Submissions are expected to be in CSV format with 2 columns (MoleculeID, Prediction). Each row will correspond to a particular molecule in a given data set. A complete submission file will have 50,478 rows (including a header row). Files without a header
 row will also work.
Please download the benchmark (ntree20_basicBenchmark.csv) from the
[data](https://www.kaggle.com/c/MerckActivity/data)
page as an example submission file.