Backport PR #35712: PERF: RangeIndex.format performance (#35904)

Co-authored-by: Terji Petersen <[email protected]>

Author: simonjayhawkins

doc/source/whatsnew/v0.25.0.rst

@@ -540,7 +540,7 @@ with :attr:`numpy.nan` in the case of an empty :class:`DataFrame` (:issue:`26397
 
 .. ipython:: python
 
-    df.describe()
+   df.describe()
 
 ``__str__`` methods now call ``__repr__`` rather than vice versa
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

doc/source/whatsnew/v1.1.2.rst

@@ -15,7 +15,7 @@ including other versions of pandas.
 Fixed regressions
 ~~~~~~~~~~~~~~~~~
 - Regression in :meth:`DatetimeIndex.intersection` incorrectly raising ``AssertionError`` when intersecting against a list (:issue:`35876`)
--
+- Performance regression for :meth:`RangeIndex.format` (:issue:`35712`)
 -
 
 .. ---------------------------------------------------------------------------
@@ -25,7 +25,7 @@ Fixed regressions
 Bug fixes
 ~~~~~~~~~
 - Bug in :meth:`DataFrame.apply` with ``result_type="reduce"`` returning with incorrect index (:issue:`35683`)
--
+- Bug in :meth:`DateTimeIndex.format` and :meth:`PeriodIndex.format` with ``name=True`` setting the first item to ``"None"`` where it should bw ``""`` (:issue:`35712`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/core/indexes/base.py

@@ -924,7 +924,9 @@ def format(
 
         return self._format_with_header(header, na_rep=na_rep)
 
-    def _format_with_header(self, header, na_rep="NaN") -> List[str_t]:
+    def _format_with_header(
+        self, header: List[str_t], na_rep: str_t = "NaN"
+    ) -> List[str_t]:
         from pandas.io.formats.format import format_array
 
         values = self._values

pandas/core/indexes/category.py

@@ -347,7 +347,7 @@ def _format_attrs(self):
             attrs.append(("length", len(self)))
         return attrs
 
-    def _format_with_header(self, header, na_rep="NaN") -> List[str]:
+    def _format_with_header(self, header: List[str], na_rep: str = "NaN") -> List[str]:
         from pandas.io.formats.printing import pprint_thing
 
         result = [

pandas/core/indexes/datetimelike.py

@@ -350,15 +350,20 @@ def format(
         """
         header = []
         if name:
-            fmt_name = ibase.pprint_thing(self.name, escape_chars=("\t", "\r", "\n"))
-            header.append(fmt_name)
+            header.append(
+                ibase.pprint_thing(self.name, escape_chars=("\t", "\r", "\n"))
+                if self.name is not None
+                else ""
+            )
 
         if formatter is not None:
             return header + list(self.map(formatter))
 
         return self._format_with_header(header, na_rep=na_rep, date_format=date_format)
 
-    def _format_with_header(self, header, na_rep="NaT", date_format=None) -> List[str]:
+    def _format_with_header(
+        self, header: List[str], na_rep: str = "NaT", date_format: Optional[str] = None
+    ) -> List[str]:
         return header + list(
             self._format_native_types(na_rep=na_rep, date_format=date_format)
         )

pandas/core/indexes/interval.py

@@ -948,7 +948,7 @@ def take(self, indices, axis=0, allow_fill=True, fill_value=None, **kwargs):
     # Rendering Methods
     # __repr__ associated methods are based on MultiIndex
 
-    def _format_with_header(self, header, na_rep="NaN") -> List[str]:
+    def _format_with_header(self, header: List[str], na_rep: str = "NaN") -> List[str]:
         return header + list(self._format_native_types(na_rep=na_rep))
 
     def _format_native_types(self, na_rep="NaN", quoting=None, **kwargs):

pandas/core/indexes/range.py

@@ -1,7 +1,7 @@
 from datetime import timedelta
 import operator
 from sys import getsizeof
-from typing import Any, Optional
+from typing import Any, List, Optional
 import warnings
 
 import numpy as np
@@ -195,6 +195,15 @@ def _format_data(self, name=None):
         # we are formatting thru the attributes
         return None
 
+    def _format_with_header(self, header: List[str], na_rep: str = "NaN") -> List[str]:
+        if not len(self._range):
+            return header
+        first_val_str = str(self._range[0])
+        last_val_str = str(self._range[-1])
+        max_length = max(len(first_val_str), len(last_val_str))
+
+        return header + [f"{x:<{max_length}}" for x in self._range]
+
     # --------------------------------------------------------------------
     _deprecation_message = (
         "RangeIndex.{} is deprecated and will be "

pandas/tests/indexes/common.py

@@ -1,5 +1,5 @@
 import gc
-from typing import Optional, Type
+from typing import Type
 
 import numpy as np
 import pytest
@@ -33,7 +33,7 @@
 class Base:
     """ base class for index sub-class tests """
 
-    _holder: Optional[Type[Index]] = None
+    _holder: Type[Index]
     _compat_props = ["shape", "ndim", "size", "nbytes"]
 
     def create_index(self) -> Index:
@@ -648,6 +648,12 @@ def test_format(self):
         expected = [str(x) for x in idx]
         assert idx.format() == expected
 
+    def test_format_empty(self):
+        # GH35712
+        empty_idx = self._holder([])
+        assert empty_idx.format() == []
+        assert empty_idx.format(name=True) == [""]
+
     def test_hasnans_isnans(self, index):
         # GH 11343, added tests for hasnans / isnans
         if isinstance(index, MultiIndex):

pandas/tests/indexes/period/test_period.py

@@ -536,6 +536,12 @@ def test_contains_raise_error_if_period_index_is_in_multi_index(self, msg, key):
         with pytest.raises(KeyError, match=msg):
             df.loc[key]
 
+    def test_format_empty(self):
+        # GH35712
+        empty_idx = self._holder([], freq="A")
+        assert empty_idx.format() == []
+        assert empty_idx.format(name=True) == [""]
+
 
 def test_maybe_convert_timedelta():
     pi = PeriodIndex(["2000", "2001"], freq="D")

pandas/tests/indexes/ranges/test_range.py

@@ -166,8 +166,14 @@ def test_cached_data(self):
         idx.any()
         assert idx._cached_data is None
 
+        idx.format()
+        assert idx._cache == {}
+
         df = pd.DataFrame({"a": range(10)}, index=idx)
 
+        str(df)
+        assert idx._cache == {}
+
         df.loc[50]
         assert idx._cached_data is None
 
@@ -506,3 +512,9 @@ def test_engineless_lookup(self):
             idx.get_loc("a")
 
         assert "_engine" not in idx._cache
+
+    def test_format_empty(self):
+        # GH35712
+        empty_idx = self._holder(0)
+        assert empty_idx.format() == []
+        assert empty_idx.format(name=True) == [""]