PDP report
target Y · 3 features · 2 plotted
1 · Overview — where to look
An additive surrogate read off the global curves reproduces 11.0% of the model's predicted variance; adding the regional plots kept by the decision sequence, 99.3%.
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 | x1 | 1.6690 | 0.0781 | 7 | split into 4 regions → |
| 2 | x3 | 0.5849 | 1.6876 | 7 | split found — rejected by the decision sequence → |
| 3 | x2 | 0.0024 | 0.0737 | · | not plotted (below the coverage cut) |
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) | · | · | 11.0% |
| + split x1 (on x3) | 4 | 1.685 → 0.078 | +88.3% → 99.3% |
| rejected · x3 (on x1) | 4 | 1.688 → 0.428 | -80.1% — 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 · x1
Split on x3 into 4 regions — worth +88.3% 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 0 - Full partition tree:
🌳 Full Tree Structure:
───────────────────────
x1 🔹 [id: 0 | heter: 1.69 | inst: 1000 | w: 1.00]
x3 < -0.00 🔹 [id: 1 | heter: 0.19 | inst: 498 | w: 0.50]
x3 < -0.10 🔹 [id: 2 | heter: 0.02 | inst: 450 | w: 0.45]
-0.10 ≤ x3 < -0.00 🔹 [id: 3 | heter: 0.53 | inst: 48 | w: 0.05]
x3 ≥ -0.00 🔹 [id: 4 | heter: 0.24 | inst: 502 | w: 0.50]
-0.00 ≤ x3 < 0.10 🔹 [id: 5 | heter: 0.63 | inst: 50 | w: 0.05]
x3 ≥ 0.10 🔹 [id: 6 | heter: 0.03 | inst: 452 | w: 0.45]
--------------------------------------------------
Feature 0 - Statistics per tree level:
🌳 Tree Summary:
─────────────────
Level 0🔹heter: 1.69
Level 1🔹heter: 0.21 | 🔻1.47 (87.42%)
Level 2🔹heter: 0.08 | 🔻0.13 (63.16%)
2.2 · x3
Global effect
Regional effects
A split on x1 into 4 regions was found (heterogeneity 1.688 → 0.428), 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.
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.
x1
