CLN: Remove unused code in Factorizer classes (pandas-dev#49547)

Author: phofl

pandas/_libs/hashtable.pyx

@@ -90,7 +90,7 @@ cdef class ObjectFactorizer(Factorizer):
         self.uniques = ObjectVector()
 
     def factorize(
-        self, ndarray[object] values, sort=False, na_sentinel=-1, na_value=None
+        self, ndarray[object] values, na_sentinel=-1, na_value=None
     ) -> np.ndarray:
         """
 
@@ -115,14 +115,6 @@ cdef class ObjectFactorizer(Factorizer):
             self.uniques = uniques
         labels = self.table.get_labels(values, self.uniques,
                                        self.count, na_sentinel, na_value)
-        mask = (labels == na_sentinel)
-        # sort on
-        if sort:
-            sorter = self.uniques.to_array().argsort()
-            reverse_indexer = np.empty(len(sorter), dtype=np.intp)
-            reverse_indexer.put(sorter, np.arange(len(sorter)))
-            labels = reverse_indexer.take(labels, mode='clip')
-            labels[mask] = na_sentinel
         self.count = len(self.uniques)
         return labels
 
@@ -136,7 +128,7 @@ cdef class Int64Factorizer(Factorizer):
         self.table = Int64HashTable(size_hint)
         self.uniques = Int64Vector()
 
-    def factorize(self, const int64_t[:] values, sort=False,
+    def factorize(self, const int64_t[:] values,
                   na_sentinel=-1, na_value=None) -> np.ndarray:
         """
         Returns
@@ -161,14 +153,5 @@ cdef class Int64Factorizer(Factorizer):
         labels = self.table.get_labels(values, self.uniques,
                                        self.count, na_sentinel,
                                        na_value=na_value)
-
-        # sort on
-        if sort:
-            sorter = self.uniques.to_array().argsort()
-            reverse_indexer = np.empty(len(sorter), dtype=np.intp)
-            reverse_indexer.put(sorter, np.arange(len(sorter)))
-
-            labels = reverse_indexer.take(labels)
-
         self.count = len(self.uniques)
         return labels

pandas/tests/test_algos.py

@@ -230,21 +230,11 @@ def test_factorize_nan(self):
         key = np.array([1, 2, 1, np.nan], dtype="O")
         rizer = ht.ObjectFactorizer(len(key))
         for na_sentinel in (-1, 20):
-            ids = rizer.factorize(key, sort=True, na_sentinel=na_sentinel)
-            expected = np.array([0, 1, 0, na_sentinel], dtype="int32")
+            ids = rizer.factorize(key, na_sentinel=na_sentinel)
+            expected = np.array([0, 1, 0, na_sentinel], dtype=np.intp)
             assert len(set(key)) == len(set(expected))
             tm.assert_numpy_array_equal(pd.isna(key), expected == na_sentinel)
-
-        # nan still maps to na_sentinel when sort=False
-        key = np.array([0, np.nan, 1], dtype="O")
-        na_sentinel = -1
-
-        # TODO(wesm): unused?
-        ids = rizer.factorize(key, sort=False, na_sentinel=na_sentinel)  # noqa
-
-        expected = np.array([2, -1, 0], dtype="int32")
-        assert len(set(key)) == len(set(expected))
-        tm.assert_numpy_array_equal(pd.isna(key), expected == na_sentinel)
+            tm.assert_numpy_array_equal(ids, expected)
 
     @pytest.mark.parametrize(
         "data, expected_codes, expected_uniques",