根据模型预测结果，对比真实值分组取出最大最小值

config_jingbo.py

@@ -178,7 +178,7 @@ is_update_report = False # 是否上传报告
 
 
 # 数据截取日期
-end_time = '2024-10-28' # 数据截取日期
+end_time = '2024-10-29' # 数据截取日期
 delweekenday = True
 is_corr = False # 特征是否参与滞后领先提升相关系数
 add_kdj = False # 是否添加kdj指标

main.py

@@ -39,8 +39,8 @@ def predict_main():
                                     edbbusinessurl=edbbusinessurl,
                                     )
 
-        # df_zhibiaoshuju,df_zhibiaoliebiao = etadata.get_eta_api_yuanyou_data(data_set=data_set,dataset=dataset)  # 原始数据，未处理
+        df_zhibiaoshuju,df_zhibiaoliebiao = etadata.get_eta_api_yuanyou_data(data_set=data_set,dataset=dataset)  # 原始数据，未处理
-        df_zhibiaoshuju,df_zhibiaoliebiao =  etadata.get_eta_api_pp_data(data_set=data_set,dataset=dataset)  # 原始数据，未处理
+        # df_zhibiaoshuju,df_zhibiaoliebiao =  etadata.get_eta_api_pp_data(data_set=data_set,dataset=dataset)  # 原始数据，未处理
 
         
         # 数据处理
@@ -75,7 +75,7 @@ def predict_main():
 
     import datetime
     # 判断当前日期是不是周一
-    is_weekday = datetime.datetime.now().weekday() == 3
+    is_weekday = datetime.datetime.now().weekday() == 4
     if is_weekday:
         logger.info('今天是周一，更新预测模型')
         try:

models/nerulforcastmodels.py

@@ -289,7 +289,7 @@ def model_losss(sqlitedb):
     df_combined3[['min_within_quantile', 'max_within_quantile','min_model','max_model']] = df_combined3.apply(find_min_max_within_quantile, axis=1)
 
     # 去除有空值的行
-    df_combined3.dropna(inplace=True)
+    # df_combined3.dropna(inplace=True)
     # 保存到数据库
     df_combined3.to_sql('testandpredict_groupby', sqlitedb.connection, if_exists='replace', index=False)
     df_combined3.to_csv(os.path.join(dataset,"testandpredict_groupby.csv"),index=False)
@@ -503,7 +503,7 @@ def model_losss_juxiting(sqlitedb):
     # 删除模型生成的cutoff列
     df_combined.drop(columns=['cutoff', 'max_cutoff'], inplace=True)
     # 获取模型名称
-    modelnames  = df_combined.columns.to_list()[2:] 
+    modelnames  = df_combined.columns.to_list()[1:] 
     if 'y' in modelnames:
         modelnames.remove('y')
     df_combined3 = df_combined.copy()  # 备份df_combined,后面画图需要
@@ -534,26 +534,101 @@ def model_losss_juxiting(sqlitedb):
     with open(os.path.join(dataset,"best_modelnames.txt"), 'w') as f:
         f.write(','.join(modelnames) + '\n')
 
-    # 使用最佳五个模型进行绘图
+    
-    best_models = pd.read_csv(os.path.join(dataset,'best_modelnames.txt'),header=None).values.flatten().tolist()
+    # 根据真实值y确定最大最小值,去掉最高最低的预测值
+    import heapq          # 使用堆来找到最大和最小的值
     def find_min_max_within_quantile(row):
-        row = row[best_models]
+        true_value = row['y']
-        q10 = row.min()
+        row.drop(['ds','y'], inplace=True)
-        q90 = row.max()
+        row = row.astype(float).round(2)
-        # 获取 row行最大最小值模型名称
-        min_model = row[row == q10].idxmin()
-        max_model = row[row == q90].idxmin()
-        
-        # # 判断flot值是否为空值
-        # if pd.isna(q10) or pd.isna(q90):
-        return pd.Series([q10, q90,min_model,max_model], index=['min_within_quantile','max_within_quantile','min_model','max_model'])
 
-    # 遍历行
+        max_heap = []
+        min_heap = []
+        for col in row.index:
+            # 对比真实值进行分类
+            if row[col] < true_value:
+                heapq.heappush(min_heap, row[col])
+            elif row[col] > true_value:
+                heapq.heappush(max_heap, -row[col])  # 使用负号来实现最大堆
+
+        if len(max_heap) == 1:
+            max_y = max_heap[0]
+        elif len(max_heap) == 0:
+            max_y = -min_heap[-1]
+        else:
+            max_y = heapq.nsmallest(2, max_heap)[1]
+
+        if len(min_heap) < 2 :
+            min_y = -max_heap[-1]
+        else:
+            min_y = heapq.nsmallest(2, min_heap)[-1]
+
+
+        # 获取最大和最小的值
+        q10 = min_y 
+        q90 = -max_y
+
+        # 获取最大和最小的模型名称
+        min_model = row[row == q10].idxmin()
+        max_model = row[row == q90].idxmax()
+
+        # 设置上下界比例
+        q10 = q10 * 0.99
+        q90 = q90 * 0.99
+
+        logger.info(min_model,q10,max_model,q90)
+
+        return pd.Series([q10, q90, min_model, max_model], index=['min_within_quantile', 'max_within_quantile', 'min_model', 'max_model'])
+    # # 遍历行
     df_combined3[['min_within_quantile', 'max_within_quantile','min_model','max_model']] = df_combined3.apply(find_min_max_within_quantile, axis=1)
     df_combined = df_combined.round(4)
     print(df_combined3)
 
+    # 使用最佳五个模型进行绘图
+    # best_models = pd.read_csv(os.path.join(dataset,'best_modelnames.txt'),header=None).values.flatten().tolist()
+    # def find_min_max_within_quantile(row):
+    #     row = row[best_models]
+    #     q10 = row.min()
+    #     q90 = row.max()
+    #     # 获取 row行最大最小值模型名称
+    #     min_model = row[row == q10].idxmin()
+    #     max_model = row[row == q90].idxmin()
+        
+    #     # # 判断flot值是否为空值
+    #     # if pd.isna(q10) or pd.isna(q90):
+    #     return pd.Series([q10, q90,min_model,max_model], index=['min_within_quantile','max_within_quantile','min_model','max_model'])
 
+    # # 遍历行
+    # df_combined3[['min_within_quantile', 'max_within_quantile','min_model','max_model']] = df_combined3.apply(find_min_max_within_quantile, axis=1)
+    # df_combined = df_combined.round(4)
+    # print(df_combined3)
+
+    # # 通道使用模型评估前80%作为置信度
+    # def find_min_max_within_quantile(row):
+    #     row.drop(['ds','y'], inplace=True)
+    #     row = row.astype(float).round(2)
+
+    #     row_sorted = row
+    #     # 计算 10% 和 90% 位置的索引
+    #     index_10 = 0
+    #     index_90 = int(len(row_sorted) * 0.8)
+    #     q10 = row_sorted[index_10]
+    #     q90 = row_sorted[index_90]
+    #     # 获取模型名称
+    #     min_model = row[row == q10].idxmin()
+    #     max_model = row[row == q90].idxmin()
+
+        
+    #     # # 判断flot值是否为空值
+    #     # if pd.isna(q10) or pd.isna(q90):
+    #     return pd.Series([q10, q90,min_model,max_model], index=['min_within_quantile','max_within_quantile','min_model','max_model'])
+
+    # # 重新排列
+    # df_combined3 = df_combined3[['ds','y'] + allmodelnames]
+    # # 遍历行
+    # df_combined3[['min_within_quantile', 'max_within_quantile','min_model','max_model']] = df_combined3.apply(find_min_max_within_quantile, axis=1)
+    # df_combined = df_combined.round(4)
+    # print(df_combined3)
 
 
     # # 通道使用预测模型的80%置信度
@@ -641,7 +716,7 @@ def model_losss_juxiting(sqlitedb):
     plt.rcParams['font.sans-serif'] = ['SimHei']
     plt.figure(figsize=(15, 10))
     # 设置有5个子图的画布
-    for n,model in enumerate(modelnames):
+    for n,model in enumerate(modelnames[:5]):
         plt.subplot(3, 2, n+1)
         plt.plot(df_combined3['ds'], df_combined3['y'], label='真实值')
         plt.plot(df_combined3['ds'], df_combined3[model], label=model)
@@ -671,11 +746,11 @@ def model_losss_juxiting(sqlitedb):
     if not sqlitedb.check_table_exists('trueandpredict'):
         first_row.to_sql('trueandpredict',sqlitedb.connection,index=False)
     else:
+        for col in first_row.columns:
+                sqlitedb.add_column_if_not_exists('trueandpredict',col,'TEXT')
         for row in first_row.itertuples(index=False):
             row_dict = row._asdict()
             columns=row_dict.keys()
-            for col in columns:
-                sqlitedb.add_column_if_not_exists('trueandpredict',col,'TEXT')
             check_query = sqlitedb.select_data('trueandpredict',where_condition = f"ds = '{row.ds}'")
             if len(check_query) > 0:
                 set_clause = ", ".join([f"{key} = '{value}'" for key, value in row_dict.items()])
@@ -688,6 +763,10 @@ def model_losss_juxiting(sqlitedb):
     # 最多频率的模型名称
     min_model_max_frequency_model = df_combined3['min_model'].tail(20).value_counts().idxmax()
     max_model_max_frequency_model = df_combined3['max_model'].tail(20).value_counts().idxmax()
+    if min_model_max_frequency_model == max_model_max_frequency_model:
+        # 取20天第二多的模型
+        max_model_max_frequency_model = df_combined3['max_model'].tail(20).value_counts().nlargest(2).index[1]
+
     df_predict['min_model'] = min_model_max_frequency_model
     df_predict['max_model'] = max_model_max_frequency_model
     df_predict['min_within_quantile'] = df_predict[min_model_max_frequency_model]