Undersampling+bagging boosting 0.006 in LB

ADDI Alzheimers Detection Challenge
#1

Hi, all,

The most difficult problem in this competition is class imbalance.
Pre and post alzheimer class is too small compared with Normal.
To tackle this problem many people use downsampling like @moto.
It is good, but exploiting the rest of Normal samples should be better.

from sklearn.model_selection import KFold
kf = KFold(n_splits = (num_total_neg//num_neg))
for _, idx in kf.split(df_neg):
    bagging_neg = df_neg[idx]
    df_samples = pd.concat([df_pos, bagging_neg])
.........

@moto’s wonderful notebook (LB 0.616) get better(LB 0.610) with this bagging.(though I don’t compare it to seed averaging)
I hope it helps.

10 Likes
#2

Nice work @jsato.
I believe the final solution will be a big ensemble of many model types. Each model type is trained on many folds and runs.

2 Likes
#3

Thanks @moto .
A example is here.
Vote me if you like.

1 Like
#4

Upvoted @jsato.

BTW, do you plan to team up with someone ?

#5

Yes, if someone wants.