some comments

Author: niruta25

pandas/core/arrays/categorical.py

@@ -468,6 +468,8 @@ def __init__(
                 try:
                     codes, categories = factorize(values, sort=True)
                 except TypeError as err:
+                    # raise, as we don't have a sortable data structure and so
+                    # the user should give us one by specifying categories
                     codes, categories = factorize(values, sort=False)
                     if dtype.ordered:
                         raise TypeError(

pandas/tests/arrays/categorical/test_constructors.py

@@ -786,3 +786,23 @@ def test_range_values_preserves_rangeindex_categories(self, values, categories):
         result = Categorical(values=values, categories=categories).categories
         expected = RangeIndex(range(5))
         tm.assert_index_equal(result, expected, exact=True)
+
+    def test_categorical_preserve_object_dtype_from_pandas(self):
+        with pd.option_context("future.infer_string", True):
+            ser = Series(["foo", "bar", "baz"], dtype="object")
+            idx = Index(["foo", "bar", "baz"], dtype="object")
+            arr = np.array(["foo", "bar", "baz"], dtype="object")
+            pylist = ["foo", "bar", "baz"]
+
+            cat_from_ser = Categorical(ser)
+            cat_from_idx = Categorical(idx)
+            cat_from_arr = Categorical(arr)
+            cat_from_list = Categorical(pylist)
+
+            # Series/Index with object dtype: preserve object dtype
+            assert cat_from_ser.categories.dtype == "object"
+            assert cat_from_idx.categories.dtype == "object"
+
+            # Numpy array or list: infer string dtype
+            assert cat_from_arr.categories.dtype == "str"
+            assert cat_from_list.categories.dtype == "str"

pandas/tests/extension/test_categorical.py

@@ -180,31 +180,6 @@ def test_array_repr(self, data, size):
     def test_groupby_extension_agg(self, as_index, data_for_grouping):
         super().test_groupby_extension_agg(as_index, data_for_grouping)
 
-    def test_categorical_preserve_object_dtype_from_pandas(self):
-        import numpy as np
-
-        import pandas as pd
-
-        pd.options.future.infer_string = True
-
-        ser = pd.Series(["foo", "bar", "baz"], dtype="object")
-        idx = pd.Index(["foo", "bar", "baz"], dtype="object")
-        arr = np.array(["foo", "bar", "baz"], dtype="object")
-        pylist = ["foo", "bar", "baz"]
-
-        cat_from_ser = Categorical(ser)
-        cat_from_idx = Categorical(idx)
-        cat_from_arr = Categorical(arr)
-        cat_from_list = Categorical(pylist)
-
-        # Series/Index with object dtype: preserve object dtype
-        assert cat_from_ser.categories.dtype == "object"
-        assert cat_from_idx.categories.dtype == "object"
-
-        # Numpy array or list: infer string dtype
-        assert cat_from_arr.categories.dtype == "str"
-        assert cat_from_list.categories.dtype == "str"
-
 
 class Test2DCompat(base.NDArrayBacked2DTests):
     def test_repr_2d(self, data):