Embeddings

Looking for usage documentation? Check out Embeddings.

`TabPFNRegressor.get_embeddings`

Gets the embeddings for the input data X.

TabPFNRegressor.get_embeddings(
    X: XType,
    data_source: Literal["train", "test"] = "test",
) -> np.ndarray

Type aliases

XType = Any

Parameters

Parameter	Type	Default	Description
`X`	`XType`	Required	The input data.
`data_source`	`Literal[“train”, “test”]`	`"test"`	Select the transformer output to return. Use `"train"` to obtain embeddings from the training tokens and `"test"` for the test tokens. When `n_estimators > 1` the returned array has shape `(n_estimators, n_samples, embedding_dim)`. `"train"` is not available with `fit_mode="fit_with_cache"`; see `tabpfn.base.get_embeddings`.

Returns

Type	Description
`np.ndarray`	`np.ndarray` The computed embeddings for each fitted estimator.