Fix/nominal attr mapping

rulekit/_helpers.py

@@ -24,6 +24,40 @@
 from rulekit.rules import BaseRule
 
 
+def _missing_to_none(value: Any) -> Any:
+    """Map pandas/numpy missing values to None for the Java DataTable.
+
+    Args:
+        value: A single cell value.
+
+    Returns:
+        None if the value is missing, otherwise the original value.
+    """
+    if value is None:
+        return None
+    try:
+        if pd.isna(value):
+            return None
+    except (TypeError, ValueError):
+        pass
+    return value
+
+
+def _to_java_object_array(values: np.ndarray) -> np.ndarray:
+    """Copy an array to dtype=object with missing cells as None.
+
+    Args:
+        values: Array produced from a pandas frame or series.
+
+    Returns:
+        Object array safe to pass through JPype into DataTable.
+    """
+    result = np.empty(values.shape, dtype=object)
+    for index, value in np.ndenumerate(values):
+        result[index] = _missing_to_none(value)
+    return result
+
+
 def get_rule_generator(expert: bool = False) -> Any:
     """Factory for Java RuleGenerator class object
 
@@ -259,7 +293,7 @@ def _sanitize_y(self, y: Union[pd.Series, np.ndarray, list]):
         elif isinstance(y, pd.Series):
             self._label_name = y.name
             self._attributes_names.append(self._label_name)
-            self._y = y.to_numpy()
+            self._y = _to_java_object_array(y.to_numpy())
         elif isinstance(y, list):
             self._label_name = self.DEFAULT_LABEL_ATTRIBUTE_NAME
             self._attributes_names.append(self._label_name)
@@ -281,9 +315,7 @@ def _sanitize_X(
     ) -> tuple[np.ndarray, np.ndarray]:
         if isinstance(X, pd.DataFrame):
             self._attributes_names = X.columns.tolist()
-            # replace nan values with None
-            X = X.where(pd.notnull(X), None)
-            self._X = X.to_numpy()
+            self._X = _to_java_object_array(X.astype(object).to_numpy())
         elif isinstance(X, np.ndarray):
             self._attributes_names = [
                 f"{self.AUTOMATIC_ATTRIBUTES_NAMES_PREFIX}{index + 1}"

rulekit/_operator.py

@@ -1,5 +1,5 @@
-"""Contains base classes for rule induction operators
-"""
+"""Contains base classes for rule induction operators"""
+
 from __future__ import annotations
 
 from abc import ABC
@@ -79,9 +79,7 @@ def fit(  # pylint: disable=missing-function-docstring
         self.model = RuleSet[BaseRule](java_model)
         return self.model
 
-    def predict(
-        self, values: Data
-    ) -> np.ndarray:  # pylint: disable=missing-function-docstring
+    def predict(self, values: Data) -> np.ndarray:  # pylint: disable=missing-function-docstring
         if self.model is None:
             raise ValueError('"fit" method must be called before calling this method')
         example_set = ExampleSetFactory(self._get_problem_type()).make(values)
@@ -90,7 +88,8 @@ def predict(
         )
 
     def get_params(
-        self, deep: bool = True  # pylint: disable=unused-argument
+        self,
+        deep: bool = True,  # pylint: disable=unused-argument
     ) -> dict[str, Any]:
         """
         Parameters
@@ -146,6 +145,17 @@ def get_coverage_matrix(self, values: Data) -> np.ndarray:
         if self.model is None:
             raise ValueError('"fit" method must be called before calling this method')
         example_set = ExampleSetFactory(self._get_problem_type()).make(values)
+
+        # update mapping for nominal attributes
+        header = self.model._java_object.getTrainingHeader()
+        if header is not None:
+            try:
+                example_set = example_set.updateMapping(header)
+            except Exception as e:
+                raise ValueError(
+                    "Error updating mapping. Check if the given set agrees with the training set."
+                ) from e
+
         covering_info = self.model.covering(example_set)
         if isinstance(values, (pd.Series, pd.DataFrame)):
             values = values.to_numpy()

rulekit/main.py

@@ -14,7 +14,7 @@
 
 from rulekit._logging import _RuleKitJavaLoggerConfig
 
-__RULEKIT_RELEASE_VERSION__ = "2.1.24"
+__RULEKIT_RELEASE_VERSION__ = "2.1.26"
 __VERSION__ = f"{__RULEKIT_RELEASE_VERSION__}.1"
 
 

setup.py

@@ -10,7 +10,7 @@
 
 setuptools.setup(
     name="rulekit",
-    version='2.1.24.2',
+    version='2.1.26.1',
     author="Cezary Maszczyk",
     author_email="cezary.maszczyk@gmail.com",
     description="Comprehensive suite for rule-based learning",
@@ -34,7 +34,7 @@
     python_requires='>=3.9',
     install_requires=[
         'numpy>=1.24',
-        'pandas>=1.5',
+        'pandas>=1.5,<=3.0.5',
         'scipy>=1.11',
         'scikit-learn>=1.1',
         'JPype1==1.5.2',

tests/test_survival.py

@@ -135,9 +135,7 @@ def test_passing_survival_time_column_to_fit_method(self):
         )
         X, y = test_case.example_set.values, test_case.example_set.labels
         survival_time_col: pd.Series = X[test_case.survival_time]
-        X_without_time_col: pd.DataFrame = X.drop(
-            columns=[test_case.survival_time], axis=1
-        )
+        X_without_time_col: pd.DataFrame = X.drop(columns=[test_case.survival_time])
         surv1.fit(X_without_time_col, y, survival_time=survival_time_col)
         surv2.fit(X, y)
 
@@ -154,9 +152,7 @@ def test_ibs_calculation(self):
         )
         X, y = test_case.example_set.values, test_case.example_set.labels
         survival_time_col: pd.Series = X[test_case.survival_time]
-        X_without_time_col: pd.DataFrame = X.drop(
-            columns=[test_case.survival_time], axis=1
-        )
+        X_without_time_col: pd.DataFrame = X.drop(columns=[test_case.survival_time])
         surv.fit(X, y)
 
         ibs: float = surv.score(X, y)