Result Detail – Random Forest Help

Back to Results Dashboard view Export CSV Export Excel Export PDF Download Full Report

Download Model (.pkl) Notebook

Possible data leakage detected:

Feature "CF_NUMBER" is almost perfectly correlated with the target "CW_NUMBER" (r = 0.996) — likely data leakage or a duplicate measurement; consider excluding it.
Mean cross-validated R² is negative (-0.049) — the model performs worse than simply predicting the mean target value. Results are unreliable; check for leakage, too few samples, or an unsuitable target.
Only 2 cross-validation split(s) requested — variance between splits is high with fewer than 3 folds; consider raising n_splits.

Feature	Pearson r	Pearson p	Pearson FDR	Spearman ρ	Spearman FDR	ANOVA F	ANOVA FDR	Significant?
MEAN_PC_SHOOTMASS	0.7414	0.0058	0.0550	0.5263	0.5670	12.2050	0.0550	✗ No
MEAN_RC_SHOOTMASS	0.5022	0.0962	0.3327	0.4000	0.5670	3.3721	0.3327	✗ No
MEAN_PC_HEIGHT	0.5215	0.0821	0.3327	0.3544	0.5670	3.7351	0.3327	✗ No
MEAN_ENV_SOILOC	0.1793	0.5771	0.9621	0.3474	0.5670	0.3322	0.9621	✗ No
MEAN_ENV_SOILMOIS	0.1431	0.6572	0.9621	0.1860	0.9721	0.2091	0.9621	✗ No
MEAN_ENV_SOILTN	0.2084	0.5157	0.9621	0.3544	0.5670	0.4540	0.9621	✗ No
MEAN_COVER_TOTAL_JUL	0.5775	0.0492	0.3119	0.3965	0.5670	5.0047	0.3119	✗ No
MEAN_COVER_SHANNON_JUL	-0.0670	0.8360	0.9621	-0.0947	0.9927	0.0451	0.9621	✗ No
MEAN_PC_WOODMASS	-0.4277	0.1654	0.4490	-0.3509	0.5670	2.2393	0.4490	✗ No
PLOT_COUNT	-0.0412	0.8988	0.9621	-0.0242	0.9927	0.0170	0.9621	✗ No
PASTURE_TOTALAREA	-0.0154	0.9621	0.9621	0.0386	0.9927	0.0024	0.9621	✗ No
PASTURE_FORESTAREA	0.1155	0.7208	0.9621	0.0386	0.9927	0.1352	0.9621	✗ No
PASTURE_WETLANDAREA	0.0861	0.7901	0.9621	0.0772	0.9927	0.0747	0.9621	✗ No
MEAN_ENV_PH	-0.4910	0.1051	0.3327	-0.3684	0.5670	3.1760	0.3327	✗ No
MEAN_ENV_SOILP	0.0278	0.9318	0.9621	0.0000	1.0000	0.0077	0.9621	✗ No
PASTURE_BIOMASS_PREDICTED	-0.2480	0.4371	0.9228	-0.1544	0.9927	0.6551	0.9228	✗ No
PASTURE_HA	-0.2723	0.3919	0.9228	-0.3123	0.6138	0.8009	0.9228	✗ No
CF_NUMBER	0.9959	0.0000	0.0000	0.9930	0.0000	1224.9963	0.0000	✓ Yes
SR_NUMBER	0.0723	0.8234	0.9621	0.0782	0.9927	0.0525	0.9621	✗ No

Download CSV

Rank	Feature	Importance (Mean)	SD
1	CF_NUMBER	0.2971	0.0042
2	MEAN_ENV_PH	0.0975	0.0073
3	MEAN_PC_SHOOTMASS	0.0772	0.0032
4	MEAN_COVER_SHANNON_JUL	0.0744	0.0057
5	MEAN_COVER_TOTAL_JUL	0.0602	0.0098
6	MEAN_ENV_SOILTN	0.0440	0.0001
7	PASTURE_FORESTAREA	0.0424	0.0100
8	MEAN_ENV_SOILMOIS	0.0421	0.0232
9	MEAN_PC_WOODMASS	0.0420	0.0006
10	PASTURE_WETLANDAREA	0.0397	0.0046
11	PASTURE_HA	0.0387	0.0233
12	SR_NUMBER	0.0367	0.0038
13	MEAN_RC_SHOOTMASS	0.0322	0.0176
14	MEAN_ENV_SOILOC	0.0250	0.0069
15	PASTURE_TOTALAREA	0.0156	0.0121
16	PASTURE_BIOMASS_PREDICTED	0.0124	0.0023
17	MEAN_PC_HEIGHT	0.0100	0.0062
18	PLOT_COUNT	0.0067	0.0064
19	MEAN_ENV_SOILP	0.0060	0.0016

Download CSV

Rank	Feature	Perm. Importance (Mean)	SD
1	CF_NUMBER	0.3776	0.2402
2	MEAN_ENV_SOILTN	0.3282	0.0149
3	PASTURE_HA	0.2403	0.1183
4	MEAN_ENV_SOILOC	0.1988	0.0757
5	MEAN_COVER_TOTAL_JUL	0.1326	0.0675
6	MEAN_RC_SHOOTMASS	0.1305	0.1049
7	MEAN_ENV_SOILMOIS	0.0882	0.1146
8	MEAN_PC_SHOOTMASS	0.0848	0.0056
9	MEAN_ENV_SOILP	0.0598	0.0180
10	MEAN_PC_HEIGHT	0.0261	0.0197
11	PASTURE_BIOMASS_PREDICTED	0.0137	0.0000
12	SR_NUMBER	0.0041	0.0068
13	MEAN_ENV_PH	-0.0044	0.0015
14	PASTURE_FORESTAREA	-0.0196	0.0233
15	MEAN_COVER_SHANNON_JUL	-0.0279	0.0316
16	PASTURE_TOTALAREA	-0.0378	0.0538
17	PLOT_COUNT	-0.0490	0.0555
18	MEAN_PC_WOODMASS	-0.0560	0.0252
19	PASTURE_WETLANDAREA	-0.1805	0.1198

Download CSV

Download CSV

Download CSV

Feature importance Download PNG

Permutation importance Download PNG

SHAP summary Download PNG

Observed vs predicted (out-of-fold) Download PNG

Cross-validation score distribution Download PNG

Run Pathway Analysis

Method & Provenance

Method: Random Forest (Regression)
Method key: random_forest (result type: random_forest, result #143)
Engine: Python · scikit-learn v1.8.0
Dataset(s): #697 gallery — catg_example_02_grazing_carrying_capacity.csv
Status: completed
Permanent link: https://cat-g-omxpert.wishartlab.com/results/by-token/c2f085d2764a43e3b8a578284d15edb5 Bookmark or share this URL — it does not depend on your session.
Created: 2026-09-21 02:13:52.593069

Reconstructed from the parameters stored with this result — represents the Python/R calls the analysis service made.

from sklearn.ensemble import RandomForestRegressor

model = RandomForestRegressor(n_estimators=60, random_state=42)

scores = sklearn.model_selection.cross_val_score(model, X, y, cv=2)