Update annotated_casl_app.py

annotated_casl_app.py

@@ -5,6 +5,7 @@ import logging
 import requests
 import re
 import time
+
 # Configure logging
 logging.basicConfig(level=logging.INFO)
 logger = logging.getLogger(__name__)
@@ -136,10 +137,7 @@ def combine_sections_smartly(sections_dict):
 
 
 def call_claude_api_quick_analysis(prompt):
-    """Call Claude API for quick focused analysis - single response only
-    Responses are cleaned to remove asterisks, hashtags, and convert simple tables to lists
-    to match formatting used in the main analysis pipeline.
-    """
+    """Call Claude API for quick focused analysis - single response only"""
     if not ANTHROPIC_API_KEY:
         return "❌ Claude API key not configured. Please set ANTHROPIC_API_KEY environment variable."
     
@@ -170,16 +168,7 @@ def call_claude_api_quick_analysis(prompt):
         
         if response.status_code == 200:
             response_json = response.json()
-            response_text = response_json['content'][0]['text']
-
-            # Clean formatting (remove asterisks, hashtags, convert simple tables) so
-            # Targeted Analysis and Quick Questions match the main analysis output
-            try:
-                cleaned = clean_output_formatting(response_text)
-            except Exception:
-                # If cleaning fails for any reason, fall back to raw response
-                cleaned = response_text
-            return cleaned
+            return response_json['content'][0]['text']
         else:
             logger.error(f"Claude API error: {response.status_code} - {response.text}")
             return f"❌ Claude API Error: {response.status_code}"
@@ -1556,88 +1545,140 @@ def analyze_with_backup(annotated_transcript, original_transcript, age, gender,
     - Count [REPETITION] markers: Categorize by type (word, phrase, sound)
     - Count [REVISION] markers: Analyze self-correction patterns
     - Count [PAUSE] markers: Assess hesitation frequency
-    - Total disfluency assessment: Use verified total of {marker_analysis.get('category_totals', {}).get('fluency_issues', 0)} 
-      * Rate: {marker_analysis.get('category_totals', {}).get('fluency_issues', 0)/linguistic_metrics.get('total_words', 1)*100:.2f} per 100 words
-      * Provide objective rate calculation
+    - Calculate total disfluency rate
 
     B. Word Retrieval Issues:
-    - Circumlocutions: Count and analyze from transcript
-    - Incomplete thoughts: Identify abandoned utterances
-    - Generic language use: Count vague terms
-    - Word-finding efficiency: Assess retrieval success rate
+    - Count [CIRCUMLOCUTION] markers: List each roundabout description
+    - Count [INCOMPLETE] markers: Analyze abandoned thought patterns
+    - Count [GENERIC] markers: Calculate specificity ratio
+    - Count [WORD_SEARCH] markers: Identify retrieval difficulty areas
 
-    C. Grammatical Errors (use verified counts):
-    - Grammar errors: Use verified count of {marker_counts.get('GRAM_ERROR', 0)}
-    - Syntax errors: Use verified count of {marker_counts.get('SYNTAX_ERROR', 0)}
-    - Morphological errors: Use verified count of {marker_counts.get('MORPH_ERROR', 0)}
-    - Calculate overall grammatical accuracy rate
+    C. Grammatical Errors:
+    - Count [GRAM_ERROR] markers by subcategory (verb tense, subject-verb agreement, etc.)
+    - Count [SYNTAX_ERROR] markers: Analyze word order problems
+    - Count [MORPH_ERROR] markers: Categorize morphological mistakes
+    - Count [RUN_ON] markers: Assess sentence boundary awareness
 
-    2. LANGUAGE SKILLS ASSESSMENT
+    2. LANGUAGE SKILLS ASSESSMENT (with specific evidence):
 
-    A. Vocabulary Analysis (use verified data):
-    - Simple vocabulary: Use verified count of {marker_counts.get('SIMPLE_VOCAB', 0)}
-    - Complex vocabulary: Use verified count of {marker_counts.get('COMPLEX_VOCAB', 0)}
-    - Sophistication ratio: Use verified ratio of {category_totals.get('vocab_sophistication_ratio', 0):.3f}
-    - Type-Token Ratio: Use verified TTR from basic metrics
-    - Provide examples of each vocabulary level from transcript
+    A. Lexical/Semantic Skills:
+    - Use calculated Type-Token Ratio: {linguistic_metrics.get('type_token_ratio', 0)}
+    - Count [SIMPLE_VOCAB] vs [COMPLEX_VOCAB] markers
+    - Assess vocabulary sophistication ratio: {marker_analysis.get('category_totals', {}).get('vocab_sophistication_ratio', 0):.3f}
+    - Count [SEMANTIC_ERROR] markers and analyze patterns
 
-    B. Grammar and Morphology:
-    - Error pattern analysis using verified counts
-    - Pattern analysis only
-    - Morphological complexity evaluation
+    B. Syntactic Skills:
+    - Count [SIMPLE_SENT], [COMPLEX_SENT], [COMPOUND_SENT] markers
+    - Calculate sentence complexity ratios
+    - Assess clause complexity and embedding
 
-    3. COMPLEX SENTENCE ANALYSIS (use verified counts)
+    C. Supralinguistic Skills:
+    - Identify cause-effect relationships, inferences, non-literal language
+    - Assess problem-solving language and metalinguistic awareness
 
-    A. Sentence Structure Distribution:
-    - Simple sentences: Use verified count of {marker_counts.get('SIMPLE_SENT', 0)}
-    - Complex sentences: Use verified count of {marker_counts.get('COMPLEX_SENT', 0)}
-    - Compound sentences: Use verified count of {marker_counts.get('COMPOUND_SENT', 0)}
-    - Calculate percentages of each type
+    3. COMPLEX SENTENCE ANALYSIS (with exact counts):
 
-    B. Syntactic Complexity:
-    - MLU analysis: Use verified MLU of {linguistic_metrics.get('mlu_words', 0):.2f} words
-    - Average sentence length: Use verified length of {linguistic_metrics.get('avg_sentence_length', 0):.2f} words
-    - Subordination and coordination patterns
+    A. Coordinating Conjunctions:
+    - Count and cite EVERY use of: and, but, or, so, yet, for, nor
+    - Analyze patterns and age-appropriateness
 
-    4. FIGURATIVE LANGUAGE ANALYSIS
-    - Figurative expressions: Use verified count of {marker_counts.get('FIGURATIVE', 0)}
-    - Metaphor and idiom identification from transcript
-    - Age-appropriate development assessment
-    - Abstract language abilities
+    B. Subordinating Conjunctions:
+    - Count and cite EVERY use of: because, although, while, since, if, when, where, that, which, who
+    - Analyze clause complexity and embedding depth
 
-    5. PRAGMATIC LANGUAGE ASSESSMENT
-    - Topic shifts: Use verified count of {marker_counts.get('TOPIC_SHIFT', 0)}
-    - Tangential speech: Use verified count of {marker_counts.get('TANGENT', 0)}
-    - Coherence breaks: Use verified count of {marker_counts.get('COHERENCE_BREAK', 0)}
-    - Referential clarity: Use verified count of {marker_counts.get('PRONOUN_REF', 0)}
-    - Overall conversational patterns observed
+    C. Sentence Structure Analysis:
+    - Use calculated MLU: {linguistic_metrics.get('mlu_words', 0)} words, {linguistic_metrics.get('mlu_morphemes', 0)} morphemes
+    - Calculate complexity ratios
 
-    6. VOCABULARY AND SEMANTIC ANALYSIS
-    - Semantic errors: Use verified count of {marker_counts.get('SEMANTIC_ERROR', 0)}
-    - Lexical diversity: Use verified measures from stats summary
-    - Word association patterns from transcript analysis
-    - Semantic precision and appropriateness
+    4. FIGURATIVE LANGUAGE ANALYSIS (with exact counts):
 
-    7. MORPHOLOGICAL AND PHONOLOGICAL ANALYSIS
-    - Morphological complexity assessment
-    - Derivational and inflectional morphology patterns
-    - Error analysis using verified counts
-    - Pattern analysis only
+    A. Similes and Metaphors:
+    - Count [FIGURATIVE] markers for similes (using "like" or "as")
+    - Count [FIGURATIVE] markers for metaphors (direct comparisons)
 
-    8. QUANTITATIVE METRICS AND NLP FEATURES (use ALL verified data)
-    - Total words: {total_words}
-    - Total sentences: {linguistic_metrics.get('total_sentences', 0)}
+    B. Idioms and Non-literal Language:
+    - Count and analyze idiomatic expressions
+    - Assess comprehension and appropriate use
+
+    5. PRAGMATIC LANGUAGE ASSESSMENT (with specific examples):
+
+    A. Discourse Management:
+    - Count [TOPIC_SHIFT] markers: Assess transition appropriateness
+    - Count [TANGENT] markers: Analyze tangential speech patterns
+    - Count [COHERENCE_BREAK] markers: Assess logical flow
+
+    B. Referential Communication:
+    - Count [PRONOUN_REF] markers: Analyze referential clarity
+    - Assess communicative effectiveness
+
+    6. VOCABULARY AND SEMANTIC ANALYSIS (with quantification):
+
+    A. Vocabulary Diversity:
+    - Total words: {linguistic_metrics.get('total_words', 0)}
     - Unique words: {linguistic_metrics.get('unique_words', 0)}
-    - MLU words: {linguistic_metrics.get('mlu_words', 0):.2f}
-    - MLU morphemes: {linguistic_metrics.get('mlu_morphemes', 0):.2f}
-    - All error rates and ratios from verified counts
+    - Type-Token Ratio: {linguistic_metrics.get('type_token_ratio', 0)}
+    - Vocabulary sophistication: {linguistic_metrics.get('vocabulary_sophistication', 0)}
+
+    B. Semantic Relationships:
+    - Analyze word frequency patterns
+    - Assess semantic precision and relationships
+
+    7. MORPHOLOGICAL AND PHONOLOGICAL ANALYSIS (with counts):
 
+    A. Morphological Markers:
+    - Count [MORPH_ERROR] markers and categorize
+    - Analyze morpheme use patterns
+    - Assess morphological complexity
 
+    B. Phonological Patterns:
+    - Identify speech sound patterns from transcript
+    - Assess syllable structure complexity
 
-    CRITICAL: Complete ALL 13 sections using verified data and specific transcript examples.
+    8. COGNITIVE-LINGUISTIC FACTORS (with evidence):
+
+    A. Working Memory:
+    - Assess sentence length complexity using average: {linguistic_metrics.get('avg_sentence_length', 0)} words
+    - Analyze information retention patterns
+
+    B. Processing Efficiency:
+    - Analyze linguistic complexity and word-finding patterns
+    - Assess cognitive demands of language structures
+
+    C. Executive Function:
+    - Count self-correction patterns ([REVISION] markers)
+    - Assess planning and organization in discourse
+
+    9. FLUENCY AND RHYTHM ANALYSIS (with quantification):
+
+    A. Disfluency Patterns:
+    - Total fluency issues: {marker_analysis.get('category_totals', {}).get('fluency_issues', 0)}
+    - Calculate disfluency rate per 100 words
+    - Analyze impact on communication
+
+    B. Language Flow:
+    - Assess sentence length variability: std = {linguistic_metrics.get('sentence_length_std', 0)}
+    - Analyze linguistic markers of hesitation
+
+    10. QUANTITATIVE METRICS:
+    - Total words: {linguistic_metrics.get('total_words', 0)}
+    - Total sentences: {linguistic_metrics.get('total_sentences', 0)}
+    - MLU (words): {linguistic_metrics.get('mlu_words', 0)}
+    - MLU (morphemes): {linguistic_metrics.get('mlu_morphemes', 0)}
+    - Type-Token Ratio: {linguistic_metrics.get('type_token_ratio', 0)}
+    - Grammar error rate: Calculate from marker counts
+    - Vocabulary sophistication ratio: {marker_analysis.get('category_totals', {}).get('vocab_sophistication_ratio', 0):.3f}
+
+    CRITICAL REQUIREMENTS:
+    - Use the provided calculated metrics in your analysis
+    - Provide EXACT counts for every marker type
+    - Calculate precise percentages and show your work
+    - Give specific examples from the transcript
+    - If annotation is incomplete, supplement with analysis of the original transcript
+    - Complete ALL 8 sections - use <CONTINUE> if needed
+    - Focus on objective data only - NO clinical interpretations
     """
     
-    return call_claude_api_with_continuation(final_prompt)
+    return call_claude_api_with_continuation(analysis_prompt)
 
 def full_analysis_pipeline(transcript_content, age, gender, slp_notes, progress_callback=None):
     """Complete pipeline: annotate then analyze with progressive updates"""
@@ -1649,7 +1690,6 @@ def full_analysis_pipeline(transcript_content, age, gender, slp_notes, progress_
     if progress_callback:
         progress_callback("🏷️ Step 1: Annotating transcript with linguistic markers...")
     
-    
     annotated_transcript = annotate_transcript(transcript_content, age, gender, slp_notes)
     
     if annotated_transcript.startswith("❌"):
@@ -1657,7 +1697,7 @@ def full_analysis_pipeline(transcript_content, age, gender, slp_notes, progress_
     
     # Return annotated transcript immediately
     if progress_callback:
-        progress_callback("Step 1 Complete: Annotation finished! Starting analysis...")
+        progress_callback("✅ Step 1 Complete: Annotation finished! Starting analysis...")
     
     # Check if annotation was incomplete
     if annotated_transcript.startswith("⚠️ ANNOTATION INCOMPLETE"):
@@ -1669,12 +1709,12 @@ def full_analysis_pipeline(transcript_content, age, gender, slp_notes, progress_
     # Step 2: Analyze annotated transcript with original as backup
     logger.info("Step 2: Analyzing annotated transcript...")
     if progress_callback:
-        progress_callback("Step 2: Analyzing annotated transcript (this may take several minutes)...")
+        progress_callback("📊 Step 2: Analyzing annotated transcript (this may take several minutes)...")
     
     analysis_result = analyze_with_backup(annotated_transcript, transcript_content, age, gender, slp_notes)
     
     if progress_callback:
-        progress_callback("Analysis Complete!")
+        progress_callback("✅ Analysis Complete!")
     
     return annotated_transcript, analysis_note + analysis_result
 
@@ -1686,7 +1726,7 @@ def progressive_analysis_pipeline(transcript_content, age, gender, slp_notes):
     
     # Step 1: Annotate transcript
     logger.info("Step 1: Annotating transcript with linguistic markers...")
-    yield "", "", "Step 1: Annotating transcript with linguistic markers..."
+    yield "", "", "🏷️ Step 1: Annotating transcript with linguistic markers..."
     
     annotated_transcript = annotate_transcript(transcript_content, age, gender, slp_notes)
     
@@ -1695,19 +1735,19 @@ def progressive_analysis_pipeline(transcript_content, age, gender, slp_notes):
         return
     
     # Return annotated transcript immediately after completion
-    yield annotated_transcript, "", "Step 1 Complete! Starting analysis..."
+    yield annotated_transcript, "", "✅ Step 1 Complete! Starting analysis..."
     
     # Check if annotation was incomplete
     if annotated_transcript.startswith("⚠️ ANNOTATION INCOMPLETE"):
         logger.warning("Annotation incomplete, proceeding with analysis")
-        analysis_note = "Note: Annotation was incomplete. Analysis primarily based on original transcript.\n\n"
-        yield annotated_transcript, "", "Annotation incomplete, continuing with analysis..."
+        analysis_note = "⚠️ Note: Annotation was incomplete. Analysis primarily based on original transcript.\n\n"
+        yield annotated_transcript, "", "⚠️ Annotation incomplete, continuing with analysis..."
     else:
         analysis_note = ""
     
     # Step 2: Analyze annotated transcript
     logger.info("Step 2: Analyzing annotated transcript...")
-    yield annotated_transcript, "", "Step 2: Analyzing annotated transcript (this may take several minutes)..."
+    yield annotated_transcript, "", "📊 Step 2: Analyzing annotated transcript (this may take several minutes)..."
     
     analysis_result = analyze_with_backup(annotated_transcript, transcript_content, age, gender, slp_notes)
     
@@ -1766,9 +1806,10 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
                     lines=3
                 )
                 
-                with gr.Row():
-                    example_btn = gr.Button("Load Example Transcript", variant="secondary", size="sm")
-                    ultimate_analysis_btn = gr.Button("Run Complete Speech Analysis", variant="primary", size="lg")
+                example_btn = gr.Button("📄 Load Example Transcript", variant="secondary", size="sm")
+                
+                # Single main analysis button
+                ultimate_analysis_btn = gr.Button("🚀 Run Complete Speech Analysis", variant="primary", size="lg")
             
             with gr.Column(scale=3):
                 status_display = gr.Markdown("Ready to analyze transcript")
@@ -1787,7 +1828,7 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
                     show_copy_button=True
                 )
     
-    with gr.Tab("Annotation Only"):
+    with gr.Tab("🏷️ Annotation Only"):
         gr.Markdown("### Step 1: Annotate transcript with linguistic markers")
         
         with gr.Row():
@@ -1811,9 +1852,8 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
                     lines=3
                 )
                 
-                with gr.Row():
-                    example_btn_2 = gr.Button("Load Example Transcript", variant="secondary", size="sm")
-                    annotate_btn = gr.Button("Annotate Transcript", variant="secondary")
+                example_btn_2 = gr.Button("📄 Load Example Transcript", variant="secondary", size="sm")
+                annotate_btn = gr.Button("🏷️ Annotate Transcript", variant="secondary")
             
             with gr.Column():
                 annotation_output = gr.Textbox(
@@ -1865,8 +1905,8 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
                     q5_btn = gr.Button("Word finding issues?", size="sm", variant="secondary")
                     q6_btn = gr.Button("Fluency problems?", size="sm", variant="secondary")
                 
-                example_btn_4 = gr.Button("Load Example Transcript", variant="secondary", size="sm")
-                ask_question_btn = gr.Button("Ask Question", variant="primary")
+                example_btn_4 = gr.Button("📄 Load Example Transcript", variant="secondary", size="sm")
+                ask_question_btn = gr.Button("❓ Ask Question", variant="primary")
             
             with gr.Column():
                 question_output = gr.Textbox(
@@ -1875,7 +1915,7 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
                     show_copy_button=True
                 )
     
-    with gr.Tab("Targeted Analysis"):
+    with gr.Tab("🎯 Targeted Analysis"):
         gr.Markdown("### Focus on specific areas of speech and language")
         
         with gr.Row():
@@ -1912,8 +1952,8 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
                     lines=2
                 )
                 
-                example_btn_5 = gr.Button("Load Example Transcript", variant="secondary", size="sm")
-                targeted_analysis_btn = gr.Button("Run Targeted Analysis", variant="primary")
+                example_btn_5 = gr.Button("📄 Load Example Transcript", variant="secondary", size="sm")
+                targeted_analysis_btn = gr.Button("🎯 Run Targeted Analysis", variant="primary")
             
             with gr.Column():
                 targeted_output = gr.Textbox(
@@ -1951,11 +1991,11 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         annotated_transcript = annotate_transcript(transcript_content, age, gender, slp_notes)
         
         if annotated_transcript.startswith("❌"):
-            return annotated_transcript, "Annotation failed"
+            return annotated_transcript, "❌ Annotation failed"
         elif annotated_transcript.startswith("⚠️ ANNOTATION INCOMPLETE"):
-            return annotated_transcript, "Annotation incomplete but proceeding"
+            return annotated_transcript, "⚠️ Annotation incomplete but proceeding"
         else:
-            return annotated_transcript, "Annotation complete! Click 'Run Analysis' to continue."
+            return annotated_transcript, "✅ Annotation complete! Click 'Run Analysis' to continue."
     
     def run_analysis_step(annotated_transcript, original_transcript, age, gender, slp_notes):
         """Run the analysis step on the annotated transcript"""
@@ -1966,12 +2006,11 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         
         # Check if annotation was incomplete
         if annotated_transcript.startswith("⚠️ ANNOTATION INCOMPLETE"):
-            analysis_note = "Note: Annotation was incomplete. Analysis primarily based on original transcript.\n\n"
+            analysis_note = "⚠️ Note: Annotation was incomplete. Analysis primarily based on original transcript.\n\n"
         else:
             analysis_note = ""
         
         analysis_result = analyze_with_backup(annotated_transcript, original_transcript, age, gender, slp_notes)
-        
         return analysis_note + analysis_result
     
     def run_manual_count_only(annotated_transcript):
@@ -2136,12 +2175,8 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         - Repetitions: Use verified count of {marker_counts.get('REPETITION', 0)}
           * Categorize types (word, phrase, sound level)
           * Provide examples and count summary
-        - Revisions: Use verified count of {marker_counts.get('REVISION', 0)}
-          * Analyze self-correction patterns
-        - Pauses: Use verified count of {marker_counts.get('PAUSE', 0)}
-          * Assess hesitation frequency
-        - Total disfluency assessment: Use verified total of {category_totals.get('fluency_issues', 0)} 
-          * Rate: {category_totals.get('fluency_issues', 0)/linguistic_metrics.get('total_words', 1)*100:.2f} per 100 words
+        - Total disfluency assessment: Use verified total of {category_totals['fluency_issues']} 
+          * Rate: {category_totals['fluency_issues']/total_words*100:.2f} per 100 words
           * Provide objective rate calculation
 
         B. Word Retrieval Issues:
@@ -2161,7 +2196,7 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         A. Vocabulary Analysis (use verified data):
         - Simple vocabulary: Use verified count of {marker_counts.get('SIMPLE_VOCAB', 0)}
         - Complex vocabulary: Use verified count of {marker_counts.get('COMPLEX_VOCAB', 0)}
-        - Sophistication ratio: Use verified ratio of {category_totals.get('vocab_sophistication_ratio', 0):.3f}
+        - Sophistication ratio: Use verified ratio of {category_totals['vocab_sophistication_ratio']:.3f}
         - Type-Token Ratio: Use verified TTR from basic metrics
         - Provide examples of each vocabulary level from transcript
 
@@ -2239,7 +2274,7 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         # Step 2: Run analysis
         analysis_result = run_analysis_step(annotated_transcript, transcript_content, age, gender, slp_notes)
         
-        return annotated_transcript, analysis_result, "Complete analysis finished!"
+        return annotated_transcript, analysis_result, "✅ Complete analysis finished!"
     
     def run_complete_speech_analysis(transcript_content, age, gender, slp_notes):
         """Run the complete speech analysis pipeline with ultimate analysis"""
@@ -2255,7 +2290,7 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         # Step 2: Run ultimate analysis
         ultimate_result = run_ultimate_analysis(annotated_transcript, transcript_content, age, gender, slp_notes)
         
-        return annotated_transcript, ultimate_result, "Complete speech analysis finished!"
+        return annotated_transcript, ultimate_result, "✅ Complete speech analysis finished!"
     
     # Single main event handler
     ultimate_analysis_btn.click(
@@ -2284,4 +2319,12 @@ with gr.Blocks(title="Speech Analysis", theme=gr.themes.Soft()) as demo:
         fn=analyze_targeted_area,
         inputs=[transcript_input_5, analysis_area, age_input_5, gender_input_5, slp_notes_input_5],
         outputs=[targeted_output]
+    )
+
+if __name__ == "__main__":
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860,
+        share=True,
+        show_error=True
     )