import os
import streamlit as st
from huggingface_hub import login
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
from keybert import KeyBERT

# ─── Streamlit Page Config ─────────────────────────────────────────────────
st.set_page_config(page_title="Review Analyzer", layout="wide")

# ─── Authenticate to Hugging Face Hub ───────────────────────────────────────
# ensure HF_TOKEN is set in your environment
token = os.environ.get("HF_TOKEN", "")
login(token=token, add_to_git_credential=False)

# ─── Cached resource: Sentiment Analysis Pipeline ────────────────────────────
@st.cache_resource
def load_sentiment_pipeline():
    model_name = "mayf/amazon_reviews_bert_ft"
    tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
    model = AutoModelForSequenceClassification.from_pretrained(model_name, use_auth_token=True)
    return pipeline(
        "sentiment-analysis",
        model=model,
        tokenizer=tokenizer,
        return_all_scores=True
    )

# ─── Cached resource: KeyBERT Model ─────────────────────────────────────────
@st.cache_resource
def load_keybert_model():
    return KeyBERT(model="all-MiniLM-L6-v2")

# ─── Main Application ───────────────────────────────────────────────────────
def main():
    sentiment_pipeline = load_sentiment_pipeline()
    kw_model = load_keybert_model()

    st.title("📊 Review Sentiment & Keyword Analyzer")
    review = st.text_area("Enter your review:")

    if st.button("Analyze Review"):
        if not review:
            st.warning("Please enter a review to analyze.")
            return

        # Sentiment Analysis
        scores = sentiment_pipeline(review)[0]
        sentiment_results = {item['label']: float(item['score']) for item in scores}
        st.subheader("Sentiment Scores")
        st.json({k: round(v, 4) for k, v in sentiment_results.items()})

        # Keyword Extraction (top 3)
        keywords = kw_model.extract_keywords(
            review,
            keyphrase_ngram_range=(1, 2),
            stop_words="english",
            top_n=3
        )
        st.subheader("Top 3 Keywords")
        for kw, score in keywords:
            st.write(f"- **{kw}** (Score: {score:.4f})")

        # Highest Sentiment Label
        max_label, max_score = max(sentiment_results.items(), key=lambda x: x[1])
        st.subheader("Highest Sentiment")
        st.write(f"{max_label} (Score: {max_score:.4f})")
        st.write("Keywords used for this analysis:")
        st.write(', '.join([kw for kw, _ in keywords]))

if __name__ == "__main__":
    main()