v3: add SHAP + Captum IG interpretability artefacts

.gitattributes

@@ -42,3 +42,5 @@ figures/fig_dl_02_lorenz_curves.png filter=lfs diff=lfs merge=lfs -text
 figures/fig_dl_03_training_curves.png filter=lfs diff=lfs merge=lfs -text
 figures/fig_dl_08_calibration_deciles.png filter=lfs diff=lfs merge=lfs -text
 figures/fig_dl_11_ensemble_variance.png filter=lfs diff=lfs merge=lfs -text
+figures/fig_dl_05_cann_residuals.png filter=lfs diff=lfs merge=lfs -text
+figures/fig_dl_06_attention_heatmap.png filter=lfs diff=lfs merge=lfs -text

INTERPRETABILITY.md

@@ -0,0 +1,100 @@
+# Interpretability summary: `house_prices_8arch_interp`
+
+## Performance ranking
+
+| Rank | Model | Test Gini | Test MAE | A/E ratio | n params | Train time |
+|---:|---|---:|---:|---:|---:|---:|
+| 1 | **xgboost** | 0.2049 | 17203.89 | 0.999 | 462 | 0.4s |
+| 2 | **stacked_ensemble** | 0.2049 | 17203.89 | 0.999 | 9 | 0.0s |
+| 3 | **catboost** | 0.1996 | 29223.45 | 1.161 | 499 | 2.7s |
+| 4 | **localglmnet** | 0.1991 | 23419.59 | 0.988 | 22,620 | 6.3s |
+| 5 | **drn** | 0.1962 | 27927.62 | 0.981 | 53,010 | 6.6s |
+| 6 | **cann** | 0.1941 | 24906.06 | 1.024 | 52,815 | 6.5s |
+| 7 | **cann_gbm** | 0.1940 | 32932.26 | 1.193 | 52,815 | 5.8s |
+| 8 | **ft_transformer** | 0.0368 | 187771.09 | 3337.260 | 483,267 | 340.8s |
+| 9 | **tabm** | 0.0331 | 187802.11 | 7436.716 | 410,364 | 176.6s |
+
+
+## Top-10 features per architecture
+
+| Rank | catboost | xgboost |
+|---|---|---|
+| 1 | `TotalSF` (0.096) | `TotalSF` (0.138) |
+| 2 | `OverallQual` (0.043) | `OverallQual` (0.103) |
+| 3 | `GrLivArea` (0.043) | `GrLivArea` (0.032) |
+| 4 | `YearRemodAdd` (0.038) | `YearRemodAdd` (0.025) |
+| 5 | `LotArea` (0.030) | `OverallCond` (0.025) |
+| 6 | `KitchenQual` (0.028) | `HouseAge` (0.021) |
+| 7 | `OverallCond` (0.028) | `GarageCars` (0.020) |
+| 8 | `MSZoning` (0.022) | `LotArea` (0.019) |
+| 9 | `HouseAge` (0.022) | `YearBuilt` (0.012) |
+| 10 | `GarageCars` (0.021) | `KitchenQual` (0.011) |
+
+
+## Cross-method agreement
+
+Features that appear in **top-5** across **every** model with importance scores:
+
+
+- `GrLivArea`
+
+- `OverallQual`
+
+- `TotalSF`
+
+- `YearRemodAdd`
+
+
+This cross-method agreement is a strong signal - when both tree-based SHAP and gradient-based Captum IG identify the same feature as critical, the finding is unlikely to be a method-specific artefact.
+
+
+## LocalGLMnet coefficient analysis
+
+LocalGLMnet emits one row of coefficients per test record. We summarise the distribution of each feature's coefficient across the sampled test set (mean ± std):
+
+| Feature | Mean coef | Std | Sign stability |
+|---|---:|---:|---:|
+| `LotArea` | 2.912e-04 | 1.847e-04 | 98% |
+| `YearBuilt` | 3.377e-04 | 2.296e-04 | 99% |
+| `YearRemodAdd` | 3.083e-04 | 2.715e-04 | 97% |
+| `TotalBsmtSF` | 2.400e-04 | 1.464e-04 | 99% |
+| `1stFlrSF` | 2.361e-04 | 1.171e-04 | 100% |
+| `2ndFlrSF` | -2.467e-04 | 2.454e-04 | 96% |
+| `GrLivArea` | -5.616e-05 | 1.236e-04 | 72% |
+| `FullBath` | 1.693e-04 | 2.968e-04 | 86% |
+| `BedroomAbvGr` | -9.640e-05 | 1.435e-04 | 80% |
+| `TotRmsAbvGrd` | -1.148e-04 | 1.200e-04 | 84% |
+| `GarageCars` | 3.736e-04 | 4.435e-04 | 98% |
+| `GarageArea` | 2.725e-04 | 1.512e-04 | 99% |
+| `OverallQual` | 1.848e-04 | 1.240e-04 | 98% |
+| `OverallCond` | 2.792e-04 | 3.282e-04 | 99% |
+| `TotalSF` | 2.274e-04 | 1.413e-04 | 99% |
+| `HouseAge` | -3.340e-04 | 2.015e-04 | 100% |
+| `LotArea_raw` | 3.759e-08 | 2.385e-08 | 98% |
+| `YearBuilt_raw` | 1.106e-05 | 7.519e-06 | 99% |
+| `YearRemodAdd_raw` | 1.493e-05 | 1.314e-05 | 97% |
+| `TotalBsmtSF_raw` | 5.483e-07 | 3.345e-07 | 99% |
+| `1stFlrSF_raw` | 6.213e-07 | 3.082e-07 | 100% |
+| `2ndFlrSF_raw` | -5.686e-07 | 5.655e-07 | 96% |
+| `GrLivArea_raw` | -1.075e-07 | 2.365e-07 | 72% |
+| `FullBath_raw` | 3.079e-04 | 5.398e-04 | 86% |
+| `BedroomAbvGr_raw` | -1.181e-04 | 1.757e-04 | 80% |
+| `TotRmsAbvGrd_raw` | -7.042e-05 | 7.359e-05 | 84% |
+| `GarageCars_raw` | 5.017e-04 | 5.955e-04 | 98% |
+| `GarageArea_raw` | 1.298e-06 | 7.199e-07 | 99% |
+| `OverallQual_raw` | 1.338e-04 | 8.976e-05 | 98% |
+| `OverallCond_raw` | 2.500e-04 | 2.938e-04 | 99% |
+| `TotalSF_raw` | 2.768e-07 | 1.720e-07 | 99% |
+| `HouseAge_raw` | -1.091e-05 | 6.583e-06 | 100% |
+
+_Sign stability is the fraction of test records where the coefficient has the same sign as the mean. Values close to 100% mean the model is confident about that feature's direction; values closer to 50% mean the feature's effect flips across records (which is exactly what LocalGLMnet was designed to detect)._
+
+## Artefacts on disk
+
+- `dashboard_dl_interpretability.html` - interactive Plotly dashboard with SHAP beeswarm plots, Captum IG heatmaps, FT-Transformer attention matrices, CANN residual histograms.
+
+- `localglmnet_coefficients.csv` - per-test-record coefficients from LocalGLMnet (one row per test record, one column per continuous feature).
+
+- `feature_importance.csv` - consolidated importances (CatBoost / XGBoost native importance scores).
+
+- `drn_distributional_outputs.csv` - DRN's predictive distribution moments (mean, variance, quantiles) per test row.

README.md

@@ -40,7 +40,7 @@ model-index:
             name: Test MAE (XGBoost, USD)
 ---
 
-# House Prices - Tabular Models (8 architectures)
+# House Prices - Tabular Models (8 architectures + interpretability)
 
 Pre-trained models for the
 [t22000t/house-prices-tabular](https://huggingface.co/datasets/t22000t/house-prices-tabular)
@@ -49,10 +49,13 @@ dataset, covering all **eight** architectures from the
 two gradient-boosted machines (CatBoost, XGBoost) and six deep-learning
 models (CANN, CANN-GBM, FT-Transformer, TabM, LocalGLMnet, DRN).
 
-> **v2 release** - this drop replaces the earlier GBM-only baseline.
-> The CatBoost loss now correctly uses `Tweedie:variance_power=1.99`
-> (the closest valid approximation to gamma in CatBoost), so its
-> numbers differ slightly from v1's RMSE-trained model.
+> **v3 release** - adds the full interpretability stack: SHAP
+> TreeExplainer for the GBMs, Captum Integrated Gradients for the DL
+> models, per-layer attention for FT-Transformer, residual analysis
+> for CANN / CANN-GBM, per-row coefficients for LocalGLMnet, and full
+> distributional outputs (mean, variance, quantiles, VaR) for DRN.
+> See [`INTERPRETABILITY.md`](./INTERPRETABILITY.md) and
+> [`dashboard_dl_interpretability.html`](./dashboard_dl_interpretability.html).
 
 ## Results
 
@@ -88,22 +91,68 @@ literature consistently shows they need 10k+ rows to outperform GBMs.
 For a comparison where these architectures actually compete, see the
 companion drop on Bike Sharing (17k rows): **[t22000t/bike-sharing-tabular-models](https://huggingface.co/t22000t/bike-sharing-tabular-models)**.
 
-## Files
+## Interpretability (new in v3)
+
+Multiple methods applied side by side so findings can be triangulated:
 
-| File | What it is | Size |
+| Method | Applies to | What it measures |
 |---|---|---|
-| `catboost.cbm` | Trained CatBoost (Tweedie:variance_power=1.99) | ~1 MB |
-| `xgboost.json` | Trained XGBoost Booster (reg:gamma) | ~1 MB |
-| `cann_member{0,1,2}.pt` | CANN 3-seed ensemble | ~600 KB each |
-| `cann_gbm_member{0,1,2}.pt` | CANN-GBM 3-seed ensemble | ~600 KB each |
-| `ft_transformer_member{0,1,2}.pt` | FT-Transformer 3-seed ensemble | ~2 MB each |
-| `tabm_member{0,1,2}.pt` | TabM 3-seed ensemble | ~1.5 MB each |
-| `localglmnet_member{0,1,2}.pt` | LocalGLMnet 3-seed ensemble | ~250 KB each |
-| `drn_member{0,1,2}.pt` | DRN 3-seed ensemble | ~600 KB each |
+| **SHAP TreeExplainer** | CatBoost, XGBoost | Per-row Shapley contribution of each feature to the model's log-prediction. |
+| **Native importance** (CatBoost / XGBoost) | CatBoost, XGBoost | Loss reduction (CatBoost) / gain (XGBoost). |
+| **Captum Integrated Gradients** | All 6 DL architectures | Gradient-based attribution for continuous features, averaged over 50 integration steps. |
+| **FT-Transformer attention** | FT-Transformer | Per-layer multi-head self-attention weights, averaged across heads. |
+| **CANN / CANN-GBM residual analysis** | CANN, CANN-GBM | Distribution of the neural network's correction to the GBM/GLM base. Here: mean=0.005, std=0.107 -> the NN added almost no correction beyond what the base already captured. |
+| **LocalGLMnet coefficients** | LocalGLMnet | Per-row linear coefficients - exposes *how* the effective regression formula varies across the input space. |
+| **DRN distributional output** | DRN | Full predicted gamma distribution per row. Here: mean shape ≈ 1.04, CoV ≈ 0.98, VaR95 ≈ $1.18M, VaR99 ≈ $2.5M. The wide upper tail is consistent with House Prices' heavy right skew. |
+
+### Cross-method consensus (the high-confidence finding)
+
+Both CatBoost and XGBoost ranked the following four features in their
+**top-5 most important** for predicting `SalePrice`. Cross-method
+agreement is a strong signal - independent methods identifying the
+same drivers means the finding is unlikely to be a method-specific
+artefact:
+
+| Feature | CatBoost | XGBoost | Interpretation |
+|---|---:|---:|---|
+| `TotalSF` (derived) | 0.096 | **0.138** | Total square footage (basement + 1st + 2nd floor). Dominant predictor across both models. |
+| `OverallQual` | 0.043 | 0.103 | Material and finish quality 1-10. Strongly monotonic with price. |
+| `GrLivArea` | 0.043 | 0.032 | Above-grade living area sq ft. |
+| `YearRemodAdd` | 0.038 | 0.025 | Year of most recent remodel - matters more than `YearBuilt`. |
+
+Note the derived feature **`TotalSF`** (defined in
+[`configs/example_house_prices.py`](https://github.com/timothy22000/tabular_data_modelling_pipeline/blob/master/configs/example_house_prices.py)
+as `TotalBsmtSF + 1stFlrSF + 2ndFlrSF`) is more predictive than any
+of its components individually - the pipeline's `derived_features`
+mechanism paid off here.
+
+Full breakdown - per-method top-10 tables, LocalGLMnet coefficient
+distributions, sign-stability analysis - is in
+[`INTERPRETABILITY.md`](./INTERPRETABILITY.md). For the interactive
+plots see
+[`dashboard_dl_interpretability.html`](./dashboard_dl_interpretability.html).
+
+## Files
+
+| File | What it is |
+|---|---|
+| `catboost.cbm` | Trained CatBoost (Tweedie:variance_power=1.99) |
+| `xgboost.json` | Trained XGBoost Booster (reg:gamma) |
+| `cann_member{0,1,2}.pt` | CANN 3-seed ensemble |
+| `cann_gbm_member{0,1,2}.pt` | CANN-GBM 3-seed ensemble |
+| `ft_transformer_member{0,1,2}.pt` | FT-Transformer 3-seed ensemble |
+| `tabm_member{0,1,2}.pt` | TabM 3-seed ensemble |
+| `localglmnet_member{0,1,2}.pt` | LocalGLMnet 3-seed ensemble |
+| `drn_member{0,1,2}.pt` | DRN 3-seed ensemble |
 | `evaluation_summary.csv` | Per-model train/test metrics |
 | `ensemble_weights.json` | NNLS weights over the 8 base predictions |
-| `dashboard_dl_models.html` | Interactive Plotly dashboard |
-| `figures/fig_dl_*.png` | Standalone publication figures |
+| `dashboard_dl_models.html` | Performance dashboard (Lorenz, calibration, A/P scatter) |
+| **`dashboard_dl_interpretability.html`** | **Interpretability dashboard** (SHAP, IG, attention, residuals) |
+| **`feature_importance.csv`** | **Consolidated importances** across CatBoost + XGBoost |
+| **`localglmnet_coefficients.csv`** | **LocalGLMnet per-row coefficients** (304 rows × 16 continuous features) |
+| **`drn_distributional_outputs.csv`** | **DRN per-row distributional moments** (mean, variance, VaR95, VaR99) |
+| **`INTERPRETABILITY.md`** | **Human-readable interpretability summary report** |
+| `figures/fig_dl_*.png` | Standalone publication figures (incl. attention heatmap) |
 | `model_summary.json` | Structured run record |
 
 ## Loading and inference

catboost.cbm

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf9ffe2d002b62da46c9d38582619693f60ab8e02fd19becbe97e4b80cfeecbd
+oid sha256:06132211b7f97d5c4ddd4388ae1b487756397b0f87a23912a33c7dd586c825db
 size 567896

dashboard_dl_models.html

@@ -3883,6 +3883,6 @@ maplibre-gl/dist/maplibre-gl.js:
 
 window.Plotly = Plotly;
 return Plotly;
-}));</script>                <div id="4c34d7d5-96aa-4b7d-8a0c-bf05b90b6063" class="plotly-graph-div" style="height:100%; width:100%;"></div>            <script>                window.PLOTLYENV=window.PLOTLYENV || {};                                if (document.getElementById("4c34d7d5-96aa-4b7d-8a0c-bf05b90b6063")) {                    Plotly.newPlot(                        "4c34d7d5-96aa-4b7d-8a0c-bf05b90b6063",                        [{"name":"xgboost","text":["0.2049"],"textposition":"auto","x":["xgboost"],"y":[0.2049],"type":"bar"},{"name":"stacked_ensemble","text":["0.2049"],"textposition":"auto","x":["stacked_ensemble"],"y":[0.2049],"type":"bar"},{"name":"catboost","text":["0.1996"],"textposition":"auto","x":["catboost"],"y":[0.1996],"type":"bar"},{"name":"localglmnet","text":["0.1991"],"textposition":"auto","x":["localglmnet"],"y":[0.1991],"type":"bar"},{"name":"GLM","text":["0.1984"],"textposition":"auto","x":["GLM"],"y":[0.1984],"type":"bar"},{"name":"drn","text":["0.1962"],"textposition":"auto","x":["drn"],"y":[0.1962],"type":"bar"},{"name":"cann","text":["0.1941"],"textposition":"auto","x":["cann"],"y":[0.1941],"type":"bar"},{"name":"cann_gbm","text":["0.1940"],"textposition":"auto","x":["cann_gbm"],"y":[0.194],"type":"bar"}],                        {"template":{"data":{"histogram2dcontour":[{"type":"histogram2dcontour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"choropleth":[{"type":"choropleth","colorbar":{"outlinewidth":0,"ticks":""}}],"histogram2d":[{"type":"histogram2d","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"heatmap":[{"type":"heatmap","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"contourcarpet":[{"type":"contourcarpet","colorbar":{"outlinewidth":0,"ticks":""}}],"contour":[{"type":"contour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"surface":[{"type":"surface","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"mesh3d":[{"type":"mesh3d","colorbar":{"outlinewidth":0,"ticks":""}}],"scatter":[{"fillpattern":{"fillmode":"overlay","size":10,"solidity":0.2},"type":"scatter"}],"parcoords":[{"type":"parcoords","line":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolargl":[{"type":"scatterpolargl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"bar":[{"error_x":{"color":"#2a3f5f"},"error_y":{"color":"#2a3f5f"},"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"bar"}],"scattergeo":[{"type":"scattergeo","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolar":[{"type":"scatterpolar","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"histogram":[{"marker":{"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"histogram"}],"scattergl":[{"type":"scattergl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatter3d":[{"type":"scatter3d","line":{"colorbar":{"outlinewidth":0,"ticks":""}},"marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattermap":[{"type":"scattermap","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattermapbox":[{"type":"scattermapbox","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterternary":[{"type":"scatterternary","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattercarpet":[{"type":"scattercarpet","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"carpet":[{"aaxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"baxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"type":"carpet"}],"table":[{"cells":{"fill":{"color":"#EBF0F8"},"line":{"color":"white"}},"header":{"fill":{"color":"#C8D4E3"},"line":{"color":"white"}},"type":"table"}],"barpolar":[{"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"barpolar"}],"pie":[{"automargin":true,"type":"pie"}]},"layout":{"autotypenumbers":"strict","colorway":["#636efa","#EF553B","#00cc96","#ab63fa","#FFA15A","#19d3f3","#FF6692","#B6E880","#FF97FF","#FECB52"],"font":{"color":"#2a3f5f"},"hovermode":"closest","hoverlabel":{"align":"left"},"paper_bgcolor":"white","plot_bgcolor":"#E5ECF6","polar":{"bgcolor":"#E5ECF6","angularaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"radialaxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"ternary":{"bgcolor":"#E5ECF6","aaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"baxis":{"gridcolor":"white","linecolor":"white","ticks":""},"caxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"coloraxis":{"colorbar":{"outlinewidth":0,"ticks":""}},"colorscale":{"sequential":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"sequentialminus":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"diverging":[[0,"#8e0152"],[0.1,"#c51b7d"],[0.2,"#de77ae"],[0.3,"#f1b6da"],[0.4,"#fde0ef"],[0.5,"#f7f7f7"],[0.6,"#e6f5d0"],[0.7,"#b8e186"],[0.8,"#7fbc41"],[0.9,"#4d9221"],[1,"#276419"]]},"xaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"yaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"scene":{"xaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"yaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"zaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2}},"shapedefaults":{"line":{"color":"#2a3f5f"}},"annotationdefaults":{"arrowcolor":"#2a3f5f","arrowhead":0,"arrowwidth":1},"geo":{"bgcolor":"white","landcolor":"#E5ECF6","subunitcolor":"white","showland":true,"showlakes":true,"lakecolor":"white"},"title":{"x":0.05},"mapbox":{"style":"light"}}},"title":{"text":"DL Pipeline — Model Gini Comparison"},"yaxis":{"title":{"text":"Test Gini"}},"showlegend":true},                        {"responsive": true}                    )                };            </script>        </div>
+}));</script>                <div id="5eeb3948-75de-4a7b-80ec-2694eb81456d" class="plotly-graph-div" style="height:100%; width:100%;"></div>            <script>                window.PLOTLYENV=window.PLOTLYENV || {};                                if (document.getElementById("5eeb3948-75de-4a7b-80ec-2694eb81456d")) {                    Plotly.newPlot(                        "5eeb3948-75de-4a7b-80ec-2694eb81456d",                        [{"name":"xgboost","text":["0.2049"],"textposition":"auto","x":["xgboost"],"y":[0.2049],"type":"bar"},{"name":"stacked_ensemble","text":["0.2049"],"textposition":"auto","x":["stacked_ensemble"],"y":[0.2049],"type":"bar"},{"name":"catboost","text":["0.1996"],"textposition":"auto","x":["catboost"],"y":[0.1996],"type":"bar"},{"name":"localglmnet","text":["0.1991"],"textposition":"auto","x":["localglmnet"],"y":[0.1991],"type":"bar"},{"name":"GLM","text":["0.1984"],"textposition":"auto","x":["GLM"],"y":[0.1984],"type":"bar"},{"name":"drn","text":["0.1962"],"textposition":"auto","x":["drn"],"y":[0.1962],"type":"bar"},{"name":"cann","text":["0.1941"],"textposition":"auto","x":["cann"],"y":[0.1941],"type":"bar"},{"name":"cann_gbm","text":["0.1940"],"textposition":"auto","x":["cann_gbm"],"y":[0.194],"type":"bar"}],                        {"template":{"data":{"histogram2dcontour":[{"type":"histogram2dcontour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"choropleth":[{"type":"choropleth","colorbar":{"outlinewidth":0,"ticks":""}}],"histogram2d":[{"type":"histogram2d","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"heatmap":[{"type":"heatmap","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"contourcarpet":[{"type":"contourcarpet","colorbar":{"outlinewidth":0,"ticks":""}}],"contour":[{"type":"contour","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"surface":[{"type":"surface","colorbar":{"outlinewidth":0,"ticks":""},"colorscale":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]]}],"mesh3d":[{"type":"mesh3d","colorbar":{"outlinewidth":0,"ticks":""}}],"scatter":[{"fillpattern":{"fillmode":"overlay","size":10,"solidity":0.2},"type":"scatter"}],"parcoords":[{"type":"parcoords","line":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolargl":[{"type":"scatterpolargl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"bar":[{"error_x":{"color":"#2a3f5f"},"error_y":{"color":"#2a3f5f"},"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"bar"}],"scattergeo":[{"type":"scattergeo","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterpolar":[{"type":"scatterpolar","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"histogram":[{"marker":{"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"histogram"}],"scattergl":[{"type":"scattergl","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatter3d":[{"type":"scatter3d","line":{"colorbar":{"outlinewidth":0,"ticks":""}},"marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattermap":[{"type":"scattermap","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattermapbox":[{"type":"scattermapbox","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scatterternary":[{"type":"scatterternary","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"scattercarpet":[{"type":"scattercarpet","marker":{"colorbar":{"outlinewidth":0,"ticks":""}}}],"carpet":[{"aaxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"baxis":{"endlinecolor":"#2a3f5f","gridcolor":"white","linecolor":"white","minorgridcolor":"white","startlinecolor":"#2a3f5f"},"type":"carpet"}],"table":[{"cells":{"fill":{"color":"#EBF0F8"},"line":{"color":"white"}},"header":{"fill":{"color":"#C8D4E3"},"line":{"color":"white"}},"type":"table"}],"barpolar":[{"marker":{"line":{"color":"#E5ECF6","width":0.5},"pattern":{"fillmode":"overlay","size":10,"solidity":0.2}},"type":"barpolar"}],"pie":[{"automargin":true,"type":"pie"}]},"layout":{"autotypenumbers":"strict","colorway":["#636efa","#EF553B","#00cc96","#ab63fa","#FFA15A","#19d3f3","#FF6692","#B6E880","#FF97FF","#FECB52"],"font":{"color":"#2a3f5f"},"hovermode":"closest","hoverlabel":{"align":"left"},"paper_bgcolor":"white","plot_bgcolor":"#E5ECF6","polar":{"bgcolor":"#E5ECF6","angularaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"radialaxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"ternary":{"bgcolor":"#E5ECF6","aaxis":{"gridcolor":"white","linecolor":"white","ticks":""},"baxis":{"gridcolor":"white","linecolor":"white","ticks":""},"caxis":{"gridcolor":"white","linecolor":"white","ticks":""}},"coloraxis":{"colorbar":{"outlinewidth":0,"ticks":""}},"colorscale":{"sequential":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"sequentialminus":[[0.0,"#0d0887"],[0.1111111111111111,"#46039f"],[0.2222222222222222,"#7201a8"],[0.3333333333333333,"#9c179e"],[0.4444444444444444,"#bd3786"],[0.5555555555555556,"#d8576b"],[0.6666666666666666,"#ed7953"],[0.7777777777777778,"#fb9f3a"],[0.8888888888888888,"#fdca26"],[1.0,"#f0f921"]],"diverging":[[0,"#8e0152"],[0.1,"#c51b7d"],[0.2,"#de77ae"],[0.3,"#f1b6da"],[0.4,"#fde0ef"],[0.5,"#f7f7f7"],[0.6,"#e6f5d0"],[0.7,"#b8e186"],[0.8,"#7fbc41"],[0.9,"#4d9221"],[1,"#276419"]]},"xaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"yaxis":{"gridcolor":"white","linecolor":"white","ticks":"","title":{"standoff":15},"zerolinecolor":"white","automargin":true,"zerolinewidth":2},"scene":{"xaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"yaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2},"zaxis":{"backgroundcolor":"#E5ECF6","gridcolor":"white","linecolor":"white","showbackground":true,"ticks":"","zerolinecolor":"white","gridwidth":2}},"shapedefaults":{"line":{"color":"#2a3f5f"}},"annotationdefaults":{"arrowcolor":"#2a3f5f","arrowhead":0,"arrowwidth":1},"geo":{"bgcolor":"white","landcolor":"#E5ECF6","subunitcolor":"white","showland":true,"showlakes":true,"lakecolor":"white"},"title":{"x":0.05},"mapbox":{"style":"light"}}},"title":{"text":"DL Pipeline — Model Gini Comparison"},"yaxis":{"title":{"text":"Test Gini"}},"showlegend":true},                        {"responsive": true}                    )                };            </script>        </div>
 </body>
 </html>

drn_distributional_outputs.csv

@@ -0,0 +1,305 @@
+mean_pred,shape,rate,cov,p95,p99
+166832.06,1.1352229,6.8045847e-06,0.93855435,478016.14923773624,721254.9099381872
+278323.62,0.9492861,3.4107277e-06,1.0263641,849302.3354340823,1315886.6186128075
+157789.25,1.1175181,7.0823457e-06,0.9459599,454592.584709396,687472.6217717165
+150245.22,0.9534981,6.3462794e-06,1.0240946,457751.8693478883,708751.1651297203
+251697.1,1.1386057,4.5237143e-06,0.93715906,720428.5187275356,1086552.7785925164
+159102.12,0.8245741,5.182672e-06,1.101248,510540.40414591436,808546.9411210199
+249959.77,1.0393051,4.1578896e-06,0.9809084,738696.6244969857,1129054.626309322
+129395.91,0.9252575,7.1505933e-06,1.0396059,398466.4704994394,619797.2569524832
+226680.38,1.2632608,5.5728724e-06,0.88972026,625907.7979726512,930180.5777165998
+171501.39,1.1992786,6.9928215e-06,0.9131455,482114.0434157505,721748.0759779258
+405734.25,1.1294098,2.7836195e-06,0.9409666,1164614.4257499038,1758531.6190511358
+309616.38,1.1901598,3.843982e-06,0.916637,872677.9434028661,1307858.5220097692
+195714.48,0.98543876,5.0350836e-06,1.007361,589358.2475901156,907984.8511102279
+75514.164,0.89490694,1.1850849e-05,1.0570878,235321.76302777242,367920.5623894723
+290930.8,1.1300379,3.8842154e-06,0.9407051,834922.1333556449,1260605.2626688886
+425168.12,1.1720786,2.7567414e-06,0.92368025,1204749.427790882,1809469.2494096437
+241296.11,1.0213382,4.2327174e-06,0.9894986,717489.2439400721,1099483.409548526
+163913.61,1.0631232,6.4858755e-06,0.96985805,480562.96837895754,732060.3883898477
+179737.4,0.98146045,5.4605243e-06,1.0094007,542021.92820369,835565.7867389561
+130450.89,1.0091846,7.7361265e-06,0.9954391,389535.5810487474,597992.5364215004
+330804.88,1.1667795,3.527093e-06,0.92577535,938839.4002184373,1411000.3640465739
+302523.03,1.1003469,3.6372335e-06,0.9533122,876302.6360715246,1328201.1380566736
+257044.42,0.9968879,3.878271e-06,1.0015596,770885.272085077,1185592.2145746858
+277619.16,1.0874567,3.917081e-06,0.95894575,807489.5718019839,1226006.9307531763
+218531.11,0.98934,4.5272272e-06,1.005373,657146.7757955017,1011820.6518901614
+179840.25,0.8907802,4.953175e-06,1.0595336,561354.2330120133,878295.0028823696
+262580.78,1.0051724,3.82805e-06,0.99742377,785188.8947218806,1206094.7225715085
+330585.7,1.2219876,3.6964323e-06,0.9046209,923314.9171189407,1378582.6951887608
+172640.33,0.8706141,5.0429358e-06,1.0717344,543307.0173917705,853096.946241651
+294023.53,1.2859232,4.3735386e-06,0.8818455,806915.6619191605,1196213.1795374197
+104413.695,0.8558806,8.197015e-06,1.0809196,330607.21696355037,520508.4126053905
+168787.81,1.2836676,7.6052147e-06,0.88261986,463498.74243239616,687282.1140304039
+164697.17,1.0173483,6.1770843e-06,0.99143714,490400.5615863731,751930.0688239024
+144306.12,0.8661595,6.0022367e-06,1.0744867,454971.8291042395,714967.442808725
+312803.28,1.0248797,3.276435e-06,0.98778754,928979.7381606868,1422839.3173323504
+111512.93,0.91387445,8.195233e-06,1.0460603,344914.1331414483,537520.8912086848
+344084.62,1.0787086,3.1350098e-06,0.9628262,1003650.026502785,1525637.4618503938
+129601.66,1.0067385,7.767945e-06,0.99664766,387331.55090289685,594824.7409240201
+302980.16,1.1218795,3.7028149e-06,0.94411933,871702.8534393776,1317517.9950559612
+159182.78,1.1669278,7.3307415e-06,0.9257165,451748.0949539495,678928.832326459
+320629.97,1.1962655,3.7309844e-06,0.9142948,902120.3673660433,1351000.2568723783
+232043.58,1.0168996,4.3823648e-06,0.9916558,691038.0847074775,1059636.8005206988
+170652.47,1.2891188,7.554059e-06,0.88075185,467938.97951041587,693457.4913887496
+161568.7,1.1844432,7.330895e-06,0.91884625,456154.5900703705,684095.0055896892
+300060.75,0.95737517,3.1906045e-06,1.0220189,912878.6614758437,1412566.7305430942
+186200.78,0.94598156,5.0804383e-06,1.0281552,568894.4611696536,881898.337687741
+176645.17,0.94234776,5.334693e-06,1.0301356,540438.0548845326,838277.1154706985
+114770.82,0.9812978,8.550063e-06,1.0094843,346126.9186134683,533592.86635682
+156257.58,0.85969853,5.501804e-06,1.0785167,493974.028278346,777169.6334732516
+200804.58,0.924546,4.604208e-06,1.0400058,618534.2841684587,962216.7493820533
+141067.1,0.9684082,6.864877e-06,1.0161803,427429.33426788467,660246.353292847
+257059.39,1.0275189,3.997204e-06,0.9865182,762736.5973434538,1167772.3048754057
+156800.33,1.1245167,7.171648e-06,0.94301164,450759.95316853636,681060.7947453618
+84569.38,1.026258,1.21351e-05,0.9871241,251039.62271784636,384419.23637686577
+200184.02,0.9927263,4.959069e-06,1.0036567,601247.7698938651,925276.8479899735
+182360.42,0.96950537,5.3164244e-06,1.0156051,552325.1935710727,853025.7725504824
+164383.52,0.99847066,6.0740317e-06,1.0007656,492715.50933608663,757597.4898367445
+179113.7,0.9268474,5.1746315e-06,1.0387137,551232.3183675407,857192.1038749017
+257655.52,1.0281539,3.9904207e-06,0.9862135,764338.9040150058,1170118.0667102288
+138690.7,0.9687947,6.9852895e-06,1.0159776,420169.4917055722,648992.960446143
+140051.1,0.81550217,5.82289e-06,1.1073564,451195.4101606792,715822.9187788115
+224318.97,0.9648329,4.301165e-06,1.0180613,680572.2563378732,1051862.8224886113
+260634.3,1.0747601,4.1236326e-06,0.9645933,761214.7505109259,1157736.1177945228
+238013.56,1.0994524,4.6192845e-06,0.9537,689637.7089623072,1045399.1733422993
+194413.31,0.9612749,4.944491e-06,1.0199437,590613.5747084116,913337.8565285912
+100659.73,0.83809566,8.3260275e-06,1.0923283,321127.1411044783,507260.588999881
+108396.96,1.0382172,9.577918e-06,0.9814222,320459.604303716,489879.7595800098
+118042.04,0.959668,8.129883e-06,1.0207973,358816.10969596426,555021.9766701047
+159233.78,0.94994766,5.9657423e-06,1.0260066,485780.38684334175,752575.5013843976
+130880.25,0.8229717,6.287975e-06,1.1023197,420272.8255201044,665795.5471890384
+308091.12,1.1661994,3.785242e-06,0.9260055,874527.851263446,1314438.7730431396
+108173.02,0.9091927,8.404985e-06,1.0487502,335196.62136719463,522790.6919066931
+173349.75,1.3191217,7.6095967e-06,0.870678,471608.7417258907,696672.6997137533
+171922.61,1.0589525,6.159472e-06,0.9717662,504740.37000983866,769335.6780735061
+285195.03,1.0269991,3.6010415e-06,0.9867678,846370.5062485442,1295915.727641853
+304425.7,1.1794626,3.8743856e-06,0.92078435,860737.6669086721,1291623.6610690218
+131529.69,1.0039672,7.633008e-06,0.9980223,393476.7717571586,604511.1586002671
+316580.1,1.1661327,3.6835313e-06,0.92603207,898641.9829753165,1350694.0215026375
+122082.05,0.88815165,7.275039e-06,1.0611002,381469.7794900776,597121.7833231709
+356870.53,1.1286035,3.1625011e-06,0.94130266,1024611.8880756026,1547291.7615869052
+413320.34,1.1585476,2.8030258e-06,0.92905843,1175912.075678248,1769094.4298953945
+220651.25,1.2553631,5.689354e-06,0.8925146,610575.3685956917,908191.0197948773
+376933.22,1.1700482,3.104126e-06,0.9244813,1068714.9470529645,1605550.4758642835
+109516.15,0.9424459,8.6055425e-06,1.030082,335047.4111582123,519686.04686133284
+175490.9,0.8597807,4.8992893e-06,1.0784652,554757.0220391612,872786.4525619863
+169332.95,1.016582,6.0034504e-06,0.9918107,504338.1346259816,773387.3752486496
+115928.805,1.0997317,9.486268e-06,0.9535789,335870.61919339944,509116.4214286956
+657059.75,1.3110155,1.9952759e-06,0.87336564,1791340.305035473,2648468.754669457
+220202.58,1.0378866,4.7133262e-06,0.98157847,651069.4024978089,995322.8557216418
+199425.86,1.1880169,5.9571857e-06,0.9174633,562448.5132569829,843142.3082262499
+191256.03,1.0427858,5.4523025e-06,0.97927,564546.841341165,862449.9697408882
+105714.53,0.92056435,8.708021e-06,1.0422524,326131.07981402637,507678.9871091106
+123259.04,0.9675666,7.849863e-06,1.0166222,373586.58419696335,577151.8554917708
+195279.77,1.102355,5.6450035e-06,0.9524436,565296.0352222932,856584.9397670018
+132842.95,1.0666094,8.0291e-06,0.9682719,389022.33248337306,592327.8240593439
+307785.7,1.0566121,3.4329476e-06,0.97284174,904318.0343779009,1378829.4665840482
+107170.83,0.96245885,8.980604e-06,1.0193162,325435.0813436128,503166.0794577761
+318553.47,1.0591636,3.3249162e-06,0.9716693,935162.2978880018,1425351.8162127924
+127821.28,0.99720854,7.801585e-06,1.0013987,383296.93505741435,589467.6758374197
+189644.5,1.088792,5.7412262e-06,0.9583575,551367.3003648751,836987.8860610828
+200768.52,0.9956477,4.9591827e-06,1.0021832,602376.9257450594,926605.7859446707
+156424.66,1.0230621,6.5402864e-06,0.9886646,464849.0875906457,712157.851088953
+124867.086,0.9546715,7.645502e-06,1.023465,380266.29014135804,588667.8340725659
+296573.53,1.0260587,3.4597108e-06,0.9872199,880422.7390942882,1348238.201829679
+120989.88,0.904533,7.4761047e-06,1.051448,375599.7177593587,586270.4663562577
+152125.75,0.98220074,6.4565056e-06,1.0090202,458632.88707220124,706935.2717301068
+287747.1,1.0516449,3.6547544e-06,0.9751365,846843.484496883,1292094.4665090465
+178122.23,1.0666174,5.9881204e-06,0.9682682,521618.5060157497,794218.7091053854
+764982.7,1.0846268,1.4178449e-06,0.96019584,2227078.93481166,3382649.4095277777
+129243.42,0.9606711,7.433037e-06,1.0202641,392719.6997888879,607368.2764744718
+125692.19,0.90652287,7.2122452e-06,1.0502933,389891.89923669584,608372.4710633622
+143123.4,1.3038574,9.110023e-06,0.8757597,390928.1295745157,578419.1882952695
+192559.27,1.0403609,5.402809e-06,0.98041064,568859.7107539122,869338.1243437402
+254350.9,1.1810576,4.643418e-06,0.9201624,718818.4672020847,1078451.7799386953
+244585.78,1.0062925,4.114272e-06,0.99686855,731091.1673236537,1122810.5030654513
+251649.22,1.0095596,4.0117734e-06,0.99525416,751343.769518529,1153355.557696117
+192000.95,1.0569552,5.5049477e-06,0.9726838,564061.6605161041,859993.5062822565
+273718.38,1.1525103,4.21057e-06,0.9314887,780155.5660922959,1174580.8497329687
+475418.38,0.9049299,1.903439e-06,1.0512174,1475652.9365456393,2303178.2553187897
+288639.44,1.03522,3.5865507e-06,0.9828419,854189.1264477312,1306340.241302142
+431398.06,1.0373758,2.4046835e-06,0.9818202,1275728.752990223,1950413.5695103977
+294716.88,1.1686463,3.9653187e-06,0.92503566,835955.7458369482,1256087.2400497166
+119829.73,0.9716343,8.108458e-06,1.0144919,362652.9036807986,559905.1031137612
+355159.56,1.0462009,2.9457208e-06,0.9776703,1047149.3627300952,1598941.6129400404
+123792.336,0.9324274,7.53219e-06,1.0356011,380165.01745804364,590631.0024163224
+142063.45,1.0910662,7.680133e-06,0.9573582,412729.68813293526,626342.0742416941
+150806.56,1.013308,6.7192573e-06,0.9934116,449671.132514261,689889.0052122392
+172815.4,1.0715722,6.200675e-06,0.9660271,505255.183423822,768780.5185550255
+192757.73,1.0548686,5.4725097e-06,0.97364545,566678.435161371,864234.8166233064
+133672.7,0.9152816,6.847184e-06,1.0452559,413228.65310778987,643831.0056902114
+317266.34,1.1572978,3.6477172e-06,0.92956,902973.5978663245,1358683.8905133558
+80398.414,0.9593543,1.1932502e-05,1.0209641,244417.95088172812,378087.9955986347
+294665.03,1.0058737,3.4136174e-06,0.99707603,880912.5546439207,1352990.549330076
+134390.31,0.9631531,7.1668346e-06,1.0189487,407985.39843923575,630730.9504138263
+151846.86,0.958432,6.3118327e-06,1.0214552,461784.8519304105,714435.229608422
+187481.17,1.218265,6.498066e-06,0.90600187,524180.7143526031,782980.7530750686
+78339.08,0.84513295,1.078814e-05,1.087771,249171.61060711154,393077.90378994873
+99099.414,0.95751137,9.66213e-06,1.0219462,301476.20328494726,466487.03211639944
+210951.02,0.9816323,4.653366e-06,1.0093124,636111.2888373492,980585.4364488603
+149400.36,1.0239449,6.8536974e-06,0.9882384,443839.84461891744,679884.0412382581
+389814.03,1.2874656,3.3027686e-06,0.8813171,1069362.8503996814,1585014.2128461713
+437846.53,1.1875755,2.7123099e-06,0.9176338,1235034.6559314895,1851485.103013863
+190686.28,0.9884888,5.1838483e-06,1.0058059,573589.044475688,883279.6050942191
+160443.22,0.89937794,5.605584e-06,1.0544571,499094.5119580264,779721.4052111759
+203864.34,1.0120076,4.9641226e-06,0.9940498,608153.166464473,933212.2421888608
+312738.8,1.1967437,3.8266558e-06,0.91411203,879796.0406330165,1317492.9372799858
+212817.9,1.5045342,7.069585e-06,0.8152653,553812.0521287238,803662.420261854
+110732.2,0.8966241,8.0972295e-06,1.0560751,344834.383167704,538981.0443671134
+253534.0,1.0775691,4.2501956e-06,0.96333516,739799.8046595393,1124735.7065563176
+159424.69,0.8657719,5.430601e-06,1.0747273,502718.5053185008,790054.5579348801
+226970.1,1.1846073,5.2192217e-06,0.91878265,640770.6764193319,960944.7844671466
+329609.06,1.0381836,3.149742e-06,0.98143816,974451.6295192788,1489630.5594204024
+180933.11,1.0557191,5.8348587e-06,0.97325313,531765.1353841726,810892.5982895063
+190910.39,0.8853075,4.6372934e-06,1.0628034,597221.336918293,935308.0771312263
+130004.21,1.0721378,8.246947e-06,0.96577215,380018.98668109794,578180.262866281
+155517.45,1.2394502,7.969847e-06,0.8982257,432234.4860436369,644072.1610475004
+102847.33,0.986306,9.590001e-06,1.0069181,309609.43824238563,476931.4287058275
+178151.56,1.077673,6.0491916e-06,0.96328884,519819.98170723807,790283.856797518
+209287.27,0.9970006,4.76379e-06,1.0015031,627634.7913461213,965262.0694084284
+208611.52,1.1918612,5.7133047e-06,0.9159825,587696.9305737544,880586.4010826175
+174855.14,1.0316644,5.900109e-06,0.98453414,518087.60380520026,792733.3211868819
+307317.25,1.20344,3.915953e-06,0.91156536,862876.1924852708,1291132.9792559585
+267357.78,1.1474019,4.2916345e-06,0.9335599,763205.5599584838,1149794.9791802056
+132447.78,0.9842771,7.4314353e-06,1.0079554,399008.78417202947,614835.3050608903
+152960.53,0.9105454,5.952813e-06,1.0479709,473728.9397492918,738683.741064698
+228744.08,1.0171013,4.4464596e-06,0.9915575,681164.3508032975,1044465.5539444785
+274558.06,0.9947242,3.6230012e-06,1.0026484,824042.2140299517,1267758.7294487327
+106805.42,0.9028028,8.452781e-06,1.0524551,331792.0629941348,518044.7551618809
+199151.66,0.9906046,4.9741216e-06,1.004731,598600.0420403854,921498.2833360175
+243917.36,1.0505465,4.306977e-06,0.9756462,718115.9438412471,1095853.9106489306
+216791.23,0.97417,4.493586e-06,1.0131707,655491.6445240964,1011624.6740709364
+138874.84,1.191362,8.578674e-06,0.91617435,391292.7135000216,586335.4810443
+171467.2,1.1234882,6.5522045e-06,0.9434432,493080.83634084,745102.7461655881
+170756.56,1.4168134,8.29727e-06,0.8401245,453417.6378211168,663295.18855133
+297698.38,1.2064512,4.0525956e-06,0.91042703,835146.3659935917,1249198.0093263753
+164550.66,0.9303067,5.6536187e-06,1.0367807,505742.8874681359,786004.9820107832
+126129.14,0.9600702,7.611803e-06,1.0205834,383341.7390362683,592920.8832250419
+90473.06,0.79576623,8.795615e-06,1.1210042,294048.355995669,468344.32448452985
+137892.8,0.9409278,6.8236186e-06,1.0309126,422103.0641670732,654877.6016573401
+101828.13,1.0528572,1.03395505e-05,0.97457504,299560.17903253395,456984.4104123033
+137365.27,0.9395647,6.8399004e-06,1.0316601,420704.9664630158,652852.9913482026
+214601.6,1.142905,5.325706e-06,0.93539476,613444.7551863552,924697.4692132312
+111226.914,0.96384287,8.665555e-06,1.018584,337579.658900901,521829.56420675036
+283309.94,1.1438096,4.0373084e-06,0.93502486,809626.4100508057,1220279.8199357516
+145455.69,1.0618068,7.299864e-06,0.97045916,426633.5754136971,650026.0973877915
+139811.52,1.0318333,7.380174e-06,0.9844535,414231.0783829156,633805.5523760837
+598175.94,1.203517,2.0119783e-06,0.9115361,1679503.259447543,2513039.98868932
+127836.37,0.85905635,6.7199685e-06,1.0789198,404234.70192621637,636057.3300071023
+126654.39,1.2713366,1.003784e-05,0.88689,348952.27687947423,518127.3342384742
+345534.84,1.134734,3.283993e-06,0.9387565,990193.6189835559,1494146.9678706115
+187696.94,1.0438187,5.561192e-06,0.9787853,553848.1174653427,845981.7894282015
+454026.34,1.2112818,2.6678667e-06,0.90860975,1271941.4053001625,1901472.731505968
+145505.22,1.0770302,7.402004e-06,0.9635762,424651.5926651648,645655.5004505975
+98059.67,1.1018842,1.1236874e-05,0.9526471,283905.6322872014,430224.8517718563
+257194.53,1.0339043,4.019931e-06,0.98346704,761473.3058989368,1164766.4446144507
+131294.3,1.0043825,7.649856e-06,0.99781597,392715.1676261841,603303.7433924146
+461399.56,1.1971422,2.594589e-06,0.91395986,1297858.5759549823,1943448.9317054634
+403627.38,1.062733,2.6329558e-06,0.97003615,1183509.9652955479,1802984.4161593148
+102705.3,0.9006852,8.769608e-06,1.0536915,319322.3269730529,498756.2182877265
+348370.53,1.1731037,3.3674023e-06,0.92327654,986837.4015981561,1481991.953858186
+85557.836,0.9073897,1.0605571e-05,1.0497916,265306.39907783305,413912.9177826606
+143266.17,0.9854829,6.878685e-06,1.0073385,431412.95642753196,664644.6234023123
+133960.55,0.9155439,6.8344298e-06,1.0451062,414076.1911665493,645123.0517904307
+166270.16,1.0236863,6.156765e-06,0.9883632,494000.82188527123,756750.20433641
+205593.66,1.2549295,6.1039314e-06,0.8926687,568976.3305574969,846356.1016643628
+115868.5,1.0022949,8.65028e-06,0.9988545,346829.89609241515,532979.020084762
+205701.08,0.9555643,4.6454024e-06,1.0229868,626227.7805357923,969288.6438976728
+185195.02,1.0699875,5.777626e-06,0.9667421,541730.3588292068,824459.0493447965
+253894.9,1.0265301,4.04313e-06,0.9869932,753602.8010368065,1153953.278059896
+146467.1,0.9099852,6.2128984e-06,1.0482934,453717.8361418203,707547.6569117226
+100958.55,1.0998013,1.0893593e-05,0.95354867,292492.10205161554,443358.69640827045
+310387.2,0.9653969,3.1102986e-06,1.0177639,941503.7279241345,1455018.3515444358
+226927.98,0.93562937,4.1230232e-06,1.0338274,696044.3550563361,1080819.6395223592
+125514.76,0.9645992,7.685146e-06,1.0181847,380838.06772788195,588628.3218516953
+177031.31,1.208015,6.823736e-06,0.9098375,496411.28053380176,742387.50575366
+169934.9,0.77807903,4.5786887e-06,1.1336739,556790.5493522492,890051.5263966607
+178927.22,0.8653513,4.8363313e-06,1.0749884,564314.4379676281,886924.0556113259
+154727.55,1.1064781,7.1511386e-06,0.9506674,447320.9872166937,677451.1986370583
+299563.1,1.0795593,3.6037795e-06,0.96244687,873544.936546777,1327712.880611325
+252090.75,1.2119837,4.8077277e-06,0.9083467,706083.4038963236,1055463.9540457402
+347024.2,1.0793992,3.110444e-06,0.9625182,1011997.1905514753,1538181.7506949669
+141905.23,1.3141978,9.261094e-06,0.8723076,386555.460268538,571324.7521161744
+108645.984,0.9057747,8.336937e-06,1.050727,337114.5168088078,526087.731423206
+212126.64,1.1491201,5.417142e-06,0.93286175,605226.1530568808,911597.5801024594
+170207.17,0.99249375,5.8310925e-06,1.0037744,511255.45085284516,786812.8580031897
+99680.34,0.9670009,9.701019e-06,1.0169195,302184.431541619,466884.38856276806
+198755.36,0.9097596,4.577283e-06,1.0484233,615748.0190967354,960261.4129062857
+295860.56,1.1412952,3.857544e-06,0.9360542,846141.1808346383,1275719.4301736322
+95896.414,0.94858074,9.891723e-06,1.0267456,292704.4174904323,453559.82289016066
+176228.45,1.2597078,7.1481522e-06,0.89097416,487071.7487587989,724137.2288995525
+147423.03,0.9107166,6.177573e-06,1.0478723,456548.3456475612,711873.4700696015
+209347.62,1.0205672,4.874988e-06,0.98987234,622656.9192043463,954269.2629428104
+127126.78,1.1288943,8.880067e-06,0.9411814,364961.20442085346,551116.4266903582
+94047.04,0.9106509,9.68293e-06,1.0479101,291257.9076822309,454149.23828442395
+227838.67,1.1903512,5.2245355e-06,0.9165633,642145.336826942,962343.606600866
+180873.89,0.8914529,4.928588e-06,1.0591338,564428.536550369,883001.5691145327
+132064.72,0.9975543,7.553526e-06,1.0012251,395973.1724597751,608930.6531053202
+120241.58,0.93813926,7.80212e-06,1.0324436,368459.5643069149,571910.8203820443
+366098.3,1.1099749,3.0319038e-06,0.94916874,1057232.0852846217,1600405.4658644341
+216155.67,1.3212907,6.112681e-06,0.86996305,587735.0531467362,868020.7045031851
+171319.67,0.967447,5.647028e-06,1.016685,519276.62229769677,802242.604384026
+150832.7,0.8972026,5.9483295e-06,1.0557345,469604.4043558742,733925.0137255134
+172788.42,1.0119219,5.856422e-06,0.9940918,515465.1399519337,790992.2824232179
+102767.78,1.3477948,1.31149545e-05,0.86136675,277543.8372594737,408783.7305186735
+128121.445,0.97955644,7.645531e-06,1.0103812,386632.9811090327,596197.020648553
+311639.75,0.99197316,3.1830764e-06,1.0040377,936253.6829572939,1440990.9568713217
+485484.0,1.1974546,2.4665171e-06,0.9138407,1365481.7200663337,2044633.9522071457
+117241.47,0.9889668,8.435299e-06,1.0055627,352604.89578804316,542942.8593915713
+142586.06,1.0180106,7.1396225e-06,0.9911145,424465.2499459707,650768.4845722539
+129258.15,0.81249684,6.285846e-06,1.1094025,416976.5864635199,661924.9855663806
+121622.68,0.78760505,6.4758074e-06,1.1267972,396755.8283448015,632982.2777829143
+137616.92,0.903844,6.567826e-06,1.0518486,427332.63737936044,667098.507419454
+232005.33,0.9886537,4.2613406e-06,1.0057219,697836.551178175,1074583.5172650837
+112405.13,0.9476646,8.430795e-06,1.0272417,343211.73205409053,531901.6406994434
+270729.7,1.0446126,3.858508e-06,0.97841334,798643.8712058567,1219760.7853676896
+149304.89,0.9407326,6.3007487e-06,1.0310196,457070.2964057573,709150.4546142927
+316496.97,0.94350666,2.9810922e-06,1.0295027,967885.6419355406,1501012.5133996229
+116454.06,0.9904401,8.504985e-06,1.0048145,350052.3423969297,538891.8474092971
+299335.66,1.1389112,3.8047965e-06,0.9370334,856703.5709903646,1292033.3321833722
+127601.87,0.9085477,7.1201757e-06,1.0491223,395500.94379923167,616912.1041963793
+300193.12,1.0804781,3.5992766e-06,0.96203756,875121.0931158665,1329942.8848103757
+337137.1,1.109678,3.291474e-06,0.9492957,973687.8451875247,1473995.9999128357
+179864.34,1.2792864,7.112507e-06,0.88412994,494494.8277872608,733592.5153224176
+321635.1,1.0931957,3.3988695e-06,0.95642525,933792.1872879762,1416682.6420549587
+93732.02,0.8588894,9.163244e-06,1.0790247,296413.112755022,466415.89005295414
+536741.94,1.1052231,2.059133e-06,0.951207,1552349.5533083088,2351364.205014692
+153732.94,0.9795273,6.371616e-06,1.0103962,463925.85009260237,715387.6259573995
+178561.16,0.9327568,5.2237383e-06,1.0354182,548290.6110154971,851787.8085043727
+249999.64,1.1506991,4.602803e-06,0.9322215,712942.2339569259,1073628.7605034765
+121860.47,1.0884281,8.931757e-06,0.9585176,354335.3264263802,537915.1985598101
+503461.03,1.1093472,2.2034421e-06,0.9494372,1454200.5272571142,2201504.90043836
+191735.88,0.986715,5.1462202e-06,1.0067095,577112.9463517894,888946.2033766655
+331082.97,1.1291757,3.410552e-06,0.94106424,950405.0970103008,1435125.161222547
+142062.81,0.9254818,6.514596e-06,1.0394799,437435.6821182339,680386.8663024826
+169822.16,1.0972371,6.461095e-06,0.95466226,492402.42773306626,746635.9786673314
+183310.73,1.0906755,5.9498725e-06,0.95752966,532630.1320134249,808340.4527299344
+207071.06,1.0220534,4.9357614e-06,0.98915243,615569.7540686412,943203.2985574933
+284163.44,0.90139234,3.1720913e-06,1.0532782,883248.8261173784,1379397.3103680627
+195479.86,0.98605,5.0442536e-06,1.0070488,588522.5638735626,906612.7695129038
+605717.06,1.2154964,2.0067066e-06,0.90703315,1694862.7030953856,2532469.3004906476
+245160.72,0.8377177,3.4170143e-06,1.0925747,782244.2470257264,1235741.113881613
+1.4439141e+06,1.5817193,1.0954386e-06,0.7951248,3695415.9834123673,5327305.388855582
+89789.56,0.9474875,1.0552312e-05,1.0273378,274176.7714092971,424924.9472857335
+224944.52,0.99270034,4.4130898e-06,1.00367,675621.6061438434,1039736.8918075006
+136284.77,0.82828367,6.0775956e-06,1.0987792,436618.566637702,690983.0213659925
+89906.85,0.84942263,9.447807e-06,1.0850208,285446.90247283416,449944.11344593327
+214943.31,0.9876185,4.594786e-06,1.0062488,646756.3654350666,996083.1380810891
+150358.11,0.9534068,6.3409075e-06,1.0241437,458111.39170109713,709318.151855491
+420748.47,1.2007961,2.8539525e-06,0.91256833,1182264.318664359,1769589.432125519
+264213.28,1.0335777,3.911907e-06,0.9836225,782340.6755625601,1196741.7201095526
+348913.4,1.1456729,3.283545e-06,0.9342641,996539.0922139083,1501645.4353845855
+304180.56,1.121115,3.685689e-06,0.9444412,875364.7922705609,1323183.3084470376
+143029.4,0.95694673,6.6905595e-06,1.0222477,435209.33249955083,673478.3432174281
+332219.97,1.1823133,3.5588268e-06,0.9196736,938537.3909386236,1407885.410514304
+139896.89,1.1039331,7.891048e-06,0.9517626,404771.0466846899,613216.1244882051
+87258.305,1.0459851,1.19872275e-05,0.97777116,257290.28339776883,392880.61114008806
+115224.11,0.9530415,8.271199e-06,1.0243399,351112.8228706802,543678.2729517398
+155679.61,1.1972787,7.690659e-06,0.9139078,437889.7220584116,655697.4335653097
+117960.484,0.90144235,7.641901e-06,1.0532489,366642.5306558662,572592.1908754628
+114835.164,0.9449212,8.2285005e-06,1.028732,350992.7830233731,544200.887147126
+234947.83,0.996297,4.240503e-06,1.0018567,704764.5778532373,1083997.495810722
+147766.83,0.9792526,6.627012e-06,1.010538,445965.99279423145,687722.0702979297
+160473.95,0.99986494,6.230699e-06,1.0000676,480759.9852880545,739060.1542647472
+278228.38,1.1533431,4.145311e-06,0.93115234,792810.794869553,1193510.4420652601

evaluation_summary.csv

@@ -1,10 +1,10 @@
 model,gini_train,gini_test,mae,rmse,cv_rmse,ae_ratio,gamma_deviance,n_params,training_time
-xgboost,0.2212,0.2049,17203.89,29715.99,0.1582,0.9985,-4.691965,462,0.3
+xgboost,0.2212,0.2049,17203.89,29715.99,0.1582,0.9985,-4.691965,462,0.4
 stacked_ensemble,0.2212,0.2049,17203.89,29715.99,0.1582,0.9985,-4.691965,9,0.0
-catboost,0.2172,0.1996,29223.45,42466.58,0.2261,1.1608,-14.947891,499,2.1
-localglmnet,0.206,0.1991,23419.59,41406.01,0.2204,0.9881,-7.820823,22620,4.5
-drn,0.2021,0.1962,27927.62,50086.19,0.2667,0.9813,-10.697358,53010,4.8
-cann,0.2024,0.1941,24906.06,40934.77,0.2179,1.0241,-9.638748,52815,8.2
-cann_gbm,0.215,0.194,32932.2,48574.48,0.2586,1.193,-20.046702,52815,4.2
-ft_transformer,0.0593,0.0368,187771.09,203270.26,1.0822,3337.2602,-2023550.169534,483267,171.7
-tabm,0.0648,0.0332,187802.11,203298.92,1.0824,7436.716,-4515436.943944,410364,126.8
+catboost,0.2172,0.1996,29223.45,42466.58,0.2261,1.1608,-14.947891,499,2.7
+localglmnet,0.206,0.1991,23419.59,41406.01,0.2204,0.9881,-7.820823,22620,6.3
+drn,0.2021,0.1962,27927.62,50086.19,0.2667,0.9813,-10.697358,53010,6.6
+cann,0.2024,0.1941,24906.06,40934.79,0.2179,1.0241,-9.638755,52815,6.5
+cann_gbm,0.215,0.194,32932.26,48574.52,0.2586,1.193,-20.046771,52815,5.8
+ft_transformer,0.0593,0.0368,187771.09,203270.26,1.0822,3337.2602,-2023550.196912,483267,340.8
+tabm,0.0649,0.0331,187802.11,203298.92,1.0824,7436.7159,-4515436.929884,410364,176.6

feature_importance.csv

@@ -0,0 +1,31 @@
+,catboost,xgboost
+LotArea,0.0299558890709282,0.018735945224761963
+YearBuilt,0.009944529413332888,0.011890393681824207
+YearRemodAdd,0.03808294250943824,0.02543613314628601
+TotalBsmtSF,0.00612565957775995,0.005671687424182892
+1stFlrSF,0.0177018573042125,0.005975295789539814
+2ndFlrSF,0.006153301136166478,0.006476496811956167
+GrLivArea,0.042954046634248746,0.03230186924338341
+FullBath,0.004621338428952026,0.0021380428224802017
+BedroomAbvGr,0.004002707512544635,0.005364640150219202
+TotRmsAbvGrd,0.005516047312148908,0.002059247111901641
+GarageCars,0.021077496363544362,0.01970186084508896
+GarageArea,0.01672833192315018,0.011155343614518642
+OverallQual,0.04304413355254438,0.10281679779291153
+OverallCond,0.027940178417433383,0.0248036477714777
+TotalSF,0.09628637381758418,0.13827185332775116
+HouseAge,0.02171022194904836,0.02106185257434845
+MSZoning,0.022420450976467183,0.00972825102508068
+Street,0.002728593016693207,4.0004691982176155e-05
+LotShape,0.006271055566533644,0.002093958668410778
+Neighborhood,0.0,0.009759566746652126
+BldgType,0.005452511822146627,0.006014882121235132
+HouseStyle,0.0,0.006607345771044493
+RoofStyle,0.0017120094213143252,0.0005743123474530876
+ExterQual,0.007995776226058742,0.00540172029286623
+Foundation,0.005492159211350321,0.0005980093847028911
+Heating,0.00589738071852314,0.0001287364138988778
+CentralAir,0.012354306219268222,0.0036354013718664646
+KitchenQual,0.02836237118000965,0.011459688656032085
+SaleType,0.0,0.0019649819005280733
+SaleCondition,0.012806486390969712,0.0067738075740635395

model_summary.json

@@ -1,6 +1,6 @@
 {
   "pipeline": "dl",
-  "timestamp": "2026-06-22T21:39:24.767656",
+  "timestamp": "2026-06-29T20:45:12.755636",
   "config": {
     "seed": 42,
     "n_tuning_trials": 30,
@@ -54,7 +54,7 @@
         "mean_predicted": 161815.4533,
         "gamma_deviance": -14.947891
       },
-      "training_time": 2.090752124786377,
+      "training_time": 2.687849998474121,
       "best_params": {},
       "n_params": 499
     },
@@ -85,7 +85,7 @@
         "mean_predicted": 188117.697,
         "gamma_deviance": -4.691965
       },
-      "training_time": 0.30820369720458984,
+      "training_time": 0.39440107345581055,
       "best_params": {
         "max_depth": 6,
         "eta": 0.05,
@@ -103,29 +103,29 @@
         "split": "train",
         "n": 1156,
         "n_params": 0,
-        "gini": 0.202412,
-        "mae": 23155.4632,
-        "rmse": 34338.3056,
+        "gini": 0.202411,
+        "mae": 23155.4686,
+        "rmse": 34338.3103,
         "cv_rmse": 0.192227,
         "ae_ratio": 1.018042,
         "mean_actual": 178634.4191,
-        "mean_predicted": 175468.5637,
-        "gamma_deviance": -37.783694
+        "mean_predicted": 175468.5434,
+        "gamma_deviance": -37.783704
       },
       "metrics_test": {
         "split": "test",
         "n": 304,
         "n_params": 0,
         "gini": 0.194059,
-        "mae": 24906.0552,
-        "rmse": 40934.7729,
+        "mae": 24906.0643,
+        "rmse": 40934.7862,
         "cv_rmse": 0.217938,
         "ae_ratio": 1.024133,
         "mean_actual": 187827.3717,
-        "mean_predicted": 183401.3429,
-        "gamma_deviance": -9.638748
+        "mean_predicted": 183401.323,
+        "gamma_deviance": -9.638755
       },
-      "training_time": 8.172953128814697,
+      "training_time": 6.516291856765747,
       "best_params": {
         "hidden_dims": [
           128,
@@ -149,28 +149,28 @@
         "n": 1156,
         "n_params": 0,
         "gini": 0.214997,
-        "mae": 26973.7479,
-        "rmse": 36715.2346,
+        "mae": 26973.8176,
+        "rmse": 36715.2832,
         "cv_rmse": 0.205533,
-        "ae_ratio": 1.167738,
+        "ae_ratio": 1.167739,
         "mean_actual": 178634.4191,
-        "mean_predicted": 152974.7022,
-        "gamma_deviance": -40.585075
+        "mean_predicted": 152974.6205,
+        "gamma_deviance": -40.585313
       },
       "metrics_test": {
         "split": "test",
         "n": 304,
         "n_params": 0,
         "gini": 0.194023,
-        "mae": 32932.1965,
-        "rmse": 48574.4771,
-        "cv_rmse": 0.258612,
+        "mae": 32932.265,
+        "rmse": 48574.5172,
+        "cv_rmse": 0.258613,
         "ae_ratio": 1.192998,
         "mean_actual": 187827.3717,
-        "mean_predicted": 157441.5228,
-        "gamma_deviance": -20.046702
+        "mean_predicted": 157441.4424,
+        "gamma_deviance": -20.046771
       },
-      "training_time": 4.1777918338775635,
+      "training_time": 5.8221588134765625,
       "best_params": {
         "hidden_dims": [
           128,
@@ -197,25 +197,25 @@
         "mae": 178578.1372,
         "rmse": 194469.1036,
         "cv_rmse": 1.088643,
-        "ae_ratio": 3173.923664,
+        "ae_ratio": 3173.923706,
         "mean_actual": 178634.4191,
         "mean_predicted": 56.2819,
-        "gamma_deviance": -7317306.628657
+        "gamma_deviance": -7317306.734206
       },
       "metrics_test": {
         "split": "test",
         "n": 304,
         "n_params": 0,
-        "gini": 0.036793,
+        "gini": 0.036815,
         "mae": 187771.0898,
         "rmse": 203270.2569,
         "cv_rmse": 1.082219,
-        "ae_ratio": 3337.260163,
+        "ae_ratio": 3337.260207,
         "mean_actual": 187827.3717,
         "mean_predicted": 56.2819,
-        "gamma_deviance": -2023550.169534
+        "gamma_deviance": -2023550.196912
       },
-      "training_time": 171.6630778312683,
+      "training_time": 340.80848002433777,
       "best_params": {
         "d_model": 64,
         "n_heads": 4,
@@ -238,29 +238,29 @@
         "split": "train",
         "n": 1156,
         "n_params": 0,
-        "gini": 0.064841,
+        "gini": 0.064854,
         "mae": 178609.1615,
         "rmse": 194497.5932,
         "cv_rmse": 1.088802,
-        "ae_ratio": 7072.489806,
+        "ae_ratio": 7072.489783,
         "mean_actual": 178634.4191,
         "mean_predicted": 25.2576,
-        "gamma_deviance": -16328852.883661
+        "gamma_deviance": -16328852.827116
       },
       "metrics_test": {
         "split": "test",
         "n": 304,
         "n_params": 0,
-        "gini": 0.033202,
+        "gini": 0.033122,
         "mae": 187802.1149,
         "rmse": 203298.9164,
         "cv_rmse": 1.082371,
-        "ae_ratio": 7436.715966,
+        "ae_ratio": 7436.715938,
         "mean_actual": 187827.3717,
         "mean_predicted": 25.2568,
-        "gamma_deviance": -4515436.943944
+        "gamma_deviance": -4515436.929884
       },
-      "training_time": 126.83994007110596,
+      "training_time": 176.6026849746704,
       "best_params": {
         "n_members": 8,
         "hidden_dims": [
@@ -306,7 +306,7 @@
         "mean_predicted": 190085.4273,
         "gamma_deviance": -7.820823
       },
-      "training_time": 4.459076642990112,
+      "training_time": 6.341158151626587,
       "best_params": {
         "hidden_dims": [
           64,
@@ -331,28 +331,28 @@
         "n": 1156,
         "n_params": 0,
         "gini": 0.202143,
-        "mae": 25139.4592,
-        "rmse": 48095.4966,
+        "mae": 25139.4589,
+        "rmse": 48095.4937,
         "cv_rmse": 0.26924,
         "ae_ratio": 1.002491,
         "mean_actual": 178634.4191,
-        "mean_predicted": 178190.4894,
-        "gamma_deviance": -42.297569
+        "mean_predicted": 178190.489,
+        "gamma_deviance": -42.297568
       },
       "metrics_test": {
         "split": "test",
         "n": 304,
         "n_params": 0,
         "gini": 0.196194,
-        "mae": 27927.624,
-        "rmse": 50086.187,
+        "mae": 27927.6243,
+        "rmse": 50086.1878,
         "cv_rmse": 0.266661,
         "ae_ratio": 0.981333,
         "mean_actual": 187827.3717,
-        "mean_predicted": 191400.3008,
+        "mean_predicted": 191400.3003,
         "gamma_deviance": -10.697358
       },
-      "training_time": 4.845325231552124,
+      "training_time": 6.589911937713623,
       "best_params": {
         "hidden_dims": [
           128,
@@ -398,7 +398,7 @@
         "mean_predicted": 188117.697,
         "gamma_deviance": -4.691965
       },
-      "training_time": 0.0029859542846679688,
+      "training_time": 0.0017802715301513672,
       "best_params": {},
       "n_params": 9,
       "base_weights": {