The dataset is split into training (~80%) and test (~20%) subsets provided as two separate CSV files.
-	The training set: ML-MATT-CompetitionQT2021_train.csv contains 36,904 samples, each having 13 features and a label. Note that there may be erroneous samples and outliers.
-	The test set: ML-MATT-CompetitionQT2021_test.csv contains 9,158 samples following the same structure as the training set but not including the labels.
You will have to upload the predictions for the test set and Kaggle will compare your predictions with the ground-truth labels in order to compute a score.