import streamlit as st
import pandas as pd

from datasets import load_dataset

@st.cache_data
def cache_load_dataset():
    dataset  = load_dataset("kraina/airbnb", "all")
    return dataset

dataset = cache_load_dataset()
data = pd.DataFrame(dataset['train']).dropna()
data['lon'] = data['lng']

st.title("Airbnb Dataset")
st.subheader("https://huggingface.co/datasets/kraina/airbnb")

st.write('Based on: https://doi.org/10.1016/j.tourman.2021.104319')
st.write(f'Cities: {len(data["city"].unique())}')
st.write(f'Total listings: {len(data)}')
st.map(data)