anchorboosting 0.2.1__tar.gz → 0.3.0__tar.gz

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/.github/workflows/ci.yml

@@ -8,6 +8,28 @@ name: CI
 
 jobs:
 
+  asv-bench:
+    name: ASV Benchmarks
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+      - name: Set up micromamba
+        uses: mamba-org/setup-micromamba@d05808540d968a55ca33c798e0661fb98f533c73
+        with:
+          micromamba-version: 1.5.10-0
+          environment-file: benchmarks/environment.yml
+    
+      - name: Install repository
+        run: python -m pip install --no-build-isolation --no-deps --disable-pip-version-check -e .
+      - name: Run benchmarks
+        shell: bash -l {0}
+        run: |
+          asv machine --machine github --yes
+          # asv run --machine github --python=same
+          asv continuous origin/main HEAD -e --factor 1.05 --machine github --python=same
+
   test:
     name: Unit tests - ${{ matrix.PYTHON_VERSION }}
     runs-on: ubuntu-latest

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/CHANGELOG.rst

@@ -1,6 +1,12 @@
 Changelog
 =========
 
+0.3.0 (2025-09-15)
+------------------
+
+- Fixed handling of feature names for numpy input in `AnchorBooster`.
+- Added support for pandas DataFrame input in `AnchorBooster`.
+
 0.2.1 (2025-07-01)
 ------------------
 

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anchorboosting
-Version: 0.2.1
+Version: 0.3.0
 Summary: Efficient tree-based nonlinear anchor regression and classification
 Author-email: Malte Londschien <malte@londschien.ch>
 Project-URL: homepage, https://github.com/mlondschien/anchorboosting/
@@ -15,8 +15,15 @@ Dynamic: license-file
 
 # Anchor Boosting
 
-Efficient tree-based nonlinear anchor regression and classification for Python [1]
+Efficient tree-based nonlinear anchor regression and classification for Python.
 
-## References
+If you use this, please consider citing
 
-[1] Londschien, M., M. Burger, G. Rätsch, P. Bühlmann (2025). Working paper.
+```
+article{londschien2025,
+  title={Domain Generalization and Adaptation in Intensive Care with Anchor Regression},
+  author={Londschien, Malte, Burger, Manuel, R{\"a}tsch, Gunnar and B{\"u}hlmann, Peter},
+  journal={arXiv preprint arXiv:2507.21783},
+  year={2025}
+}
+```

anchorboosting-0.3.0/README.md

@@ -0,0 +1,14 @@
+# Anchor Boosting
+
+Efficient tree-based nonlinear anchor regression and classification for Python.
+
+If you use this, please consider citing
+
+```
+article{londschien2025,
+  title={Domain Generalization and Adaptation in Intensive Care with Anchor Regression},
+  author={Londschien, Malte, Burger, Manuel, R{\"a}tsch, Gunnar and B{\"u}hlmann, Peter},
+  journal={arXiv preprint arXiv:2507.21783},
+  year={2025}
+}
+```

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/anchorboosting/models.py

@@ -174,7 +174,9 @@ class AnchorBooster:
             )
 
         if hasattr(X, "columns"):
-            feature_name = X.columns
+            feature_name = list(X.columns)
+        else:
+            feature_name = None
 
         if _POLARS_INSTALLED and isinstance(X, pl.DataFrame):
             X = X.to_arrow()

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/anchorboosting/simulate.py

@@ -2,7 +2,7 @@ import numpy as np
 import polars as pl
 
 
-def simulate(f, n=100, shift=0, seed=0):
+def simulate(f, n=100, shift=0, seed=0, return_dtype="polars"):
     rng = np.random.RandomState(seed)
 
     p = 3
@@ -23,6 +23,15 @@ def simulate(f, n=100, shift=0, seed=0):
         schema={"x1": pl.Float64, "x2": pl.Float64, "x3": pl.Int64},
     )
 
+    if return_dtype == "numpy":
+        df = df.to_numpy()
+        a = a.astype(np.float32)
+        y = y.astype(np.float32)
+    elif return_dtype == "pandas":
+        df = df.to_pandas()
+        a = a.astype(np.float32)
+        y = y.astype(np.float32)
+
     return df, y, a
 
 

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/anchorboosting.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: anchorboosting
-Version: 0.2.1
+Version: 0.3.0
 Summary: Efficient tree-based nonlinear anchor regression and classification
 Author-email: Malte Londschien <malte@londschien.ch>
 Project-URL: homepage, https://github.com/mlondschien/anchorboosting/
@@ -15,8 +15,15 @@ Dynamic: license-file
 
 # Anchor Boosting
 
-Efficient tree-based nonlinear anchor regression and classification for Python [1]
+Efficient tree-based nonlinear anchor regression and classification for Python.
 
-## References
+If you use this, please consider citing
 
-[1] Londschien, M., M. Burger, G. Rätsch, P. Bühlmann (2025). Working paper.
+```
+article{londschien2025,
+  title={Domain Generalization and Adaptation in Intensive Care with Anchor Regression},
+  author={Londschien, Malte, Burger, Manuel, R{\"a}tsch, Gunnar and B{\"u}hlmann, Peter},
+  journal={arXiv preprint arXiv:2507.21783},
+  year={2025}
+}
+```

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/anchorboosting.egg-info/SOURCES.txt

@@ -3,6 +3,7 @@
 CHANGELOG.rst
 LICENSE
 README.md
+asv.conf.json
 environment.yml
 pyproject.toml
 readthedocs.yaml
@@ -16,6 +17,11 @@ anchorboosting.egg-info/SOURCES.txt
 anchorboosting.egg-info/dependency_links.txt
 anchorboosting.egg-info/requires.txt
 anchorboosting.egg-info/top_level.txt
+benchmarks/__init__.py
+benchmarks/benchmark.py
+benchmarks/environment.yml
+benchmarks/load.py
+benchmarks/data/.gitignore
 docs/Makefile
 docs/bib.bib
 docs/changelog.rst

anchorboosting-0.3.0/asv.conf.json

@@ -0,0 +1,18 @@
+{
+    "version": 1,
+    "branches": ["main"],
+    "project": "anchorboosting",
+    "project_url": "https://github.com/mlondschien/anchorboosting",
+    "repo": "..",
+    "environment_type": "conda",
+    "show_commit_url": "https://github.com/mlondschien/anchorboosting/commit/",
+    "pythons": ["3.12"],
+    "conda_channels": ["conda-forge"],
+    "build_command": "",
+    "install_command": "python -mpip install --no-deps .",
+    "conda_environment_file": "benchmarks/environment.yml",
+    "benchmark_dir": "benchmarks",
+    "env_dir": ".asv/env",
+    "results_dir": ".asv/results",
+    "html_dir": ".asv/html"
+}

anchorboosting-0.3.0/benchmarks/benchmark.py

@@ -0,0 +1,77 @@
+import timeit
+from abc import ABC, abstractmethod
+from typing import Any
+
+from lightgbm import LGBMModel
+
+from anchorboosting import AnchorBooster
+
+from .load import load_nyc_taxi
+
+
+class Benchmark(ABC):
+    # Measure wall time instead of CPU usage
+    timer = timeit.default_timer
+
+    name = ""
+
+    params: Any
+    param_names: Any
+
+    def setup(self, *params):
+        self._setup_data(params)
+        self._setup_model(params)
+
+    def _setup_data(self, params):
+        idx = self.param_names.index("n")
+        n = params[idx]
+        self.X, self.Z, self.y, self.y_binary = load_nyc_taxi(n)
+
+    @abstractmethod  # Required for asv to skip.
+    def _setup_model(self, params):
+        pass
+
+
+class AnchorBoosterBenchmark(Benchmark):
+    def __init__(self, n_jobs=2):
+        self.n_jobs = n_jobs  # GitHub CI has two nodes.
+
+    name = "AnchorBooster"
+    param_names = ["objective", "n", "num_boost_round", "max_depth"]
+    params = (["regression", "binary"], [100_000], [100], [3])
+
+    def _setup_model(self, params):
+        objective, _, num_boost_round, max_depth = params
+        self.model = AnchorBooster(
+            gamma=2,
+            num_boost_round=num_boost_round,
+            max_depth=max_depth,
+            n_jobs=self.n_jobs,
+            objective=objective,
+        )
+
+    def time_fit(self, *args):
+        y = self.y_binary if self.model.objective == "binary" else self.y
+        self.model.fit(self.X, y, self.Z)
+
+
+class LGBMBenchmark(Benchmark):
+    def __init__(self, n_jobs=2):
+        self.n_jobs = n_jobs  # GitHub CI has two nodes.
+
+    name = "LGBM Booster"
+    param_names = ["objective", "n", "num_boost_round", "max_depth"]
+    params = (["regression", "binary"], [100_000], [100], [3])
+
+    def _setup_model(self, params):
+        objective, _, num_boost_round, max_depth = params
+        self.model = LGBMModel(
+            num_boost_round=num_boost_round,
+            max_depth=max_depth,
+            objective=objective,
+            n_jobs=self.n_jobs,
+        )
+
+    def time_fit(self, *args):
+        y = self.y_binary if self.model.objective == "binary" else self.y
+        self.model.fit(self.X, y)

anchorboosting-0.3.0/benchmarks/data/.gitignore

@@ -0,0 +1 @@
+*.parquet

anchorboosting-0.3.0/benchmarks/environment.yml

@@ -0,0 +1,14 @@
+name: benchmarks
+channels:
+  - conda-forge
+  - nodefaults
+dependencies:
+  - python =3.12
+  - numpy
+  - lightgbm
+  - asv
+  - scikit-learn <=1.5.2  # https://github.com/microsoft/LightGBM/issues/6849
+  - polars
+  - pyarrow
+  - cffi  # https://github.com/microsoft/LightGBM/pull/6785
+  - libmambapy

anchorboosting-0.3.0/benchmarks/load.py

@@ -0,0 +1,110 @@
+# From https://github.com/xhochy/nyc-taxi-fare-prediction-deployment-example
+from pathlib import Path
+
+import polars as pl
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import OrdinalEncoder
+
+DATA_PATH = Path(__file__).resolve().parent / "data"
+NYC_TAXI_DATASET_PATH = DATA_PATH / "nyc_taxi_data.parquet"
+NYC_TAXI_DATASET_URL = (
+    "https://d37ci6vzurychx.cloudfront.net/trip-data/yellow_tripdata_2019-01.parquet"
+)
+NYC_TAXI_BURROWS_PATH = DATA_PATH / "nyc_taxi_burrows.parquet"
+NYC_TAXI_BURROWS_URL = "https://d37ci6vzurychx.cloudfront.net/misc/taxi_zone_lookup.csv"
+
+
+def load_nyc_taxi_raw():
+    if NYC_TAXI_DATASET_PATH.exists():
+        return pl.read_parquet(NYC_TAXI_DATASET_PATH)
+    else:
+        df = pl.read_parquet(NYC_TAXI_DATASET_URL)
+        df.write_parquet(NYC_TAXI_DATASET_PATH)
+        return df
+
+
+def load_nyc_taxi_burrows():
+    if NYC_TAXI_BURROWS_PATH.exists():
+        return pl.read_parquet(NYC_TAXI_BURROWS_PATH)
+    else:
+        df = pl.read_csv(NYC_TAXI_BURROWS_URL)
+        df.write_parquet(NYC_TAXI_BURROWS_PATH)
+        return df
+
+
+def load_nyc_taxi(n):
+    df = load_nyc_taxi_raw().head(n)
+
+    burrows = load_nyc_taxi_burrows()
+
+    df = (
+        df.filter(pl.col("total_amount").is_not_null() & pl.col("total_amount").gt(0))
+        .join(
+            burrows.with_columns(pl.col("Borough").alias("pickup_borough")),
+            left_on="PULocationID",
+            right_on="LocationID",
+            how="left",
+        )
+        .join(
+            burrows.with_columns(pl.col("Borough").alias("dropoff_borough")),
+            left_on="DOLocationID",
+            right_on="LocationID",
+            how="left",
+        )
+        .with_columns(
+            pl.col("total_amount").log().alias("total_amount_log"),
+            pl.col("tpep_pickup_datetime").dt.weekday().alias("pickup_weekday"),
+            pl.col("tpep_pickup_datetime").dt.hour().alias("pickup_hour"),
+            pl.col("tpep_pickup_datetime").dt.minute().alias("pickup_minute"),
+            pl.col("pickup_borough").fill_null("Unknown").alias("pickup_borough"),
+        )
+    )
+
+    continuous_columns = [
+        "passenger_count",
+        "trip_distance",
+        "extra",
+        "mta_tax",
+        "tip_amount",
+        "tolls_amount",
+        "improvement_surcharge",
+        "congestion_surcharge",
+        "pickup_hour",
+        "pickup_minute",
+    ]
+    df = df.with_columns(pl.col(c).cast(pl.Float64) for c in continuous_columns)
+
+    ordinal_columns = [
+        "VendorID",
+        "RatecodeID",
+        "store_and_fwd_flag",
+        "payment_type",
+        "service_zone",
+        "Borough",
+        "Zone",
+        "pickup_weekday",
+        "pickup_borough",
+        "dropoff_borough",
+    ]
+
+    preprocessor = ColumnTransformer(
+        transformers=[
+            ("continuous", "passthrough", continuous_columns),
+            (
+                "categorical",
+                OrdinalEncoder(
+                    handle_unknown="use_encoded_value",
+                    unknown_value=-1,
+                ),
+                ordinal_columns,
+            ),
+        ]
+    ).set_output(transform="polars")
+
+    y = df.select(pl.col("total_amount_log")).to_numpy().ravel()
+    y_binary = (y > y.mean()).astype(int)
+
+    X = preprocessor.fit_transform(df)
+    Z = X.select("categorical__Zone").to_numpy().astype("int32").ravel()
+
+    return X.drop("categorical__Zone"), Z, y, y_binary

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/docs/index.rst

@@ -30,7 +30,7 @@ API Reference
    :maxdepth: 1
    :caption: Other
 
-   GitHub <https://github.com/mlondschien/ivmodels>
+   GitHub <https://github.com/mlondschien/anchorboosting>
    changelog
 
 

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/environment.yml

@@ -11,6 +11,7 @@ dependencies:
   - pip  # build
   - pytest-cov  # tests
   - pytest  # tests
+  - pandas  # tests
   - polars  # tests
   - pyarrow  # tests
   - sphinx  # docs

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/pyproject.toml

@@ -5,7 +5,7 @@ requires = ['setuptools', 'setuptools-scm', 'wheel']
 name = "anchorboosting"
 description = "Efficient tree-based nonlinear anchor regression and classification"
 readme = "README.md"
-version = "0.2.1"
+version = "0.3.0"
 requires-python = ">=3.9"
 authors = [
     { name = "Malte Londschien", email = "malte@londschien.ch" }

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/tests/test_anchor_boosting.py

@@ -10,13 +10,14 @@ from anchorboosting.simulate import f1, simulate
 @pytest.mark.parametrize("gamma", [1.0, 2.0, 100])
 @pytest.mark.parametrize("objective", ["regression", "binary"])
 @pytest.mark.parametrize("categorical_z", [True, False])
-def test_anchor_boosting_second_order(gamma, objective, categorical_z):
+@pytest.mark.parametrize("input_dtype", ["polars", "numpy"])
+def test_anchor_boosting_second_order(gamma, objective, categorical_z, input_dtype):
     learning_rate = 0.1
     num_leaves = 5
     n = 200
     num_boost_round = 10
 
-    x, y, a = simulate(f1, n=n, shift=0, seed=0)
+    x, y, a = simulate(f1, n=n, shift=0, seed=0, return_dtype=input_dtype)
     if categorical_z:
         a = np.digitize(a[:, 0], bins=[-1, 0, 1, 2, 3])
         assert np.issubdtype(a.dtype, np.integer)
@@ -36,7 +37,7 @@ def test_anchor_boosting_second_order(gamma, objective, categorical_z):
     f = model.predict(x, num_iteration=num_boost_round - 1, raw_score=True)
 
     leaves = model.booster_.predict(
-        x.to_arrow(),
+        x.to_arrow() if hasattr(x, "to_arrow") else x,
         pred_leaf=True,
         start_iteration=num_boost_round - 1,
         num_iteration=1,
@@ -144,8 +145,19 @@ def test_anchor_boosting_decreases_loss(gamma, objective):
         {"lambda_l2": 0.1},
     ],
 )
-def test_compare_anchor_boosting_to_lgbm(parameters):
-    X, y, a = simulate(f1, shift=0, seed=0)
+@pytest.mark.parametrize("input_dtype", ["polars", "numpy", "pandas"])
+def test_compare_anchor_boosting_to_lgbm(parameters, input_dtype):
+    X, y, a = simulate(f1, shift=0, seed=0, return_dtype=input_dtype)
+
+    if input_dtype == "polars":
+        X_arrow = X.to_arrow()
+        categorical_feature = ["x3"]
+    elif input_dtype == "pandas":
+        X_arrow = X
+        categorical_feature = ["x3"]
+    elif input_dtype == "numpy":
+        X_arrow = X
+        categorical_feature = [2]
 
     lgbm_model = lgb.train(
         params={
@@ -153,7 +165,7 @@ def test_compare_anchor_boosting_to_lgbm(parameters):
             "objective": "regression",
             **parameters,
         },
-        train_set=lgb.Dataset(X.to_arrow(), y, categorical_feature=[2]),
+        train_set=lgb.Dataset(X_arrow, y, categorical_feature=[2]),
         num_boost_round=50,
     )
 
@@ -163,7 +175,7 @@ def test_compare_anchor_boosting_to_lgbm(parameters):
         objective="regression",
         learning_rate=0.1,
         **parameters,
-    ).fit(X, y, Z=a, categorical_feature=["x3"])
+    ).fit(X, y, Z=a, categorical_feature=categorical_feature)
 
     anchor_booster_noncat = AnchorBooster(
         gamma=1,
@@ -173,7 +185,7 @@ def test_compare_anchor_boosting_to_lgbm(parameters):
         **parameters,
     ).fit(X, y, Z=a)
 
-    lgbm_pred = lgbm_model.predict(X.to_arrow())
+    lgbm_pred = lgbm_model.predict(X_arrow)
     anchor_booster_pred = anchor_booster.predict(X)
     anchor_booster_noncat_pred = anchor_booster_noncat.predict(X)
 
@@ -181,6 +193,38 @@ def test_compare_anchor_boosting_to_lgbm(parameters):
     assert not np.allclose(lgbm_pred, anchor_booster_noncat_pred)
 
 
+@pytest.mark.parametrize("gamma", [1, 10])
+def test_compare_input_types(gamma):
+    X_polars, y_polars, a_polars = simulate(f1, shift=0, seed=0, return_dtype="polars")
+    X_numpy, y_numpy, a_numpy = simulate(f1, shift=0, seed=0, return_dtype="numpy")
+    X_pandas, y_pandas, a_pandas = simulate(f1, shift=0, seed=0, return_dtype="pandas")
+
+    model_polars = AnchorBooster(
+        gamma=gamma,
+        num_boost_round=10,
+        objective="regression",
+    ).fit(X_polars, y_polars, Z=a_polars)
+
+    model_numpy = AnchorBooster(
+        gamma=gamma,
+        num_boost_round=10,
+        objective="regression",
+    ).fit(X_numpy, y_numpy, Z=a_numpy)
+
+    model_pandas = AnchorBooster(
+        gamma=gamma,
+        num_boost_round=10,
+        objective="regression",
+    ).fit(X_pandas, y_pandas, Z=a_pandas)
+
+    pred_pandas = model_pandas.predict(X_pandas)
+    pred_polars = model_polars.predict(X_polars)
+    pred_numpy = model_numpy.predict(X_numpy)
+
+    np.testing.assert_allclose(pred_polars, pred_numpy, rtol=1e-5)
+    np.testing.assert_allclose(pred_polars, pred_pandas, rtol=1e-5)
+
+
 @pytest.mark.parametrize("objective", ["regression", "binary"])
 def test_categorical_and_onehot_is_the_same(objective):
     X, y, a = simulate(f1, shift=0, seed=0)

{anchorboosting-0.2.1 → anchorboosting-0.3.0}/tests/test_refit.py

@@ -9,9 +9,10 @@ from anchorboosting.simulate import f1, f2, simulate
 @pytest.mark.parametrize("seed", [0, 1])
 @pytest.mark.parametrize("fun", [f1, f2])
 @pytest.mark.parametrize("objective", ["regression", "binary"])
-def test_refit(objective, seed, fun):
+@pytest.mark.parametrize("input_dtype", ["numpy", "pandas", "polars"])
+def test_refit(objective, seed, fun, input_dtype):
 
-    X, y, a = simulate(fun, shift=0, seed=seed)
+    X, y, a = simulate(fun, shift=0, seed=seed, return_dtype=input_dtype)
 
     if objective == "binary":
         y = (y > 0).astype(int)

anchorboosting-0.2.1/README.md

@@ -1,7 +0,0 @@
-# Anchor Boosting
-
-Efficient tree-based nonlinear anchor regression and classification for Python [1]
-
-## References
-
-[1] Londschien, M., M. Burger, G. Rätsch, P. Bühlmann (2025). Working paper.