Add EasyCom interaction weak-label pipeline

test_derive_easycom_interaction_events.py

@@ -0,0 +1,108 @@
+"""Focused tests for transcript-derived EasyCom interaction proxies."""
+
+from __future__ import annotations
+
+import unittest
+
+from derive_easycom_interaction_events import Rules, Utterance, classify_utterance
+
+
+def utterance(
+    uid: str,
+    participant: int,
+    start: float,
+    end: float,
+    text: str,
+    *,
+    target: tuple[int | str, ...] = ("Group",),
+) -> Utterance:
+    return Utterance(
+        uid=uid,
+        session="Session_7",
+        clip_stem="00-00-000",
+        clip_index=0,
+        segment_id=0,
+        participant_id=participant,
+        target_of_speech=target,
+        transcription=text,
+        source_start_frame=round(start * 20) + 1,
+        source_end_frame=round(end * 20),
+        dense_start_frame=round(start * 20),
+        dense_end_frame_exclusive=round(end * 20),
+        dense_start_seconds=start,
+        dense_end_seconds=end,
+        duration_seconds=end - start,
+        starts_at_clip_boundary=False,
+        ends_at_clip_boundary=False,
+        annotation_end_frame_clamped_by=0,
+        is_cross_clip_continuation=False,
+    )
+
+
+class InteractionProxyTests(unittest.TestCase):
+    def setUp(self) -> None:
+        self.rules = Rules()
+
+    def classify(self, target: Utterance, rows: list[Utterance]):
+        return classify_utterance(
+            target,
+            rows,
+            camera_wearer_id=2,
+            rules=self.rules,
+        )
+
+    def test_short_feedback_inside_retained_floor_is_backchannel_proxy(self) -> None:
+        floor = utterance("floor", 4, 0.0, 4.0, "Long explanation")
+        feedback = utterance("feedback", 2, 1.0, 1.4, "Yeah.", target=(4,))
+        event = self.classify(feedback, [floor, feedback])
+        self.assertEqual(event.event_type, "backchannel_proxy_high")
+        self.assertTrue(event.trainable_auxiliary)
+        self.assertEqual(event.retained_floor_participant_id, 4)
+
+    def test_short_answer_without_floor_return_is_not_backchannel(self) -> None:
+        question = utterance("question", 4, 0.0, 1.0, "Ready?")
+        answer = utterance("answer", 2, 1.1, 2.3, "Yeah, let us start.", target=(4,))
+        event = self.classify(answer, [question, answer])
+        self.assertEqual(event.event_type, "ordinary_switch")
+
+    def test_overlap_takeover_after_cutoff_is_interruption_proxy(self) -> None:
+        old = utterance("old", 4, 0.0, 2.0, "I was going to-")
+        incoming = utterance("incoming", 2, 1.7, 3.2, "Wait, that is wrong.", target=(4,))
+        event = self.classify(incoming, [old, incoming])
+        self.assertEqual(event.event_type, "interruption_proxy_high")
+        self.assertTrue(event.trainable_auxiliary)
+
+    def test_overlap_takeover_without_cutoff_is_not_called_interruption(self) -> None:
+        old = utterance("old", 4, 0.0, 2.0, "I finished my point.")
+        incoming = utterance("incoming", 2, 1.7, 3.2, "Here is my response.", target=(4,))
+        event = self.classify(incoming, [old, incoming])
+        self.assertEqual(event.event_type, "overlap_takeover")
+        self.assertTrue(event.trainable_auxiliary)
+
+    def test_short_nonlexical_floor_return_is_masked_candidate(self) -> None:
+        before = utterance("before", 4, 0.0, 1.2, "First part")
+        brief = utterance("brief", 2, 1.25, 1.8, "Possibly.", target=(4,))
+        after = utterance("after", 4, 1.9, 3.0, "Second part")
+        event = self.classify(brief, [before, brief, after])
+        self.assertEqual(event.event_type, "backchannel_candidate")
+        self.assertFalse(event.trainable_auxiliary)
+
+    def test_hesitation_marker_is_not_nonverbal_feedback(self) -> None:
+        floor = utterance("floor", 4, 0.0, 4.0, "Long explanation")
+        hesitation = utterance("hesitation", 2, 1.0, 1.2, "[H]", target=(4,))
+        event = self.classify(hesitation, [floor, hesitation])
+        self.assertEqual(event.event_type, "nonverbal_candidate")
+        self.assertFalse(event.trainable_auxiliary)
+
+    def test_cross_clip_continuation_never_creates_switch(self) -> None:
+        row = utterance("continued", 2, 60.0, 61.0, "[X] continued")
+        row = Utterance(
+            **{**row.__dict__, "is_cross_clip_continuation": True}
+        )
+        event = self.classify(row, [row])
+        self.assertEqual(event.event_type, "cross_clip_continuation")
+        self.assertFalse(event.trainable_auxiliary)
+
+
+if __name__ == "__main__":
+    unittest.main()