Validation

generator/train.py

@@ -1,6 +1,7 @@
 """Explicit, deterministic supervised training; never called by an asset build."""
 from __future__ import annotations
 import argparse
+import collections
 import dataclasses
 import hashlib
 import json
@@ -49,6 +50,8 @@ def load_examples(manifest):
     if evidence['discrepancies']:raise ValueError(entry['id']+': '+str(evidence['discrepancies']))
     ctx=Context(document)
     training_io.validate_harmony(document,evidence,entry['id'])
+    from generator.solo.authored import validate_evidence
+    checked=validate_evidence(document,evidence)
     events=[];cursor=F()
     from generator import fretboard
     for n in evidence['sounding_events']:
@@ -61,7 +64,8 @@ def load_examples(manifest):
       events.append((start,end,pitch));cursor=end
     if cursor<a.boundaries[-1]:events.append((cursor,a.boundaries[-1],None))
     source_hash=hashlib.sha256(source.read_bytes()).hexdigest()
-    examples.append({'id':entry['id'],'song':source_hash,'role':role,'analysis':a,'harmony':ctx,'events':tuple(events)})
+    examples.append({'id':entry['id'],'song':source_hash,'role':role,'analysis':a,'harmony':ctx,'events':tuple(events),
+      'harmonic_validation':{'valid':checked.valid,'treatments':dict(sorted(collections.Counter(c.rule for c in checked.contracts).items()))}})
     provenance.append({'id':entry['id'],'source_sha256':source_hash,'solo_sha256':evidence['sha256'],
       'pitch_convention':entry['pitch_convention'],'measures':len(spans),'pickup_beats':str(a.body_offset),
       'slot':entry['slot'],'attacks':len(evidence['sounding_events']),'annotations':len(evidence['annotations']),
@@ -136,6 +140,7 @@ def main():
   value=learned.fit(examples,provenance);predictor=learned.Model(value)
   report={'version':learned.VERSION,'training':provenance,'model_sha256':vocabulary.fingerprint(value),
     'contexts':len(value['contexts']),'in_sample_event_nll':{e['id']:likelihood(predictor,e) for e in examples},
+    'harmonic_validation':{e['id']:e['harmonic_validation'] for e in examples},
     'limitations':'A small corpus does not establish generalization. Likelihood is teacher-forced, not free generation or musical preference.'}
   if args.leave_one_song_out:
     report['held_out_event_nll']={}