diff --git a/.idea/misc.xml b/.idea/misc.xml
index 695b918..3141537 100644
--- a/.idea/misc.xml
+++ b/.idea/misc.xml
@@ -1,4 +1,4 @@
-
+
\ No newline at end of file
diff --git a/.idea/pytorch2.iml b/.idea/pytorch2.iml
index 5cfdc49..719cec4 100644
--- a/.idea/pytorch2.iml
+++ b/.idea/pytorch2.iml
@@ -2,7 +2,7 @@
-
+
\ No newline at end of file
diff --git a/入模数据/丽水.xlsx b/入模数据/丽水.xlsx
index 5a919d7..66d3c30 100644
Binary files a/入模数据/丽水.xlsx and b/入模数据/丽水.xlsx differ
diff --git a/各地级市日电量模型/hangzhou.bin b/各地级市日电量模型/hangzhou.bin
index b63515a..90f056e 100644
Binary files a/各地级市日电量模型/hangzhou.bin and b/各地级市日电量模型/hangzhou.bin differ
diff --git a/各地级市日电量模型/huzhou.bin b/各地级市日电量模型/huzhou.bin
index c37fa7d..b087cdd 100644
Binary files a/各地级市日电量模型/huzhou.bin and b/各地级市日电量模型/huzhou.bin differ
diff --git a/各地级市日电量模型/jiaxing.bin b/各地级市日电量模型/jiaxing.bin
index 1d2f3b2..5a113d9 100644
Binary files a/各地级市日电量模型/jiaxing.bin and b/各地级市日电量模型/jiaxing.bin differ
diff --git a/各地级市日电量模型/jinhua.bin b/各地级市日电量模型/jinhua.bin
index 61e2fe0..1ba6d54 100644
Binary files a/各地级市日电量模型/jinhua.bin and b/各地级市日电量模型/jinhua.bin differ
diff --git a/各地级市日电量模型/quzhou.bin b/各地级市日电量模型/quzhou.bin
index 1a3d1b4..bc812cd 100644
Binary files a/各地级市日电量模型/quzhou.bin and b/各地级市日电量模型/quzhou.bin differ
diff --git a/各地级市日电量模型/shaoxing.bin b/各地级市日电量模型/shaoxing.bin
index 9f1d451..8095997 100644
Binary files a/各地级市日电量模型/shaoxing.bin and b/各地级市日电量模型/shaoxing.bin differ
diff --git a/各地级市日电量模型/taizhou.bin b/各地级市日电量模型/taizhou.bin
index f25a190..6f7d37f 100644
Binary files a/各地级市日电量模型/taizhou.bin and b/各地级市日电量模型/taizhou.bin differ
diff --git a/各地级市日电量模型/wenzhou.bin b/各地级市日电量模型/wenzhou.bin
index a23febb..f24a947 100644
Binary files a/各地级市日电量模型/wenzhou.bin and b/各地级市日电量模型/wenzhou.bin differ
diff --git a/各地级市日电量模型/zhoushan.bin b/各地级市日电量模型/zhoushan.bin
index 8d569a6..2d89acf 100644
Binary files a/各地级市日电量模型/zhoushan.bin and b/各地级市日电量模型/zhoushan.bin differ
diff --git a/各地级市日电量模型/丽水.py b/各地级市日电量模型/丽水.py
index e536fa7..b454534 100644
--- a/各地级市日电量模型/丽水.py
+++ b/各地级市日电量模型/丽水.py
@@ -5,8 +5,10 @@ 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)
+
+mpl.rcParams['font.sans-serif'] = ['kaiti']
+pd.set_option('display.width', None)
+
def season(x):
if str(x)[5:7] in ('01', '10', '11'):
@@ -15,16 +17,17 @@ def season(x):
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[(ndlow)]
+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/丽水.xlsx'),index_col='dtdate')
-data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+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 = []
@@ -42,56 +45,50 @@ data = data.loc[normal(data['售电量']).index]
# print(list0,list1,list2)
-
data['season'] = data.index.map(season)
-
df_eval = data.loc['2023-10']
# df_train = data.loc['2021-1':'2023-8']
df_train = data[450:-1]
# df_train = data.loc['2022-4':'2023-9'][:-3]
-df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
+df_train = df_train[['tem_max', 'tem_min', 'holiday', '24ST', '售电量', 'season']]
-X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
+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']
# best_goal = 1
# 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)
+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)
+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 = 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)
+result_eval = pd.DataFrame({'eval': df_eval['售电量'], 'pred': eval_pred}, index=df_eval['售电量'].index)
print(result_eval)
-goal = (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(goal)
-goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
+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)
-
# 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')
import numpy as np
-loaded_model = xgb.XGBRegressor()
-loaded_model.load_model('lishui.bin')
+
X_eval = np.array([
- [22.3,16.19,23,1,0],
- [23.69,14.5,23,0,0],
- [23.69,14,23,0,0]])
+ [21,10,10,0,0],
+ [21, 11, 10, 0, 0],
+ [18, 7, 10, 0, 0],
+ [17, 9, 10, 0, 0],
+ [17, 10, 10, 0, 0]
+])
print(model.predict(X_eval))
-
diff --git a/各地级市日电量模型/台州.py b/各地级市日电量模型/台州.py
index 3ae6660..2680d68 100644
--- a/各地级市日电量模型/台州.py
+++ b/各地级市日电量模型/台州.py
@@ -83,11 +83,12 @@ print(result_eval)
# 保存模型
model.save_model('taizhou.bin')
import numpy as np
-loaded_model = xgb.XGBRegressor()
-loaded_model.load_model('taizhou.bin')
+
X_eval = np.array([
- [22.6,15.3,23,1,0],
- [23.89,13.4,23,0,0],
- [24.69,13.4,23,0,0]])
+ [19,11,10,0,0],
+ [21, 7, 10, 0, 0],
+ [19, 5, 10, 0, 0],
+ [17, 8, 10, 0, 0],
+ [16, 7, 10, 0, 0]
+])
print(model.predict(X_eval))
-
diff --git a/各地级市日电量模型/嘉兴.py b/各地级市日电量模型/嘉兴.py
index 78e5f86..01dbc3f 100644
--- a/各地级市日电量模型/嘉兴.py
+++ b/各地级市日电量模型/嘉兴.py
@@ -5,8 +5,10 @@ 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)
+
+mpl.rcParams['font.sans-serif'] = ['kaiti']
+pd.set_option('display.width', None)
+
def season(x):
if str(x)[5:7] in ('04', '10'):
@@ -16,15 +18,16 @@ def season(x):
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[(ndlow)]
+ 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/嘉兴.xlsx'),index_col='dtdate')
-data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+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]
# list2 = []
@@ -46,33 +49,30 @@ df_train = data.iloc[450:-1]
# df_train = data[450:][:-3]
print(df_train)
+df_train = df_train[['tem_max', 'tem_min', 'holiday', '24ST', '售电量', 'season']]
-df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
-
-
-X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
+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']
# 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=0.1,random_state=158)
+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)
-
+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 = 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()
-goal2 = (result_eval['eval'][-23:].sum()-result_eval['pred'][-23:].sum())/result_eval['eval'].sum()
-print(goal,goal2)
+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()
+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 :
@@ -87,8 +87,12 @@ model.save_model('jiaxing.bin')
loaded_model = xgb.XGBRegressor()
loaded_model.load_model('jiaxing.bin')
import numpy as np
+
X_eval = np.array([
- [23.8,16.69,23,1,0],
- [24.8,15.09,23,0,0],
- [25.5,14.3,23,0,0]])
-print(model.predict(X_eval))
\ No newline at end of file
+ [17, 9, 10, 0, 1],
+ [16, 3, 10, 0, 1],
+ [15, 3, 10, 0, 1],
+ [15, 7, 10, 0, 1],
+ [14, 5, 10, 0, 1]
+])
+print(model.predict(X_eval))
diff --git a/各地级市日电量模型/宁波.py b/各地级市日电量模型/宁波.py
index 1be7cd3..f4c6ea2 100644
--- a/各地级市日电量模型/宁波.py
+++ b/各地级市日电量模型/宁波.py
@@ -5,8 +5,10 @@ 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)
+
+mpl.rcParams['font.sans-serif'] = ['kaiti']
+pd.set_option('display.width', None)
+
def season(x):
if str(x)[5:7] in ('01', '04', '10'):
@@ -15,14 +17,17 @@ def season(x):
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[(ndlow)]
+ 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')
+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 = []
@@ -45,34 +50,32 @@ df_eval = data.loc['2023-10']
df_train = data.loc['2022-01':'2023-10'][:-1]
+df_train = df_train[['tem_max', 'tem_min', 'holiday', '24ST', '售电量', 'season']]
-
-df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
-
-X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
+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']
# 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=0.1,random_state=142)
+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)
+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 = 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)
+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()
+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()
+goal2 = (result_eval['eval'][-23:].sum() - result_eval['pred'][-23:].sum()) / result_eval['eval'].sum()
print(goal2)
print(result_eval)
# if abs(goal) < best_goal :
@@ -85,14 +88,12 @@ print(result_eval)
# 保存模型
# model.save_model('ningbo.bin')
import numpy as np
-loaded_model = xgb.XGBRegressor()
-loaded_model.load_model('ningbo.bin')
X_eval = np.array([
- [24.39,17.39,23,1,0],
- [24.8,15.09,23,0,0],
- [25.8,14.3,23,0,0]])
+ [20, 10, 10, 0, 1],
+ [19, 12, 10, 0, 1],
+ [18, 9, 10, 0, 1],
+ [21, 9, 10, 0, 1],
+ [14, 9, 10, 0, 1]
+])
print(model.predict(X_eval))
-
-
-
diff --git a/各地级市日电量模型/杭州.py b/各地级市日电量模型/杭州.py
index 95adec6..862c91e 100644
--- a/各地级市日电量模型/杭州.py
+++ b/各地级市日电量模型/杭州.py
@@ -6,8 +6,10 @@ 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)
+
+mpl.rcParams['font.sans-serif'] = ['kaiti']
+pd.set_option('display.width', None)
+
def season(x):
if str(x)[5:7] in ('04', '10'):
@@ -16,19 +18,24 @@ def season(x):
return 1
else:
return 2
+
+
def month(x):
- if str(x)[5:7] in ('08','09','10','12','01','02'):
+ 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[(ndlow)]
+ 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/杭州.xlsx'),index_col='dtdate')
-data.index = pd.to_datetime(data.index,format='%Y-%m-%d')
+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]
# list2 = []
@@ -54,33 +61,33 @@ df_train = data[500:-1]
df_eval = data.loc['2023-10']
print(df_train)
-X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
+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']
# 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=42)
model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
-model.fit(x_train,y_train)
+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 = 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)
+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)
+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()
+goal2 = (result_eval['eval'][-23:].sum() - result_eval['pred'][-23:].sum()) / result_eval['eval'].sum()
-print('goal2:',goal2)
+print('goal2:', goal2)
print(result_eval)
-print('r2:',r2_score(y_test,y_pred))
+print('r2:', r2_score(y_test, y_pred))
#
# # result_eval.to_csv('asda.csv',encoding='gbk')
# # if abs(goal) < best_goal:
@@ -107,9 +114,11 @@ model.save_model('hangzhou.bin')
loaded_model = xgb.XGBRegressor()
loaded_model.load_model('hangzhou.bin')
-X_eval = np.array([[24.19,15.30,23,1,0],
- [25.1,13.3,23,0,0],
- [26.1,11.69,23,0,0]])
-
-print(loaded_model.predict(X_eval))
-
+X_eval = np.array([
+ [18, 9, 10, 0, 0],
+ [20, 7, 10, 0, 0],
+ [17, 4, 10, 0, 0],
+ [15, 8, 10, 0, 0],
+ [12, 7, 10, 0, 0]
+])
+print(model.predict(X_eval))
diff --git a/各地级市日电量模型/温州.py b/各地级市日电量模型/温州.py
index ad2a1f5..9d8ab27 100644
--- a/各地级市日电量模型/温州.py
+++ b/各地级市日电量模型/温州.py
@@ -5,8 +5,10 @@ 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)
+
+mpl.rcParams['font.sans-serif'] = ['kaiti']
+pd.set_option('display.width', None)
+
def season(x):
if str(x)[5:7] in ('01', '02', '10'):
@@ -16,15 +18,16 @@ def season(x):
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[(ndlow)]
+ 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')
+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 = []
@@ -49,33 +52,33 @@ df_train = data[450:-1]
# df_train = data[450:][:-3]
print(df_train)
-df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
+df_train = df_train[['tem_max', 'tem_min', 'holiday', '24ST', '售电量', 'season']]
-X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
+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']
# 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=0.1,random_state=42)
+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)
+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 = 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)
+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()
+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()
+goal2 = (result_eval['eval'][-23:].sum() - result_eval['pred'][-23:].sum()) / result_eval['eval'].sum()
print(goal2)
print(result_eval)
# if abs(goal) < best_goal :
@@ -90,8 +93,12 @@ loaded_model = xgb.XGBRegressor()
loaded_model.load_model('wenzhou.bin')
import numpy as np
-X_eval = np.array([[22.8,15.0,23,1,0],
- [24,13.59,23,0,0],
- [24.39,14.09,23,0,0]])
-print(model.predict(X_eval))
\ No newline at end of file
+X_eval = np.array([
+ [23, 11, 10, 0, 1],
+ [21, 8, 10, 0, 1],
+ [21, 8, 10, 0, 1],
+ [21, 9, 10, 0, 1],
+ [17, 7, 10, 0, 1]
+])
+print(model.predict(X_eval))
diff --git a/各地级市日电量模型/湖州.py b/各地级市日电量模型/湖州.py
index 7edc090..6bc0de8 100644
--- a/各地级市日电量模型/湖州.py
+++ b/各地级市日电量模型/湖州.py
@@ -4,11 +4,13 @@ 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']
-pd.set_option('display.width',None)
+
+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 ('10'):
return 0
@@ -17,15 +19,16 @@ def season(x):
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[(ndlow)]
+ 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')
+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 = []
@@ -49,40 +52,41 @@ df_eval = data.loc['2023-10']
df_train = data[450:-1]
# df_train = data[450:][:-3]
print(df_train)
-df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
+df_train = df_train[['tem_max', 'tem_min', 'holiday', '24ST', '售电量', 'season']]
-
-X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
+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']
-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=158)
model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
-model.fit(x_train,y_train)
-
+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 = 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)
+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()
+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()
+goal2 = (result_eval['eval'][-23:].sum() - result_eval['pred'][-23:].sum()) / result_eval['eval'].sum()
print(goal2)
print(result_eval)
# 保存模型
model.save_model('huzhou.bin')
loaded_model = xgb.XGBRegressor()
loaded_model.load_model('huzhou.bin')
-import numpy as np
-X_eval = np.array([[23.89,15.5,23,1,0],
- [24.5,13.30,23,0,0],
- [25.39,13.5,23,0,0]
- ])
+import numpy as np
+
+X_eval = np.array([
+ [15, 8, 10, 0, 1],
+ [18, 9, 10, 0, 1],
+ [15, 8, 10, 0, 1],
+ [16, 8, 10, 0, 1],
+ [12, 7, 10, 0, 1]
+])
print(model.predict(X_eval))
-
diff --git a/各地级市日电量模型/绍兴.py b/各地级市日电量模型/绍兴.py
index a192be4..65a1702 100644
--- a/各地级市日电量模型/绍兴.py
+++ b/各地级市日电量模型/绍兴.py
@@ -5,8 +5,10 @@ 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)
+
+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'):
@@ -16,15 +18,16 @@ def season(x):
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[(ndlow)]
+ 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')
+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 = []
@@ -48,35 +51,33 @@ df_train = data[450:-1]
# df_train = data[450:][:-3]
print(df_train)
+df_train = df_train[['tem_max', 'tem_min', 'holiday', '24ST', '售电量', 'season']]
-df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
-
-X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
+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']
# 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=0.1,random_state=42)
+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)
-
+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 = 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)
+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()
+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()
+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)
@@ -89,8 +90,12 @@ model.save_model('shaoxing.bin')
loaded_model = xgb.XGBRegressor()
loaded_model.load_model('shaoxing.bin')
import numpy as np
-X_eval = np.array([[25.1,17.1,23,1,0],
- [25.8,13.5,23,0,0],
- [26.6,13.5,23,0,0]])
-print(model.predict(X_eval))
+X_eval = np.array([
+ [17, 9, 10, 0, 0],
+ [20, 6, 10, 0, 0],
+ [17, 5, 10, 0, 0],
+ [16, 8, 10, 0, 0],
+ [12, 7, 10, 0, 0]
+])
+print(model.predict(X_eval))
diff --git a/各地级市日电量模型/舟山.py b/各地级市日电量模型/舟山.py
index c94bbe9..7837aa2 100644
--- a/各地级市日电量模型/舟山.py
+++ b/各地级市日电量模型/舟山.py
@@ -4,28 +4,31 @@ 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']
-pd.set_option('display.width',None)
+
+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 ('01', '02', '03', '04', '05', '06', '09', '10', '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[(ndlow)]
+ 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')
+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 = []
@@ -46,30 +49,28 @@ df_eval = data.loc['2023-10']
df_train = data.iloc[450:-1]
# df_train = data.iloc[450:][:-3]
-df_train = df_train[['tem_max','tem_min','holiday','24ST','售电量','season']]
-X = df_train[['tem_max','tem_min','24ST','holiday','season']]
-X_eval = df_eval[['tem_max','tem_min','24ST','holiday','season']]
+df_train = df_train[['tem_max', 'tem_min', 'holiday', '24ST', '售电量', 'season']]
+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']
-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=42)
model = xgb.XGBRegressor(max_depth=6, learning_rate=0.05, n_estimators=150)
-model.fit(x_train,y_train)
-
+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 = 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)
+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()
+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()
+goal2 = (result_eval['eval'][-23:].sum() - result_eval['pred'][-23:].sum()) / result_eval['eval'].sum()
print(goal2)
print(result_eval)
@@ -77,8 +78,12 @@ model.save_model('zhoushan.bin')
loaded_model = xgb.XGBRegressor()
loaded_model.load_model('zhoushan.bin')
import numpy as np
-X_eval = np.array([[23.19,19.3,23,1,0],
- [23.8,18.39,23,0,0],
- [23.69,18.3,23,0,0]])
-print(model.predict(X_eval))
+X_eval = np.array([
+ [18, 11, 10, 0, 1],
+ [17, 9, 10, 0, 1],
+ [17, 8, 10, 0, 1],
+ [18, 10, 10, 0, 1],
+ [14, 7, 10, 0, 1]
+])
+print(model.predict(X_eval))
diff --git a/各地级市日电量模型/衢州.py b/各地级市日电量模型/衢州.py
index dc5314c..36ca8db 100644
--- a/各地级市日电量模型/衢州.py
+++ b/各地级市日电量模型/衢州.py
@@ -73,13 +73,17 @@ model.save_model('quzhou.bin')
loaded_model = xgb.XGBRegressor()
loaded_model.load_model('quzhou.bin')
import numpy as np
-X_eval = np.array([[23.69,16.5,23,1,0],
- [24.5,15.19,23,0,0],
- [25.19,13.9,23,0,0]])
-
+X_eval = np.array([
+ [19,10,10,0,1],
+ [19, 7, 10, 0, 1],
+ [18, 6, 10, 0, 1],
+ [16, 7, 10, 0, 1],
+ [14, 10, 10, 0, 1]
+])
print(model.predict(X_eval))
+
# import torch
# from torch import nn
# from torch.utils.data import TensorDataset,DataLoader
diff --git a/各地级市日电量模型/金华.py b/各地级市日电量模型/金华.py
index 1cb6eb8..e674061 100644
--- a/各地级市日电量模型/金华.py
+++ b/各地级市日电量模型/金华.py
@@ -88,8 +88,11 @@ model.save_model('jinhua.bin')
loaded_model = xgb.XGBRegressor()
loaded_model.load_model('jinhua.bin')
import numpy as np
-X_eval = np.array([[25,16.39,23,1,0],
- [25.8,13.69,23,0,0],
- [26.39,13.69,23,0,0]])
+X_eval = np.array([
+ [19,12,10,0,1],
+ [20, 10, 10, 0, 1],
+ [18, 5, 10, 0, 1],
+ [17, 6, 10, 0, 1],
+ [14, 8, 10, 0, 1]
+])
print(model.predict(X_eval))
-
diff --git a/文档处理.py b/文档处理.py
index bfe4db5..5de17ae 100644
--- a/文档处理.py
+++ b/文档处理.py
@@ -60,3 +60,10 @@
# df = pd.concat(list1,ignore_index=True)
# df.to_csv('各市行业电量预测结果.csv',encoding='gbk')
# print(df)
+import pandas as pd
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江省11月分行业售电量预测v2.xlsx',sheet_name=1)
+print(df.head())
+print(df[df.columns[2:]].groupby(df['city_name']).sum().T)
+df2 = df[df.columns[2:]].groupby(df['city_name']).sum().T
+df2.to_excel(r'C:\Users\鸽子\Desktop\1.xlsx')
+
diff --git a/浙江电压等级电量/电压等级_输入10_输出3.py b/浙江电压等级电量/电压等级_输入10_输出3.py
index 9fa622d..1066cd7 100644
--- a/浙江电压等级电量/电压等级_输入10_输出3.py
+++ b/浙江电压等级电量/电压等级_输入10_输出3.py
@@ -49,40 +49,39 @@ def data_preprocessing(data):
data = data.astype(float)
for col in data.columns:
data[col] = normal(data[col])
-
return data
# 拼接数据集
-file_dir = r'./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)
-
-df = data[data.columns[0]]
-df.dropna(inplace = True)
-dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
-
-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))
-
-
-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.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))
+# file_dir = r'./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)
+#
+# df = data[data.columns[0]]
+# df.dropna(inplace = True)
+# dataset_x, dataset_y = create_dataset(df, DAYS_FOR_TRAIN)
+#
+# 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))
+#
+#
+# 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.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))
@@ -90,31 +89,31 @@ for excel in os.listdir(file_dir)[1:]:
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)
-#
-# print(max_value,min_value)
+# 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)
+# #
+# # print(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]
+# eval_x = dataset_x[train_size:]
+# eval_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, 3)
+# eval_x = eval_x.reshape(-1, 1, DAYS_FOR_TRAIN)
+# eval_y = eval_y.reshape(-1, 1, 3)
#
-# # 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]
-eval_x = dataset_x[train_size:]
-eval_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, 3)
-eval_x = eval_x.reshape(-1, 1, DAYS_FOR_TRAIN)
-eval_y = eval_y.reshape(-1, 1, 3)
-
-# 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)
-eval_x = torch.from_numpy(eval_x).to(device).type(torch.float32)
-eval_y = torch.from_numpy(eval_y).to(device).type(torch.float32)
+# # 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)
+# eval_x = torch.from_numpy(eval_x).to(device).type(torch.float32)
+# eval_y = torch.from_numpy(eval_y).to(device).type(torch.float32)
model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=3, 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
@@ -164,16 +163,15 @@ model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=3, num_layers=2).to(devi
# 创建测试集
max_value,min_value = 192751288.47,0.0
-model.load_state_dict(torch.load('8_dy3.pth')) # cpu跑加上,map_location=torch.device('cpu')
-file_dir = r'./浙江各地市分电压日电量数据'
-for excel in os.listdir(file_dir):
- df_city = pd.read_excel(os.path.join(file_dir,excel),index_col='stat_date')
- df_city.index = pd.to_datetime(df_city.index)
- df_city = df_city.loc['2023-9'][:-3]
- df_city.drop(columns=[i for i in df_city.columns if (df_city[i] == 0).sum() / len(df_city) >= 0.5], inplace=True)
+model.load_state_dict(torch.load('best_dy3.pth',map_location=torch.device('cpu'))) # cpu跑加上,map_location=torch.device('cpu')
+# file_dir = r'./浙江各地市分电压日电量数据'
- city = df_city['地市'].iloc[0]
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江电量20231127.xlsx',sheet_name=1)
+df = df[df['county_name'].isnull()]
+for city in df['city_name'].drop_duplicates():
+ df_city = df[df['city_name']==city].drop(columns=['county_name','500kv(含330kv)以上']).set_index('pt_date').sort_index()
+ # df_city.drop(columns=[i for i in df_city.columns if (df_city[i] == 0).sum() / len(df_city) >= 0.5], inplace=True)
result_dict = {}
for level in df_city.columns[1:]:
x, y = create_dataset(df_city[level], 10)
@@ -184,13 +182,11 @@ for excel in os.listdir(file_dir):
pred = pred * (max_value - min_value) + min_value
result = pred.cpu().detach().numpy()[-3:]
result_dict[level] = list(result)
- df = pd.DataFrame(result_dict,index=['2023-09-28','2023-09-29','2023-09-30'])
- df.to_excel(fr'C:\Users\user\Desktop\1\9月分压电量预测28-30\{city} .xlsx')
-# print(result_dict)
-
-
+ df1 = pd.DataFrame(result_dict,index=['2023-11-28','2023-11-29','2023-11-30'])
+ df1.to_excel(fr'C:\Users\鸽子\Desktop\11月分压电量预测28-30\{city} .xlsx')
+print(result_dict)
-# # 打印指标
+# 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()
diff --git a/浙江行业电量/行业电量_输出为3_步长为10.py b/浙江行业电量/行业电量_输出为3_步长为10.py
index bbed281..b0c39a4 100644
--- a/浙江行业电量/行业电量_输出为3_步长为10.py
+++ b/浙江行业电量/行业电量_输出为3_步长为10.py
@@ -141,36 +141,36 @@ min_loss = 1
# # 保存/读取模型
# torch.save(best_para,'hy3.pth')
model = LSTM_Regression(DAYS_FOR_TRAIN, 32, output_size=3, num_layers=2).to(device)
-model.load_state_dict(torch.load('hy3.pth'))
+model.load_state_dict(torch.load('hy3.pth',map_location=torch.device('cpu')))
# 测试
model = model.eval()
-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
-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*3, train_size*3), (0, 1), 'g--')
-plt.legend(loc='best')
-plt.show()
+# 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
+# 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*3, train_size*3), (0, 1), 'g--')
+# plt.legend(loc='best')
+# plt.show()
# model.load_state_dict(torch.load('hy3.pth',map_location=torch.device('cpu')))
# max_value = 354024930.8
# min_value = 0.0
-# 创建测试集
-file_dir = './浙江各地市行业电量数据'
-for excel in os.listdir(file_dir):
- df_city = pd.read_excel(os.path.join(file_dir,excel),index_col='stat_date')
- df_city.index = df_city.index.map(lambda x:str(x).strip()[:10])
+# 测试
+# file_dir = './浙江各地市行业电量数据'
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\浙江电量20231127.xlsx',sheet_name=2)
+for city in df['city_name'].drop_duplicates():
+ df_city = df[df['city_name']==city].sort_values(by='stat_date').set_index('stat_date')
- df_city.index = pd.to_datetime(df_city.index)
- df_city = df_city.loc['2023-9'][:-3]
- city = df_city['地市'].iloc[0]
+ # df_city.index = df_city.index.map(lambda x:str(x).strip()[:10])
+ # df_city.index = pd.to_datetime(df_city.index)
+ # df_city = df_city.loc['2023-9'][:-3]
result_dict = {}
for industry in df_city.columns[1:]:
df_city[industry] = df_city[industry].astype('float')
@@ -182,8 +182,8 @@ for excel in os.listdir(file_dir):
pred = pred * (max_value - min_value) + min_value
result = pred.cpu().detach().numpy()[-3:]
result_dict[industry] = list(result)
- df = pd.DataFrame(result_dict,index=['2023-09-28','2023-09-29','2023-09-30'])
- df.to_excel(fr'C:\Users\user\Desktop\9月行业电量预测28-30\{city} .xlsx')
+ df1 = pd.DataFrame(result_dict,index=['2023-11-28','2023-11-29','2023-11-30'])
+ df1.to_excel(fr'C:\Users\鸽子\Desktop\11月行业电量预测27-30\{city} .xlsx')
print(time.time()-t1)
print(result_dict)