REF: avoid _with_infer constructor (#50001)

Author: jbrockmendel

Diff for: pandas/_testing/__init__.py

@@ -274,7 +274,7 @@ def box_expected(expected, box_cls, transpose: bool = True):
         else:
             expected = pd.array(expected, copy=False)
     elif box_cls is Index:
-        expected = Index._with_infer(expected)
+        expected = Index(expected)
     elif box_cls is Series:
         expected = Series(expected)
     elif box_cls is DataFrame:

Diff for: pandas/core/algorithms.py

@@ -894,7 +894,7 @@ def value_counts(
 
             # For backwards compatibility, we let Index do its normal type
             #  inference, _except_ for if if infers from object to bool.
-            idx = Index._with_infer(keys)
+            idx = Index(keys)
             if idx.dtype == bool and keys.dtype == object:
                 idx = idx.astype(object)
 

Diff for: pandas/core/indexes/base.py

@@ -2678,6 +2678,7 @@ def fillna(self, value=None, downcast=None):
             if downcast is None:
                 # no need to care metadata other than name
                 # because it can't have freq if it has NaTs
+                # _with_infer needed for test_fillna_categorical
                 return Index._with_infer(result, name=self.name)
             raise NotImplementedError(
                 f"{type(self).__name__}.fillna does not support 'downcast' "
@@ -4230,10 +4231,10 @@ def _reindex_non_unique(
                 new_indexer = np.arange(len(self.take(indexer)), dtype=np.intp)
                 new_indexer[~check] = -1
 
-        if isinstance(self, ABCMultiIndex):
-            new_index = type(self).from_tuples(new_labels, names=self.names)
+        if not isinstance(self, ABCMultiIndex):
+            new_index = Index(new_labels, name=self.name)
         else:
-            new_index = Index._with_infer(new_labels, name=self.name)
+            new_index = type(self).from_tuples(new_labels, names=self.names)
         return new_index, indexer, new_indexer
 
     # --------------------------------------------------------------------
@@ -6477,7 +6478,7 @@ def insert(self, loc: int, item) -> Index:
         if self._typ == "numericindex":
             # Use self._constructor instead of Index to retain NumericIndex GH#43921
             # TODO(2.0) can use Index instead of self._constructor
-            return self._constructor._with_infer(new_values, name=self.name)
+            return self._constructor(new_values, name=self.name)
         else:
             return Index._with_infer(new_values, name=self.name)
 
@@ -6850,7 +6851,7 @@ def ensure_index_from_sequences(sequences, names=None) -> Index:
     if len(sequences) == 1:
         if names is not None:
             names = names[0]
-        return Index._with_infer(sequences[0], name=names)
+        return Index(sequences[0], name=names)
     else:
         return MultiIndex.from_arrays(sequences, names=names)
 
@@ -6893,7 +6894,7 @@ def ensure_index(index_like: Axes, copy: bool = False) -> Index:
 
     if isinstance(index_like, ABCSeries):
         name = index_like.name
-        return Index._with_infer(index_like, name=name, copy=copy)
+        return Index(index_like, name=name, copy=copy)
 
     if is_iterator(index_like):
         index_like = list(index_like)
@@ -6909,9 +6910,9 @@ def ensure_index(index_like: Axes, copy: bool = False) -> Index:
 
             return MultiIndex.from_arrays(index_like)
         else:
-            return Index._with_infer(index_like, copy=copy, tupleize_cols=False)
+            return Index(index_like, copy=copy, tupleize_cols=False)
     else:
-        return Index._with_infer(index_like, copy=copy)
+        return Index(index_like, copy=copy)
 
 
 def ensure_has_len(seq):

Diff for: pandas/core/indexes/multi.py

@@ -2112,7 +2112,7 @@ def append(self, other):
             # setting names to None automatically
             return MultiIndex.from_tuples(new_tuples)
         except (TypeError, IndexError):
-            return Index._with_infer(new_tuples)
+            return Index(new_tuples)
 
     def argsort(self, *args, **kwargs) -> npt.NDArray[np.intp]:
         if len(args) == 0 and len(kwargs) == 0:

Diff for: pandas/core/strings/accessor.py

@@ -319,7 +319,7 @@ def cons_row(x):
                     out = out.get_level_values(0)
                 return out
             else:
-                return Index._with_infer(result, name=name)
+                return Index(result, name=name)
         else:
             index = self._orig.index
             # This is a mess.

Diff for: pandas/core/util/hashing.py

@@ -344,9 +344,7 @@ def _hash_ndarray(
             )
 
             codes, categories = factorize(vals, sort=False)
-            cat = Categorical(
-                codes, Index._with_infer(categories), ordered=False, fastpath=True
-            )
+            cat = Categorical(codes, Index(categories), ordered=False, fastpath=True)
             return _hash_categorical(cat, encoding, hash_key)
 
         try:

Diff for: pandas/tests/arithmetic/test_numeric.py

@@ -1147,6 +1147,9 @@ def test_numarr_with_dtype_add_nan(self, dtype, box_with_array):
 
         ser = tm.box_expected(ser, box)
         expected = tm.box_expected(expected, box)
+        if box is Index and dtype is object:
+            # TODO: avoid this; match behavior with Series
+            expected = expected.astype(np.float64)
 
         result = np.nan + ser
         tm.assert_equal(result, expected)
@@ -1162,6 +1165,9 @@ def test_numarr_with_dtype_add_int(self, dtype, box_with_array):
 
         ser = tm.box_expected(ser, box)
         expected = tm.box_expected(expected, box)
+        if box is Index and dtype is object:
+            # TODO: avoid this; match behavior with Series
+            expected = expected.astype(np.int64)
 
         result = 1 + ser
         tm.assert_equal(result, expected)

Diff for: pandas/tests/arrays/integer/test_dtypes.py

@@ -89,7 +89,7 @@ def test_astype_index(all_data, dropna):
         other = all_data
 
     dtype = all_data.dtype
-    idx = pd.Index._with_infer(np.array(other))
+    idx = pd.Index(np.array(other))
     assert isinstance(idx, ABCIndex)
 
     result = idx.astype(dtype)

Diff for: pandas/tests/extension/base/groupby.py

@@ -33,7 +33,7 @@ def test_groupby_extension_agg(self, as_index, data_for_grouping):
         _, uniques = pd.factorize(data_for_grouping, sort=True)
 
         if as_index:
-            index = pd.Index._with_infer(uniques, name="B")
+            index = pd.Index(uniques, name="B")
             expected = pd.Series([3.0, 1.0, 4.0], index=index, name="A")
             self.assert_series_equal(result, expected)
         else:
@@ -61,7 +61,7 @@ def test_groupby_extension_no_sort(self, data_for_grouping):
         result = df.groupby("B", sort=False).A.mean()
         _, index = pd.factorize(data_for_grouping, sort=False)
 
-        index = pd.Index._with_infer(index, name="B")
+        index = pd.Index(index, name="B")
         expected = pd.Series([1.0, 3.0, 4.0], index=index, name="A")
         self.assert_series_equal(result, expected)
 

Diff for: pandas/tests/extension/test_string.py

@@ -391,7 +391,7 @@ def test_groupby_extension_agg(self, as_index, data_for_grouping):
             _, uniques = pd.factorize(data_for_grouping, sort=True)
 
         if as_index:
-            index = pd.Index._with_infer(uniques, name="B")
+            index = pd.Index(uniques, name="B")
             expected = pd.Series([3.0, 1.0, 4.0], index=index, name="A")
             self.assert_series_equal(result, expected)
         else:

Diff for: pandas/tests/io/test_stata.py

@@ -20,7 +20,6 @@
     DataFrame,
     Series,
 )
-from pandas.core.indexes.api import ensure_index
 from pandas.tests.io.test_compression import _compression_to_extension
 
 from pandas.io.parsers import read_csv
@@ -1144,7 +1143,7 @@ def _convert_categorical(from_frame: DataFrame) -> DataFrame:
             if is_categorical_dtype(ser.dtype):
                 cat = ser._values.remove_unused_categories()
                 if cat.categories.dtype == object:
-                    categories = ensure_index(cat.categories._values)
+                    categories = pd.Index._with_infer(cat.categories._values)
                     cat = cat.set_categories(categories)
                 from_frame[col] = cat
         return from_frame