Submission Format
You need to submit classes of 11700 tuples which are not labelled in the dataset. The submission file must contain exactly two attributes: 'ID' of the tuples and its corresponding 'Class' label.
The submission file should contain a header and have the following format:
id,Class
id1300,1
id1301,1
id1302,1
id1303,1
etc.
For your reference a sample_submission.csv has been uploaded in the Data tab that will clarify any doubt regarding submission format.
You are given 7 days with 5 submissions on each day.
Your submissions will be evaluated on 50% of the dataset to give your results on the public
leaderboard. At the end of the competition, your selected submissions (you can select
maximum 2 submissions) will be evaluated on rest 50% of the data and will be shown on the
private leaderboard. However, the final score will be based on your performance on 100%
data.
The evaluation metric for this competition is
Accuracy
. The
Accuracy
score is given by:  \[\frac{\#CorrectPredictions}{Total Labels(11700)}\]
Note:
AFTER
the competition ends, you need to upload the jupyter notebook that gave you your best result (corresponding to the public leaderboard) as a kernel on Kaggle. The result obtained on running your uploaded kernel must match your score on the private leaderboard. In case of mismatch, no marks will be awarded.