mtszkw / lish-moa Goto Github PK

Final code for Kaggle lish-moa competition.

• Using g- (genes) and c- (cells) features,
• PCA,
• QuantileTransform,
• VarianceThreshold,

• MultilabelStratifiedKFold instead of traditional sklearn KFold
• Single NN model with only few linear layers (see /src/model.py),
• SmoothBCEwLogits loss function for training (torch.nn.BCEWithLogitsLoss for validation)

• Prediciton clipping (np.clip(y_hat, 0.001, 0.999))
• Averaging results from best folds (best val_loss checkpoint from each fold)

!pip install ../input/iterativestratification/
from iterstrat.ml_stratifiers import MultilabelStratifiedKFold

(only for logging)
!pip install neptune-client