> ## Documentation Index
> Fetch the complete documentation index at: https://docs.priorlabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> TabPFN-3 and later versions support up to 1,000,000 rows, subject to feature count and checkpoint/API limits.
> For large datasets, use per-estimator subsampling, e.g. inference_config={"SUBSAMPLE_SAMPLES": 100_000}, in TabPFNClassifier or TabPFNRegressor from tabpfn or tabpfn_client.
> Pass raw pandas DataFrames to fit and predict. Categorical strings/categories, raw text, and missing feature values are handled automatically; no manual integer/one-hot encoding, imputation, scaling, or outlier removal is needed.

# Partial dependence

> Plot partial dependence and individual conditional expectation for TabPFN.

<Info>
  Looking for usage documentation? Check out [Interpretability](/capabilities/interpretability).
</Info>

<div className="python-reference-heading">
  <h2 id="partial-dependence-plots">
    `pdp.partial_dependence_plots`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-extensions/blob/840c15a1848a986b39c85bc17efc61e0e377f983/src/tabpfn_extensions/interpretability/pdp.py#L18" aria-label="View source for pdp.partial_dependence_plots"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Plot partial dependence (and ICE) for 1D/2D feature(s).

```python theme={null}
pdp.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
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="partial-dependence-plots-estimator" /><code className="python-reference-parameter">estimator</code> | <code className="python-reference-type">Base<wbr />Estimator</code> | Required | fitted estimator or TabPFN-like estimator (fit-at-predict-time is fine) |
  | <span id="partial-dependence-plots-x" /><code className="python-reference-parameter">X</code> | <code className="python-reference-type"><a href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html">np.ndarray</a></code> | Required | array of shape `(n_samples, n_features)` |
  | <span id="partial-dependence-plots-features" /><code className="python-reference-parameter">features</code> | <code className="python-reference-type">Sequence\[int \| tuple\[int, int]]</code> | Required | list of feature indices (e.g., `[0, 3]`) or pairs for interactions (e.g., `[(0, 3)]`) |
  | <span id="partial-dependence-plots-grid-resolution" /><code className="python-reference-parameter">grid\_<wbr />resolution</code> | <code className="python-reference-type">int</code> | `20` | number of grid points per feature |
  | <span id="partial-dependence-plots-kind" /><code className="python-reference-parameter">kind</code> | <code className="python-reference-type">str</code> | `"average"` | `"average"` for PD, `"individual"` for ICE, `"both"` in newer sklearn |
  | <span id="partial-dependence-plots-target-class" /><code className="python-reference-parameter">target\_<wbr />class</code> | <code className="python-reference-type">int \| None</code> | `None` | for classifiers, the class index for which to plot probabilities |
  | <span id="partial-dependence-plots-ax" /><code className="python-reference-parameter">ax</code> | <code className="python-reference-type"><a href="https://matplotlib.org/stable/api/_as_gen/matplotlib.axes.Axes.html">Axes</a> \| None</code> | `None` | optional matplotlib [`Axes`](https://matplotlib.org/stable/api/_as_gen/matplotlib.axes.Axes.html) |
  | <span id="partial-dependence-plots-kwargs" /><code className="python-reference-parameter">\*\*kwargs</code> | — | — | forwarded to [`PartialDependenceDisplay.from_estimator`](https://scikit-learn.org/stable/modules/generated/sklearn.inspection.PartialDependenceDisplay.html#sklearn.inspection.PartialDependenceDisplay.from_estimator) |
</div>

**Returns**

<div className="python-reference-table python-reference-returns">
  | Type | Description |
  | - | - |
  | <code className="python-reference-type"><a href="https://scikit-learn.org/stable/modules/generated/sklearn.inspection.PartialDependenceDisplay.html">Partial<wbr />Dependence<wbr />Display</a></code> | Display containing the computed partial dependence results and plot artists. |
</div>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.