from datasets import load_dataset
import streamlit as st
import pandas as pd
import os

token = os.getenv('HF_TOKEN')

data_files = {
    "Part_A": "ELG_Busan_PoC_per_CA_site_0226_0407.csv",
    "Part_B": "ELG_Busan_PoC_per_CA_site_0408_0519.csv"
}

@st.cache_data(show_spinner=False)
def load_data():

    dataset = load_dataset('skt-asap/busan-poc-dataset', data_files=data_files, token=token)
    df = dataset['Part_A'].to_pandas()

    df.fillna(0, inplace=True)
    df.drop(columns=['Unnamed: 0'], inplace=True)

    df['ru_svc_lat_val'] = df['ru_svc_lat_val'].astype(float)
    df['ru_svc_lng_val'] = df['ru_svc_lng_val'].astype(float)

    df_map = df.drop_duplicates(subset=['ru_svc_lat_val', 'ru_svc_lng_val'])

    return df, df_map