准确率调试

config_jingbo.py

@@ -135,10 +135,6 @@ ClassifyId = 1214
 # }
 
 # 生产环境数据库
-#   url: jdbc:mysql://rm-2zehj3r1n60ttz9x5.mysql.rds.aliyuncs.com:3306/jingbo?autoReconnect=true&useUnicode=true&characterEncoding=utf8&zeroDateTimeBehavior=convertToNull&transformedBitIsBoolean=true&useSSL=false&serverTimezone=GMT%2B8&nullCatalogMeansCurrent=true
-#   username: jingbo
-#   password: shihua@123
-#   table-schema: jingbo
 # host = 'rm-2zehj3r1n60ttz9x5.mysql.rds.aliyuncs.com'
 # port = 3306
 # dbusername ='jingbo'  
@@ -146,6 +142,8 @@ ClassifyId = 1214
 # dbname = 'jingbo'
 # table_name = 'v_tbl_crude_oil_warning'
 
+
+
 # 预生产环境
 # host = 'rm-2zehj3r1n60ttz9x5ko.mysql.rds.aliyuncs.com'
 # port = 3306

models/nerulforcastmodels.py

@@ -353,12 +353,33 @@ def model_losss(sqlitedb):
     df_combined3[['min_within_quantile','max_within_quantile']] = names_df.apply(add_upper_lower_bound, axis=1)
 
 
+
+    def find_closest_values(row):
+        x = row.y
+        if x is None:
+            return pd.Series([None, None], index=['min_within_quantile','max_within_quantile'])
+        row = row.drop('ds')
+        row = row[:,0].values.tolist()
+        row = row.sort()
+        print(row)
+        # x 在row中的索引
+        index = row.index(x)
+        if index == 0:
+            return pd.Series([row[index+1], row[index+2]], index=['min_within_quantile','max_within_quantile'])
+        elif index == len(row)-1:
+            return pd.Series([row[index-2], row[index-1]], index=['min_within_quantile','max_within_quantile'])
+        else:
+            return pd.Series([row[index-1], row[index+1]], index=['min_within_quantile','max_within_quantile'])
+
+    # df_combined3[['min_within_quantile','max_within_quantile']] = df_combined3.apply(find_closest_values, axis=1)
+    
+    
     def find_most_common_model():
         # 最多频率的模型名称
         min_model_max_frequency_model = df_combined3['min_model'].tail(60).value_counts().idxmax()
         max_model_max_frequency_model = df_combined3['max_model'].tail(60).value_counts().idxmax()
         if min_model_max_frequency_model == max_model_max_frequency_model:
-            # 取20天第二多的模型
+            # 取60天第二多的模型
             max_model_max_frequency_model = df_combined3['max_model'].tail(60).value_counts().nlargest(2).index[1]
 
         df_predict['min_model'] = min_model_max_frequency_model
@@ -369,26 +390,33 @@ def model_losss(sqlitedb):
 
     # find_most_common_model()
 
+    df_combined3['ds'] = pd.to_datetime(df_combined3['ds'])
+    df_combined3['ds'] = df_combined3['ds'].dt.strftime('%Y-%m-%d')
     df_predict2 = df_combined3.tail(horizon)
-    df_predict2['ds'] = pd.to_datetime(df_predict2['ds'])
-    df_predict2['ds'] = df_predict2['ds'].dt.strftime('%Y-%m-%d')
 
     # 保存到数据库
-    if not sqlitedb.check_table_exists('accuracy'):
-        sqlitedb.create_table('accuracy', columns="id int,PREDICT_DATE datetime,CREAT_DATE datetime, MIN_PRICE TEXT,MAX_PRICE TEXT,HIGH_PRICE TEXT,LOW_PRICE TEXT,RIGHT_ROTE ")
-    existing_data = sqlitedb.select_data(table_name = "accuracy")
-    if  not existing_data.empty:
-        max_id = existing_data['id'].astype(int).max()
-        df_predict2['id'] = range(max_id + 1, max_id + 1 + len(df_predict2))
-    else:
-        df_predict2['id'] = range(1, 1 + len(df_predict2))
+    # if not sqlitedb.check_table_exists('accuracy'):
+    #     columns = ','.join(df_combined3.columns.to_list()+['id','CREAT_DATE'])
+    #     sqlitedb.create_table('accuracy',columns=columns)
+    # existing_data = sqlitedb.select_data(table_name = "accuracy")
+    # update_y = sqlitedb.select_data(table_name = "accuracy",where_condition='y is null')
+    # df_combined4 = df_combined3[(df_combined3['ds'].isin(update_y['ds'])) & (df_combined3['y'].notnull())]
+    # if len(df_combined4) > 0:
+    #     for index, row in df_combined4.iterrows():
+    #         sqlitedb.update_data('accuracy',f"y = {row['y']}",f"ds = '{row['ds']}'")
+    # print(df_combined4)
+    # if  not existing_data.empty:
+    #     max_id = existing_data['id'].astype(int).max()
+    #     df_predict2['id'] = range(max_id + 1, max_id + 1 + len(df_predict2))
+    # else:
+    #     df_predict2['id'] = range(1, 1 + len(df_predict2))
     
-    df_predict2['CREAT_DATE'] = end_time
-    df_predict2['PREDICT_DATE'] = df_predict2['ds']
-    df_predict2['MIN_PRICE'] = df_predict2['min_within_quantile']
-    df_predict2['MAX_PRICE'] = df_predict2['max_within_quantile']
-    df_predict2 = df_predict2[['id','PREDICT_DATE','CREAT_DATE','MIN_PRICE','MAX_PRICE']]
-    df_predict2.to_sql("accuracy",  con=sqlitedb.connection, if_exists='append', index=False)
+    # df_predict2['CREAT_DATE'] = now if end_time == '' else end_time
+    # df_predict2['PREDICT_DATE'] = df_predict2['ds']
+    # df_predict2['MIN_PRICE'] = df_predict2['min_within_quantile']
+    # df_predict2['MAX_PRICE'] = df_predict2['max_within_quantile']
+    # df_predict2 = df_predict2[['id','PREDICT_DATE','CREAT_DATE','MIN_PRICE','MAX_PRICE']]
+    # df_predict2.to_sql("accuracy",  con=sqlitedb.connection, if_exists='append', index=False)