Skip to content

Console Output

+ python tests/analyze_tuner_sample_history.py output_tuner/new_tuner_test -metric scaled_rmse -min_samples 2 --require_param_variation
Discovered 2 sample-history target(s).

=== Sample history 1/2: output_tuner/new_tuner_test/complex/cli_arm_bomex_20260707_050910_871189_1226173 ===
Tuner Sample History
  job: output_tuner/new_tuner_test/complex/cli_arm_bomex_20260707_050910_871189_1226173
  chunks: 1
  first_chunk: output_tuner/new_tuner_test/complex/cli_arm_bomex_20260707_050910_871189_1226173/sample_history/sample_history_000001.npz
  samples: 4
  params: 102
  cases: 2
  fields: 2
  observations: 10
  metrics: scaled_rmse, correlation, std_ratio, centered_rmse_norm, bias_norm
Checks performed
  - sample-history chunks exist and are sequentially numbered
  - every chunk contains required metadata, sample, and loss arrays
  - metadata arrays match exactly across chunks
  - schema version matches the current observation-axis format
  - sample IDs are unique and cover 0..sample_count-1
  - parameter and loss arrays have the expected shapes and finite values
  - observation metadata covers every case/field/window exactly once
  - at least 2 sample(s) are present
  - at least one tuned parameter varies across samples
  checks: OK
SVD (scaled_rmse)
  matrix_shape: 4 samples x 10 retained columns
  mode 1: singular=6.21645, explained=96.61%
    strongest observations:
      bomex/rcm/w1:7200-9900s/scaled_rmse loading=-0.322
      bomex/rcm/w3:12600-15300s/scaled_rmse loading=-0.320
      bomex/cloud_frac/w4:15300-18000s/scaled_rmse loading=-0.319
      bomex/cloud_frac/w2:9900-12600s/scaled_rmse loading=-0.318
      bomex/cloud_frac/w3:12600-15300s/scaled_rmse loading=-0.317
    strongest parameter correlations:
      C8=+0.999
      C11=+0.016
  mode 2: singular=1.10021, explained=3.03%
    strongest observations:
      bomex/rcm/w4:15300-18000s/scaled_rmse loading=-0.473
      bomex/rcm/w2:9900-12600s/scaled_rmse loading=-0.457
      arm/rcm/w1:68400-72000s/scaled_rmse loading=-0.349
      bomex/cloud_frac/w1:7200-9900s/scaled_rmse loading=+0.335
      bomex/cloud_frac/w3:12600-15300s/scaled_rmse loading=+0.317
    strongest parameter correlations:
      C11=-0.944
      C8=-0.001
  mode 3: singular=0.381194, explained=0.36%
    strongest observations:
      arm/rcm/w1:68400-72000s/scaled_rmse loading=-0.508
      arm/cloud_frac/w1:68400-72000s/scaled_rmse loading=-0.432
      bomex/rcm/w3:12600-15300s/scaled_rmse loading=-0.425
      bomex/rcm/w4:15300-18000s/scaled_rmse loading=+0.401
      bomex/rcm/w2:9900-12600s/scaled_rmse loading=+0.262
    strongest parameter correlations:
      C11=-0.329
      C8=+0.052

=== Sample history 2/2: output_tuner/new_tuner_test/simple/cli_bomex_20260707_050901_891782_1226028 ===
Tuner Sample History
  job: output_tuner/new_tuner_test/simple/cli_bomex_20260707_050901_891782_1226028
  chunks: 1
  first_chunk: output_tuner/new_tuner_test/simple/cli_bomex_20260707_050901_891782_1226028/sample_history/sample_history_000001.npz
  samples: 8
  params: 102
  cases: 1
  fields: 1
  observations: 1
  metrics: scaled_rmse, correlation, std_ratio, centered_rmse_norm, bias_norm
Checks performed
  - sample-history chunks exist and are sequentially numbered
  - every chunk contains required metadata, sample, and loss arrays
  - metadata arrays match exactly across chunks
  - schema version matches the current observation-axis format
  - sample IDs are unique and cover 0..sample_count-1
  - parameter and loss arrays have the expected shapes and finite values
  - observation metadata covers every case/field/window exactly once
  - at least 2 sample(s) are present
  - at least one tuned parameter varies across samples
  checks: OK
SVD (scaled_rmse)
  matrix_shape: 8 samples x 1 retained columns
  mode 1: singular=2.82843, explained=100.00%
    strongest observations:
      bomex/cloud_frac/w1:10800-21600s/scaled_rmse loading=+1.000
    strongest parameter correlations:
      C8=-0.999