continue feature selection

bayesclass/clfs.py

@@ -891,7 +891,6 @@ class BoostAODE(ClassifierMixin, BaseEnsemble):
                 SelectKBestWeighted(k=1)
                 .fit(self.X_, self.y_, weights)
                 .get_feature_names_out(self.feature_names_in_)
-                .tolist()[0]
             )
             # Step 2: Build & train spode with the first feature as sparent
             estimator = clone(self.estimator_)
@@ -914,13 +913,3 @@ class BoostAODE(ClassifierMixin, BaseEnsemble):
             ]
             # Step 4: Add the new model
             self.estimators_.append(estimator)
-        """
-        class_edges = [(self.class_name_, f) for f in self.feature_names_in_]
-        feature_edges = [
-            (sparent, f) for f in self.feature_names_in_ if f != sparent
-        ]
-        self.weights_ = weights.copy() if weights is not None else None
-        feature_edges.extend(class_edges)
-        self.model_ = BayesianNetwork(feature_edges, show_progress=False)
-        return self.model_
-        """

bayesclass/feature_selection.py

@@ -1,6 +1,6 @@
 import numpy as np
 from sklearn.feature_selection import mutual_info_classif
-
+from sklearn.utils.validation import check_X_y, check_is_fitted
 
 """
 Compute the weighted mutual information between each feature and the
@@ -24,10 +24,17 @@ entropy are given.
 
 
 class SelectKBestWeighted:
+    def __init__(self, k):
+        self.k = k
+        
     def fit(self, X, y, sample_weight):
+        self.X_, self.y_ = check_X_y(X, y)
         self.X_ = X
         self.y_ = y
+        self.n_features_in_ = X.shape[1]
         self.sample_weight_ = sample_weight
+        if self.k > X.shape[1] or self.k<1:
+            raise ValueError(f"k must be between 1 and {self.n_features_in_}")
         # Compute the entropy of the target variable
         entropy_y = -np.sum(
             np.multiply(
@@ -42,7 +49,8 @@ class SelectKBestWeighted:
         # Compute the weighted entropy of each feature
         entropy_weighted = []
         for i in range(X.shape[1]):
-            # Compute the weighted frequency of each unique value of the feature
+            # Compute the weighted frequency of each unique value of the 
+            # feature
             freq_weighted = np.bincount(X[:, i], weights=sample_weight)
             freq_weighted = freq_weighted[freq_weighted != 0]
 
@@ -52,8 +60,15 @@ class SelectKBestWeighted:
                 / np.sum(sample_weight)
             )
 
-        # Compute the weighted mutual information between each feature and the target
+        # Compute the weighted mutual information between each feature and
+        # the target
         mi_weighted = mi * entropy_weighted / entropy_y
 
         # Return the weighted mutual information scores
         self.mi_weighted_ = mi_weighted
+        return self
+    
+    def get_feature_names_out(self, features):
+        check_is_fitted(self, ["X_", "y_", "mi_weighted_"])
+        return [features[i] for i in np.argsort(self.mi_weighted_)[::-1][:self.k]]
+