Ml Result Result #101 — Analysis Report

Generated 2026-09-21 02:36:21 · 3 runs · CAT-G Data Analyzer

Contents

1. Pipeline Stage — Preprocessing 2026-09-21 02:12:52 · ml_result

Pipeline stage preprocessing: missing values: mean.

Field	Value
stage	preprocessing
detail	missing values: mean

Method: Random Forest
Engine: Python · scikit-learn 1.8.0
Input dataset: gallery — cat_g_field_data_plots.csv
Started: 2026-09-21 02:12:52.641122
Permanent link: https://cat-g-omxpert.wishartlab.com/results/by-token/a316fb7a42834890a899475de981b6f9

Command history

# python
# Models compared via app.services.ml_model_registry
# python
scores = sklearn.model_selection.cross_val_score(model, X, y, cv=3)

2. Pipeline Stage — Feature Selection 2026-09-21 02:12:52 · ml_result

Pipeline stage feature selection: kbest_f (k=5); 40 → 5 features.

Field	Value
stage	feature_selection
detail	kbest_f (k=5); 40 → 5 features

Method: Random Forest
Engine: Python · scikit-learn 1.8.0
Input dataset: gallery — cat_g_field_data_plots.csv
Started: 2026-09-21 02:12:52.641122
Permanent link: https://cat-g-omxpert.wishartlab.com/results/by-token/a316fb7a42834890a899475de981b6f9

Command history

# python
# Models compared via app.services.ml_model_registry
# python
scores = sklearn.model_selection.cross_val_score(model, X, y, cv=3)

3. Random Forest 2026-09-21 02:12:52 · ml_result

The model explains 27.2% of the variance in PC_SHOOTMASS under cross-validation.

stage	detail
preprocessing	missing values: mean
feature_selection	kbest_f (k=5); 40 → 5 features
model	random_forest (regression), 3-fold cross-validation

importance bar

cv boxplot

Method: Random Forest
Engine: Python · scikit-learn 1.8.0
Input dataset: gallery — cat_g_field_data_plots.csv
Started: 2026-09-21 02:12:52.641122
Permanent link: https://cat-g-omxpert.wishartlab.com/results/by-token/a316fb7a42834890a899475de981b6f9

Command history

# python
# Models compared via app.services.ml_model_registry
# python
scores = sklearn.model_selection.cross_val_score(model, X, y, cv=3)