Update pages/2_Data Cleaning and Processing .py

pages/2_Data Cleaning and Processing .py

@@ -497,11 +497,21 @@ if df is not None:
     df['review_text'] = df.apply(lambda row: 'Good' if (str(row['review_text']) == 'review') else row['review_text'], axis=1)
     df['review_text'] = df.apply(lambda row: 'Very Good' if (str(row['review_text']) == 'km') else row['review_text'], axis=1)
     df['review_text'] = df.apply(lambda row: 'Exceptional' if (str(row['review_text']) == 'stars') else row['review_text'], axis=1)
-    df['review_text'] = df.apply(lambda row: 'No Review' if (str(row['review_text']) in ['nan', 'np']) else row['review_text'], axis=1)
+    df['review_text'] = df.apply(lambda row: 'No Review' if (str(row['review_text']) in ['nan', 'np','Review']) else row['review_text'], axis=1)
     
     # Display the updated review_text column
     st.write("Replaced specific terms like 'km', 'stars', and 'nan' with more meaningful terms:")
     st.write(df['review_text'])
+    def update_rating(row):
+        if row['review_text'] == 'Exceptional':
+            return 5 if pd.isnull(row['rating']) or row['rating'] == 'Nan' else row['rating']
+        elif row['review_text'] == 'Excellent':
+            return 4 if pd.isnull(row['rating']) or row['rating'] == 'Nan' else row['rating']
+        elif row['review_text'] == 'Good':
+            return 3 if pd.isnull(row['rating']) or row['rating'] == 'Nan' else row['rating']
+        elif row['review_text'] in ['No Review', 'Review']:
+            return 0 if pd.isnull(row['rating']) or row['rating'] == 'Nan' else row['rating']
+        return row['rating']
 
    # Step: Handling Missing Values in 'reviews' column