"""Read-only warehouse layer. Dashboard reads ONLY from data/warehouse/.
Cached with @st.cache_data. No imports from ML code.
"""

import logging
from pathlib import Path

import pandas as pd

logger = logging.getLogger(__name__)

ROOT = Path(__file__).resolve().parent.parent
WAREHOUSE = ROOT / "data" / "warehouse"

_EMPTY_DEFAULTS = {
    "players.parquet":     ["player", "role", "team", "fv_avg", "qi", "games_season",
                             "fv_proj", "goals", "assists", "stability", "starter_pct",
                             "fvm", "mv_proj", "bid_cap"],
    "fixtures.parquet":    ["team", "matchday", "opp_strength", "home", "away"],
    "predictions.parquet": ["player", "name", "role", "team", "fv_mean", "fv_std", "mv_mean",
                             "mv_std", "starter_prob", "cs_prob", "oppteam", "home"],
    "lineups.parquet":     ["player", "role", "team", "starter_pct"],
    "votes.parquet":       ["player", "vote", "matchday"],
    "model_metrics.parquet": ["metric", "value"],
}


def _read_parquet_or_empty(name):
    path = WAREHOUSE / name
    if path.exists():
        return pd.read_parquet(path)
    cols = _EMPTY_DEFAULTS.get(name, [])
    df = pd.DataFrame([{c: (0.0 if c not in ("player", "role", "team", "name", "oppteam", "metric")
                              else ("—" if c in ("player", "name") else ""))
                         for c in cols}])
    return df


def load_players() -> pd.DataFrame:
    return _read_parquet_or_empty("players.parquet")


def load_fixtures() -> pd.DataFrame:
    return _read_parquet_or_empty("fixtures.parquet")


def load_predictions() -> pd.DataFrame:
    return _read_parquet_or_empty("predictions.parquet")


def load_lineups() -> pd.DataFrame:
    return _read_parquet_or_empty("lineups.parquet")


def load_votes() -> pd.DataFrame:
    return _read_parquet_or_empty("votes.parquet")


def load_model_metrics() -> pd.DataFrame:
    return _read_parquet_or_empty("model_metrics.parquet")