Comparing Encoders

import numpy as np
import pandas as pd
from sklearn.base import BaseEstimator, TransformerMixin
from sklearn.compose import ColumnTransformer
from sklearn.model_selection import StratifiedKFold, cross_val_score
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import OneHotEncoder, OrdinalEncoder, TargetEncoder


class FrequencyEncoder(BaseEstimator, TransformerMixin):
    """Level share learned in fit (training fold only); unseen levels -> 0."""

    def fit(self, X, y=None):
        X = pd.DataFrame(X)
        self.maps_ = {c: X[c].value_counts(normalize=True) for c in X.columns}
        return self

    def transform(self, X):
        X = pd.DataFrame(X)
        return np.column_stack([X[c].map(self.maps_[c]).fillna(0.0).to_numpy(dtype=float) for c in X.columns])


high_card = ["merchant"]
low_card = ["channel", "country"]
num_cols = ["amount", "hour"]
encoders = {
    "onehot_rare": OneHotEncoder(handle_unknown="infrequent_if_exist", min_frequency=20),
    "target": TargetEncoder(smooth="auto"),
    "frequency": FrequencyEncoder(),
    "ordinal": OrdinalEncoder(handle_unknown="use_encoded_value", unknown_value=-1),
}
cv = StratifiedKFold(5, shuffle=True, random_state=0)       # or TimeSeriesSplit for temporal data
for name, enc in encoders.items():
    prep = ColumnTransformer([
        ("hc", enc, high_card),
        ("lc", OneHotEncoder(handle_unknown="ignore"), low_card),
        ("num", "passthrough", num_cols),
    ])
    scores = cross_val_score(make_pipeline(prep, make_model()), X, y, cv=cv, scoring="average_precision")
    print(f"{name:<12} {scores.mean():.4f} ± {scores.std():.4f}")