Update app.py

app.py

@@ -19,25 +19,23 @@ def extract_number(entry):
             break
     return float(num_str) if num_str else 0.0
 
-def visualize_data(csv_file, sort_entries=False):
-    # Load data from CSV file
+def visualize_data(csv_file, sort_entries=False):    
     data = pd.read_csv(csv_file)
-
-    # Sorting by the first number after "plin. nat." if specified
+    
     if sort_entries:
         data['SortKey'] = data['Book/Chapter'].apply(extract_number)
         data = data.sort_values(by='SortKey')
 
     data['token_count'] = data['Context'].apply(count_tokens)
 
-    # Basic statistics
+    
     lemma_stats = data.groupby('Lemma').agg({'Context': 'count', 'token_count': 'mean'}).reset_index()
 
-    # Display the basic statistics using st.table()
+    
     st.write("Basic Statistics:")
     st.table(lemma_stats)
 
-    # Bar chart for lemma frequency using Plotly Express
+    
     fig_bar = px.bar(
         lemma_stats,
         x='Lemma',
@@ -47,21 +45,16 @@ def visualize_data(csv_file, sort_entries=False):
         title='Lemma Frequency in the Dataset'
     )
 
-    # Display the bar chart using st.plotly_chart()
-    st.plotly_chart(fig_bar)
-
-    # Additional Visualization
-    # Basic statistics for additional data
+    
+    st.plotly_chart(fig_bar)   
     lemma_stats_additional = data['Lemma'].value_counts().reset_index()
     lemma_stats_additional.columns = ['Lemma', 'Frequency']
 
-    # Find the most common lemma
+    
     most_common_lemma_additional = lemma_stats_additional.iloc[0]['Lemma']
 
-    # Distribution across chapters
-    chapter_stats_additional = data.groupby(['Lemma', 'Book/Chapter']).size().unstack(fill_value=0)
-
-    # Create a pie chart for lemma frequency using Plotly Express
+    
+    chapter_stats_additional = data.groupby(['Lemma', 'Book/Chapter']).size().unstack(fill_value=0)    
     fig_pie = px.pie(
         lemma_stats_additional,
         values='Frequency',
@@ -69,10 +62,7 @@ def visualize_data(csv_file, sort_entries=False):
         title='Lemma Frequency Distribution'
     )
 
-    # Display the pie chart using st.plotly_chart()
-    st.plotly_chart(fig_pie)
-
-    # Create a subplot for chapter-wise lemma mentions
+    st.plotly_chart(fig_pie)    
     fig_additional = px.bar(
         chapter_stats_additional,
         barmode='stack',
@@ -80,15 +70,12 @@ def visualize_data(csv_file, sort_entries=False):
         title='Chapter-wise Lemma Mentions'
     )
 
-    # Display the subplot using st.plotly_chart()
-    st.plotly_chart(fig_additional)
-
-    # Display the most common lemma
+    
+    st.plotly_chart(fig_additional)    
     st.write(f"Most Common Lemma: {most_common_lemma_additional}")
 
-    # Expandable section to display context
-    with st.expander("Click to view context"):
-        # Display context for each entry
+   
+    with st.expander("Click to view context"):       
         for index, row in data.iterrows():
             st.write(f"Lemma: {row['Lemma']}")
             st.write(f"Book/Chapter: {row['Book/Chapter']}")
@@ -98,10 +85,8 @@ def visualize_data(csv_file, sort_entries=False):
 def main():
     st.title("Lemma Frequency Visualization")
 
-    # File selection
     csv_file = st.sidebar.selectbox("Select CSV file:", ["allData.csv","places.csv","ethnonyms.csv","rivers.csv","mountains.csv","toponyms.csv"])
 
-    # Visualization based on selected file and option to sort
     visualize_data(csv_file)
 
 if __name__ == "__main__":