输出预测结果

9 months ago · 5e3d97c389
parent 6f21ab6485
commit 5e3d97c389
25 changed files with 72 additions and 87 deletions
--- a/入模数据/丽水.xlsx
+++ b/入模数据/丽水.xlsx
--- a/入模数据/台州.xlsx
+++ b/入模数据/台州.xlsx
--- a/入模数据/嘉兴.xlsx
+++ b/入模数据/嘉兴.xlsx
--- a/入模数据/宁波.xlsx
+++ b/入模数据/宁波.xlsx
--- a/入模数据/杭州.xlsx
+++ b/入模数据/杭州.xlsx
--- a/入模数据/温州.xlsx
+++ b/入模数据/温州.xlsx
--- a/入模数据/湖州.xlsx
+++ b/入模数据/湖州.xlsx
--- a/入模数据/绍兴.xlsx
+++ b/入模数据/绍兴.xlsx
--- a/入模数据/舟山.xlsx
+++ b/入模数据/舟山.xlsx
--- a/入模数据/衢州.xlsx
+++ b/入模数据/衢州.xlsx
--- a/入模数据/金华.xlsx
+++ b/入模数据/金华.xlsx
--- a/各地级市日电量模型/jiaxing.bin
+++ b/各地级市日电量模型/jiaxing.bin
--- 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
@ -83,20 +83,19 @@ print(goal2)
 import numpy as np

 X_eval = np.array([
-    [16.2, 3.2, 0, 0, 1, 2023],
-    [17.9, 6.4, 0, 0, 1, 2023],
-    [15.7, 9.0, 0, 0, 1, 2023],
-    [19.2, 8.1, 0, 3, 1, 2023],
-    [11.8, 2.4, 0, 3, 1, 2023]
+    [16.2, 6.5, 0, 0, 1, 2023],
+    [15.9, 6.9, 0, 0, 1, 2023],
+    [19.1, 7.4, 0, 3, 1, 2023],
+    [13.4, 3.2, 0, 3, 1, 2023]
 ])
 # X_eval = np.array([[6.2,5.1,0,0,1,2023]])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28','2023-12-29','2023-12-30','2023-12-31' ])
+result = pd.DataFrame(result, index=['2023-12-28','2023-12-29','2023-12-30','2023-12-31' ])
 result = pd.concat((result_eval['eval'], result))
 result.index = result.index.map(lambda x: str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx',mode='a',if_sheet_exists='replace',engine='openpyxl') as writer:
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx',mode='a',if_sheet_exists='replace',engine='openpyxl') as writer:
    result.to_excel(writer,sheet_name='丽水')
--- 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
@ -82,20 +82,19 @@ print(result_eval)
 import numpy as np

 X_eval = np.array([
-    [17.3, 2.2, 0, 0, 1, 2023],
-    [19, 5.5, 0, 0, 1, 2023],
-    [16, 6.5, 0, 0, 1, 2023],
-    [19.7, 7.9, 0, 3, 1, 2023],
-    [11.9, 3.2, 0, 3, 1, 2023]
+    [17.4, 5.4, 0, 0, 1, 2023],
+    [15.8, 4.8, 0, 0, 1, 2023],
+    [19.4, 8.9, 0, 3, 1, 2023],
+    [13.3, 3.3, 0, 3, 1, 2023]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'], result))
 result.index = result.index.map(lambda x: str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='台州')
--- 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
@ -81,20 +81,19 @@ loaded_model.load_model('jiaxing.bin')
 import numpy as np

 X_eval = np.array([
-    [13.8, 2.1, 0, 0, 1, 2023],
-    [12.1, 1.7, 0, 0, 1, 2023],
-    [10.3, 3.0, 0, 0, 1, 2023],
-    [12.1, 7.1, 0, 3, 1, 2023],
-    [8.2, 1.3, 0, 3, 1, 2023]
+    [10.7, 0.9, 0, 0, 1, 2023],
+    [9.8, 4.5, 0, 0, 1, 2023],
+    [11.2, 5.3, 0, 3, 1, 2023],
+    [9.0, 2.1, 0, 3, 1, 2023]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'], result))
 result.index = result.index.map(lambda x: str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='嘉兴')
--- 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
@ -80,21 +80,19 @@ print(result_eval)
 import numpy as np

 X_eval = np.array([
-
-    [16.0, 3.0, 0, 0, 1, 2023],
-    [14.8, 5.0, 0, 0, 1, 2023],
-    [12.8, 4.8, 0, 0, 1, 2023],
-    [20.9, 6.8, 0, 3, 1, 2023],
-    [9.5, 2.6, 0, 3, 1, 2023]
+    [14.4, 3.7, 0, 0, 1, 2023],
+    [12.6, 5.5, 0, 0, 1, 2023],
+    [16.4, 7.6, 0, 3, 1, 2023],
+    [10.9, 3.7, 0, 3, 1, 2023]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'], result))
 result.index = result.index.map(lambda x: str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='宁波')
--- 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
@ -86,20 +86,19 @@ print(result_eval)
 print('r2:', r2_score(y_test, y_pred))

 X_eval = np.array([
-    [14.9, 0.3, 0, 0, 1, 2023],
-    [14.3, 1.2, 0, 0, 1, 2023],
-    [10.6, 2.7, 0, 0, 1, 2023],
-    [17.2, 2.7, 0, 3, 1, 2023],
-    [10.7, 0.6, 0, 3, 1, 2023]
+    [13.8, 1.4, 0, 0, 1, 2023],
+    [10.1, 2.7, 0, 0, 1, 2023],
+    [15.3, 6.3, 0, 3, 1, 2023],
+    [12.2, 1.8, 0, 3, 1, 2023]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'], result))
 result.index = result.index.map(lambda x: str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='杭州')
--- 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
@ -83,20 +83,19 @@ print(result_eval)
 import numpy as np

 X_eval = np.array([
-    [18, 3.3, 0, 0, 1, 2023],
-    [18.8, 8.2, 0, 0, 1, 2023],
-    [16.9, 11.2, 0, 0, 1, 2023],
-    [20.7, 11.6, 0, 3, 1, 2023],
-    [14.5, 3.3, 0, 3, 1, 2023]
+    [19.0, 7.1, 0, 0, 1, 2023],
+    [17.2, 8.2, 0, 0, 1, 2023],
+    [19.9, 11.0, 0, 3, 1, 2023],
+    [15.8, 4.2, 0, 3, 1, 2023]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'], result))
 result.index = result.index.map(lambda x: str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='温州')
--- 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
@ -83,21 +83,19 @@ print(result_eval)
 import numpy as np

 X_eval = np.array([
-
-    [12.9, 2.1, 0, 0, 1, 2023],
-    [11.7, 2.2, 0, 0, 1, 2023],
-    [8, 1.9, 0, 0, 1, 2023],
-    [13, 4.4, 0, 3, 1, 2023],
-    [9.7, 0.7, 0, 3, 1, 2023]
+    [10.6, 1.7, 0, 0, 1, 2023],
+    [9.1, 3.7, 0, 0, 1, 2023],
+    [11, 5.1, 0, 3, 1, 2023],
+    [11.0, 1.5, 0, 3, 1, 2023]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'], result))
 result.index = result.index.map(lambda x: str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='湖州')
--- 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
@ -79,21 +79,19 @@ print(result_eval)
 import numpy as np

 X_eval = np.array([
-
-    [15.4, 0.1, 0, 0, 1, 2023],
-    [14.2, 3.5, 0, 0, 1, 2023],
-    [12.8, 4.6, 0, 0, 1, 2023],
-    [19.7, 5.2, 0, 3, 1, 2023],
-    [10.9, 0.8, 0, 3, 1, 2023]
+    [13.5, 3.2, 0, 0, 1, 2023],
+    [12.3, 4.2, 0, 0, 1, 2023],
+    [16.4, 6.2, 0, 3, 1, 2023],
+    [12.2, 2.1, 0, 3, 1, 2023]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'],result))
 result.index = result.index.map(lambda x:str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='绍兴')
--- 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
@ -74,20 +74,19 @@ print(result_eval)
 import numpy as np

 X_eval = np.array([
-    [15.1, 8.2, 0, 0, 1, 2023],
-    [12.5, 8.5, 0, 0, 1, 2023],
-    [12, 8.0, 0, 0, 1, 2023],
-    [15.0, 10.0, 0, 3, 1, 2023],
-    [9.3, 5.9, 0, 3, 1, 2023]
+    [12.3, 8.4, 0, 0, 1, 2023],
+    [13.3, 7.9, 0, 0, 1, 2023],
+    [13.0, 10.6, 0, 3, 1, 2023],
+    [10.5, 6.1, 0, 3, 1, 2023]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'], result))
 result.index = result.index.map(lambda x: str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='舟山')
--- 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
@ -69,21 +69,20 @@ print(result_eval)

 import numpy as np
 X_eval = np.array([
-    [15.0, 3.0, 0, 0, 1, 2023],
-    [15.7, 5.1, 0, 0, 1, 2023],
-    [15.2, 5.6, 0, 0, 1, 2023],
-    [17.9, 6.8, 0, 3, 1, 2023],
-    [12.0, 2.9, 0, 3, 1, 2023]
+    [15.7, 4.5, 0, 0, 1, 2023],
+    [16.0, 4.8, 0, 0, 1, 2023],
+    [17.0, 7.4, 0, 3, 1, 2023],
+    [12.9, 4.1, 0, 3, 1, 2023]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'],result))
 result.index = result.index.map(lambda x:str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='衢州')

--- 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
@ -74,20 +74,19 @@ print(result_eval)

 import numpy as np
 X_eval = np.array([
-    [16.3, 2.5, 0, 0, 1],
-    [16.9, 3.8, 0, 0, 1],
-    [16.5, 6.2, 0, 0, 1],
-    [18.8, 7.8, 0, 3, 1],
-    [12.5, 2.8, 0, 3, 1]
+    [16.8, 3.2, 0, 0, 1],
+    [17.2, 5.3, 0, 0, 1],
+    [17.2, 6.4, 0, 3, 1],
+    [13.9, 4.0, 0, 3, 1]
 ])
 print(model.predict(X_eval))
 result = model.predict(X_eval)
-result = pd.DataFrame(result, index=['2023-12-27', '2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
+result = pd.DataFrame(result, index=['2023-12-28', '2023-12-29', '2023-12-30', '2023-12-31'])
 result = pd.concat((result_eval['eval'],result))
 result.index = result.index.map(lambda x:str(x)[:10])
 result.columns = ['预测值']
 print(result)

-with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市区日电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                    engine='openpyxl') as writer:
    result.to_excel(writer, sheet_name='金华')
--- a/浙江电压等级电量/分压_移动平均.py
+++ b/浙江电压等级电量/分压_移动平均.py
@ -1,6 +1,6 @@
 import pandas as pd

-df = pd.read_excel(r'C:\Users\鸽子\Desktop\zj20231228.xlsx', sheet_name=1)
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\20231229.xlsx', sheet_name=1)
 df['pt_date'] = pd.to_datetime(df['pt_date'])

 # 移动平均
@ -21,7 +21,7 @@ for city in df['city_name'].drop_duplicates():

        # index_level.append(level)
        df_moving_avg = pd.DataFrame(df_city1[level], index=df_city1.index)
-        future = pd.date_range(start='2023-12-27', periods=5, freq='D')
+        future = pd.date_range(start='2023-12-28', periods=4, freq='D')

        for date in future:
            df_moving_avg.loc[date, level] = df_moving_avg[-3:].mean().values
@ -38,7 +38,7 @@ for city in df['city_name'].drop_duplicates():
    #                         index=index_level)
    # resut_df = pd.DataFrame({'预测电量': pred_list},index=index_level)

-    with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市分压电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+    with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\市分压电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                        engine='openpyxl') as writer:
        resut_df.to_excel(writer, sheet_name=f'{city[4:6]}')

--- a/浙江行业电量/行业_移动平均.py
+++ b/浙江行业电量/行业_移动平均.py
@ -1,12 +1,11 @@
 import pandas as pd

-df = pd.read_excel(r'C:\Users\鸽子\Desktop\zj20231228.xlsx', sheet_name=2)
+df = pd.read_excel(r'C:\Users\鸽子\Desktop\20231229.xlsx', sheet_name=2)
 df['stat_date'] = pd.to_datetime(df['stat_date'])

 # 移动平均
 for city in df['city_name'].drop_duplicates():

-    print(city)
    df_city = df[df['city_name'] == city].set_index('stat_date').loc['2023-12'].sort_index()
    dict_big = {}
    dict_ok = {}
@ -20,7 +19,7 @@ for city in df['city_name'].drop_duplicates():
    for industry in df_city.columns[2:]:
        # index_industry.append(industry)
        df_moving_avg = pd.DataFrame(df_city[industry], index=df_city.index)
-        future = pd.date_range(start='2023-12-27', periods=5, freq='D')
+        future = pd.date_range(start='2023-12-28', periods=4, freq='D')

        for date in future:
            df_moving_avg.loc[date, industry] = df_moving_avg[-3:].mean().values
@ -32,7 +31,7 @@ for city in df['city_name'].drop_duplicates():
        # pred_list.append(df_moving_avg[industry].sum())
        # loss_list.append(df_city1[industry].sum()-df_moving_avg[industry].sum())
        # rate_list.append((df_city1[industry].sum()-df_moving_avg[industry].sum())/df_city1[industry].sum())
-    with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\行业电量预测_1228.xlsx', mode='a', if_sheet_exists='replace',
+    with pd.ExcelWriter(r'C:\Users\鸽子\Desktop\行业电量预测_1229.xlsx', mode='a', if_sheet_exists='replace',
                        engine='openpyxl') as writer:
        resut_df.to_excel(writer, sheet_name=f'{city[4:6]}')