src/pages/RawData.py

from pathlib import Path
import sys

import streamlit as st

try:
    from data_store import load_metric_store
except ModuleNotFoundError:
    sys.path.append(str(Path(__file__).resolve().parents[1]))
    from data_store import load_metric_store

st.set_page_config(page_title="Raw Data", page_icon="🧾", layout="wide")

# Sidebar navigation
st.sidebar.title("Navigation")
st.sidebar.page_link("streamlit_app.py", label="Home", icon="🏠")
st.sidebar.page_link("pages/OptimizationLeaderboard.py", label="Optimization Leaderboard", icon="📊")
st.sidebar.page_link("pages/UQLeaderboard.py", label="UQ Leaderboard", icon="🎯")
st.sidebar.page_link("pages/MethodDetails.py", label="Methods", icon="📘")
st.sidebar.page_link("pages/RawData.py", label="Get Data", icon="🧾")

st.title("Raw Averaged Forward Model Runs")
st.caption("All rows are averaged over random seeds during ingestion; `metric` represents forward model runs")

metric_store = load_metric_store()
if metric_store.empty:
    st.warning("No metric data found. Expected NetCDF files in `data/` with a `metric` variable.")
    st.stop()

benchmark_options = sorted(metric_store["benchmark"].unique().tolist())
default_benchmark_index = benchmark_options.index("L63") if "L63" in benchmark_options else 0
selected_benchmark = str(st.selectbox("Benchmark", options=benchmark_options, index=default_benchmark_index))

filtered = metric_store[metric_store["benchmark"] == selected_benchmark].copy()
filtered = filtered.sort_values(["abbreviation", "rmse_target", "ensemble_size"])

st.dataframe(
    filtered[
        [
            "benchmark",
            "abbreviation",
            "Method",
            "parallelism",
            "update_type",
            "method_goal",
            "emulator_use",
            "algorithm_type",
            "algorithm_alias",
            "rmse_target",
            "ensemble_size",
            "metric",
        ]
    ],
    hide_index=True,
    use_container_width=True,
    column_config={
        "benchmark": st.column_config.TextColumn("Benchmark"),
        "abbreviation": st.column_config.TextColumn("Abbrev."),
        "Method": st.column_config.TextColumn("Method"),
        "parallelism": st.column_config.TextColumn("Parallelism"),
        "update_type": st.column_config.TextColumn("Update Type"),
        "method_goal": st.column_config.TextColumn("Method Goal"),
        "emulator_use": st.column_config.TextColumn("Emulator Use"),
        "algorithm_type": st.column_config.TextColumn("Canonical Type"),
        "algorithm_alias": st.column_config.TextColumn("Source Alias"),
        "rmse_target": st.column_config.TextColumn("RMSE Target"),
        "ensemble_size": st.column_config.NumberColumn("Ensemble Size"),
        "metric": st.column_config.NumberColumn("Mean Forward Model Runs", format="%.6f"),
    },
)

csv_data = filtered.to_csv(index=False).encode("utf-8")
st.download_button(
    label=f"Download {selected_benchmark} averaged metrics (CSV)",
    data=csv_data,
    file_name=f"{selected_benchmark.lower()}_averaged_metrics.csv",
    mime="text/csv",
)

st.page_link("pages/OptimizationLeaderboard.py", label="⬅ Back to Optimization Leaderboard", icon="↩️")