diff --git a/config_juxiting.py b/config_juxiting.py index 11e525e..bcb9242 100644 --- a/config_juxiting.py +++ b/config_juxiting.py @@ -210,7 +210,7 @@ upload_data = { ### 开关 is_train = True # 是否训练 -is_debug = True # 是否调试 +is_debug = False # 是否调试 is_eta = False # 是否使用eta接口 is_timefurture = True # 是否使用时间特征 is_fivemodels = False # 是否使用之前保存的最佳的5个模型 diff --git a/main.py b/main.py index 01fb465..c51a009 100644 --- a/main.py +++ b/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_pp_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 # 数据处理 @@ -118,36 +118,36 @@ def predict_main(): row,col = df.shape now = datetime.datetime.now().strftime('%Y%m%d%H%M%S') - # ex_Model(df, - # horizon=horizon, - # input_size=input_size, - # train_steps=train_steps, - # val_check_steps=val_check_steps, - # early_stop_patience_steps=early_stop_patience_steps, - # is_debug=is_debug, - # dataset=dataset, - # is_train=is_train, - # is_fivemodels=is_fivemodels, - # val_size=val_size, - # test_size=test_size, - # settings=settings, - # now=now, - # etadata = etadata, - # modelsindex = modelsindex, - # data = data, - # is_eta=is_eta, - # ) + ex_Model(df, + horizon=horizon, + input_size=input_size, + train_steps=train_steps, + val_check_steps=val_check_steps, + early_stop_patience_steps=early_stop_patience_steps, + is_debug=is_debug, + dataset=dataset, + is_train=is_train, + is_fivemodels=is_fivemodels, + val_size=val_size, + test_size=test_size, + settings=settings, + now=now, + etadata = etadata, + modelsindex = modelsindex, + data = data, + is_eta=is_eta, + ) # # 模型评估 model_results3 = model_losss_juxiting(sqlitedb) # 模型报告 - # title = f'{settings}--{now}-预测报告' # 报告标题 - # brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time, - # reportname=reportname,sqlitedb=sqlitedb), - # # pp_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time, - # # reportname=reportname), - # logger.info('模型训练完成') + title = f'{settings}--{now}-预测报告' # 报告标题 + brent_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time, + reportname=reportname,sqlitedb=sqlitedb), + # pp_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,time=end_time, + # reportname=reportname), + logger.info('模型训练完成') # tansuanli_export_pdf(dataset=dataset,num_models = 5 if is_fivemodels else 22,end_time=end_time,reportname=reportname) @@ -170,7 +170,7 @@ def predict_main(): file=max(glob.glob(os.path.join(dataset,'*.pdf')), key=os.path.getctime), ssl=ssl, ) - # m.send_mail() + m.send_mail() if __name__ == '__main__': diff --git a/models/nerulforcastmodels.py b/models/nerulforcastmodels.py index 7126085..7ec6e36 100644 --- a/models/nerulforcastmodels.py +++ b/models/nerulforcastmodels.py @@ -510,33 +510,11 @@ def model_losss_juxiting(sqlitedb): # 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10%分位值对应的模型名称 - 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) - - - - - # 通道使用预测模型的80%置信度 + # 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.drop(['ds','y'], inplace=True) - # # 获取分位数10%和90%的值 - # q10 = row.quantile(0.1) - # q90 = row.quantile(0.9) + # 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 # min_model = row[row == q10].idxmin() # max_model = row[row == q90].idxmin() @@ -549,6 +527,28 @@ def model_losss_juxiting(sqlitedb): # 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 + def find_min_max_within_quantile(row): + row.drop(['ds','y'], inplace=True) + # 获取分位数10%和90%的值 + q10 = row.quantile(0.1) + q90 = row.quantile(0.9) + # 获取 row行10%分位值对应的模型名称 + min_model = row[row == q10].index[0] + max_model = row[row == q90].index[0] + + # # 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) @@ -679,8 +679,8 @@ def model_losss_juxiting(sqlitedb): # 最多频率的模型名称 - min_model_max_frequency_model = df_combined3['min_model'].value_counts().idxmax() - max_model_max_frequency_model = df_combined3['max_model'].value_counts().idxmax() + 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() 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]