Update eda.py

eda.py

@@ -2,6 +2,7 @@ import streamlit as st
 import pandas as pd
 import matplotlib.pyplot as plt
 from wordcloud import WordCloud
+import re
 
 def label_sentiment(rating):
     """Label sentiment based on the rating."""
@@ -14,6 +15,12 @@ def label_sentiment(rating):
     else:
         return 'unknown'
 
+def process_review(review):
+    """Simple processing for the review text."""
+    review = review.lower()
+    review = re.sub(r'[^a-z\s]', '', review) # Remove non-alphabetical characters
+    return review
+
 def display_eda(data):
     # Derive the 'sentiment' column from 'rating' if it doesn't exist
     if 'sentiment' not in data.columns:
@@ -39,7 +46,7 @@ def display_eda(data):
     for sentiment in sentiments:
         st.write(f"Word Cloud for {sentiment}")
         subset = data[data['sentiment'] == sentiment]
-        text = " ".join(review for review in subset['processed_review'])
+        text = " ".join(process_review(review) for review in subset['review'])
         wordcloud = WordCloud(max_words=100, background_color="white").generate(text)
         plt.figure()
         plt.imshow(wordcloud, interpolation="bilinear")