Create pitcher_arsenal_model.py

models/pitcher_arsenal_model.py

@@ -0,0 +1,47 @@
+from __future__ import annotations
+
+from typing import Any
+
+import pandas as pd
+
+from models.batter_zone_model import normalize_pitch_family
+
+
+def build_pitcher_arsenal_feature_row(
+    statcast_df: pd.DataFrame,
+    pitcher_name: str,
+) -> dict[str, Any]:
+    if statcast_df is None or statcast_df.empty:
+        return {"pitcher_name": pitcher_name, "arsenal_sample_size": 0}
+
+    if "player_name" not in statcast_df.columns:
+        return {"pitcher_name": pitcher_name, "arsenal_sample_size": 0}
+
+    df = statcast_df[statcast_df["player_name"].astype(str) == str(pitcher_name)].copy()
+    if df.empty:
+        return {"pitcher_name": pitcher_name, "arsenal_sample_size": 0}
+
+    if "pitch_name" in df.columns:
+        pitch_name_series = df["pitch_name"]
+    elif "pitch_type" in df.columns:
+        pitch_name_series = df["pitch_type"]
+    else:
+        pitch_name_series = pd.Series(["unknown"] * len(df), index=df.index)
+
+    df["pitch_family"] = pitch_name_series.apply(normalize_pitch_family)
+
+    total_count = float(len(df))
+
+    out: dict[str, Any] = {
+        "pitcher_name": pitcher_name,
+        "arsenal_sample_size": int(len(df)),
+    }
+
+    for family in ["fastball", "breaking", "offspeed"]:
+        family_count = int((df["pitch_family"] == family).sum())
+        usage_rate = float(family_count / total_count) if total_count > 0 else None
+
+        out[f"{family}_usage_rate"] = usage_rate
+        out[f"sample_size_{family}"] = family_count
+
+    return out