Training table: 17,047 strains × 353 features
Distinct groups: 605
Group sizes (top 10): {'Streptomycetaceae': 798, 'Bacillaceae': 643, 'Flavobacteriaceae': 631, 'Lactobacillaceae': 472, 'Enterobacteriaceae': 439, 'Microbacteriaceae': 397, 'Pseudomonadaceae': 388, 'Roseobacteraceae': 341, 'Paenibacillaceae': 319, 'Pseudonocardiaceae': 307}

Wrote training table to /Users/miyuhoriuchi/microbe-model/data/training_table.parquet
Wrote per-strain predictions to /Users/miyuhoriuchi/microbe-model/artifacts/predictions.parquet

Results summary (234.6s):

  optimal_temperature_c     mae        = 3.2797  (n_folds=5)
  optimal_ph                mae        = 0.5202  (n_folds=5)
  oxygen_requirement        f1_macro   = 0.2791  (n_folds=5)
  salt_tolerance_pct        mae        = 2.5103  (n_folds=5)