Explainability

Understand why Nori made a prediction: which features drove it, how they interact, and how the model responds across a feature’s range. Because NoriRegressor is a scikit-learn estimator, it plugs directly into shapiq — a fast SHAP implementation with native Shapley-interaction support — and the rest of the sklearn interpretability ecosystem. The helpers in synthefy_nori.interpretability are thin convenience wrappers, so you can also use the underlying tools directly. examples/interpretability_regression.py

Needs the interpretability extra, which pulls in shapiq. It is covered by the recommended line in Installation.

Nori is regression-only, so every method below explains the regression predictive mean.

Quickstart

get_nori_imputation_explainer builds a shapiq.TabularExplainer that removes features by imputation against a background set. The training context stays fixed across coalitions, so each coalition is a single predict call and the cost is set by budget.

from synthefy_nori import NoriRegressor
from synthefy_nori.interpretability.shapiq import get_nori_imputation_explainer

model = NoriRegressor(model="nori-30m").fit(X_train, y_train)

# index="k-SII", max_order=2 captures pairwise interactions;
# use index="SV", max_order=1 for plain Shapley values.
explainer = get_nori_imputation_explainer(model, X_train, index="k-SII", max_order=2)
sv = explainer.explain(X_test[:1], budget=128)
print(sv)
sv.plot_waterfall()   # additive contribution waterfall

SHAP waterfall plot for a single Nori prediction — SHAP waterfall — each feature's additive push from the baseline to one prediction (sklearn diabetes).

Feature interactions

With index="k-SII", max_order=2 the explainer also surfaces pairwise interactions, which you can view as a network:

kv = explainer.explain(X_test[:1], budget=256)
kv.plot_network()   # interaction graph

SHAP k-SII interaction network — k-SII interaction network — node = a feature's main effect, edge = the strength/sign of each pairwise interaction.

Partial dependence / ICE

A global view of how the prediction shifts across a feature’s range:

from synthefy_nori.interpretability.pdp import partial_dependence_plots

# 1-D effects for features 0 and 2; use kind="individual" or "both" for ICE.
partial_dependence_plots(model, X_test, features=[0, 2], kind="average")

Pass (i, j) tuples in features for 2-D interaction surfaces. Returns an sklearn PartialDependenceDisplay.

Partial dependence plots for bmi and bp — Partial dependence — average effect of bmi and bp on the predicted target (sklearn diabetes).

Feature selection

Find a minimal feature subset that preserves cross-validated performance (sequential selection):

from synthefy_nori.interpretability.feature_selection import feature_selection

res = feature_selection(model, X_train, y_train, n_features_to_select=5, cv=3)
print(res.selected_indices, res.selected_score_mean)

n_features_to_select accepts an int, a fraction, or "auto" (with tol). The result also reports baseline-vs-selected CV scores.

Sequential selection re-fits Nori in-context on every CV split, so keep it to a few thousand samples and a modest feature count.

Configuration

get_nori_imputation_explainer parameters

Parameter	Default	Description
`index`	`"k-SII"`	`"SV"` for plain Shapley values, or `"k-SII"` for k-Shapley interactions.
`max_order`	`2`	Maximum interaction order. `1` = single-feature attributions, `2` = pairwise.
`imputer`	`"baseline"`	`"baseline"` runs one forward per coalition (recommended); `"marginal"` / `"conditional"` are multi-sample and much slower.

Budget trades accuracy for cost. Start at 128 and raise only if the explanation looks noisy: <10 features → 64–128; 10–20 → 128–512; 20+ → 512–2048.

Good to know

These run on the local Python package (synthefy-nori), not the hosted API.
TabPFN’s fast Shapley path reuses a KV-cache across coalitions; Nori’s public package runs one forward per coalition, which is correct and budget-controlled, just not cache-accelerated.

Get Started

Guides

Integration

Quickstart

Feature interactions

Partial dependence / ICE

Feature selection

Configuration

Good to know

Next steps

Categorical & Ordinal Targets

Embeddings

​Quickstart

​Feature interactions

​Partial dependence / ICE

​Feature selection

​Configuration

​Good to know

​Next steps

Categorical & Ordinal Targets

Embeddings

Quickstart

Feature interactions

Partial dependence / ICE

Feature selection

Configuration

Good to know

Next steps