Merge pull request #29 from perpetual-ml/max_cat_fix

max_cat fix

Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "perpetual"
-version = "0.7.4"
+version = "0.7.5"
 edition = "2021"
 authors = ["Mutlu Simsek <[email protected]>"]
 homepage = "https://perpetual-ml.com"
@@ -22,7 +22,7 @@ codegen-units = 1
 [dependencies]
 rayon = "1.8"
 thiserror = "2.0.3"
-serde_json = { version = "1.0.132", features = ["float_roundtrip"] }
+serde_json = { version = "1.0.133", features = ["float_roundtrip"] }
 serde = { version = "1.0.215", features = ["derive"] }
 approx = "0.5"
 log = "0.4"

python-package/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "py-perpetual"
-version = "0.7.4"
+version = "0.7.5"
 edition = "2021"
 authors = ["Mutlu Simsek <[email protected]>"]
 homepage = "https://perpetual-ml.com"
@@ -19,7 +19,7 @@ crate-type = ["cdylib", "rlib"]
 
 [dependencies]
 pyo3 = { version = "0.22.6", features = ["extension-module"] }
-perpetual_rs = {package="perpetual", version = "0.7.4", path = "../" }
+perpetual_rs = {package="perpetual", version = "0.7.5", path = "../" }
 numpy = "0.22.1"
 ndarray = "0.16.1"
 serde_plain = { version = "1.0" }

python-package/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "maturin"
 
 [project]
 name = "perpetual"
-version = "0.7.4"
+version = "0.7.5"
 description = "A self-generalizing gradient boosting machine which doesn't need hyperparameter optimization"
 license = { file = "LICENSE" }
 keywords = [

python-package/python/perpetual/utils.py

@@ -123,7 +123,6 @@ def convert_input_frame(
                 logger.warning(
                     f"Feature {features_[i]} will be treated as numerical since the number of categories ({len(categories)}) exceeds max_cat ({max_cat}) threshold."
                 )
-                continue
             categories = [c for c in list(categories) if c != "nan"]
             categories.insert(0, "nan")
             cat_mapping[features_[i]] = categories

python-package/tests/test_booster.py

@@ -27,6 +27,20 @@ def X_y() -> Tuple[pd.DataFrame, pd.Series]:
     return X, y
 
 
+def test_booster_max_cat(X_y):
+    df = pd.read_csv("../resources/titanic.csv")
+    X = df.drop(columns="survived").reset_index(drop=True)
+    y = df["survived"]
+
+    num_cols = X.select_dtypes(include=np.number).columns.tolist()
+    all_cols = X.columns.tolist()
+    cat_cols = [x for x in all_cols if x not in num_cols]
+    X[cat_cols] = X[cat_cols].astype("category")
+
+    model = PerpetualBooster(objective="LogLoss", max_cat=4)
+    model.fit(X, y)
+
+
 def test_booster_no_variance(X_y):
     X, y = X_y
     X.iloc[:, 3] = 1

scripts/run-single-python-test.ps1

@@ -1,4 +1,4 @@
 Set-Location python-package
 maturin develop --release
-pytest tests/test_openml.py::test_sensory -s
+pytest tests/test_booster.py::test_booster_max_cat -s
 Set-Location ..