Allowing FPS to take numpy array of ints as initialize parameter

src/skmatter/_selection.py

@@ -934,7 +934,7 @@ class _FPS(GreedySelector):
     Parameters
     ----------
 
-    initialize: int, list of int, or 'random', default=0
+    initialize: int, list of int, numpy.ndarray of int, or 'random', default=0
         Index of the first selection(s). If 'random', picks a random
         value when fit starts. Stored in :py:attr:`self.initialize`.
 
@@ -1038,7 +1038,14 @@ def _init_greedy_search(self, X, y, n_to_select):
         self.hausdorff_ = np.full(X.shape[self._axis], np.inf)
         self.hausdorff_at_select_ = np.full(X.shape[self._axis], np.inf)
 
-        if self.initialize == "random":
+        if isinstance(self.initialize, (np.ndarray, list)):
+            if all(isinstance(i, numbers.Integral) for i in self.initialize):
+                for i, val in enumerate(self.initialize):
+                    self.selected_idx_[i] = val
+                    self._update_post_selection(X, y, self.selected_idx_[i])
+            else:
+                raise ValueError("Invalid value of the initialize parameter")
+        elif self.initialize == "random":
             random_state = check_random_state(self.random_state)
             initialize = random_state.randint(X.shape[self._axis])
             self.selected_idx_[0] = initialize
@@ -1047,12 +1054,6 @@ def _init_greedy_search(self, X, y, n_to_select):
             initialize = self.initialize
             self.selected_idx_[0] = initialize
             self._update_post_selection(X, y, self.selected_idx_[0])
-        elif isinstance(self.initialize, list) and all(
-            [isinstance(i, numbers.Integral) for i in self.initialize]
-        ):
-            for i, val in enumerate(self.initialize):
-                self.selected_idx_[i] = val
-                self._update_post_selection(X, y, self.selected_idx_[i])
         else:
             raise ValueError("Invalid value of the initialize parameter")
 

src/skmatter/feature_selection/_base.py

@@ -12,7 +12,7 @@ class FPS(_FPS):
     Parameters
     ----------
 
-    initialize: int, list of int, or 'random', default=0
+    initialize: int, list of int, numpy.ndarray of int, or 'random', default=0
         Index of the first selection(s). If 'random', picks a random
         value when fit starts. Stored in :py:attr:`self.initialize`.
 

src/skmatter/sample_selection/_base.py

@@ -58,7 +58,7 @@ class FPS(_FPS):
     Parameters
     ----------
 
-    initialize: int, list of int, or 'random', default=0
+    initialize: int, list of int, numpy.ndarray of int, or 'random', default=0
         Index of the first selection(s). If 'random', picks a random
         value when fit starts. Stored in :py:attr:`self.initialize`.
 

tests/test_feature_simple_fps.py

@@ -1,5 +1,6 @@
 import unittest
 
+import numpy as np
 from sklearn.datasets import load_diabetes as get_dataset
 from sklearn.utils.validation import NotFittedError
 
@@ -42,6 +43,31 @@ def test_initialize(self):
             for i in range(4):
                 self.assertEqual(selector.selected_idx_[i], self.idx[i])
 
+        initialize = np.array(self.idx[:4])
+        with self.subTest(initialize=initialize):
+            selector = FPS(n_to_select=len(self.idx) - 1, initialize=initialize)
+            selector.fit(self.X)
+            for i in range(4):
+                self.assertEqual(selector.selected_idx_[i], self.idx[i])
+
+        initialize = np.array([1, 5, 3, 0.25])
+        with self.subTest(initialize=initialize):
+            with self.assertRaises(ValueError) as cm:
+                selector = FPS(n_to_select=len(self.idx) - 1, initialize=initialize)
+                selector.fit(self.X)
+            self.assertEqual(
+                str(cm.exception), "Invalid value of the initialize parameter"
+            )
+
+        initialize = np.array([[1, 5, 3], [2, 4, 6]])
+        with self.subTest(initialize=initialize):
+            with self.assertRaises(ValueError) as cm:
+                selector = FPS(n_to_select=len(self.idx) - 1, initialize=initialize)
+                selector.fit(self.X)
+            self.assertEqual(
+                str(cm.exception), "Invalid value of the initialize parameter"
+            )
+
         with self.assertRaises(ValueError) as cm:
             selector = FPS(n_to_select=1, initialize="bad")
             selector.fit(self.X)

tests/test_sample_simple_fps.py

@@ -1,5 +1,6 @@
 import unittest
 
+import numpy as np
 from sklearn.datasets import load_diabetes as get_dataset
 from sklearn.utils.validation import NotFittedError
 
@@ -43,6 +44,31 @@ def test_initialize(self):
             for i in range(4):
                 self.assertEqual(selector.selected_idx_[i], self.idx[i])
 
+        initialize = np.array(self.idx[:4])
+        with self.subTest(initialize=initialize):
+            selector = FPS(n_to_select=len(self.idx) - 1, initialize=initialize)
+            selector.fit(self.X)
+            for i in range(4):
+                self.assertEqual(selector.selected_idx_[i], self.idx[i])
+
+        initialize = np.array([1, 5, 3, 0.25])
+        with self.subTest(initialize=initialize):
+            with self.assertRaises(ValueError) as cm:
+                selector = FPS(n_to_select=len(self.idx) - 1, initialize=initialize)
+                selector.fit(self.X)
+            self.assertEqual(
+                str(cm.exception), "Invalid value of the initialize parameter"
+            )
+
+        initialize = np.array([[1, 5, 3], [2, 4, 6]])
+        with self.subTest(initialize=initialize):
+            with self.assertRaises(ValueError) as cm:
+                selector = FPS(n_to_select=len(self.idx) - 1, initialize=initialize)
+                selector.fit(self.X)
+            self.assertEqual(
+                str(cm.exception), "Invalid value of the initialize parameter"
+            )
+
         with self.assertRaises(ValueError) as cm:
             selector = FPS(n_to_select=1, initialize="bad")
             selector.fit(self.X)