feature: on-off-tasks

handler.py

@@ -1,5 +1,6 @@
 from typing import Dict, List, Any
 from measures.VocabularyAnalyser import VocabularyAnalyser
+from measures.OnTaskAnalyser import OnTaskAnalyser, ON_TASK_LABEL
 from scipy.special import softmax
 from collections import Counter, defaultdict
 import numpy as np
@@ -47,6 +48,7 @@ class Utterance:
         self.num_math_terms = None
         self.math_terms = None
         self.vocabulary_terms = None
+        self.on_task = None
 
         # moments
         self.uptake = None
@@ -92,8 +94,14 @@ class Utterance:
                 'questioning': True if self.question else False, 
                 'uptake': True if self.uptake else False, 
                 'focusingQuestion': True if self.focusing_question else False,
-                'mathWord': bool(self.vocabulary_terms)
+                # Legacy alias for onTask below. On/off-task is not a talk moment;
+                # this key is kept only so already-stored analyses and older
+                # frontends keep working, and is retired in the UI.
+                'mathWord': bool(self.on_task) and self.on_task.get('label') == ON_TASK_LABEL
             },
+            # On/off-task classification: a measure in its own right, alongside
+            # vocabulary. None means not classified (teacher utterance or empty text).
+            'onTask': None if self.on_task is None else self.on_task.get('label') == ON_TASK_LABEL,
             'unitMeasure': self.unit_measure,
             'aggregateUnitMeasure': self.aggregate_unit_measure,
             'wordCount': self.word_count,
@@ -537,7 +545,11 @@ class EndpointHandler():
         vocabulary_analyser = VocabularyAnalyser(str(glossary_path))
         vocabulary_analyser.run_analysis(transcript)
         del vocabulary_analyser
-        
+
+        on_task_analyser = OnTaskAnalyser()
+        on_task_analyser.run_analysis(transcript, uptake_speaker=uptake_speaker)
+        del on_task_analyser
+
         transcript.update_utterance_roles(uptake_speaker)
         sorted_math_cloud, teacher_math_cloud, student_math_cloud = run_math_density(transcript)
         transcript.calculate_aggregate_word_count()

measures/OnTaskAnalyser.py

@@ -0,0 +1,23 @@
+from transformers import pipeline
+
+ON_TASK_MODEL = 'edsi-umd/on-task-bert'
+ON_TASK_LABEL = 'on_task'  # from the model's config.json id2label: {"0": "off_task", "1": "on_task"}
+
+
+class OnTaskAnalyser:
+    def __init__(self, model_path=ON_TASK_MODEL, max_length=256):
+        self.pipe = pipeline("text-classification", model=model_path,
+                              truncation=True, max_length=max_length)
+
+    def predict_one(self, text: str):
+        return self.pipe(text)[0]  # {'label': ..., 'score': ...}
+
+    def run_analysis(self, transcript, uptake_speaker=None):
+        """Mutate transcript utterances by setting on_task for student utterances."""
+        for utt in transcript.utterances:
+            if uptake_speaker is not None and utt.speaker == uptake_speaker:
+                continue  # model trained on student utterances only
+            if not utt.text or not utt.text.strip():
+                continue
+            utt.on_task = self.predict_one(utt.text)
+        return transcript