features/batter_features.py

from __future__ import annotations

import pandas as pd


def _safe_quantile(series: pd.Series, q: float) -> float:
    valid = pd.to_numeric(series, errors="coerce").dropna()
    if valid.empty:
        return 0.0
    return float(valid.quantile(q))


def batter_summary(df: pd.DataFrame) -> pd.DataFrame:
    if df.empty or "player_name" not in df.columns:
        return pd.DataFrame()

    rows: list[dict] = []

    for player_name, group in df.groupby("player_name"):
        launch_speed = pd.to_numeric(group["launch_speed"], errors="coerce") if "launch_speed" in group.columns else pd.Series(dtype=float)
        launch_angle = pd.to_numeric(group["launch_angle"], errors="coerce") if "launch_angle" in group.columns else pd.Series(dtype=float)
        xwoba = pd.to_numeric(group["xwoba"], errors="coerce") if "xwoba" in group.columns else pd.Series(dtype=float)

        hard_hit_rate = float((launch_speed >= 95).mean()) if len(launch_speed.dropna()) else 0.0
        barrel_like_rate = float(((launch_speed >= 98) & (launch_angle.between(26, 30))).mean()) if len(launch_speed.dropna()) else 0.0

        rows.append(
            {
                "player_name": player_name,
                "events": int(len(group)),
                "ev_avg": float(launch_speed.mean()) if len(launch_speed.dropna()) else 0.0,
                "ev90": _safe_quantile(launch_speed, 0.90),
                "la_avg": float(launch_angle.mean()) if len(launch_angle.dropna()) else 0.0,
                "hard_hit_rate": hard_hit_rate,
                "barrel_like_rate": barrel_like_rate,
                "xwoba_avg": float(xwoba.mean()) if len(xwoba.dropna()) else 0.0,
            }
        )

    out = pd.DataFrame(rows)
    return out.sort_values(["ev90", "xwoba_avg"], ascending=False).reset_index(drop=True)