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):
    # Load data from CSV file
    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',
        y='Context',
        color='Lemma',
        labels={'Context': 'Frequency'},
        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
    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
    fig_pie = px.pie(
        lemma_stats_additional,
        values='Frequency',
        names='Lemma',
        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
    fig_additional = px.bar(
        chapter_stats_additional,
        barmode='stack',
        labels={'index': 'Book/Chapter'},
        title='Chapter-wise Lemma Mentions'
    )

    # Display the subplot using st.plotly_chart()
    st.plotly_chart(fig_additional)

    # Display the most common lemma
    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
        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")

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

    # Option to sort entries
    sort_entries = st.sidebar.checkbox("Sort entries by plin. nat. number")

    # Visualization based on selected file and option to sort
    visualize_data(csv_file, sort_entries)

if __name__ == "__main__":
    main()