feat: ⚡ Add factorize method to transformer

src/fimdlp/mdlp.py

@@ -150,6 +150,21 @@ class FImdlp(TransformerMixin, BaseEstimator):
         )
         return result
 
+    def factorize(self, yy):
+        """Factorize the input labels
+
+        Parameters
+        ----------
+        yy : array, shape (n_samples,)
+            Labels to be factorized, MUST be bytes, i.e. b"0", b"1", ...
+
+        Returns
+        -------
+        array, shape (n_samples,)
+            Factorized labels
+        """
+        return factorize(yy)
+
     def join_transform(self, X, y, feature, **kwargs):
         """Join the selected feature with the labels and discretize the values
         join - fit - transform
@@ -174,7 +189,7 @@ class FImdlp(TransformerMixin, BaseEstimator):
             f"{str(item_y)}{str(item_x)}".encode()
             for item_y, item_x in zip(y, X[:, feature])
         ]
-        yy = factorize(self.y_join_)
+        yy = self.factorize(self.y_join_)
         XX = np.delete(X, feature, axis=1)
         return self.fit(XX, yy).transform(XX)
 

src/fimdlp/tests/FImdlp_test.py

@@ -162,7 +162,7 @@ class FImdlpTest(unittest.TestCase):
             clf = FImdlp(algorithm=1)
             clf.transform([[1, 2], [3, 4]])
 
-    def test_factorize(self):
+    def test_cppfactorize(self):
         source = [
             b"f0",
             b"f1",
@@ -215,6 +215,16 @@ class FImdlpTest(unittest.TestCase):
         with self.assertRaises(ValueError):
             FImdlp().join_transform(x, y, 5)
 
+    def test_factorize(self):
+        y = np.array([b"f0", b"f0", b"f2", b"f3", b"f4"])
+        clf = FImdlp()
+        computed = clf.factorize(y)
+        self.assertListEqual([0, 0, 1, 2, 3], computed)
+        y = [b"f4", b"f0", b"f0", b"f2", b"f3"]
+        clf = FImdlp()
+        computed = clf.factorize(y)
+        self.assertListEqual([0, 1, 1, 2, 3], computed)
+
     def test_sklearn_transformer(self):
         for check, test in check_estimator(FImdlp(), generate_only=True):
             test(check)