dataset_import.py

import os
import pandas as pd
import streamlit as st

def download_dataset():
    # Ensure the data directory exists
    if not os.path.exists('./data'):
        os.makedirs('./data')

    # Download the dataset using Kaggle API
    os.system("kaggle datasets download -d mohaideenabuthahir/analyzeyt -p ./data --unzip")

def load_data():
    # Ensure dataset is downloaded
    download_dataset()

    # List available files in the data directory
    available_files = [f for f in os.listdir('./data') if f.endswith('.csv')]

    if len(available_files) == 0:
        st.error("No CSV files found in the dataset folder.")
        return None

    # Ask user to select which file to load
    selected_file = st.selectbox('Select a file to load', available_files)

    if selected_file:
        # Load the selected dataset
        data = pd.read_csv(f'./data/{selected_file}')
        return data
    else:
        st.error("Please select a valid file.")
        return None