Update app.py

app.py

@@ -101,48 +101,42 @@ def main():
     file = st.file_uploader("Upload an excel file", type=['xlsx'])
     review_column = None
     df = None
-    class_names = None  # New variable for class names
+    class_names = None
 
     if file is not None:
         try:
             chunk_size = 10000  # adjust this value depending on your available memory
             df = pd.concat(pd.read_excel(file, chunksize=chunk_size))
-
-            # Drop rows where all columns are NaN
             df = df.dropna(how='all')
-            # Replace blank spaces with NaN, then drop rows where all columns are NaN again
             df = df.replace(r'^\s*$', np.nan, regex=True)
             df = df.dropna(how='all')
             review_column = st.selectbox('Select the column from your excel file containing text', df.columns)
             df[review_column] = df[review_column].astype(str)
 
-            
-            filter_words_input = st.text_input('Enter words to filter the data by, separated by comma (or leave empty)')  # New input field for filter words
-            filter_words = [] if filter_words_input.strip() == "" else process_filter_words(filter_words_input)  # Process the filter words
-            class_names = st.text_input('Enter the possible class names separated by comma')  # New input field for class names
-            df = filter_dataframe(df, review_column, filter_words)  # Filter the DataFrame
+            filter_words_input = st.text_input('Enter words to filter the data by, separated by comma (or leave empty)')  
+            filter_words = [] if filter_words_input.strip() == "" else process_filter_words(filter_words_input)  
+            class_names = st.text_input('Enter the possible class names separated by comma')
+            df = filter_dataframe(df, review_column, filter_words) 
         except Exception as e:
             st.write("An error occurred while reading the uploaded file. Please make sure it's a valid Excel file.")
             return
 
     start_button = st.button('Start Analysis')
 
-    
     if start_button and df is not None:
-        # Drop rows with NaN or blank values in the review_column
         df = df[df[review_column].notna()]
         df = df[df[review_column].str.strip() != '']
-    
-        class_names = [name.strip() for name in class_names.split(',')]  # Split class names into a list
-        for name in class_names:  # Add a new column for each class name
+
+        class_names = [name.strip() for name in class_names.split(',')]
+        for name in class_names:
             if name not in df.columns:
                 df[name] = 0.0
-    
+
         if review_column in df.columns:
             with st.spinner('Performing sentiment analysis...'):
                 df, df_display = process_reviews(df, review_column, class_names)
-    
-            display_ratings(df, review_column)  # updated this line
+
+            display_ratings(df, review_column)
             display_dataframe(df, df_display)
         else:
             st.write(f'No column named "{review_column}" found in the uploaded file.')
@@ -153,6 +147,7 @@ def main():
 
 
 
+
 def process_reviews(df, review_column, class_names):
     with st.spinner('Classifying reviews...'):
         progress_bar = st.progress(0)