Looking for usage documentation? Check out Interpretability.
Interpretability
Partial dependence
Plot partial dependence and individual conditional expectation for TabPFN.
View source
Was this page helpful?
Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
Plot partial dependence and individual conditional expectation for TabPFN.
pdp.partial_dependence_plotspdp.partial_dependence_plots(
estimator: BaseEstimator,
X: np.ndarray,
features: Sequence[int | tuple[int, int]],
*,
grid_resolution: int = 20,
kind: str = "average",
target_class: int | None = None,
ax: Axes | None = None,
**kwargs,
) -> PartialDependenceDisplay
| Parameter | Type | Default | Description |
|---|---|---|---|
estimator | Base | Required | fitted estimator or TabPFN-like estimator (fit-at-predict-time is fine) |
X | np.ndarray | Required | array of shape (n_samples, n_features) |
features | Sequence[int | tuple[int, int]] | Required | list of feature indices (e.g., [0, 3]) or pairs for interactions (e.g., [(0, 3)]) |
grid_ | int | 20 | number of grid points per feature |
kind | str | "average" | "average" for PD, "individual" for ICE, "both" in newer sklearn |
target_ | int | None | None | for classifiers, the class index for which to plot probabilities |
ax | Axes | None | None | optional matplotlib Axes |
**kwargs | — | — | forwarded to PartialDependenceDisplay.from_estimator |
| Type | Description |
|---|---|
Partial | Display containing the computed partial dependence results and plot artists. |
Was this page helpful?