app.py

# app.py

# -----------------------------
# 1️⃣ Set Hugging Face / NLTK cache
# -----------------------------
import os
os.environ["TRANSFORMERS_CACHE"] = "/tmp/cache"
os.environ["NLTK_DATA"] = "/tmp/nltk_data"

# -----------------------------
# 2️⃣ Streamlit & imports
# -----------------------------
import streamlit as st
from mca_comment_analyzer import MCACommentAnalyzer

# -----------------------------
# 3️⃣ Streamlit UI
# -----------------------------
st.set_page_config(page_title="MCA Comment Analyzer Light", layout="wide")
st.title("📊 MCA Comment Analyzer Light 📝")
st.sidebar.header("Upload or Enter Comments")

# Sidebar input
upload_file = st.sidebar.file_uploader("Upload CSV/Excel/TXT", type=["csv","xlsx","txt"])
manual_input = st.sidebar.text_area("Or enter comments manually (one per line)")

comments = []
if upload_file:
    import pandas as pd
    try:
        if upload_file.name.endswith(".csv"):
            df_file = pd.read_csv(upload_file)
            if 'comment' in df_file.columns:
                comments = df_file['comment'].astype(str).tolist()
            else:
                comments = df_file.iloc[:,0].astype(str).tolist()
        elif upload_file.name.endswith(".xlsx"):
            df_file = pd.read_excel(upload_file)
            if 'comment' in df_file.columns:
                comments = df_file['comment'].astype(str).tolist()
            else:
                comments = df_file.iloc[:,0].astype(str).tolist()
        else:
            comments = upload_file.read().decode("utf-8").splitlines()
    except Exception as e:
        st.error(f"File format not supported or corrupted. {e}")
elif manual_input.strip():
    comments = manual_input.strip().split("\n")

if st.sidebar.button("Analyze"):
    if comments:
        analyzer = MCACommentAnalyzer()
        df, keyword_freq = analyzer.process_comments(comments)

        st.subheader("📌 Analysis Results")
        st.dataframe(df, use_container_width=True)

        st.subheader("📊 Sentiment Distribution")
        st.bar_chart(df["Sentiment"].value_counts())

        st.subheader("☁️ Word Cloud")
        plt_obj = analyzer.generate_wordcloud(keyword_freq)
        st.pyplot(plt_obj)
    else:
        st.warning("⚠️ Provide comments manually or upload a supported file.")