Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Output-coding wrapper that enables TabPFN-style estimators to handle many classes.
pip install "tabpfn-extensions[many_class]"
ManyClassClassifierManyClassClassifier(
estimator: BaseEstimator,
*,
alphabet_size: int | None = None,
n_estimators: int | None = None,
n_estimators_redundancy: int = 4,
random_state: int | None = None,
verbose: int = 0,
codebook_config: CodebookConfig | str | None = None,
row_weighting_config: RowWeightingConfig | WeightMode | str | None = None,
aggregation_config: AggregationConfig | None = None,
)
| Parameter | Type | Default | Description |
|---|---|---|---|
estimator | Base | Required | Base classifier (typically a TabPFN classifier) used as the underlying model. |
alphabet_ | int | None | None | Maximum number of classes the base estimator handles in a single fit. When None, it is inferred from the base estimator’s checkpoint MAX_NUMBER_OF_CLASSES. |
n_ | int | None | None | — |
n_ | int | 4 | — |
random_ | int | None | None | — |
verbose | int | 0 | — |
codebook_ | Codebook | None | — |
row_ | Row | None | — |
aggregation_ | Aggregation | None | — |
ManyClassClassifier.codebook_statistics_ManyClassClassifier.fitManyClassClassifier.predictManyClassClassifier.predict_probaManyClassClassifier.set_categorical_featuresAggregationConfigCodebookConfigRowWeightingConfigRowWeightingConfig.resolved_modeWeightModeWas this page helpful?