target_encoding.py

# from https://www.kaggle.com/samratp/wordbatch-ridge-fm-frtl-target-encoding-lgbm/notebook

class TargetEncoder:
    # Adapted from https://www.kaggle.com/ogrellier/python-target-encoding-for-categorical-features
    def __repr__(self):
        return 'TargetEncoder'

    def __init__(self, smoothing=1, min_samples_leaf=1, noise_level=0, keep_original=False, suffix='enc'):
        self.smoothing = smoothing
        self.min_samples_leaf = min_samples_leaf
        self.noise_level = noise_level
        self.keep_original = keep_original
        self.suffix = suffix

    @staticmethod
    def add_noise(series, noise_level):
        return series * (1 + noise_level * np.random.randn(len(series)))

    def encode(self, train, test, target, cols, suffix=None):
        if suffix is None:
            suffix = self.suffix

        for col in cols:
            if self.keep_original:
                train[col + suffix], test[col + suffix] = self.encode_column(train[col], test[col], target)
            else:
                train[col], test[col] = self.encode_column(train[col], test[col], target)
        return train, test

    def encode_column(self, trn_series, tst_series, target):
        temp = pd.concat([trn_series, target], axis=1)
        # Compute target mean
        averages = temp.groupby(by=trn_series.name)[target.name].agg(["mean", "count"])
        # Compute smoothing
        smoothing = 1 / (1 + np.exp(-(averages["count"] - self.min_samples_leaf) / self.smoothing))
        # Apply average function to all target data
        prior = target.mean()
        # The bigger the count the less full_avg is taken into account
        averages[target.name] = prior * (1 - smoothing) + averages["mean"] * smoothing
        averages.drop(['mean', 'count'], axis=1, inplace=True)
        # Apply averages to trn and tst series
        ft_trn_series = pd.merge(
            trn_series.to_frame(trn_series.name),
            averages.reset_index().rename(columns={'index': target.name, target.name: 'average'}),
            on=trn_series.name,
            how='left')['average'].rename(trn_series.name + '_mean').fillna(prior)
        # pd.merge does not keep the index so restore it
        ft_trn_series.index = trn_series.index
        ft_tst_series = pd.merge(
            tst_series.to_frame(tst_series.name),
            averages.reset_index().rename(columns={'index': target.name, target.name: 'average'}),
            on=tst_series.name,
            how='left')['average'].rename(trn_series.name + '_mean').fillna(prior)
        # pd.merge does not keep the index so restore it
        ft_tst_series.index = tst_series.index
        return self.add_noise(ft_trn_series, self.noise_level), self.add_noise(ft_tst_series, self.noise_level)