import streamlit as st
import pandas as pd
import pyarrow.dataset as ds

# Load and cache data
@st.cache_data
def load_data(n_rows=1_000_000):
    dataset = ds.dataset("train_series.parquet", format="parquet")
    table = dataset.scanner().head(n_rows)
    return table.to_pandas()

@st.cache_data
def load_train_series():
    return load_data()

@st.cache_data
def load_train_events():
    return pd.read_csv("train_events.csv")

@st.cache_data
def load_sample_submission():
    return pd.read_csv("sample_submission.csv")

@st.cache_data
def load_test_series():
    return pd.read_parquet("test_series.parquet")