app.py

import streamlit as st
import pandas as pd
import plotly.express as px
import nltk

nltk.download('punkt')

def count_tokens(text):
    tokens = nltk.word_tokenize(text)
    return len(tokens)

def extract_number(entry):
    start_index = entry.find("plin. nat.") + len("plin. nat.")
    num_str = ''
    for char in entry[start_index:]:
        if char.isdigit() or char == '.':
            num_str += char
        else:
            break
    return float(num_str) if num_str else 0.0

def visualize_data(csv_file, sort_entries=False):    
    data = pd.read_csv(csv_file)
    
    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)

    
    lemma_stats = data.groupby('Lemma').agg({'Context': 'count', 'token_count': 'mean'}).reset_index()

    
    st.write("Basic Statistics:")
    st.table(lemma_stats)

    
    fig_bar = px.bar(
        lemma_stats,
        x='Lemma',
        y='Context',
        color='Lemma',
        labels={'Context': 'Frequency'},
        title='Lemma Frequency in the Dataset'
    )

    
    st.plotly_chart(fig_bar)   
    lemma_stats_additional = data['Lemma'].value_counts().reset_index()
    lemma_stats_additional.columns = ['Lemma', 'Frequency']

    
    most_common_lemma_additional = lemma_stats_additional.iloc[0]['Lemma']

    
    chapter_stats_additional = data.groupby(['Lemma', 'Book/Chapter']).size().unstack(fill_value=0)    
    fig_pie = px.pie(
        lemma_stats_additional,
        values='Frequency',
        names='Lemma',
        title='Lemma Frequency Distribution'
    )

    st.plotly_chart(fig_pie)    
    fig_additional = px.bar(
        chapter_stats_additional,
        barmode='stack',
        labels={'index': 'Book/Chapter'},
        title='Chapter-wise Lemma Mentions'
    )

    
    st.plotly_chart(fig_additional)    
    st.write(f"Most Common Lemma: {most_common_lemma_additional}")

   
    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']}")
            st.write(f"Context: {row['Context']}")
            st.write('-' * 50)

def main():
    st.title("Lemma Frequency Visualization")

    csv_file = st.sidebar.selectbox("Select CSV file:", ["allData.csv","places.csv","ethnonyms.csv","rivers.csv","mountains.csv","toponyms.csv"])

    visualize_data(csv_file)

if __name__ == "__main__":
    main()