|
|
@@ -112,8 +112,8 @@ def ref(test_loss,new_test):
|
|
|
test_loss_sum=test_loss.sum(axis=1)
|
|
|
test_loss_max=test_loss.max(axis=1)
|
|
|
ref_test=new_test[['n_split','window_step']].reset_index(drop=True)
|
|
|
- ref_test['test_loss_sum']=test_loss_sum
|
|
|
- ref_test['test_loss_max']=test_loss_max
|
|
|
+ ref_test['test_loss_sum']=list(map(lambda x: round(x,3),test_loss_sum))
|
|
|
+ ref_test['test_loss_max']=list(map(lambda x: round(x,3),test_loss_max))
|
|
|
return ref_test
|
|
|
|
|
|
def prediction(df_stand,scaler,scaler2,model,model2):
|
|
|
@@ -237,6 +237,8 @@ def threshold(res,group,end_time):
|
|
|
df_res=df_res.rename(columns = {"product_id_x": "product_id"})
|
|
|
df_res=df_res.rename(columns = {"SOC[%]": "SOC"})
|
|
|
df_res2=df_res[['product_id','start_time','end_time','diff_min','SOC','AnoScoreV_sum_max','AnoScoreV_max_max','AnoScoreT_sum_max','AnoScoreT_max_max']]
|
|
|
+ df_res2['start_time']=list(map(lambda x:str(x),list(df_res2['start_time'])))
|
|
|
+ df_res2['end_time']=list(map(lambda x:str(x),list(df_res2['end_time'])))
|
|
|
return df_res2,diff
|
|
|
|
|
|
def arrange(result,result_final,start_time,diff):
|
