PDP report
target y · 3 features · 3 plotted
1 · Overview — where to look
An additive surrogate read off the global curves reproduces 94.0% of the model's predicted variance; adding the regional plots kept by the decision sequence, 99.6%.
Each point is a feature: importance (x) against heterogeneity (y). Bottom-left is ignorable; bottom-right is important and fully described by its mean effect; the top-right corner — important and heterogeneous — is where the mean hides something. An arrow marks each split the decision sequence accepted: from the feature's global point to its weighted-mean point across the subregions.
| # | feature | importance | heterogeneity | #regions | regional analysis |
|---|---|---|---|---|---|
| 1 | x_2 | 0.6679 | 0.0000 | 1 | below the search threshold → |
| 2 | x_0 | 0.1897 | 0.1713 | 7 | split found — rejected by the decision sequence → |
| 3 | x_1 | 0.1481 | 0.0440 | 7 | split into 4 regions → |
The plotted features carry 100% of the total importance mass (target 80%, ceiling top_k = 5).
The decision sequence. Starting from the global curves, each round applies the split with the largest explained-variance gain, measured on top of the splits above it, and stops when no remaining split adds at least 1.0%. A real split (its heterogeneity does drop) can still add nothing — or even hurt, by double-counting — when its variance is already explained by an earlier split.
| step | regions | heterogeneity | explained variance |
|---|---|---|---|
| global effects (GAM) | · | · | 94.0% |
| + split x_1 (on x_0) | 4 | 0.172 → 0.044 | +5.6% → 99.6% |
| rejected · x_0 (on x_1) | 4 | 0.171 → 0.076 | -4.0% — redundant (variance already explained) |
Bar view — importance and heterogeneity
2 · Regional analysis — the final CALM
The selected snapshot: global effects everywhere except the accepted splits. Features in descending importance — a split feature enters as one group at the instance-weighted mean of its subregions. The split features' global counterparts are in the baseline section at the end.
2.1 · x_2
Global effect
Regional effects
Heterogeneity below the threshold — the mean effect tells the whole story; find_regions was skipped.
2.2 · x_0
Global effect
Regional effects
A split on x_1 into 4 regions was found (heterogeneity 0.171 → 0.076), but the decision sequence skips it: it adds no explained variance beyond the splits kept there — the same variance is already read elsewhere. The regional plots are omitted; reproduce them with find_regions.
2.3 · x_1
Split on x_0 into 4 regions — worth +5.6% of explained variance on top of the splits above it; importance and heterogeneity here are the instance-weighted means over the subregions. The global counterpart is in the baseline.
Partition tree
Feature 1 - Full partition tree:
🌳 Full Tree Structure:
───────────────────────
x_1 🔹 [id: 0 | heter: 0.17 | inst: 1000 | w: 1.00]
x_0 < -0.00 🔹 [id: 1 | heter: 0.09 | inst: 510 | w: 0.51]
x_0 < -0.50 🔹 [id: 2 | heter: 0.04 | inst: 268 | w: 0.27]
-0.50 ≤ x_0 < -0.00 🔹 [id: 3 | heter: 0.05 | inst: 242 | w: 0.24]
x_0 ≥ -0.00 🔹 [id: 4 | heter: 0.09 | inst: 490 | w: 0.49]
-0.00 ≤ x_0 < 0.50 🔹 [id: 5 | heter: 0.04 | inst: 254 | w: 0.25]
x_0 ≥ 0.50 🔹 [id: 6 | heter: 0.04 | inst: 236 | w: 0.24]
--------------------------------------------------
Feature 1 - Statistics per tree level:
🌳 Tree Summary:
─────────────────
Level 0🔹heter: 0.17
Level 1🔹heter: 0.09 | 🔻0.09 (50.14%)
Level 2🔹heter: 0.04 | 🔻0.04 (48.85%)
3 · Global baseline — without regions
What you would believe about the split features without the regional analysis: their global mean effects, with the heterogeneity the accepted splits just explained still hiding inside the band. Compare with their subregions in the regional analysis above.
x_1
