use range in RangeIndex instead of _start etc. (pandas-dev#26581)

Author: topper-123

doc/source/whatsnew/v0.25.0.rst

@@ -476,6 +476,9 @@ Other Deprecations
   the :meth:`SparseArray.to_dense` method instead (:issue:`26421`).
 - The functions :func:`pandas.to_datetime` and :func:`pandas.to_timedelta` have deprecated the ``box`` keyword. Instead, use :meth:`to_numpy` or :meth:`Timestamp.to_datetime64` or :meth:`Timedelta.to_timedelta64`. (:issue:`24416`)
 - The :meth:`DataFrame.compound` and :meth:`Series.compound` methods are deprecated and will be removed in a future version (:issue:`26405`).
+- The internal attributes ``_start``, ``_stop`` and ``_step`` attributes of :class:`RangeIndex` have been deprecated.
+  Use the public attributes :attr:`~RangeIndex.start`, :attr:`~RangeIndex.stop` and :attr:`~RangeIndex.step` instead (:issue:`26581`).
+
 
 .. _whatsnew_0250.prior_deprecations:
 

pandas/core/dtypes/common.py

@@ -1,4 +1,5 @@
 """ common type operations """
+from typing import Union
 import warnings
 
 import numpy as np
@@ -125,6 +126,34 @@ def ensure_int_or_float(arr: ArrayLike, copy=False) -> np.array:
         return arr.astype('float64', copy=copy)
 
 
+def ensure_python_int(value: Union[int, np.integer]) -> int:
+    """
+    Ensure that a value is a python int.
+
+    Parameters
+    ----------
+    value: int or numpy.integer
+
+    Returns
+    -------
+    int
+
+    Raises
+    ------
+    TypeError: if the value isn't an int or can't be converted to one.
+    """
+    if not is_scalar(value):
+        raise TypeError("Value needs to be a scalar value, was type {}"
+                        .format(type(value)))
+    msg = "Wrong type {} for value {}"
+    try:
+        new_value = int(value)
+        assert (new_value == value)
+    except (TypeError, ValueError, AssertionError):
+        raise TypeError(msg.format(type(value), value))
+    return new_value
+
+
 def classes(*klasses):
     """ evaluate if the tipo is a subclass of the klasses """
     return lambda tipo: issubclass(tipo, klasses)

pandas/core/dtypes/concat.py

@@ -541,36 +541,37 @@ def _concat_rangeindex_same_dtype(indexes):
     """
     from pandas import Int64Index, RangeIndex
 
-    start = step = next = None
+    start = step = next_ = None
 
     # Filter the empty indexes
     non_empty_indexes = [obj for obj in indexes if len(obj)]
 
     for obj in non_empty_indexes:
+        rng = obj._range  # type: range
 
         if start is None:
             # This is set by the first non-empty index
-            start = obj._start
-            if step is None and len(obj) > 1:
-                step = obj._step
+            start = rng.start
+            if step is None and len(rng) > 1:
+                step = rng.step
         elif step is None:
             # First non-empty index had only one element
-            if obj._start == start:
+            if rng.start == start:
                 return _concat_index_same_dtype(indexes, klass=Int64Index)
-            step = obj._start - start
+            step = rng.start - start
 
-        non_consecutive = ((step != obj._step and len(obj) > 1) or
-                           (next is not None and obj._start != next))
+        non_consecutive = ((step != rng.step and len(rng) > 1) or
+                           (next_ is not None and rng.start != next_))
         if non_consecutive:
             return _concat_index_same_dtype(indexes, klass=Int64Index)
 
         if step is not None:
-            next = obj[-1] + step
+            next_ = rng[-1] + step
 
     if non_empty_indexes:
         # Get the stop value from "next" or alternatively
         # from the last non-empty index
-        stop = non_empty_indexes[-1]._stop if next is None else next
+        stop = non_empty_indexes[-1].stop if next_ is None else next_
         return RangeIndex(start, stop, step)
 
     # Here all "indexes" had 0 length, i.e. were empty.

pandas/core/frame.py

@@ -2282,7 +2282,7 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None,
         text_col     5 non-null object
         float_col    5 non-null float64
         dtypes: float64(1), int64(1), object(1)
-        memory usage: 200.0+ bytes
+        memory usage: 248.0+ bytes
 
         Prints a summary of columns count and its dtypes but not per column
         information:
@@ -2292,7 +2292,7 @@ def info(self, verbose=None, buf=None, max_cols=None, memory_usage=None,
         RangeIndex: 5 entries, 0 to 4
         Columns: 3 entries, int_col to float_col
         dtypes: float64(1), int64(1), object(1)
-        memory usage: 200.0+ bytes
+        memory usage: 248.0+ bytes
 
         Pipe output of DataFrame.info to buffer instead of sys.stdout, get
         buffer content and writes to a text file:
@@ -2494,7 +2494,7 @@ def memory_usage(self, index=True, deep=False):
         4      1      1.0    1.0+0.0j       1  True
 
         >>> df.memory_usage()
-        Index            80
+        Index           128
         int64         40000
         float64       40000
         complex128    80000
@@ -2513,7 +2513,7 @@ def memory_usage(self, index=True, deep=False):
         The memory footprint of `object` dtype columns is ignored by default:
 
         >>> df.memory_usage(deep=True)
-        Index             80
+        Index            128
         int64          40000
         float64        40000
         complex128     80000
@@ -2525,7 +2525,7 @@ def memory_usage(self, index=True, deep=False):
         many repeated values.
 
         >>> df['object'].astype('category').memory_usage(deep=True)
-        5168
+        5216
         """
         result = Series([c.memory_usage(index=False, deep=deep)
                          for col, c in self.iteritems()], index=self.columns)