Update mca_comment_analyzer.py

mca_comment_analyzer.py

@@ -1,5 +1,6 @@
+# mca_comment_analyzer.py
+
 import os
-import streamlit as st
 import pandas as pd
 import torch
 from transformers import pipeline
@@ -7,40 +8,42 @@ from wordcloud import WordCloud
 import matplotlib.pyplot as plt
 from collections import Counter
 import nltk
-from nltk.corpus import stopwords
 import random
 from datetime import datetime, timedelta
 
-# ---- Config
-
+# -----------------------------
+# Configs
+# -----------------------------
 os.environ["MPLCONFIGDIR"] = "/tmp/.matplotlib"
+os.environ["NLTK_DATA"] = "/tmp/nltk_data"
 
-st.set_page_config(page_title="MCA Demo Comment Analyzer", layout="wide")
-
-# ---- NLTK
-nltk.download('stopwords', quiet=True)
+# NLTK Stopwords
+nltk.download('stopwords', download_dir="/tmp/nltk_data", quiet=True)
+from nltk.corpus import stopwords
 STOPWORDS = set(stopwords.words('english'))
 
-# ---- Lightweight MCA Analyzer
+# -----------------------------
+# MCA Comment Analyzer
+# -----------------------------
 class MCACommentAnalyzer:
     def __init__(self):
         device = 0 if torch.cuda.is_available() else -1
         print("Using device:", "GPU" if device==0 else "CPU")
-        
-        # Lightweight sentiment model
+
+        # Sentiment model
         self.sentiment_model = pipeline(
             "sentiment-analysis",
             model="distilbert-base-uncased-finetuned-sst-2-english",
             device=device
         )
-        
-        # Lightweight summarizer
+
+        # Summarizer
         self.summarizer = pipeline(
             "summarization",
             model="t5-small",
             device=device
         )
-        
+
         self.stop_words = STOPWORDS
 
     def map_sentiment(self, pred, text):
@@ -121,49 +124,3 @@ class MCACommentAnalyzer:
         if filename:
             plt.savefig(filename, bbox_inches='tight')
         return plt
-
-# ---- Streamlit UI
-st.title("📊 MCA Demo Comment Analyzer")
-st.sidebar.header("Upload or Enter Comments")
-
-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:
-    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.")