Skip to content

[ENH] Use default EA repr for IntervalArray #26316

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 23 commits into from
Sep 10, 2019
Merged

[ENH] Use default EA repr for IntervalArray #26316

Show file tree
Hide file tree
Changes from 16 commits
Commits
Show all changes
23 commits
Select commit Hold shift + click to select a range
c2ab939
Use new repr and fix docstring
makbigc May 7, 2019
f9740c7
Delete one test
makbigc May 7, 2019
54bc56b
Remove relundant code
makbigc May 8, 2019
95c012a
Remove relundant import
makbigc May 8, 2019
e7b865c
merge
makbigc Jun 20, 2019
cc25182
Separate the example section from _interval_shared_docs
makbigc Jun 20, 2019
4c86f53
Fix docstring error
makbigc Jun 22, 2019
474b4c4
resolve conflict
makbigc Jul 14, 2019
0e07474
Fix the example in contain method
makbigc Jul 19, 2019
c9dea18
Merge for update
makbigc Jul 19, 2019
55f701a
Fix the black format
makbigc Jul 19, 2019
480d780
Fix docstring error
makbigc Jul 19, 2019
3bc839e
merge for update
makbigc Aug 18, 2019
3c36719
Add whatsnew entry in v1.0
makbigc Aug 19, 2019
0a62694
Fix lint error
makbigc Aug 19, 2019
f6d4f03
Fix black error
makbigc Aug 19, 2019
32ddfa9
Fix doc format error and add test_repr
makbigc Aug 30, 2019
0db48c3
4th merge for update
makbigc Aug 30, 2019
5a16fa7
Fix format error
makbigc Aug 30, 2019
64889ec
Remove tailing space in v1.0 rst
makbigc Aug 30, 2019
5ab6ae9
Fix v1.0.0.rst
makbigc Sep 6, 2019
5f31bca
remove the output in v1.0
makbigc Sep 6, 2019
6bbee48
Fix v1
makbigc Sep 6, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
23 changes: 22 additions & 1 deletion doc/source/whatsnew/v1.0.0.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,28 @@ Backwards incompatible API changes
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

- :class:`pandas.core.groupby.GroupBy.transform` now raises on invalid operation names (:issue:`27489`).
-
- :class:`pandas.core.arrays.IntervalArray` adopts a new ``__repr__`` in accordance with other array classes (:issue:`25022`)

*pandas 0.25.x*

.. code-block:: ipython

In [1]: pd.arrays.IntervalArray.from_tuples([(0, 1), (2, 3)])
Out[1]:
IntervalArray([(0, 1], (2, 3]],
closed='right',
dtype='interval[int64]')

*pandas 1.0.0*

.. ipython:: python

In [2]: pd.arrays.IntervalArray.from_tuples([(0, 1), (2, 3)])
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Since this is an actual python block I don't think you need the In/Out - that may be causing the CI failure

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@WillAyd
Thanks for your advice. Otherwise I can't pass the CI tests.

Out[2]:
<IntervalArray>
[(0, 1], (2, 3]]
Length: 2, closed: right, dtype: interval[int64]


.. _whatsnew_1000.api.other:

Expand Down
210 changes: 137 additions & 73 deletions pandas/core/arrays/interval.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,9 +129,9 @@
``Interval`` objects:

>>> pd.arrays.IntervalArray([pd.Interval(0, 1), pd.Interval(1, 5)])
IntervalArray([(0, 1], (1, 5]],
closed='right',
dtype='interval[int64]')
<IntervalArray>
[(0, 1], (1, 5]]
Length: 2, closed: right, dtype: interval[int64]

It may also be constructed using one of the constructor
methods: :meth:`IntervalArray.from_arrays`,
Expand Down Expand Up @@ -248,9 +248,8 @@ def _from_factorized(cls, values, original):
values = values.astype(original.dtype.subtype)
return cls(values, closed=original.closed)

_interval_shared_docs[
"from_breaks"
] = """
_interval_shared_docs["from_breaks"] = textwrap.dedent(
"""
Construct an %(klass)s from an array of splits.

Parameters
Expand All @@ -277,24 +276,34 @@ def _from_factorized(cls, values, original):
%(klass)s.from_arrays : Construct from a left and right array.
%(klass)s.from_tuples : Construct from a sequence of tuples.

Examples
--------
>>> pd.%(qualname)s.from_breaks([0, 1, 2, 3])
%(klass)s([(0, 1], (1, 2], (2, 3]],
closed='right',
dtype='interval[int64]')
%(examples)s\
"""
)

@classmethod
@Appender(_interval_shared_docs["from_breaks"] % _shared_docs_kwargs)
@Appender(
_interval_shared_docs["from_breaks"]
% dict(
klass="IntervalArray",
examples=textwrap.dedent(
"""\
Examples
--------
>>> pd.arrays.IntervalArray.from_breaks([0, 1, 2, 3])
<IntervalArray>
[(0, 1], (1, 2], (2, 3]]
Length: 3, closed: right, dtype: interval[int64]
"""
),
)
)
def from_breaks(cls, breaks, closed="right", copy=False, dtype=None):
breaks = maybe_convert_platform_interval(breaks)

return cls.from_arrays(breaks[:-1], breaks[1:], closed, copy=copy, dtype=dtype)

_interval_shared_docs[
"from_arrays"
] = """
_interval_shared_docs["from_arrays"] = textwrap.dedent(
"""
Construct from two arrays defining the left and right bounds.

Parameters
Expand Down Expand Up @@ -340,16 +349,25 @@ def from_breaks(cls, breaks, closed="right", copy=False, dtype=None):
using an unsupported type for `left` or `right`. At the moment,
'category', 'object', and 'string' subtypes are not supported.

Examples
--------
>>> %(klass)s.from_arrays([0, 1, 2], [1, 2, 3])
%(klass)s([(0, 1], (1, 2], (2, 3]],
closed='right',
dtype='interval[int64]')
%(examples)s\
"""
)

@classmethod
@Appender(_interval_shared_docs["from_arrays"] % _shared_docs_kwargs)
@Appender(
_interval_shared_docs["from_arrays"]
% dict(
klass="IntervalArray",
examples=textwrap.dedent(
"""\
>>> pd.arrays.IntervalArray.from_arrays([0, 1, 2], [1, 2, 3])
<IntervalArray>
[(0, 1], (1, 2], (2, 3]]
Length: 3, closed: right, dtype: interval[int64]
"""
),
)
)
def from_arrays(cls, left, right, closed="right", copy=False, dtype=None):
left = maybe_convert_platform_interval(left)
right = maybe_convert_platform_interval(right)
Expand All @@ -358,9 +376,8 @@ def from_arrays(cls, left, right, closed="right", copy=False, dtype=None):
left, right, closed, copy=copy, dtype=dtype, verify_integrity=True
)

_interval_shared_docs[
"from_tuples"
] = """
_interval_shared_docs["from_tuples"] = textwrap.dedent(
"""
Construct an %(klass)s from an array-like of tuples

Parameters
Expand Down Expand Up @@ -389,15 +406,27 @@ def from_arrays(cls, left, right, closed="right", copy=False, dtype=None):
%(klass)s.from_breaks : Construct an %(klass)s from an array of
splits.

Examples
--------
>>> pd.%(qualname)s.from_tuples([(0, 1), (1, 2)])
%(klass)s([(0, 1], (1, 2]],
closed='right', dtype='interval[int64]')
%(examples)s\
"""
)

@classmethod
@Appender(_interval_shared_docs["from_tuples"] % _shared_docs_kwargs)
@Appender(
_interval_shared_docs["from_tuples"]
% dict(
klass="IntervalArray",
examples=textwrap.dedent(
"""\
Examples
--------
>>> pd.arrays.IntervalArray.from_tuples([(0, 1), (1, 2)])
<IntervalArray>
[(0, 1], (1, 2]]
Length: 2, closed: right, dtype: interval[int64]
"""
),
)
)
def from_tuples(cls, data, closed="right", copy=False, dtype=None):
if len(data):
left, right = [], []
Expand Down Expand Up @@ -832,16 +861,20 @@ def _format_data(self):
return summary

def __repr__(self):
tpl = textwrap.dedent(
"""\
{cls}({data},
{lead}closed='{closed}',
{lead}dtype='{dtype}')"""
template = (
"{class_name}"
"{data}\n"
"Length: {length}, closed: {closed}, dtype: {dtype}"
)
return tpl.format(
cls=self.__class__.__name__,
data=self._format_data(),
lead=" " * len(self.__class__.__name__) + " ",
# the short repr has no trailing newline, while the truncated
# repr does. So we include a newline in our template, and strip
# any trailing newlines from format_object_summary
data = self._format_data()
class_name = "<{}>\n".format(self.__class__.__name__)
return template.format(
class_name=class_name,
data=data,
length=len(self),
closed=self.closed,
dtype=self.dtype,
)
Expand Down Expand Up @@ -874,9 +907,8 @@ def closed(self):
"""
return self._closed

_interval_shared_docs[
"set_closed"
] = """
_interval_shared_docs["set_closed"] = textwrap.dedent(
"""
Return an %(klass)s identical to the current one, but closed on the
specified side

Expand All @@ -892,20 +924,31 @@ def closed(self):
-------
new_index : %(klass)s

%(examples)s\
"""
)

@Appender(
_interval_shared_docs["set_closed"]
% dict(
klass="IntervalArray",
examples=textwrap.dedent(
"""\
Examples
--------
>>> index = pd.interval_range(0, 3)
>>> index = pd.arrays.IntervalArray.from_breaks(range(4))
>>> index
IntervalIndex([(0, 1], (1, 2], (2, 3]],
closed='right',
dtype='interval[int64]')
<IntervalArray>
[(0, 1], (1, 2], (2, 3]]
Length: 3, closed: right, dtype: interval[int64]
>>> index.set_closed('both')
IntervalIndex([[0, 1], [1, 2], [2, 3]],
closed='both',
dtype='interval[int64]')
<IntervalArray>
[[0, 1], [1, 2], [2, 3]]
Length: 3, closed: both, dtype: interval[int64]
"""

@Appender(_interval_shared_docs["set_closed"] % _shared_docs_kwargs)
),
)
)
def set_closed(self, closed):
if closed not in _VALID_CLOSED:
msg = "invalid option for 'closed': {closed}"
Expand Down Expand Up @@ -1028,9 +1071,8 @@ def repeat(self, repeats, axis=None):
right_repeat = self.right.repeat(repeats)
return self._shallow_copy(left=left_repeat, right=right_repeat)

_interval_shared_docs[
"contains"
] = """
_interval_shared_docs["contains"] = textwrap.dedent(
"""
Check elementwise if the Intervals contain the value.

Return a boolean mask whether the value is contained in the Intervals
Expand All @@ -1055,16 +1097,27 @@ def repeat(self, repeats, axis=None):

Examples
--------
>>> intervals = pd.%(qualname)s.from_tuples([(0, 1), (1, 3), (2, 4)])
>>> intervals
%(klass)s([(0, 1], (1, 3], (2, 4]],
closed='right',
dtype='interval[int64]')
%(examples)s
>>> intervals.contains(0.5)
array([ True, False, False])
"""
)

@Appender(_interval_shared_docs["contains"] % _shared_docs_kwargs)
@Appender(
_interval_shared_docs["contains"]
% dict(
klass="IntervalArray",
examples=textwrap.dedent(
"""\
>>> intervals = pd.arrays.IntervalArray.from_tuples([(0, 1), (1, 3), (2, 4)])
>>> intervals
<IntervalArray>
[(0, 1], (1, 3], (2, 4]]
Length: 3, closed: right, dtype: interval[int64]
"""
),
)
)
def contains(self, other):
if isinstance(other, Interval):
raise NotImplementedError("contains not implemented for two intervals")
Expand All @@ -1073,9 +1126,8 @@ def contains(self, other):
other < self.right if self.open_right else other <= self.right
)

_interval_shared_docs[
"overlaps"
] = """
_interval_shared_docs["overlaps"] = textwrap.dedent(
"""
Check elementwise if an Interval overlaps the values in the %(klass)s.

Two intervals overlap if they share a common point, including closed
Expand All @@ -1086,7 +1138,7 @@ def contains(self, other):

Parameters
----------
other : Interval
other : %(klass)s
Interval to check against for an overlap.

Returns
Expand All @@ -1100,11 +1152,7 @@ def contains(self, other):

Examples
--------
>>> intervals = pd.%(qualname)s.from_tuples([(0, 1), (1, 3), (2, 4)])
>>> intervals
%(klass)s([(0, 1], (1, 3], (2, 4]],
closed='right',
dtype='interval[int64]')
%(examples)s
>>> intervals.overlaps(pd.Interval(0.5, 1.5))
array([ True, True, False])

Expand All @@ -1117,9 +1165,25 @@ def contains(self, other):

>>> intervals.overlaps(pd.Interval(1, 2, closed='right'))
array([False, True, False])
"""
"""
)

@Appender(_interval_shared_docs["overlaps"] % _shared_docs_kwargs)
@Appender(
_interval_shared_docs["overlaps"]
% dict(
klass="IntervalArray",
examples=textwrap.dedent(
"""\
>>> data = [(0, 1), (1, 3), (2, 4)]
>>> intervals = pd.arrays.IntervalArray.from_tuples(data)
>>> intervals
<IntervalArray>
[(0, 1], (1, 3], (2, 4]]
Length: 3, closed: right, dtype: interval[int64]
"""
),
)
)
def overlaps(self, other):
if isinstance(other, (IntervalArray, ABCIntervalIndex)):
raise NotImplementedError
Expand Down
Loading