Random Forest Result #143 — Analysis Report
Contents
- random forest (#143) completed
1. Random Forest
2026-09-21 02:13:52 · random_forest
The model explains 0.0% of the variance in the target — worse than simply predicting the mean; treat predictions as unreliable.
| task_type | regression |
|---|---|
| r2_mean | -0.049195 |
| r2_std | 0.029871 |
| mse_mean | 7.227791 |
| mse_std | 0.20578 |
permutation importance
| name | mean | std |
|---|---|---|
| MEAN_PC_SHOOTMASS | 0.084806 | 0.005584 |
| MEAN_RC_SHOOTMASS | 0.130502 | 0.104911 |
| MEAN_PC_HEIGHT | 0.026103 | 0.019747 |
| MEAN_ENV_SOILOC | 0.198789 | 0.075698 |
| MEAN_ENV_SOILMOIS | 0.088199 | 0.114618 |
| MEAN_ENV_SOILTN | 0.328192 | 0.01486 |
| MEAN_COVER_TOTAL_JUL | 0.132638 | 0.067458 |
| MEAN_COVER_SHANNON_JUL | -0.027903 | 0.031621 |
| MEAN_PC_WOODMASS | -0.056028 | 0.025228 |
| PLOT_COUNT | -0.048951 | 0.055505 |
shap importance
| name | mean_abs |
|---|---|
| MEAN_PC_SHOOTMASS | 0.265275 |
| MEAN_RC_SHOOTMASS | 0.305043 |
| MEAN_PC_HEIGHT | 0.112237 |
| MEAN_ENV_SOILOC | 0.108948 |
| MEAN_ENV_SOILMOIS | 0.225008 |
| MEAN_ENV_SOILTN | 0.342947 |
| MEAN_COVER_TOTAL_JUL | 0.173261 |
| MEAN_COVER_SHANNON_JUL | 0.085411 |
| MEAN_PC_WOODMASS | 0.228746 |
| PLOT_COUNT | 0.009979 |
split metrics
| r2 | mse |
|---|---|
| -0.079067 | 7.43357 |
| -0.019324 | 7.022011 |
importance bar
permutation bar
shap summary
pred vs obs
cv boxplot
Method & Provenance
- Method
- Random Forest (Regression)
- Engine
- Python · scikit-learn 1.8.0
- Input dataset
- gallery — catg_example_02_grazing_carrying_capacity.csv
- Started
- 2026-09-21 02:13:52.593069
- Permanent link
- https://cat-g-omxpert.wishartlab.com/results/by-token/c2f085d2764a43e3b8a578284d15edb5
| Parameter | Value |
|---|---|
| task_type | regression |
| model_type | regression |
| target_column | CW_NUMBER |
| n_estimators | 60 |
| n_splits | 2 |
| test_size | 0.25 |
| run_univariate | True |
| run_permutation | True |
| run_shap | True |
| permutation_repeats | 10 |
| fdr_threshold | 0.05 |
Command history
# python from sklearn.ensemble import RandomForestRegressor # python model = RandomForestRegressor(n_estimators=60, random_state=42) # python scores = sklearn.model_selection.cross_val_score(model, X, y, cv=2)