feat: 全量標註的檢查、重標與合併工具 (#5)

verify_batches.py 逐批比對 id;make_relabel.py 挑出需重標的 none;
merge_labels.py 支援多個目錄覆蓋與 confidence 縮寫;worry 加入情緒白名單。

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
Jeffery (jiantw83)
2026-10-14 17:52:50 +00:00
co-authored by Claude Sonnet 5.5
parent c85e00a56e
commit ea6b9ca7ef
8 changed files with 131 additions and 6 deletions
+8
View File
@@ -50,6 +50,14 @@ class Check(unittest.TestCase):
def test_bad_confidence_rejected(self):
self.assertTrue(merge_labels.check({**self.good, "confidence": "sure"}))
def test_worry_is_a_valid_emotion(self):
self.assertEqual(merge_labels.check({**self.good, "emotion": "worry"}), [])
def test_confidence_abbreviations_are_normalized(self):
self.assertEqual(merge_labels.normalize({**self.good, "confidence": "m"})["confidence"], "medium")
self.assertEqual(merge_labels.normalize({**self.good, "confidence": "h"})["confidence"], "high")
self.assertEqual(merge_labels.normalize({**self.good, "confidence": "sure"})["confidence"], "sure")
def test_none_speaker_is_valid_but_never_final(self):
self.assertEqual(merge_labels.check({**self.good, "speaker": "none", "function": "other", "emotion": "neutral"}), [])