synthetic-data-gen-frontend.py

import streamlit as st
import pandas as pd
from data_generation import generate_dataset, generate_parts_of_dataset

# Sidebar with company logo and use case navigation
# Use Markdown to increase font size for the title
st.sidebar.markdown("""
    <style>
    .big-font {
        font-size:20px !important;
    }
    </style>
    """, unsafe_allow_html=True)

st.sidebar.markdown('<p class="big-font">Select a Use Case</p>',
                    unsafe_allow_html=True)

option = st.sidebar.selectbox('Select a Use Case',
                              ('Synthetic Data Generation',
                               'Targeted Data Generation'),
                              label_visibility="hidden")

# Synthetic Data Generation UI
if option == 'Synthetic Data Generation':
    st.header("Synthetic Data Generation")
    columns = st.text_input("Enter column names separated by comma")
    rows = st.number_input("Enter the number of rows", min_value=1, value=10)
    if st.button("Generate"):
        # Directly call generate_dataset function
        if columns:  # Ensure columns input is not empty
            columns_list = [column.strip() for column in columns.split(",")]
            df = generate_dataset(columns_list, rows)
            st.dataframe(df)
        else:
            st.error("Please enter at least one column name.")

# Targeted Data Generation UI
elif option == 'Targeted Data Generation':
    st.header("Targeted Data Generation")
    uploaded_file = st.file_uploader("Upload a file", type=['csv'])

    if uploaded_file is not None:
        # Determine the file format and read the file accordingly
        if uploaded_file.name.endswith('.csv'):
            df = pd.read_csv(uploaded_file)
        elif uploaded_file.name.endswith('.xlsx'):
            df = pd.read_excel(uploaded_file)

        st.write("Old dataset:")
        st.dataframe(df)

    if st.button("Fill Data"):
        # Implementation for data filling
        output_df = generate_parts_of_dataset(df)
        st.write("Data filled successfully")
        st.write("New dataset:")
        st.dataframe(output_df)