结果\衢州.csv')
+#
+# 保存模型
+model.save_model('quzhou.bin')
+loaded_model = xgb.XGBRegressor()
+loaded_model.load_model('quzhou.bin')
+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
+# from torch.utils.data import TensorDataset,DataLoader
+#
+#
+# net = nn.Sequential(
+#     nn.Linear(6,32),
+#     nn.ReLU(),
+#     nn.Linear(32,64),
+#     nn.ReLU(),
+#     nn.Linear(64,64),
+#     nn.ReLU(),
+#     nn.Linear(64,1)
+# )
+# opt = torch.optim.Adam(net.parameters(),lr=0.00005)
+# loss_fn = nn.MSELoss()
+#
+# epochs = 200
+#
+# x_train = torch.from_numpy(x_train.values).type(torch.float32)
+# x_train = (x_train - x_train.mean())/x_train.std()
+#
+# y_train = torch.from_numpy(y_train.values).type(torch.float32)
+# std1 = y_train.std()
+# mean1 = y_train.mean()
+# y_train = (y_train - mean1)/std1
+#
+# X_eval = torch.from_numpy(X_eval.values).type(torch.float32)
+# X_eval = (X_eval - X_eval.mean())/X_eval.std()
+#
+# y_eval= torch.from_numpy(df_eval['售电量'].values).type(torch.float32)
+#
+#
+# train_ds = TensorDataset(x_train,y_train)
+# train_dl = DataLoader(train_ds,shuffle=True,batch_size=64)
+#
+#
+# for i in range(epochs):
+#     for x,y in train_dl:
+#         y_pred = net(x)
+#         loss = loss_fn(y_pred,y)
+#
+#         opt.zero_grad()
+#         loss.backward()
+#         opt.step()
+#         print(round(loss.item(),2))
+#
+# predict = (net(X_eval) * std1 + mean1).detach().numpy()
+# print(y_train.std(),y_train.mean())
+# print(net(X_eval))
+# print(predict)
+# print((y_eval.detach().numpy().sum() - predict.sum())/ y_eval.detach().numpy().sum())
+
+
+

各地级市日电量模型/金华.py

@@ -0,0 +1,68 @@
+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)
+
+
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\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)
+plt.plot(range(len(df)),df['售电量'])
+plt.show()
+print(df.head())
+
+
+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_train = df_train[['tem_max','tem_min','holiday','24ST','rh','prs','售电量']]
+
+
+# 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','rh','prs']]
+X_eval = df_eval[['tem_max','tem_min','holiday','24ST','rh','prs']]
+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)
+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)
+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\鸽子\Desktop\各地市日电量预测结果\金华.csv')
+
+# 保存模型
+model.save_model('jinhua.bin')
+loaded_model = xgb.XGBRegressor()
+loaded_model.load_model('jinhua.bin')
+model.predict(X_eval)
+

杭州日电量/industry_elec_cws.py

@@ -5,7 +5,7 @@ import pandas as pd
 import torch
 from torch import nn
 import os
-from multiprocessing import Process, Pool
+from multiprocessing import Pool
 
 DAYS_FOR_TRAIN = 9