app.py

import streamlit as st
from transformers import (
    pipeline,
    AutoModelForSequenceClassification,
    AutoTokenizer
)
import torch
import re

# ===== CONSTANTS =====
MAX_CHARS = 1500  # Increased character limit
SUPPORTED_LANGUAGES = {
    'en': 'English',
    'zh': 'Chinese',
    'yue': 'Cantonese', 
    'ja': 'Japanese',
    'ko': 'Korean'
}

# ===== ASPECT CONFIGURATION =====
aspect_map = {
    # Location related
    "location": ["location", "near", "close", "access", "transport", "distance", "area", "tsim sha tsui", "kowloon"],
    "view": ["view", "scenery", "vista", "panorama", "outlook", "skyline"],
    "parking": ["parking", "valet", "garage", "car park", "vehicle"],

    # Room related
    "room comfort": ["comfortable", "bed", "pillows", "mattress", "linens", "cozy", "hard", "soft"],
    "room cleanliness": ["clean", "dirty", "spotless", "stains", "hygiene", "sanitation", "dusty"],
    "room amenities": ["amenities", "minibar", "coffee", "tea", "fridge", "facilities", "tv", "kettle"],
    "bathroom": ["bathroom", "shower", "toilet", "sink", "towel", "faucet", "toiletries"],

    # Service related
    "staff service": ["staff", "friendly", "helpful", "rude", "welcoming", "employee", "manager"],
    "reception": ["reception", "check-in", "check-out", "front desk", "welcome", "registration"],
    "housekeeping": ["housekeeping", "maid", "cleaning", "towels", "service", "turndown"],
    "concierge": ["concierge", "recommendation", "advice", "tips", "guidance", "directions"],
    "room service": ["room service", "food delivery", "order", "meal", "tray"],

    # Facilities
    "dining": ["breakfast", "dinner", "restaurant", "meal", "food", "buffet", "lunch"],
    "bar": ["bar", "drinks", "cocktail", "wine", "lounge", "happy hour"],
    "pool": ["pool", "swimming", "jacuzzi", "sun lounger", "deck", "towels"],
    "spa": ["spa", "massage", "treatment", "relax", "wellness", "sauna"],
    "fitness": ["gym", "fitness", "exercise", "workout", "training", "weights"],

    # Technical
    "Wi-Fi": ["wifi", "internet", "connection", "online", "network", "speed"],
    "AC": ["air conditioning", "AC", "temperature", "heating", "cooling", "ventilation"],
    "elevator": ["elevator", "lift", "escalator", "vertical transport", "wait"],

    # Value
    "pricing": ["price", "expensive", "cheap", "value", "rate", "cost", "worth"],
    "extra charges": ["charge", "fee", "bill", "surcharge", "additional", "hidden"]
}

aspect_responses = {
    "location": "We're delighted you enjoyed our prime location in the heart of Tsim Sha Tsui, with convenient access to Nathan Road shopping and the Star Ferry pier.",
    "view": "It's wonderful to hear you appreciated the beautiful harbor or city skyline views from your room.",
    "room comfort": "Our housekeeping team takes special care with our pillow menu and mattress toppers to ensure your comfort.",
    "room cleanliness": "Your commendation of our cleanliness standards means a lot to our dedicated housekeeping staff.",
    "staff service": "Your kind words about our team, especially {staff_name}, have been shared with them - such recognition means everything to us.",
    "reception": "We're pleased our front desk team made your arrival and departure experience seamless.",
    "spa": "Our award-winning spa therapists will be delighted you enjoyed their signature treatments.",
    "pool": "We're glad you had a refreshing time at our rooftop pool with its stunning city views.",
    "dining": "Thank you for appreciating our culinary offerings at The Burgeroom and Chinese Restaurant - we've shared your feedback with Executive Chef Wong.",
    "concierge": "We're happy our concierge team could enhance your stay with their local expertise and recommendations.",
    "fitness": "It's great to hear you made use of our 24-hour fitness center with its panoramic views.",
    "room service": "We're pleased our 24-hour in-room dining met your expectations for both quality and timeliness.",
    "parking": "We're glad our convenient valet parking service made your arrival experience hassle-free.",
    "bathroom": "Our housekeeping team takes special pride in maintaining our marble bathrooms with premium amenities."
}

improvement_actions = {
    "AC": "completed a comprehensive inspection and maintenance of all air conditioning units",
    "housekeeping": "implemented additional training for our housekeeping team and revised cleaning schedules",
    "bathroom": "conducted deep cleaning of all bathrooms and replenished premium toiletries",
    "parking": "introduced new digital key management with our valet service to reduce wait times",
    "dining": "reviewed all menu pricing and quality standards with our culinary leadership team",
    "reception": "provided enhanced customer service training focused on cultural sensitivity",
    "elevator": "performed full servicing of all elevators and adjusted peak-time scheduling",
    "room amenities": "begun upgrading in-room amenities including new coffee machines and smart TVs",
    "Wi-Fi": "upgraded our network infrastructure to provide faster and more reliable internet",
    "noise": "initiated soundproofing improvements in corridors and between rooms",
    "pricing": "started a comprehensive review of our pricing structure and value proposition",
    "room service": "revised our in-room dining operations to improve delivery times",
    "view": "scheduled window cleaning and tree trimming to maintain optimal views",
    "fitness": "upgraded gym equipment based on guest feedback about variety"
}

# ===== MODEL LOADING =====
@st.cache_resource
def load_sentiment_model():
    model = AutoModelForSequenceClassification.from_pretrained("smtsead/fine_tuned_bertweet_hotel")
    tokenizer = AutoTokenizer.from_pretrained('finiteautomata/bertweet-base-sentiment-analysis')
    return model, tokenizer

@st.cache_resource
def load_aspect_classifier():
    return pipeline("zero-shot-classification", model="MoritzLaurer/deberta-v3-base-zeroshot-v1.1-all-33")

# ===== CORE FUNCTIONS =====
def analyze_sentiment(text, model, tokenizer):
    inputs = tokenizer(text, padding=True, truncation=True, max_length=512, return_tensors='pt')
    with torch.no_grad():
        outputs = model(**inputs)
        probs = torch.nn.functional.softmax(outputs.logits, dim=-1)
        predicted_label = torch.argmax(probs).item()
        confidence = torch.max(probs).item()
    return {
        'label': predicted_label,
        'confidence': f"{confidence:.0%}",
        'sentiment': 'POSITIVE' if predicted_label else 'NEGATIVE'
    }

def detect_aspects(text, aspect_classifier):
    relevant_aspects = []
    text_lower = text.lower()
    for aspect, keywords in aspect_map.items():
        if any(re.search(rf'\b{kw}\b', text_lower) for kw in keywords):
            relevant_aspects.append(aspect)
    
    if relevant_aspects:
        result = aspect_classifier(
            text,
            candidate_labels=relevant_aspects,
            multi_label=True,
            hypothesis_template="This review discusses the hotel's {}."
        )
        return [(aspect, f"{score:.0%}") for aspect, score in 
                zip(result['labels'], result['scores']) if score > 0.6]
    return []

def generate_response(sentiment, aspects, original_text):
    # Personalization
    guest_name = ""
    name_match = re.search(r"(Mr\.|Ms\.|Mrs\.)\s(\w+)", original_text, re.IGNORECASE)
    if name_match:
        guest_name = f" {name_match.group(2)}"
    
    # Staff name extraction
    staff_name = ""
    staff_match = re.search(r"(receptionist|manager|concierge|chef)\s(\w+)", original_text, re.IGNORECASE)
    if staff_match:
        staff_name = staff_match.group(2)

    if sentiment['label'] == 1:
        response = f"""Dear{guest_name if guest_name else ' Valued Guest'},

Thank you for choosing The Kimberley Hotel Hong Kong and for sharing your wonderful feedback!"""
        
        # Add relevant aspect responses
        added_aspects = set()
        for aspect, _ in aspects:
            if aspect in aspect_responses:
                response_text = aspect_responses[aspect]
                if "{staff_name}" in response_text and staff_name:
                    response_text = response_text.format(staff_name=staff_name)
                response += "\n\n" + response_text
                added_aspects.add(aspect)
                if len(added_aspects) >= 3:  # Limit to 3 main points
                    break
        
        # Special offers
        if "room" in added_aspects or "dining" in added_aspects:
            response += "\n\nAs a token of our appreciation, we'd like to offer you a complimentary room upgrade or dining credit on your next stay. Simply mention code VIP2024 when booking."
        
        response += "\n\nWe look forward to welcoming you back to your home in Hong Kong!\n\nWarm regards,"
    else:
        response = f"""Dear{guest_name if guest_name else ' Guest'},

Thank you for your valuable feedback - we sincerely apologize that your experience didn't meet our usual high standards."""
        
        # Add improvement actions
        added_improvements = set()
        for aspect, _ in aspects:
            if aspect in improvement_actions:
                response += f"\n\nRegarding your comments about the {aspect}, we've {improvement_actions[aspect]}."
                added_improvements.add(aspect)
                if len(added_improvements) >= 2:  # Limit to 2 main improvements
                    break
        
        # Recovery offer
        recovery_offer = "\n\nTo make amends, we'd like to offer you:"
        if "room" in added_improvements:
            recovery_offer += "\n- One night complimentary room upgrade"
        if "dining" in added_improvements:
            recovery_offer += "\n- HKD 300 dining credit at our restaurants"
        if not ("room" in added_improvements or "dining" in added_improvements):
            recovery_offer += "\n- 15% discount on your next stay"
        
        response += recovery_offer
        response += "\n\nPlease contact our Guest Relations Manager Ms. Chan directly at [email protected] to arrange this."
        
        response += "\n\nWe hope for another opportunity to provide you with the exceptional experience we're known for.\n\nSincerely,"
    
    return response + "\nMichael Wong\nGuest Experience Manager\nThe Kimberley Hotel Hong Kong\n+852 1234 5678"

# ===== STREAMLIT UI =====
def main():
    # Page Config
    st.set_page_config(
        page_title="Kimberley Review Assistant",
        page_icon="🏨",
        layout="centered"
    )
    
    # Custom CSS
    st.markdown("""
    <style>
        .header {
            color: #003366;
            font-size: 28px;
            font-weight: bold;
            margin-bottom: 10px;
        }
        .subheader {
            color: #666666;
            font-size: 16px;
            margin-bottom: 30px;
        }
        .badge {
            background-color: #e6f2ff;
            color: #003366;
            padding: 3px 10px;
            border-radius: 15px;
            font-size: 14px;
            display: inline-block;
            margin: 0 5px 5px 0;
        }
        .char-counter {
            font-size: 12px;
            color: #666;
            text-align: right;
            margin-top: -15px;
            margin-bottom: 15px;
        }
        .char-counter.warning {
            color: #ff6b6b;
        }
        .result-box {
            border-left: 4px solid #003366;
            padding: 15px;
            background-color: #f9f9f9;
            margin: 20px 0;
            border-radius: 0 8px 8px 0;
            white-space: pre-wrap;
        }
        .aspect-badge {
            background-color: #e6f2ff;
            color: #003366;
            padding: 2px 8px;
            border-radius: 4px;
            font-size: 14px;
            display: inline-block;
            margin: 2px;
        }
    </style>
    """, unsafe_allow_html=True)
    
    # Header
    st.markdown('<div class="header">The Kimberley Hotel Hong Kong</div>', unsafe_allow_html=True)
    st.markdown('<div class="subheader">Guest Review Analysis System</div>', unsafe_allow_html=True)
    
    # Supported Languages
    st.markdown("**Supported Review Languages:**")
    lang_cols = st.columns(5)
    for i, (code, name) in enumerate(SUPPORTED_LANGUAGES.items()):
        lang_cols[i].markdown(f'<div class="badge">{name}</div>', unsafe_allow_html=True)
    
    # Review Input with Character Counter
    review = st.text_area("**Paste Guest Review:**", 
                         height=250,
                         max_chars=MAX_CHARS,
                         placeholder=f"Enter review in any supported language (max {MAX_CHARS} characters)...",
                         key="review_input")
    
    char_count = len(st.session_state.review_input) if 'review_input' in st.session_state else 0
    char_class = "warning" if char_count > MAX_CHARS else ""
    st.markdown(f'<div class="char-counter {char_class}">{char_count}/{MAX_CHARS} characters</div>', 
                unsafe_allow_html=True)
    
    if st.button("Analyze & Generate Response", type="primary"):
        if not review.strip():
            st.error("Please enter a review")
            return
        
        if char_count > MAX_CHARS:
            st.warning(f"Review truncated to {MAX_CHARS} characters for analysis")
            review = review[:MAX_CHARS]
        
        with st.spinner("Analyzing feedback..."):
            # Load models
            sentiment_model, tokenizer = load_sentiment_model()
            aspect_classifier = load_aspect_classifier()
            
            # Process review
            sentiment = analyze_sentiment(review, sentiment_model, tokenizer)
            aspects = detect_aspects(review, aspect_classifier)
            response = generate_response(sentiment, aspects, review)
            
            # Display results
            st.divider()
            
            # Sentiment and Aspects
            col1, col2 = st.columns(2)
            with col1:
                st.markdown("### Sentiment Analysis")
                sentiment_icon = "✅" if sentiment['label'] == 1 else "⚠️"
                st.markdown(f"{sentiment_icon} **{sentiment['sentiment']}**")
                st.caption(f"Confidence level: {sentiment['confidence']}")
            
            with col2:
                st.markdown("### Key Aspects Detected")
                if aspects:
                    for aspect, score in sorted(aspects, key=lambda x: float(x[1][:-1]), reverse=True):
                        st.markdown(f'<div class="aspect-badge">{aspect} ({score})</div>', unsafe_allow_html=True)
                else:
                    st.markdown("_No specific aspects detected_")
            
            # Generated Response
            st.divider()
            st.markdown("### Draft Response")
            st.markdown(f'<div class="result-box">{response}</div>', unsafe_allow_html=True)
            
            # Copy button
            if st.button("Copy Response to Clipboard"):
                st.session_state.copied = True
                st.rerun()
            
            if st.session_state.get("copied", False):
                st.success("Response copied to clipboard!")
                st.session_state.copied = False

if __name__ == "__main__":
    main()