更新聚烯烃画图，模型取80%置信度

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 = '' # 数据截取日期
+end_time = '2024-10-28' # 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

lib/dataread.py

@@ -20,8 +20,8 @@ plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
 plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号
 
 from datetime import timedelta
-# from config_jingbo import *
+from config_jingbo import *
-from config_juxiting import *
+# from config_juxiting import *
 from sklearn import metrics
 from reportlab.pdfbase import pdfmetrics   # 注册字体
 from reportlab.pdfbase.ttfonts import TTFont # 字体类

main.py

@@ -1,7 +1,7 @@
 # 读取配置
-# from config_jingbo import *
+from config_jingbo import *
 # from config_tansuanli import *
-from config_juxiting import *
+# from config_juxiting import *
 from lib.dataread import *
 from lib.tools import *
 from models.nerulforcastmodels import ex_Model,model_losss,brent_export_pdf,tansuanli_export_pdf,pp_export_pdf,model_losss_juxiting
@@ -78,26 +78,31 @@ def predict_main():
     is_weekday = datetime.datetime.now().weekday() == 3
     if is_weekday:
         logger.info('今天是周一，更新预测模型')
-        # 计算最近20天预测残差最低的模型名称
+        try:
+            # 计算最近20天预测残差最低的模型名称
     
-        model_results = sqlitedb.select_data('trueandpredict',order_by = "ds DESC",limit = "20")
+            model_results = sqlitedb.select_data('trueandpredict',order_by = "ds DESC",limit = "20")
-        model_results = model_results.dropna()
+            model_results = model_results.dropna()
-        modelnames  = model_results.columns.to_list()[2:] 
+            modelnames  = model_results.columns.to_list()[2:] 
-        for col in model_results[modelnames].select_dtypes(include=['object']).columns:
+            for col in model_results[modelnames].select_dtypes(include=['object']).columns:
-            model_results[col] = model_results[col].astype(np.float32)
+                model_results[col] = model_results[col].astype(np.float32)
-        # 计算每个预测值与真实值之间的偏差率
+            # 计算每个预测值与真实值之间的偏差率
-        for model in modelnames:
+            for model in modelnames:
-            model_results[f'{model}_abs_error_rate'] = abs(model_results['y'] - model_results[model]) / model_results['y']
+                model_results[f'{model}_abs_error_rate'] = abs(model_results['y'] - model_results[model]) / model_results['y']
 
-        # 获取每行对应的最小偏差率值
+            # 获取每行对应的最小偏差率值
-        min_abs_error_rate_values = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1)
+            min_abs_error_rate_values = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].min(), axis=1)
-        # 获取每行对应的最小偏差率值对应的列名
+            # 获取每行对应的最小偏差率值对应的列名
-        min_abs_error_rate_column_name = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1)
+            min_abs_error_rate_column_name = model_results.apply(lambda row: row[[f'{model}_abs_error_rate' for model in modelnames]].idxmin(), axis=1)
-        # 将列名索引转换为列名
+            # 将列名索引转换为列名
-        min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(lambda x: x.split('_')[0])
+            min_abs_error_rate_column_name = min_abs_error_rate_column_name.map(lambda x: x.split('_')[0])
-        # 取出现次数最多的模型名称
+            # 取出现次数最多的模型名称
-        most_common_model = min_abs_error_rate_column_name.value_counts().idxmax()
+            most_common_model = min_abs_error_rate_column_name.value_counts().idxmax()
-        logger.info(f"最近20天预测残差最低的模型名称：{most_common_model}")
+            logger.info(f"最近20天预测残差最低的模型名称：{most_common_model}")
+        except Exception as e:
+            logger.error(f"最近20天预测残差最低的模型名称计算失败：{e}")
+            # 取txt中的模型名称
+            most_common_model = pd.read_csv(os.path.join(dataset,'best_modelnames.txt'),header=None).values.flatten().tolist()[0]
 
         # 保存结果到数据库
         
@@ -118,25 +123,25 @@ def predict_main():
     row,col = df.shape
     
     now = datetime.datetime.now().strftime('%Y%m%d%H%M%S')
-    # ex_Model(df,
+    ex_Model(df,
-    #         horizon=horizon,
+            horizon=horizon,
-    #         input_size=input_size,
+            input_size=input_size,
-    #         train_steps=train_steps,
+            train_steps=train_steps,
-    #         val_check_steps=val_check_steps,
+            val_check_steps=val_check_steps,
-    #         early_stop_patience_steps=early_stop_patience_steps,
+            early_stop_patience_steps=early_stop_patience_steps,
-    #         is_debug=is_debug,
+            is_debug=is_debug,
-    #         dataset=dataset,
+            dataset=dataset,
-    #         is_train=is_train,
+            is_train=is_train,
-    #         is_fivemodels=is_fivemodels,
+            is_fivemodels=is_fivemodels,
-    #         val_size=val_size,
+            val_size=val_size,
-    #         test_size=test_size,
+            test_size=test_size,
-    #         settings=settings,
+            settings=settings,
-    #         now=now,
+            now=now,
-    #         etadata = etadata,
+            etadata = etadata,
-    #         modelsindex = modelsindex,
+            modelsindex = modelsindex,
-    #         data = data,
+            data = data,
-    #         is_eta=is_eta,
+            is_eta=is_eta,
-    #         )
+            )
 
 
     logger.info('模型训练完成')

models/nerulforcastmodels.py

@@ -540,7 +540,7 @@ def model_losss_juxiting(sqlitedb):
         row = row[best_models]
         q10 = row.min()
         q90 = row.max()
-        # 获取 row行10%分位值对应的模型名称
+        # 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()
         
@@ -559,12 +559,18 @@ def model_losss_juxiting(sqlitedb):
     # # 通道使用预测模型的80%置信度
     # def find_min_max_within_quantile(row):
     #     row.drop(['ds','y'], inplace=True)
-    #     # 获取分位数10%和90%的值
+    #     row = row.astype(float).round(2)
-    #     q10 = row.quantile(0.1)
+
-    #     q90 = row.quantile(0.9)
+    #     row_sorted = row.sort_values(ascending=True).reset_index(drop=True)
-    #     # 获取 row行10%分位值对应的模型名称
+    #     # 计算 10% 和 90% 位置的索引
-    #     min_model = row[row == q10].index[0]
+    #     index_10 = int(len(row_sorted) * 0.1)
-    #     max_model = row[row == q90].index[0]
+    #     index_90 = int(len(row_sorted) * 0.9)
+    #     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):