copy_of_casl_analysis.py

import gradio as gr
import boto3
import json
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import re
import logging
import os
from PIL import Image
import io
import PyPDF2
from datetime import datetime

# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

# AWS credentials for Bedrock API
# For HuggingFace Spaces, set these as secrets in the Space settings
AWS_ACCESS_KEY = os.getenv("AWS_ACCESS_KEY", "")
AWS_SECRET_KEY = os.getenv("AWS_SECRET_KEY", "")
AWS_REGION = os.getenv("AWS_REGION", "us-east-1")

# Initialize Bedrock client if credentials are available
bedrock_client = None
if AWS_ACCESS_KEY and AWS_SECRET_KEY:
    try:
        bedrock_client = boto3.client(
            'bedrock-runtime',
            aws_access_key_id=AWS_ACCESS_KEY,
            aws_secret_access_key=AWS_SECRET_KEY,
            region_name=AWS_REGION
        )
        logger.info("Bedrock client initialized successfully")
    except Exception as e:
        logger.error(f"Failed to initialize Bedrock client: {str(e)}")

# Sample transcript for the demo
SAMPLE_TRANSCRIPT = """*PAR: today I would &-um like to talk about &-um a fun trip I took last &-um summer with my family.
*PAR: we went to the &-um &-um beach [//] no to the mountains [//] I mean the beach actually.
*PAR: there was lots of &-um &-um swimming and &-um sun.
*PAR: we [/] we stayed for &-um three no [//] four days in a &-um hotel near the water [: ocean] [*].
*PAR: my favorite part was &-um building &-um castles with sand.
*PAR: sometimes I forget [//] forgetted [: forgot] [*] what they call those things we built.
*PAR: my brother he [//] he helped me dig a big hole.
*PAR: we saw [/] saw fishies [: fish] [*] swimming in the water.
*PAR: sometimes I wonder [/] wonder where fishies [: fish] [*] go when it's cold.
*PAR: maybe they have [/] have houses under the water.
*PAR: after swimming we [//] I eat [: ate] [*] &-um ice cream with &-um chocolate things on top.
*PAR: what do you call those &-um &-um sprinkles! that's the word.
*PAR: my mom said to &-um that I could have &-um two scoops next time.
*PAR: I want to go back to the beach [/] beach next year."""

# ===============================
# Utility Functions
# ===============================

def read_pdf(file_path):
    """Read text from a PDF file"""
    try:
        with open(file_path, 'rb') as file:
            pdf_reader = PyPDF2.PdfReader(file)
            text = ""
            for page in pdf_reader.pages:
                text += page.extract_text()
            return text
    except Exception as e:
        logger.error(f"Error reading PDF: {str(e)}")
        return ""

def process_upload(file):
    """Process an uploaded file (PDF or text)"""
    if file is None:
        return ""
    
    file_path = file.name
    if file_path.endswith('.pdf'):
        return read_pdf(file_path)
    else:
        with open(file_path, 'r', encoding='utf-8', errors='ignore') as f:
            return f.read()

# ===============================
# AI Model Interface Functions
# ===============================

def call_bedrock(prompt, max_tokens=4096):
    """Call the AWS Bedrock API to analyze text using Claude"""
    if not bedrock_client:
        return "AWS credentials not configured. Please set your AWS credentials as secrets in the Space settings."
    
    try:
        body = json.dumps({
            "anthropic_version": "bedrock-2023-05-31",
            "max_tokens": max_tokens,
            "messages": [
                {
                    "role": "user",
                    "content": prompt
                }
            ],
            "temperature": 0.3,
            "top_p": 0.9
        })

        modelId = 'anthropic.claude-3-sonnet-20240229-v1:0'
        response = bedrock_client.invoke_model(
            body=body, 
            modelId=modelId, 
            accept='application/json', 
            contentType='application/json'
        )
        response_body = json.loads(response.get('body').read())
        return response_body['content'][0]['text']
    except Exception as e:
        logger.error(f"Error in call_bedrock: {str(e)}")
        return f"Error: {str(e)}"

def generate_demo_response(prompt):
    """Generate a simulated response for demo purposes"""
    # This function generates a realistic but fake response for demo purposes
    # In a real deployment, you would call an actual LLM API
    
    random_seed = sum(ord(c) for c in prompt) % 1000  # Generate a seed based on prompt
    np.random.seed(random_seed)
    
    # Simulate speech factors with random but reasonable values
    factors = [
        "Difficulty producing fluent speech",
        "Word retrieval issues",
        "Grammatical errors",
        "Repetitions and revisions",
        "Neologisms",
        "Perseveration",
        "Comprehension issues"
    ]
    
    occurrences = np.random.randint(1, 15, size=len(factors))
    percentiles = np.random.randint(30, 95, size=len(factors))
    
    # Simulate CASL scores
    domains = ["Lexical/Semantic", "Syntactic", "Supralinguistic"]
    scores = np.random.randint(80, 115, size=3)
    percentiles_casl = [int(np.interp(s, [70, 85, 100, 115, 130], [2, 16, 50, 84, 98])) for s in scores]
    
    perf_levels = []
    for s in scores:
        if s < 70: perf_levels.append("Well Below Average")
        elif s < 85: perf_levels.append("Below Average")
        elif s < 115: perf_levels.append("Average")
        elif s < 130: perf_levels.append("Above Average")
        else: perf_levels.append("Well Above Average")
    
    # Build response
    response = "## Speech Factor Analysis\n\n"
    for i, factor in enumerate(factors):
        response += f"{factor}: {occurrences[i]}, {percentiles[i]}\n"
    
    response += "\n## CASL-2 Assessment\n\n"
    for i, domain in enumerate(domains):
        response += f"{domain} Skills: Standard Score ({scores[i]}), Percentile Rank ({percentiles_casl[i]}%), Performance Level ({perf_levels[i]})\n"
    
    response += "\n## Other analysis/Best plans of action:\n\n"
    suggestions = [
        "Implement word-finding strategies with semantic cuing",
        "Practice structured narrative tasks with visual supports",
        "Use sentence formulation exercises with increasing complexity",
        "Incorporate self-monitoring techniques during structured conversations",
        "Work on grammatical forms through structured practice"
    ]
    for suggestion in suggestions:
        response += f"- {suggestion}\n"
    
    response += "\n## Explanation:\n\n"
    response += "Based on the analysis, this patient demonstrates moderate word-finding difficulties with compensatory strategies like filler words and repetitions. Their syntactic skills show some weakness in verb tense consistency. Treatment should focus on building vocabulary access, grammatical accuracy, and narrative structure using scaffolded support.\n"
    
    response += "\n## Additional Analysis:\n\n"
    response += "The patient shows relative strengths in conversation maintenance and topic coherence. Consider building on these strengths while addressing specific language formulation challenges. Recommended frequency: 2-3 sessions per week for 10-12 weeks with periodic reassessment."
    
    return response

def generate_demo_transcription(audio_path):
    """Generate a simulated transcription response"""
    # In a real app, this would process an audio file
    return "*PAR: today I want to tell you about my favorite toy.\n*PAR: it's a &-um teddy bear that I got for my birthday.\n*PAR: he has &-um brown fur and a red bow.\n*PAR: I like to sleep with him every night.\n*PAR: sometimes I take him to school in my backpack."

def generate_demo_qa_response(question):
    """Generate a simulated Q&A response"""
    qa_responses = {
        "what is casl": "CASL-2 (Comprehensive Assessment of Spoken Language, Second Edition) is a standardized assessment tool used by Speech-Language Pathologists to evaluate a child's oral language abilities across multiple domains including lexical/semantic, syntactic, and supralinguistic skills. It helps identify language disorders and guides intervention planning.",
        "how do i interpret scores": "CASL-2 scores include standard scores (mean=100, SD=15), percentile ranks, and performance levels. Standard scores below 85 indicate below average performance, 85-115 is average, and above 115 is above average. Percentile ranks show how a child performs relative to same-age peers.",
        "what activities help word finding": "Activities to improve word-finding skills include semantic feature analysis (describing attributes of objects), categorization tasks, word association games, rapid naming practice, and structured conversation with gentle cueing. Visual supports and semantic mapping can also be helpful.",
        "how often should therapy occur": "The recommended frequency for speech-language therapy typically ranges from 1-3 sessions per week, depending on the severity of the impairment. For moderate difficulties, twice weekly sessions of 30-45 minutes are common. Consistency is important for progress.",
        "when should i reassess": "Reassessment is typically recommended every 3-6 months to track progress and adjust treatment goals. For educational settings, annual reassessment is common. More frequent informal assessments can help guide ongoing intervention.",
    }
    
    # Simple keyword matching for demo purposes
    for key, response in qa_responses.items():
        if key in question.lower():
            return response
    
    return "I don't have specific information about that topic. For detailed professional guidance, consult with a licensed Speech-Language Pathologist who can provide advice specific to your situation."

# ===============================
# Analysis Functions
# ===============================

def parse_casl_response(response):
    """Parse the LLM response for CASL analysis into structured data"""
    lines = response.split('\n')
    data = {
        'Factor': [],
        'Occurrences': [],
        'Severity': []
    }
    
    casl_data = {
        'Domain': ['Lexical/Semantic', 'Syntactic', 'Supralinguistic'],
        'Standard Score': [0, 0, 0],
        'Percentile': [0, 0, 0],
        'Performance Level': ['', '', '']
    }
    
    treatment_suggestions = []
    explanation = ""
    additional_analysis = ""
    
    # Pattern to match factor lines
    factor_pattern = re.compile(r'([\w\s/]+):\s*(\d+)[,\s]+(\d+)')
    
    # Pattern to match CASL data
    casl_pattern = re.compile(r'(\w+/?\w*)\s+Skills:\s+Standard\s+Score\s+\((\d+)\),\s+Percentile\s+Rank\s+\((\d+)%\),\s+Performance\s+Level\s+\(([\w\s]+)\)')
    
    in_suggestions = False
    in_explanation = False
    in_additional = False
    
    for line in lines:
        line = line.strip()
        
        # Skip empty lines
        if not line:
            continue
            
        # Check for factor data
        factor_match = factor_pattern.search(line)
        if factor_match:
            factor = factor_match.group(1).strip()
            occurrences = int(factor_match.group(2))
            severity = int(factor_match.group(3))
            
            data['Factor'].append(factor)
            data['Occurrences'].append(occurrences)
            data['Severity'].append(severity)
            continue
            
        # Check for CASL data
        casl_match = casl_pattern.search(line)
        if casl_match:
            domain = casl_match.group(1)
            score = int(casl_match.group(2))
            percentile = int(casl_match.group(3))
            level = casl_match.group(4)
            
            if "Lexical" in domain:
                casl_data['Standard Score'][0] = score
                casl_data['Percentile'][0] = percentile
                casl_data['Performance Level'][0] = level
            elif "Syntactic" in domain:
                casl_data['Standard Score'][1] = score
                casl_data['Percentile'][1] = percentile
                casl_data['Performance Level'][1] = level
            elif "Supralinguistic" in domain:
                casl_data['Standard Score'][2] = score
                casl_data['Percentile'][2] = percentile
                casl_data['Performance Level'][2] = level
            continue
        
        # Check for section headers
        if "Other analysis/Best plans of action:" in line or "### Recommended Treatment Approaches" in line:
            in_suggestions = True
            in_explanation = False
            in_additional = False
            continue
        elif "Explanation:" in line or "### Clinical Rationale" in line:
            in_suggestions = False
            in_explanation = True
            in_additional = False
            continue
        elif "Additional Analysis:" in line:
            in_suggestions = False
            in_explanation = False
            in_additional = True
            continue
            
        # Add content to appropriate section
        if in_suggestions and line.startswith("- "):
            treatment_suggestions.append(line[2:])  # Remove the bullet point
        elif in_explanation:
            explanation += line + "\n"
        elif in_additional:
            additional_analysis += line + "\n"
    
    return {
        'speech_factors': pd.DataFrame(data),
        'casl_data': pd.DataFrame(casl_data),
        'treatment_suggestions': treatment_suggestions,
        'explanation': explanation,
        'additional_analysis': additional_analysis
    }

def create_casl_plots(speech_factors, casl_data):
    """Create visualizations for the CASL analysis results"""
    
    # Set a professional style for the plots
    plt.style.use('seaborn-v0_8-pastel')
    
    # Create figure with two subplots
    fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(14, 6), dpi=100)
    
    # Plot speech factors - sorted by occurrence count
    if not speech_factors.empty:
        # Sort the dataframe
        speech_factors_sorted = speech_factors.sort_values('Occurrences', ascending=False)
        
        # Custom colors
        speech_colors = ['#4C72B0', '#55A868', '#C44E52', '#8172B3', '#CCB974', '#64B5CD', '#4C72B0']
        
        # Create horizontal bar chart
        bars = ax1.barh(speech_factors_sorted['Factor'], 
               speech_factors_sorted['Occurrences'], 
               color=speech_colors[:len(speech_factors_sorted)])
        
        # Add count labels at the end of each bar
        for bar in bars:
            width = bar.get_width()
            ax1.text(width + 0.3, bar.get_y() + bar.get_height()/2, 
                    f'{width:.0f}', ha='left', va='center')
        
        ax1.set_title('Speech Factors Analysis', fontsize=14, fontweight='bold')
        ax1.set_xlabel('Number of Occurrences', fontsize=11)
        # No y-label needed for horizontal bar chart
        
        # Remove top and right spines
        ax1.spines['top'].set_visible(False)
        ax1.spines['right'].set_visible(False)
    
    # Plot CASL domains
    domain_names = casl_data['Domain']
    y_scores = casl_data['Standard Score']
    
    # Custom color scheme
    casl_colors = ['#4C72B0', '#55A868', '#C44E52']
    
    # Create bars with nice colors
    bars = ax2.bar(domain_names, y_scores, color=casl_colors)
    
    # Add score labels on top of each bar
    for bar in bars:
        height = bar.get_height()
        ax2.text(bar.get_x() + bar.get_width()/2., height + 1,
                f'{height:.0f}', ha='center', va='bottom')
    
    # Add score reference lines
    ax2.axhline(y=100, linestyle='--', color='gray', alpha=0.7, label='Average (100)')
    ax2.axhline(y=85, linestyle=':', color='orange', alpha=0.7, label='Below Average (<85)')
    ax2.axhline(y=115, linestyle=':', color='green', alpha=0.7, label='Above Average (>115)')
    
    # Add labels and title
    ax2.set_title('CASL-2 Standard Scores', fontsize=14, fontweight='bold')
    ax2.set_ylabel('Standard Score', fontsize=11)
    ax2.set_ylim(bottom=0, top=max(130, max(y_scores) + 15))  # Set y-axis limit with some padding
    
    # Add legend
    ax2.legend(loc='upper right', fontsize='small')
    
    # Remove top and right spines
    ax2.spines['top'].set_visible(False)
    ax2.spines['right'].set_visible(False)
    
    plt.tight_layout()
    
    # Save plot to buffer
    buf = io.BytesIO()
    plt.savefig(buf, format='png', bbox_inches='tight')
    buf.seek(0)
    plt.close()
    
    return buf

def create_casl_radar_chart(speech_factors):
    """Create a radar chart for speech factors (percentiles)"""
    
    if speech_factors.empty or 'Severity' not in speech_factors.columns:
        # Create a placeholder image if no data
        plt.figure(figsize=(8, 8))
        plt.text(0.5, 0.5, "No data available for radar chart", 
                ha='center', va='center', fontsize=14)
        plt.axis('off')
        
        buf = io.BytesIO()
        plt.savefig(buf, format='png')
        buf.seek(0)
        plt.close()
        return buf
    
    # Prepare data for radar chart
    categories = speech_factors['Factor'].tolist()
    percentiles = speech_factors['Severity'].tolist()
    
    # Need to repeat first value to close the polygon
    categories = categories + [categories[0]]
    percentiles = percentiles + [percentiles[0]]
    
    # Convert to radians and calculate points
    N = len(categories) - 1  # Subtract 1 for the repeated point
    angles = [n / float(N) * 2 * np.pi for n in range(N)]
    angles += angles[:1]  # Repeat the first angle to close the polygon
    
    # Create the plot
    fig = plt.figure(figsize=(8, 8))
    ax = fig.add_subplot(111, polar=True)
    
    # Draw percentile lines with labels
    plt.xticks(angles[:-1], categories[:-1], size=12)
    ax.set_rlabel_position(0)
    plt.yticks([20, 40, 60, 80, 100], ["20", "40", "60", "80", "100"], color="grey", size=10)
    plt.ylim(0, 100)
    
    # Plot data
    ax.plot(angles, percentiles, linewidth=1, linestyle='solid', color='#4C72B0')
    ax.fill(angles, percentiles, color='#4C72B0', alpha=0.25)
    
    # Add title
    plt.title('Speech Factors Severity (Percentile)', size=15, fontweight='bold', pad=20)
    
    # Save to buffer
    buf = io.BytesIO()
    plt.savefig(buf, format='png', bbox_inches='tight')
    buf.seek(0)
    plt.close()
    
    return buf

def analyze_transcript(transcript, age, gender):
    """Analyze a speech transcript using the CASL framework"""
    
    # Instructions for the LLM analysis
    instructions = """
    You're a professional Speech-Language Pathologist analyzing this transcription sample.
    
    For your analysis, count occurrences of:
    
    1. Difficulty producing fluent, grammatical speech - Speech that is slow, halting, with pauses while searching for words
    2. Word retrieval issues - Trouble finding specific words, using fillers like "um", circumlocution, or semantically similar substitutions
    3. Grammatical errors - Missing/incorrect function words, verb tense problems, simplified sentences
    4. Repetitions and revisions - Repeating or restating due to word-finding or sentence construction difficulties
    5. Neologisms - Creating nonexistent "new" words
    6. Perseveration - Unintentionally repeating words or phrases
    7. Comprehension issues - Difficulty understanding complex sentences or fast speech
    
    Analyze using the CASL-2 (Comprehensive Assessment of Spoken Language) framework:
    
    Lexical/Semantic Skills:
    - Evaluate vocabulary diversity, word retrieval difficulties, and semantic precision
    - Estimate Standard Score (mean=100, SD=15), percentile rank, and performance level
    
    Syntactic Skills:
    - Assess sentence structure, grammatical accuracy, and syntactic complexity
    - Estimate Standard Score, percentile rank, and performance level
    
    Supralinguistic Skills:
    - Evaluate figurative language use, inferencing, and contextual understanding
    - Estimate Standard Score, percentile rank, and performance level
    
    Format your analysis with:
    1. Speech factor counts with severity percentiles
    2. CASL-2 domain scores with performance levels
    3. Treatment recommendations based on findings
    4. Brief explanation of your rationale
    5. Any additional insights
    """
    
    # Prepare prompt for Claude
    prompt = f"""
    You are an experienced Speech-Language Pathologist analyzing this transcript for a patient who is {age} years old and {gender}.
    
    TRANSCRIPT:
    {transcript}
    
    {instructions}
    
    Be precise, professional, and empathetic in your analysis. Focus on the linguistic patterns present in the sample.
    """
    
    # Call the appropriate API or fallback to demo mode
    if bedrock_client:
        response = call_bedrock(prompt)
    else:
        response = generate_demo_response(prompt)
    
    # Parse the response
    results = parse_casl_response(response)
    
    # Create visualizations
    plot_image = create_casl_plots(results['speech_factors'], results['casl_data'])
    radar_image = create_casl_radar_chart(results['speech_factors'])
    
    return results, plot_image, radar_image, response

def generate_report(patient_info, analysis_results, report_type="formal"):
    """Generate a professional report based on analysis results"""
    
    patient_name = patient_info.get("name", "")
    record_id = patient_info.get("record_id", "")
    age = patient_info.get("age", "")
    gender = patient_info.get("gender", "")
    assessment_date = patient_info.get("assessment_date", datetime.now().strftime('%m/%d/%Y'))
    clinician = patient_info.get("clinician", "")
    
    prompt = f"""
    You are a professional Speech-Language Pathologist creating a {report_type} report based on an assessment.
    
    PATIENT INFORMATION:
    Name: {patient_name}
    Record ID: {record_id}
    Age: {age}
    Gender: {gender}
    Assessment Date: {assessment_date}
    Clinician: {clinician}
    
    ASSESSMENT RESULTS:
    {analysis_results}
    
    Please create a professional {report_type} report that includes:
    1. Patient information and assessment details
    2. Summary of findings (strengths and areas of concern)
    3. Detailed analysis of language domains
    4. Specific recommendations for therapy
    5. Recommendation for frequency and duration of services
    
    Use clear, professional language appropriate for {'educational professionals' if report_type == 'formal' else 'parents and caregivers'}.
    Format the report with proper headings and sections.
    """
    
    # Call the API or use demo mode
    if bedrock_client:
        report = call_bedrock(prompt, max_tokens=6000)
    else:
        # For demo, create a simulated report
        if report_type == 'formal':
            report = f"""
            # FORMAL LANGUAGE ASSESSMENT REPORT
            
            **Date of Assessment:** {assessment_date}
            **Clinician:** {clinician}
            
            ## PATIENT INFORMATION
            **Name:** {patient_name}
            **Record ID:** {record_id}
            **Age:** {age}
            **Gender:** {gender}
            
            ## ASSESSMENT SUMMARY
            
            The patient was assessed using the Comprehensive Assessment of Spoken Language, Second Edition (CASL-2) to evaluate language skills across multiple domains. The assessment involved language sample analysis and standardized testing.
            
            ## KEY FINDINGS
            
            **Areas of Strength:**
            - Ability to maintain conversational topics 
            - Good vocabulary for everyday topics
            - Strong nonverbal communication skills
            
            **Areas of Challenge:**
            - Word-finding difficulties during conversation
            - Grammatical errors in complex sentences
            - Difficulty with abstract language concepts
            
            ## DETAILED ANALYSIS
            
            **Lexical/Semantic Skills:** Standard Score 91 (27th percentile) - Low Average Range
            The student demonstrates adequate vocabulary but struggles with retrieving specific words during conversation. Word-finding pauses were noted throughout the language sample.
            
            **Syntactic Skills:** Standard Score 85 (16th percentile) - Low Average Range
            The student shows difficulty with complex grammatical structures, particularly verb tense consistency and complex sentence formation.
            
            **Supralinguistic Skills:** Standard Score 83 (13th percentile) - Below Average Range
            The student struggles with understanding figurative language, making inferences, and comprehending abstract concepts.
            
            ## RECOMMENDATIONS
            
            1. Speech-Language Therapy focused on:
               - Word-finding strategies using semantic feature analysis
               - Structured grammatical exercises to improve sentence complexity
               - Explicit instruction in figurative language comprehension
               - Narrative language development using visual supports
            
            2. Frequency of service: Twice weekly sessions of 30 minutes each for 12 weeks, followed by a reassessment to measure progress.
            
            3. Classroom accommodations including:
               - Extended time for verbal responses
               - Visual supports for complex instructions
               - Pre-teaching of vocabulary for academic units
            
            ## PROGNOSIS
            
            The prognosis for improvement is good with consistent therapeutic intervention and support. Regular reassessment is recommended to monitor progress.
            
            Respectfully submitted,
            
            {clinician}
            Speech-Language Pathologist
            """
        else:
            report = f"""
            # PARENT-FRIENDLY LANGUAGE ASSESSMENT SUMMARY
            
            **Date of Assessment:** {assessment_date}
            **Clinician:** {clinician}
            
            ## PATIENT INFORMATION
            **Name:** {patient_name}
            **Record ID:** {record_id}
            **Age:** {age}
            **Gender:** {gender}
            
            ## ASSESSMENT SUMMARY
            
            We completed a language assessment to better understand your child's communication strengths and challenges. This helps us create a plan to support their development.
            
            ## KEY FINDINGS
            
            **Areas of Strength:**
            - Ability to maintain conversational topics 
            - Good vocabulary for everyday topics
            - Strong nonverbal communication skills
            
            **Areas of Challenge:**
            - Word-finding difficulties during conversation
            - Grammatical errors in complex sentences
            - Difficulty with abstract language concepts
            
            ## DETAILED ANALYSIS
            
            **Lexical/Semantic Skills:** Standard Score 91 (27th percentile) - Low Average Range
            The student demonstrates adequate vocabulary but struggles with retrieving specific words during conversation. Word-finding pauses were noted throughout the language sample.
            
            **Syntactic Skills:** Standard Score 85 (16th percentile) - Low Average Range
            The student shows difficulty with complex grammatical structures, particularly verb tense consistency and complex sentence formation.
            
            **Supralinguistic Skills:** Standard Score 83 (13th percentile) - Below Average Range
            The student struggles with understanding figurative language, making inferences, and comprehending abstract concepts.
            
            ## RECOMMENDATIONS
            
            We recommend:
               - Word-finding strategies using semantic feature analysis
               - Structured grammatical exercises to improve sentence complexity
               - Explicit instruction in figurative language comprehension
               - Narrative language development using visual supports
            
            2. We recommend therapy twice a week for 30 minutes. This consistency will help your child make better progress.
            
            3. In school, your child may benefit from:
               - Extended time for verbal responses
               - Visual supports for complex instructions
               - Pre-teaching of vocabulary for academic units
            
            ## PROGNOSIS
            
            With regular therapy and support at home, we expect your child to make good progress in these areas.
            
            Please reach out with any questions!
            
            {clinician}
            Speech-Language Pathologist
            """
    
    return report

def transcribe_audio(audio_path, patient_age):
    """Transcribe an audio recording using CHAT format"""
    # In a real implementation, this would use a speech-to-text service
    # For demo purposes, we'll return a simulated transcription
    
    if bedrock_client:
        # In a real implementation, you would process the audio file and send it to a transcription service
        # Here we just simulate the result
        transcription = generate_demo_transcription(audio_path)
    else:
        transcription = generate_demo_transcription(audio_path)
    
    return transcription

def answer_slp_question(question):
    """Answer a question about SLP practice or CASL assessment"""
    
    prompt = f"""
    You are an experienced Speech-Language Pathologist answering a question from a colleague.
    
    QUESTION:
    {question}
    
    Please provide a clear, evidence-based answer focused specifically on the question asked.
    Reference best practices and current research where appropriate.
    Keep your answer concise but comprehensive.
    """
    
    if bedrock_client:
        answer = call_bedrock(prompt)
    else:
        answer = generate_demo_qa_response(question)
    
    return answer

# ===============================
# Gradio Interface
# ===============================

def create_interface():
    """Create the main Gradio interface"""
    
    # Use a simple theme with default colors
    custom_theme = gr.themes.Soft(
        font=[gr.themes.GoogleFont("Inter"), "system-ui", "sans-serif"]
    )
    
    with gr.Blocks(theme=custom_theme, css="""
        .header {
            text-align: center;
            margin-bottom: 20px;
        }
        .header img {
            max-height: 100px;
            margin-bottom: 10px;
        }
        .container {
            border-radius: 10px;
            padding: 10px;
            margin-bottom: 20px;
        }
        .patient-info {
            background-color: #e3f2fd;
        }
        .speech-sample {
            background-color: #f0f8ff;
        }
        .results-container {
            background-color: #f9f9f9; 
        }
        .viz-container {
            display: flex;
            justify-content: center;
            margin-bottom: 20px;
        }
        .footer {
            text-align: center;
            margin-top: 30px;
            padding: 10px;
            font-size: 0.8em;
            color: #78909C;
        }
        .info-box {
            background-color: #e8f5e9;
            border-left: 4px solid #4CAF50;
            padding: 10px 15px;
            margin-bottom: 15px;
            border-radius: 4px;
        }
        .warning-box {
            background-color: #fff8e1;
            border-left: 4px solid #FFC107;
            padding: 10px 15px;
            border-radius: 4px;
        }
        .markdown-text h3 {
            color: #2C7FB8;
            border-bottom: 1px solid #eaeaea;
            padding-bottom: 5px;
        }
        .evidence-table {
            border-collapse: collapse;
            width: 100%;
        }
        .evidence-table th, .evidence-table td {
            border: 1px solid #ddd;
            padding: 8px;
            text-align: left;
        }
        .evidence-table th {
            background-color: #f5f7fa;
            color: #333;
        }
        .evidence-table tr:nth-child(even) {
            background-color: #f9f9f9;
        }
        .tab-content {
            padding: 15px;
            background-color: white;
            border-radius: 0 0 8px 8px;
            box-shadow: 0 2px 5px rgba(0,0,0,0.05);
        }
    """) as app:
        # Create header with logo
        gr.HTML(
            """
            <div class="header">
                <h1>SLP Analysis Tool</h1>
                <p>A comprehensive assessment tool for Speech-Language Pathologists</p>
            </div>
            """
        )
        
        # Main tabs
        with gr.Tabs() as main_tabs:
            # ===============================
            # CASL Analysis Tab
            # ===============================
            with gr.TabItem("CASL Analysis", id=0):
                with gr.Row():
                    # Left column - Input section
                    with gr.Column(scale=1):
                        # Patient information panel
                        with gr.Group(elem_classes="container patient-info"):
                            gr.Markdown("### Patient Information")
                            
                            with gr.Row():
                                patient_name = gr.Textbox(label="Patient Name", placeholder="Enter patient name")
                                record_id = gr.Textbox(label="Record ID", placeholder="Enter record ID")
                            
                            with gr.Row():
                                age = gr.Number(label="Age", value=8, minimum=1, maximum=120)
                                gender = gr.Radio(["male", "female", "other"], label="Gender", value="male")
                            
                            with gr.Row():
                                assessment_date = gr.Textbox(
                                    label="Assessment Date", 
                                    placeholder="MM/DD/YYYY", 
                                    value=datetime.now().strftime('%m/%d/%Y')
                                )
                                clinician_name = gr.Textbox(
                                    label="Clinician", 
                                    placeholder="Enter clinician name"
                                )
                        
                        # Speech sample panel
                        with gr.Group(elem_classes="container speech-sample"):
                            gr.Markdown("### Speech Sample")
                            
                            # Sample button
                            sample_btn = gr.Button("Load Sample Transcript", size="sm")
                            
                            # Transcript input
                            transcript = gr.Textbox(
                                label="Transcript", 
                                placeholder="Paste the speech transcript here...",
                                lines=10
                            )
                            
                            # Add info about transcript format
                            gr.Markdown(
                                """
                                <div class="info-box">
                                    <strong>Transcript Format:</strong> Use CHAT format with *PAR: for patient lines. 
                                    Mark word-finding with &-um, paraphasias with [*], and provide intended words with [: word].
                                </div>
                                """,
                                elem_classes="markdown-text"
                            )
                            
                            # File upload
                            file_upload = gr.File(
                                label="Or upload a transcript file", 
                                file_types=["text", "txt", "pdf", "rtf"]
                            )
                            
                            # Analysis button
                            analyze_btn = gr.Button("Analyze Speech Sample", variant="primary", size="lg")
                    
                    # Right column - Results section
                    with gr.Column(scale=1):
                        with gr.Group(elem_classes="container results-container"):
                            with gr.Tabs() as results_tabs:
                                # Summary tab
                                with gr.TabItem("Summary", id=0, elem_classes="tab-content"):
                                    with gr.Row():
                                        output_image = gr.Image(
                                            label="Speech Factors & CASL-2 Scores", 
                                            show_label=True, 
                                            elem_classes="viz-container"
                                        )
                                    
                                    with gr.Row():
                                        radar_chart = gr.Image(
                                            label="Severity Profile", 
                                            show_label=True, 
                                            elem_classes="viz-container"
                                        )
                                        
                                    with gr.Group():
                                        gr.Markdown("### Key Findings", elem_classes="markdown-text")
                                        speech_factors_table = gr.DataFrame(
                                            label="Speech Factors Analysis", 
                                            headers=["Factor", "Occurrences", "Severity (Percentile)"],
                                            interactive=False
                                        )
                                        casl_table = gr.DataFrame(
                                            label="CASL-2 Assessment", 
                                            headers=["Domain", "Standard Score", "Percentile", "Performance Level"],
                                            interactive=False
                                        )
                                
                                # Treatment tab
                                with gr.TabItem("Treatment Plan", id=1, elem_classes="tab-content"):
                                    gr.Markdown("### Recommended Treatment Approaches", elem_classes="markdown-text")
                                    treatment_md = gr.Markdown(elem_classes="treatment-panel")
                                    
                                    gr.Markdown("### Clinical Rationale", elem_classes="markdown-text")
                                    explanation_md = gr.Markdown(elem_classes="panel")
                                    
                                    with gr.Accordion("Supporting Evidence", open=False):
                                        gr.Markdown("""
                                        <table class="evidence-table">
                                          <tr>
                                            <th>Factor</th>
                                            <th>Evidence-based Approaches</th>
                                            <th>References</th>
                                          </tr>
                                          <tr>
                                            <td>Word Retrieval</td>
                                            <td>Semantic feature analysis, phonological cueing, word generation tasks</td>
                                            <td>Boyle, 2010; Kiran & Thompson, 2003</td>
                                          </tr>
                                          <tr>
                                            <td>Grammatical Errors</td>
                                            <td>Treatment of Underlying Forms (TUF), Morphosyntactic therapy</td>
                                            <td>Thompson et al., 2003; Ebbels, 2014</td>
                                          </tr>
                                          <tr>
                                            <td>Fluency/Prosody</td>
                                            <td>Rate control, rhythmic cueing, contrastive stress exercises</td>
                                            <td>Ballard et al., 2010; Tamplin & Baker, 2017</td>
                                          </tr>
                                        </table>
                                        """, elem_classes="markdown-text")
                                
                                # Full report tab
                                with gr.TabItem("Full Report", id=2, elem_classes="tab-content"):
                                    full_analysis = gr.Markdown()
                                    
                                    # Add PDF export option
                                    export_btn = gr.Button("Export Report as PDF", variant="secondary")
                                    export_status = gr.Markdown("")
            
            # ===============================
            # Report Generator Tab
            # ===============================
            with gr.TabItem("Report Generator", id=1):
                with gr.Row():
                    with gr.Column(scale=1):
                        gr.Markdown("### Generate Professional Reports")
                        
                        # Patient info
                        with gr.Group(elem_classes="container patient-info"):
                            gr.Markdown("#### Patient Information")
                            report_patient_name = gr.Textbox(label="Patient Name", placeholder="Enter patient name")
                            report_record_id = gr.Textbox(label="Record ID", placeholder="Enter record ID")
                            report_age = gr.Number(label="Age", value=8, minimum=1, maximum=120)
                            report_gender = gr.Radio(["male", "female", "other"], label="Gender", value="male")
                            report_date = gr.Textbox(
                                label="Assessment Date", 
                                placeholder="MM/DD/YYYY", 
                                value=datetime.now().strftime('%m/%d/%Y')
                            )
                            report_clinician = gr.Textbox(label="Clinician", placeholder="Enter clinician name")
                        
                        with gr.Group():
                            gr.Markdown("#### Assessment Results")
                            report_results = gr.Textbox(
                                label="Paste assessment results or notes here", 
                                placeholder="Include key findings, test scores, and observations...",
                                lines=10
                            )
                            
                            report_type = gr.Radio(
                                ["Formal (for professionals)", "Parent-friendly"], 
                                label="Report Type",
                                value="Formal (for professionals)"
                            )
                            
                            generate_report_btn = gr.Button("Generate Report", variant="primary")
                    
                    with gr.Column(scale=1):
                        report_output = gr.Markdown()
                        report_download_btn = gr.Button("Download Report as PDF", variant="secondary")
                        report_download_status = gr.Markdown("")
            
            # ===============================
            # Transcription Tool Tab
            # ===============================
            with gr.TabItem("Transcription Tool", id=2):
                with gr.Row():
                    with gr.Column(scale=1):
                        gr.Markdown("### Audio Transcription Tool")
                        gr.Markdown("Upload an audio recording to automatically transcribe it in CHAT format.")
                        
                        audio_input = gr.Audio(type="filepath", label="Upload Audio Recording")
                        
                        with gr.Row():
                            transcription_age = gr.Number(label="Patient Age", value=8, minimum=1, maximum=120)
                            transcribe_btn = gr.Button("Transcribe Audio", variant="primary")
                    
                    with gr.Column(scale=1):
                        transcription_output = gr.Textbox(
                            label="Transcription Result", 
                            placeholder="Transcription will appear here...",
                            lines=12
                        )
                        
                        with gr.Row():
                            copy_to_analysis_btn = gr.Button("Use for Analysis", variant="secondary")
                            edit_transcription_btn = gr.Button("Edit Transcription", variant="secondary")
            
            # ===============================
            # SLP Assistant Tab
            # ===============================
            with gr.TabItem("SLP Assistant", id=3):
                with gr.Row():
                    with gr.Column(scale=1):
                        gr.Markdown("### SLP Knowledge Assistant")
                        gr.Markdown("Ask questions about CASL assessment, therapy techniques, or SLP best practices.")
                        
                        question_input = gr.Textbox(
                            label="Your Question", 
                            placeholder="e.g., What activities help improve word-finding skills?",
                            lines=3
                        )
                        
                        ask_question_btn = gr.Button("Ask Question", variant="primary")
                        
                        # Quick question buttons
                        gr.Markdown("#### Common Questions")
                        with gr.Row():
                            q1_btn = gr.Button("What is CASL?")
                            q2_btn = gr.Button("How do I interpret scores?")
                        
                        with gr.Row():
                            q3_btn = gr.Button("Activities for word finding")
                            q4_btn = gr.Button("When to reassess")
                    
                    with gr.Column(scale=1):
                        answer_output = gr.Markdown()
                        
                        with gr.Accordion("References", open=False):
                            gr.Markdown("""
                            - American Speech-Language-Hearing Association (ASHA)
                            - Comprehensive Assessment of Spoken Language (CASL-2) Manual
                            - Evidence-Based Practice in Speech-Language Pathology
                            - Current research in pediatric language intervention
                            """)
        
        # ===============================
        # Event Handlers
        # ===============================
        
        # Load sample transcript button
        def load_sample():
            return SAMPLE_TRANSCRIPT
        
        sample_btn.click(load_sample, outputs=[transcript])
        
        # File upload handler
        file_upload.upload(process_upload, file_upload, transcript)
        
        # Analysis button handler
        def on_analyze_click(transcript_text, age_val, gender_val, patient_name_val, record_id_val, clinician_val, assessment_date_val):
            if not transcript_text or len(transcript_text.strip()) < 50:
                return (
                    pd.DataFrame(), 
                    pd.DataFrame(), 
                    None,
                    None,
                    "Error: Please provide a longer transcript for analysis.",
                    "The transcript is too short for meaningful analysis.",
                    "Please provide a speech sample with at least 50 characters."
                )
            
            try:
                results, plot_img, radar_img, full_text = analyze_transcript(transcript_text, age_val, gender_val)
                
                # Format treatment suggestions as markdown
                treatment_text = ""
                for i, suggestion in enumerate(results['treatment_suggestions']):
                    treatment_text += f"- {suggestion}\n"
                
                # Format to include patient metadata in the full report
                patient_info = ""
                if patient_name_val:
                    patient_info += f"**Patient:** {patient_name_val}\n"
                if record_id_val:
                    patient_info += f"**Record ID:** {record_id_val}\n"
                if age_val:
                    patient_info += f"**Age:** {age_val} years\n"
                if gender_val:
                    patient_info += f"**Gender:** {gender_val}\n"
                if assessment_date_val:
                    patient_info += f"**Assessment Date:** {assessment_date_val}\n"
                if clinician_val:
                    patient_info += f"**Clinician:** {clinician_val}\n"
                
                if patient_info:
                    full_report = f"## Patient Information\n\n{patient_info}\n\n## Analysis Report\n\n{full_text}"
                else:
                    full_report = f"## Complete Analysis Report\n\n{full_text}"
                
                # Convert image buffers to PIL images
                plot_img_pil = Image.open(plot_img)
                radar_img_pil = Image.open(radar_img)
                
                return (
                    results['speech_factors'],
                    results['casl_data'],
                    plot_img_pil,
                    radar_img_pil,
                    treatment_text,
                    results['explanation'],
                    full_report
                )
            except Exception as e:
                logger.exception("Error during analysis")
                return (
                    pd.DataFrame(), 
                    pd.DataFrame(), 
                    None,
                    None,
                    f"Error during analysis: {str(e)}",
                    "An error occurred while processing the transcript.",
                    f"Error details: {str(e)}"
                )
        
        analyze_btn.click(
            on_analyze_click,
            inputs=[
                transcript, age, gender, 
                patient_name, record_id, clinician_name, assessment_date
            ],
            outputs=[
                speech_factors_table,
                casl_table,
                output_image,
                radar_chart, 
                treatment_md,
                explanation_md,
                full_analysis
            ]
        )
        
        # Export report button simulation
        def export_pdf_simulation():
            return "Report export initiated. The PDF would be downloaded in a production environment."
        
        export_btn.click(export_pdf_simulation, outputs=[export_status])
        report_download_btn.click(export_pdf_simulation, outputs=[report_download_status])
        
        # Report generator button
        def on_generate_report(name, record_id, age, gender, date, clinician, results, report_type):
            patient_info = {
                "name": name,
                "record_id": record_id,
                "age": age,
                "gender": gender,
                "assessment_date": date,
                "clinician": clinician
            }
            
            report_type_val = "formal" if "Formal" in report_type else "parent-friendly"
            
            try:
                report = generate_report(patient_info, results, report_type_val)
                return report
            except Exception as e:
                logger.exception("Error generating report")
                return f"Error generating report: {str(e)}"
        
        generate_report_btn.click(
            on_generate_report,
            inputs=[
                report_patient_name, report_record_id, report_age,
                report_gender, report_date, report_clinician,
                report_results, report_type
            ],
            outputs=[report_output]
        )
        
        # Transcription button
        def on_transcribe_audio(audio_path, age):
            try:
                if not audio_path:
                    return "Please upload an audio file to transcribe."
                
                transcription = transcribe_audio(audio_path, age)
                return transcription
            except Exception as e:
                logger.exception("Error transcribing audio")
                return f"Error transcribing audio: {str(e)}"
        
        transcribe_btn.click(
            on_transcribe_audio,
            inputs=[audio_input, transcription_age],
            outputs=[transcription_output]
        )
        
        # Copy transcription to analysis
        def copy_to_analysis(transcription):
            return transcription, gr.update(selected=0)  # Switches to the Analysis tab
        
        copy_to_analysis_btn.click(
            copy_to_analysis,
            inputs=[transcription_output],
            outputs=[transcript, main_tabs]
        )
        
        # SLP Assistant question handling
        def on_ask_question(question):
            try:
                answer = answer_slp_question(question)
                return answer
            except Exception as e:
                logger.exception("Error getting answer")
                return f"Error: {str(e)}"
        
        ask_question_btn.click(
            on_ask_question,
            inputs=[question_input],
            outputs=[answer_output]
        )
        
        # Quick question buttons
        q1_btn.click(lambda: "What is CASL?", outputs=[question_input])
        q2_btn.click(lambda: "How do I interpret CASL scores?", outputs=[question_input])
        q3_btn.click(lambda: "What activities help with word finding difficulties?", outputs=[question_input])
        q4_btn.click(lambda: "When should I reassess a patient?", outputs=[question_input])
        
    return app

# ===============================
# Main Application
# ===============================

# Create requirements.txt file for HuggingFace Spaces
def create_requirements_file():
    requirements = [
        "gradio>=4.0.0",
        "pandas",
        "matplotlib",
        "numpy",
        "Pillow",
        "PyPDF2",
        "boto3"
    ]
    
    with open("requirements.txt", "w") as f:
        for req in requirements:
            f.write(f"{req}\n")

# Create and launch the interface
if __name__ == "__main__":
    # Create requirements.txt for HuggingFace Spaces
    create_requirements_file()
    
    # Check for AWS credentials
    if not AWS_ACCESS_KEY or not AWS_SECRET_KEY:
        print("NOTE: AWS credentials not found. The app will run in demo mode with simulated responses.")
        print("To enable full functionality, set AWS_ACCESS_KEY and AWS_SECRET_KEY environment variables.")
    
    # Launch the Gradio app
    app = create_interface()
    app.launch()