backcaster 0.3.4__tar.gz → 0.3.5__tar.gz

{backcaster-0.3.4/src/backcaster.egg-info → backcaster-0.3.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: backcaster
-Version: 0.3.4
+Version: 0.3.5
 Summary: Marcel-style MLB projection CLI using local Lahman CSV data
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/jeffreywevans/backcaster
@@ -56,10 +56,10 @@ Upgrade to the latest release available on PyPI:
 python -m pip install --upgrade backcaster
 ```
 
-To install a specific release, such as 0.3.4:
+To install a specific release, such as 0.3.5:
 
 ```powershell
-python -m pip install --upgrade backcaster==0.3.4
+python -m pip install --upgrade backcaster==0.3.5
 ```
 
 Run the command using the same Python environment where you run Backcaster.
@@ -123,8 +123,8 @@ All projections use local Lahman CSVs. On Windows, the default directory is
 Set the `LAHMAN_DATA_DIR` environment variable to change the default, or pass
 `--data-dir` to override it for one command. No network requests or online
 fallbacks are made. The directory must contain `People.csv`, `Teams.csv`, and
-`Batting.csv` or `Pitching.csv` for the selected kind. Batter projections also
-require `Appearances.csv` and a valid `birthYear` in `People.csv`. Filenames are matched
+`Batting.csv` or `Pitching.csv` for the selected kind. Both kinds require valid
+`birthYear` values in `People.csv`; batters additionally require `Appearances.csv`. Filenames are matched
 without regard to case. The database is not bundled with Backcaster.
 
 For the default Windows directory, no additional flag is needed:
@@ -166,7 +166,8 @@ ambiguous name lookups report the matching IDs.
 
 Batter league regression and rebaselining use all non-pitcher player-seasons;
 qualification selects the displayed players. Pitching retains its qualified-only
-baseline. See [the batter model](docs/BATTER_MODEL.md) for the six-stage calculation,
+baseline, with real-age performance adjustments documented in
+[the pitcher model](docs/PITCHER_MODEL.md). See [the batter model](docs/BATTER_MODEL.md) for the six-stage calculation,
 real-age adjustment, PA formula, and explicit rebaselining choices.
 Single-player projections require qualification in all three preceding seasons.
 Team and batch projections use each player's available qualified seasons within

{backcaster-0.3.4 → backcaster-0.3.5}/README.md

@@ -25,10 +25,10 @@ Upgrade to the latest release available on PyPI:
 python -m pip install --upgrade backcaster
 ```
 
-To install a specific release, such as 0.3.4:
+To install a specific release, such as 0.3.5:
 
 ```powershell
-python -m pip install --upgrade backcaster==0.3.4
+python -m pip install --upgrade backcaster==0.3.5
 ```
 
 Run the command using the same Python environment where you run Backcaster.
@@ -92,8 +92,8 @@ All projections use local Lahman CSVs. On Windows, the default directory is
 Set the `LAHMAN_DATA_DIR` environment variable to change the default, or pass
 `--data-dir` to override it for one command. No network requests or online
 fallbacks are made. The directory must contain `People.csv`, `Teams.csv`, and
-`Batting.csv` or `Pitching.csv` for the selected kind. Batter projections also
-require `Appearances.csv` and a valid `birthYear` in `People.csv`. Filenames are matched
+`Batting.csv` or `Pitching.csv` for the selected kind. Both kinds require valid
+`birthYear` values in `People.csv`; batters additionally require `Appearances.csv`. Filenames are matched
 without regard to case. The database is not bundled with Backcaster.
 
 For the default Windows directory, no additional flag is needed:
@@ -135,7 +135,8 @@ ambiguous name lookups report the matching IDs.
 
 Batter league regression and rebaselining use all non-pitcher player-seasons;
 qualification selects the displayed players. Pitching retains its qualified-only
-baseline. See [the batter model](docs/BATTER_MODEL.md) for the six-stage calculation,
+baseline, with real-age performance adjustments documented in
+[the pitcher model](docs/PITCHER_MODEL.md). See [the batter model](docs/BATTER_MODEL.md) for the six-stage calculation,
 real-age adjustment, PA formula, and explicit rebaselining choices.
 Single-player projections require qualification in all three preceding seasons.
 Team and batch projections use each player's available qualified seasons within

{backcaster-0.3.4 → backcaster-0.3.5}/THIRD_PARTY_NOTICES.md

@@ -12,11 +12,13 @@ Reference revision: `13a1c7943f5a7317c9c812a28e299c2184060046` (March 1, 2020).
 See [reference and adaptation notes](docs/MARCELR_REFERENCE.md) for the files
 reviewed, formulas examined, current differences, and attribution practices.
 
-At the time this notice was added, marcelR source had been inspected, but no R
-source had been copied or translated into Backcaster, and its datasets had not
-been bundled. Backcaster does not depend on R or marcelR. The notice is retained
-for acknowledgment and to accompany future attributed adaptations. Neither the
-review nor the acknowledgment implies endorsement or verified numerical parity.
+Backcaster's pitcher-aging equations in `src/backcaster/marcel.py` are adapted
+from the age-adjustment formulas in marcelR's `R/utilities.R` and their stat-specific
+application in `inst/scripts/marcel_data_exporter.R` at the revision above.
+The implementation is Python, with local birth-year validation and unchanged
+pitching opportunities; it is not a complete port of marcelR. No marcelR datasets
+are bundled. Backcaster does not depend on R or marcelR. Attribution does not
+imply endorsement or verified numerical parity.
 
 The following is marcelR's MIT license notice, reproduced without changes:
 

{backcaster-0.3.4 → backcaster-0.3.5}/src/backcaster/__init__.py

@@ -1,4 +1,4 @@
 """backcaster package."""
 
 __all__ = ["__version__"]
-__version__ = "0.3.4"
+__version__ = "0.3.5"

{backcaster-0.3.4 → backcaster-0.3.5}/src/backcaster/lahman.py

@@ -124,6 +124,7 @@ class LahmanSource:
         if kind == "batting":
             seasons, batting = self._batting_population(year)
         else:
+            self.read("People", {"playerID", "nameFirst", "nameLast", "birthYear"})
             seasons = pd.concat(
                 [self.season(y, kind) for y in (year - 1, year - 2, year - 3)], ignore_index=True
             )

{backcaster-0.3.4 → backcaster-0.3.5}/src/backcaster/marcel.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import math
+
 import pandas as pd
 
 from backcaster.normalize import safe_divide
@@ -14,6 +16,26 @@ BATTING_COMPONENTS = ["PA", "AB", "H", "2B", "3B", "HR", "BB", "SO", "HBP", "SF"
 PITCHING_COMPONENTS = ["IP", "ER", "H", "HR", "BB", "SO", "BF"]
 
 
+def _pitcher_age(prior: pd.DataFrame, year: int, fallback: float) -> float:
+    age = fallback
+    if "birthYear" in prior:
+        age = year - float(pd.to_numeric(prior["birthYear"].iloc[0], errors="coerce"))
+    if not math.isfinite(age) or not 15 <= age <= 70:
+        raise ProjectionError("A valid birthYear or explicit age is required for pitcher aging.")
+    return age
+
+
+def _age_pitching(counts: pd.Series, age: float) -> pd.Series:
+    # Equations adapted from Ben Dilday's marcelR, utilities.R and
+    # inst/scripts/marcel_data_exporter.R, revision 13a1c7943f5a7317c9c812a28e299c2184060046.
+    # Copyright (c) 2017 Ben Dilday, MIT; see THIRD_PARTY_NOTICES.md.
+    benefit = 1 / (1 + 0.003 * (age - 29)) if age > 29 else 1 + 0.006 * (29 - age)
+    result = counts.copy()
+    result[["ER", "H", "HR", "BB"]] /= benefit
+    result["SO"] *= benefit
+    return result
+
+
 def _weighted_row(
     rows: list[pd.Series], weights: tuple[float, float, float], cols: list[str]
 ) -> pd.Series:
@@ -148,7 +170,7 @@ def project_player(
         regressed[c] = regressed_rate * weighted_pt
 
     growth = config.default_pa_growth if kind == "batting" else config.default_ip_growth
-    age_adj = config.age_adjustment_fn(age)
+    age_adj = config.age_adjustment_fn(age) if kind == "batting" else 1.0
     projected_pt = weighted_pt * growth * age_adj
     pt_scale = safe_divide(projected_pt, weighted_pt)
     regressed *= pt_scale
@@ -156,12 +178,16 @@ def project_player(
     if kind == "batting":
         rates = _derive_batting_rates(regressed)
     else:
+        age = _pitcher_age(prior_df, year, age)
+        regressed = _age_pitching(regressed, age)
         rates = _derive_pitching_rates(regressed)
 
     output = pd.concat([regressed, rates])
     output["Reliability"] = reliability
     output["Name"] = player_name
     output["Year"] = year
+    if kind == "pitching":
+        output["Age"] = age
     return output.to_frame().T
 
 

{backcaster-0.3.4 → backcaster-0.3.5/src/backcaster.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: backcaster
-Version: 0.3.4
+Version: 0.3.5
 Summary: Marcel-style MLB projection CLI using local Lahman CSV data
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/jeffreywevans/backcaster
@@ -56,10 +56,10 @@ Upgrade to the latest release available on PyPI:
 python -m pip install --upgrade backcaster
 ```
 
-To install a specific release, such as 0.3.4:
+To install a specific release, such as 0.3.5:
 
 ```powershell
-python -m pip install --upgrade backcaster==0.3.4
+python -m pip install --upgrade backcaster==0.3.5
 ```
 
 Run the command using the same Python environment where you run Backcaster.
@@ -123,8 +123,8 @@ All projections use local Lahman CSVs. On Windows, the default directory is
 Set the `LAHMAN_DATA_DIR` environment variable to change the default, or pass
 `--data-dir` to override it for one command. No network requests or online
 fallbacks are made. The directory must contain `People.csv`, `Teams.csv`, and
-`Batting.csv` or `Pitching.csv` for the selected kind. Batter projections also
-require `Appearances.csv` and a valid `birthYear` in `People.csv`. Filenames are matched
+`Batting.csv` or `Pitching.csv` for the selected kind. Both kinds require valid
+`birthYear` values in `People.csv`; batters additionally require `Appearances.csv`. Filenames are matched
 without regard to case. The database is not bundled with Backcaster.
 
 For the default Windows directory, no additional flag is needed:
@@ -166,7 +166,8 @@ ambiguous name lookups report the matching IDs.
 
 Batter league regression and rebaselining use all non-pitcher player-seasons;
 qualification selects the displayed players. Pitching retains its qualified-only
-baseline. See [the batter model](docs/BATTER_MODEL.md) for the six-stage calculation,
+baseline, with real-age performance adjustments documented in
+[the pitcher model](docs/PITCHER_MODEL.md). See [the batter model](docs/BATTER_MODEL.md) for the six-stage calculation,
 real-age adjustment, PA formula, and explicit rebaselining choices.
 Single-player projections require qualification in all three preceding seasons.
 Team and batch projections use each player's available qualified seasons within

{backcaster-0.3.4 → backcaster-0.3.5}/tests/test_lahman.py

@@ -337,3 +337,24 @@ def test_missing_birth_year_column(lahman: Path) -> None:
     source = LahmanSource(str(lahman))
     with pytest.raises(DataFetchError, match="birthYear"):
         source.project("batch", 2022, "batting")
+
+
+def test_pitcher_aging_consistent_across_commands(lahman: Path) -> None:
+    source = LahmanSource(str(lahman))
+    player = source.project("player", 2022, "pitching", name="Test Star").iloc[0]
+    team = source.project("team", 2022, "pitching", team="BOS")
+    batch = source.project("batch", 2022, "pitching")
+    assert player["Age"] == 32
+    assert player["IP"] == pytest.approx(487 / 3)
+    for result in [team, batch]:
+        row = result[result.Name == "Test Star"].iloc[0]
+        for stat in ["IP", "SO", "ERA", "WHIP", "Age"]:
+            assert row[stat] == pytest.approx(player[stat])
+
+
+def test_pitcher_requires_birth_year(lahman: Path) -> None:
+    path = lahman / "People.csv"
+    pd.read_csv(path).drop(columns="birthYear").to_csv(path, index=False)
+    source = LahmanSource(str(lahman))
+    with pytest.raises(DataFetchError, match="birthYear"):
+        source.project("batch", 2022, "pitching")

{backcaster-0.3.4 → backcaster-0.3.5}/tests/test_marcel_math.py

@@ -408,3 +408,30 @@ def test_one_season_regression_uses_only_available_weights() -> None:
     result = project_player("One Season", prior, "batting", 2025, league_rates=rates)
     assert float(result.loc[0, "HR"]) / float(result.loc[0, "PA"]) == pytest.approx(324 / 4200)
     assert float(result.loc[0, "Reliability"]) == pytest.approx(3000 / 4200)
+
+
+@pytest.mark.parametrize("age, factor", [(25, 1.024), (29, 1.0), (34, 1 / 1.015)])
+def test_pitcher_age_curve_changes_rates_not_opportunities(age: int, factor: float) -> None:
+    neutral = project_player("Pitcher", _pitching_prior(), "pitching", 2026, age=29).iloc[0]
+    result = project_player("Pitcher", _pitching_prior(), "pitching", 2026, age=age).iloc[0]
+    assert result["IP"] == pytest.approx(neutral["IP"])
+    assert result["BF"] == pytest.approx(neutral["BF"])
+    assert result["Reliability"] == pytest.approx(neutral["Reliability"])
+    for stat in ["ER", "H", "HR", "BB", "ERA", "WHIP"]:
+        assert result[stat] == pytest.approx(neutral[stat] / factor)
+    assert result["SO"] == pytest.approx(neutral["SO"] * factor)
+    assert result["Age"] == age
+
+
+def test_pitcher_birth_year_overrides_default_age() -> None:
+    prior = _pitching_prior().assign(birthYear=1992)
+    actual = project_player("Pitcher", prior, "pitching", 2026)
+    expected = project_player("Pitcher", _pitching_prior(), "pitching", 2026, age=34)
+    pd.testing.assert_frame_equal(actual, expected)
+
+
+@pytest.mark.parametrize("birth", [float("nan"), float("inf"), "unknown", 1800, 2025])
+def test_pitcher_invalid_birth_year(birth: object) -> None:
+    prior = _pitching_prior().assign(birthYear=birth)
+    with pytest.raises(ProjectionError, match="valid birthYear"):
+        project_player("Pitcher", prior, "pitching", 2026)