drop_labels_function.py

def dropLabels(events,minPct=.05):
    # apply weights, drop labels with insufficient examples
    while True:
        # Count the number of observations the prediction feature has for each label
        df0=events['y'].value_counts(normalize=True)
        # If the label with minimum number of observations is lower than the minPct threshold 
        # or the number of labels in the prediction features is 2, then break the while loop
        if (df0.min()>minPct) or (df0.shape[0]<3):break
        # Drop the label with minimum number of observations
        events = events[events['y']!=df0.index[df0.argmin()]]
    return events