Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
TabPFN experiments model for imputation, outlier detection, and synthetic data generation.
TabPFNUnsupervisedModel>>> tabpfn_clf = TabPFNClassifier()
>>> tabpfn_reg = TabPFNRegressor()
>>> model = TabPFNUnsupervisedModel(tabpfn_clf, tabpfn_reg)
>>>
>>> X = [[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]]
>>> model.fit(X)
>>>
>>> X_imputed = model.impute(X)
>>> X_outliers = model.outliers(X)
>>> X_synthetic = model.generate_synthetic_data(n_samples=100)
TabPFNUnsupervisedModel.
TabPFNUnsupervisedModel(
tabpfn_clf: TabPFNClassifier,
tabpfn_reg: TabPFNRegressor,
)
| Parameter | Type | Default | Description |
|---|---|---|---|
tabpfn_ | Tab | Required | TabPFNClassifier instance for handling categorical features. If not provided, the model assumes that there are no categorical features in the data. |
tabpfn_ | Tab | Required | TabPFNRegressor instance for handling numerical features. If not provided, the model assumes that there are no numerical features in the data. |
| Attribute | Type | Description |
|---|---|---|
categorical_features | list[int] | List of indices of categorical features in the input data. |
ValueError
If both tabpfn_clf and tabpfn_reg are None.
TabPFNUnsupervisedModel.fitTabPFNUnsupervisedModel.fit(
X: np.ndarray | torch.Tensor | pd.DataFrame,
y: np.ndarray | torch.Tensor | pd.Series | None = None,
) -> TabPFNUnsupervisedModel
| Parameter | Type | Default | Description |
|---|---|---|---|
X | np.ndarray | torch.Tensor | pd.Data | Required | Union[np.ndarray, torch.Tensor, pd.DataFrame] Input data to fit the model, shape (n_samples, n_features). |
y | np.ndarray | torch.Tensor | pd.Series | None | None | Optional[Union[np.ndarray, torch.Tensor, pd.Series]], default=None Target values, shape (n_samples,). Optional since this is an unsupervised model. |
| Type | Description |
|---|---|
Tab | TabPFNUnsupervisedModel Fitted model instance (self). |
TabPFNUnsupervisedModel.init_model_and_get_model_configTabPFNUnsupervisedModel.init_model_and_get_model_config() -> None
RuntimeError
If model initialization fails
Returns
| Type | Description |
|---|---|
None | — |
TabPFNUnsupervisedModel.set_categorical_featuresTabPFNUnsupervisedModel.set_categorical_features(
categorical_features: list[int],
) -> None
| Parameter | Type | Default | Description |
|---|---|---|---|
categorical_ | list[int] | Required | List of indices of categorical features |
| Type | Description |
|---|---|
None | — |
TabPFNUnsupervisedModel.use_classifier_TabPFNUnsupervisedModel.use_classifier_(
column_idx: int,
y: torch.Tensor | np.ndarray,
) -> bool
| Parameter | Type | Default | Description |
|---|---|---|---|
column_ | int | Required | Index of the column to check |
y | torch.Tensor | np.ndarray | Required | Values of the feature |
| Type | Description |
|---|---|
bool | True if a classifier should be used, False for a regressor |
efficient_random_permutationefficient_random_permutation(
indices: list[int],
n_permutations: int = 10,
) -> list[tuple[int, ...]]
| Parameter | Type | Default | Description |
|---|---|---|---|
indices | list[int] | Required | List of indices to permute |
n_ | int | 10 | Number of unique permutations to generate |
| Type | Description |
|---|---|
list[tuple[int, …]] | List of unique permutations |
efficient_random_permutation_efficient_random_permutation_(
indices: list[int],
) -> tuple[int, ...]
| Parameter | Type | Default | Description |
|---|---|---|---|
indices | list[int] | Required | List of indices to permute |
| Type | Description |
|---|---|
tuple[int, …] | A tuple representing a random permutation of the input indices |
Was this page helpful?