app.py

import os
import numpy as np
import pandas as pd
import streamlit as st
from huggingface_hub import login
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
from keybert import KeyBERT
from openai import AzureOpenAI  # new

# ─── Azure OpenAI Client ─────────────────────────────────────────────────────
openai_client = AzureOpenAI(
  api_key = "fbca46bfd8814334be46a2e5c323904c", # use your key here
  api_version = "2023-05-15", # apparently HKUST uses a deprecated version
  azure_endpoint = "https://hkust.azure-api.net" # per HKUST instructions
)

@st.cache_resource
def load_sentiment_pipeline():
    model_name = "mayf/amazon_reviews_bert_ft"
    tok = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
    mdl = AutoModelForSequenceClassification.from_pretrained(model_name, use_auth_token=True)
    return pipeline(
        "sentiment-analysis",
        model=mdl,
        tokenizer=tok,
        return_all_scores=True
    )

@st.cache_resource
def load_keybert_model():
    return KeyBERT(model="all-MiniLM-L6-v2")

LABEL_MAP = {
    "LABEL_0": "Very Negative",
    "LABEL_1": "Negative",
    "LABEL_2": "Neutral",
    "LABEL_3": "Positive",
    "LABEL_4": "Very Positive"
}


def main():
    st.title("📊 Amazon Review Analyzer")

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

    # Initialize progress bar
    progress = st.progress(0)

    # Load models
    progress.text("Loading models...")
    sentiment_pipeline = load_sentiment_pipeline()
    kw_model = load_keybert_model()
    progress.progress(20)

    # Run sentiment analysis
    progress.text("Analyzing sentiment...")
    raw_scores = sentiment_pipeline(review)[0]
    # Map labels
    sentiment_results = {LABEL_MAP[item['label']]: float(item['score']) for item in raw_scores}
    progress.progress(40)

    # Extract keywords
    progress.text("Extracting keywords...")
    keywords = kw_model.extract_keywords(
        review,
        keyphrase_ngram_range=(1, 2),
        stop_words="english",
        top_n=3
    )
    progress.progress(60)

    # Display scores and keywords side by side
    col1, col2 = st.columns(2)
    with col1:
        st.subheader("Sentiment Scores")
        st.json({k: round(v, 4) for k, v in sentiment_results.items()})
    with col2:
        st.subheader("Top 3 Keywords")
        for kw, score in keywords:
            st.write(f"• {kw} ({score:.4f})")

    # Bar chart
    progress.text("Rendering chart...")
    df_scores = pd.DataFrame.from_dict(sentiment_results, orient='index', columns=['score'])
    df_scores.index.name = 'Sentiment'
    st.bar_chart(df_scores)
    progress.progress(80)

    # Highlight highest sentiment
    max_label, max_score = max(sentiment_results.items(), key=lambda x: x[1])
    st.markdown(f"**Highest Sentiment:** **{max_label}** ({max_score:.4f})")

    # GPT-Driven Analysis & Suggestions
    progress.text("Generating insights...")
    prompt = f"""
You are an analytical amazon feedback expert.
Review: \"{review}\"
Sentiment Scores: {sentiment_results}
Top Keywords: {[kw for kw, _ in keywords]}
Tasks:
1. Write a concise paragraph (3 sentences) interpreting customer sentiment by combining the scores and keywords.
2. Provide 3 actionable suggestions with brief explanations (up to 3 sentences each).
"""

    response = openai_client.chat.completions.create(
        model="gpt-35-turbo",
        messages=[
            {"role": "system", "content": "You are a product-feedback analyst."},
            {"role": "user", "content": prompt}
        ],
        temperature=0.7,
        max_tokens=200
    )
    gpt_reply = response.choices[0].message.content.strip()
    st.markdown(gpt_reply)

    # Complete
    progress.progress(100)
    progress.text("Done!")

if __name__ == "__main__":
    main()