distclassipy 0.2.1__py3-none-any.whl → 0.2.2a1__py3-none-any.whl

distclassipy/__init__.py

@@ -26,9 +26,9 @@ from .classifier import (
     DistanceMetricClassifier,
     EnsembleDistanceClassifier,
 )
-from .distances import Distance, _ALL_METRICS
+from .distances import _ALL_METRICS
 
-__version__ = "0.2.1"
+__version__ = "0.2.2a1"
 
 __all__ = [
     "DistanceMetricClassifier",

distclassipy/classifier.py

@@ -46,14 +46,15 @@ from sklearn.base import BaseEstimator, ClassifierMixin
 from sklearn.metrics import accuracy_score
 from sklearn.model_selection import train_test_split
 from sklearn.utils.multiclass import unique_labels
-from sklearn.utils.validation import check_X_y, check_array, check_is_fitted
+from sklearn.utils.validation import check_is_fitted, check_array
 
-from .distances import Distance, _ALL_METRICS
+from . import distances
+from .distances import _ALL_METRICS
 
 # Hardcoded source packages to check for distance metrics.
 METRIC_SOURCES_ = {
     "scipy.spatial.distance": scipy.spatial.distance,
-    "distances.Distance": Distance(),
+    "distclassipy.distances": distances,
 }
 
 
@@ -61,7 +62,7 @@ def initialize_metric_function(metric):
     """Set the metric function based on the provided metric.
 
     If the metric is a string, the function will look for a corresponding
-    function in scipy.spatial.distance or distances.Distance. If the metric
+    function in scipy.spatial.distance or distclassipy.distances. If the metric
     is a function, it will be used directly.
     """
     if callable(metric):
@@ -95,7 +96,7 @@ def initialize_metric_function(metric):
             raise ValueError(
                 f"{metric} metric not found. Please pass a string of the "
                 "name of a metric in scipy.spatial.distance or "
-                "distances.Distance, or pass a metric function directly. For a "
+                "distclassipy.distances, or pass a metric function directly. For a "
                 "list of available metrics, see: "
                 "https://sidchaini.github.io/DistClassiPy/distances.html or "
                 "https://docs.scipy.org/doc/scipy/reference/spatial.distance.html"
@@ -103,7 +104,7 @@ def initialize_metric_function(metric):
     return metric_fn_, metric_arg_
 
 
-class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
+class DistanceMetricClassifier(ClassifierMixin, BaseEstimator):
     """A distance-based classifier that supports different distance metrics.
 
     The distance metric classifier determines the similarity between features in a
@@ -151,11 +152,13 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
 
     def __init__(
         self,
+        metric: str | Callable = None,
         scale: bool = True,
         central_stat: str = "median",
         dispersion_stat: str = "std",
     ) -> None:
         """Initialize the classifier with specified parameters."""
+        self.metric = metric
         self.scale = scale
         self.central_stat = central_stat
         self.dispersion_stat = dispersion_stat
@@ -186,11 +189,8 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         self : object
             Fitted estimator.
         """
-        X, y = check_X_y(X, y)
+        X, y = self._validate_data(X, y)
         self.classes_ = unique_labels(y)
-        self.n_features_in_ = X.shape[
-            1
-        ]  # Number of features seen during fit - required for sklearn compatibility.
 
         if feat_labels is None:
             feat_labels = [f"Feature_{x}" for x in range(X.shape[1])]
@@ -242,7 +242,7 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
     def predict(
         self,
         X: np.array,
-        metric: str | Callable = "euclidean",
+        metric: str | Callable = None,
     ) -> np.ndarray:
         """Predict the class labels for the provided X.
 
@@ -269,7 +269,7 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         See Also
         --------
         scipy.spatial.dist : Other distance metrics provided in SciPy
-        distclassipy.Distance : Distance metrics included with DistClassiPy
+        distclassipy.distances : Distance metrics included with DistClassiPy
 
         Notes
         -----
@@ -277,9 +277,15 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         which allows SciPy to use an optimized C version of the code instead of the
         slower Python version.
         """
-        check_is_fitted(self, "is_fitted_")
-        X = check_array(X)
-        metric_fn_, metric_arg_ = initialize_metric_function(metric)
+        check_is_fitted(self)
+        X = self._validate_data(X, reset=False)
+
+        metric_to_use = metric if metric is not None else self.metric
+        if metric_to_use is None:
+            # defaults to euclidean
+            metric_to_use = "euclidean"
+        metric_fn_, metric_arg_ = initialize_metric_function(metric_to_use)
+
         if not self.scale:
             dist_arr = scipy.spatial.distance.cdist(
                 XA=X, XB=self.df_centroid_.to_numpy(), metric=metric_arg_
@@ -309,7 +315,7 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
     def predict_and_analyse(
         self,
         X: np.array,
-        metric: str | Callable = "euclidean",
+        metric: str | Callable = None,
     ) -> np.ndarray:
         """Predict the class labels for the provided X and perform analysis.
 
@@ -336,7 +342,7 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         See Also
         --------
         scipy.spatial.dist : Other distance metrics provided in SciPy
-        distclassipy.Distance : Distance metrics included with DistClassiPy
+        distclassipy.distances : Distance metrics included with DistClassiPy
 
         Notes
         -----
@@ -345,10 +351,14 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         of the slower Python version.
 
         """
-        check_is_fitted(self, "is_fitted_")
-        X = check_array(X)
+        check_is_fitted(self)
+        X = self._validate_data(X, reset=False)
 
-        metric_fn_, metric_arg_ = initialize_metric_function(metric)
+        metric_to_use = metric if metric is not None else self.metric
+        if metric_to_use is None:
+            # defaults to euclidean
+            metric_to_use = "euclidean"
+        metric_fn_, metric_arg_ = initialize_metric_function(metric_to_use)
 
         if not self.scale:
             dist_arr = scipy.spatial.distance.cdist(
@@ -409,7 +419,7 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
 
         return self.confidence_df_.to_numpy()
 
-    def score(self, X, y, metric: str | Callable = "euclidean") -> float:
+    def score(self, X, y, metric: str | Callable = None) -> float:
         """Return the mean accuracy on the given test data and labels.
 
         Parameters
@@ -426,11 +436,12 @@ class DistanceMetricClassifier(BaseEstimator, ClassifierMixin):
         score : float
             Mean accuracy of self.predict(X) wrt. y.
         """
-        y_pred = self.predict(X, metric=metric)
+        metric_to_use = metric if metric is not None else self.metric
+        y_pred = self.predict(X, metric=metric_to_use)
         return accuracy_score(y, y_pred)
 
 
-class EnsembleDistanceClassifier(BaseEstimator, ClassifierMixin):
+class EnsembleDistanceClassifier(ClassifierMixin, BaseEstimator):
     """An ensemble classifier that uses different metrics for each quantile.
 
     This classifier splits the data into quantiles based on a specified
@@ -532,8 +543,8 @@ class EnsembleDistanceClassifier(BaseEstimator, ClassifierMixin):
         predictions : np.ndarray
             The predicted class labels.
         """
-        check_is_fitted(self, "is_fitted_")
-        X = check_array(X)
+        check_is_fitted(self)
+        X = self._validate_data(X, reset=False)
 
         # notes for pred during best:
         # option 1: