-
-
Notifications
You must be signed in to change notification settings - Fork 18.4k
ENH: Merge DataFrame and Series using on
(GH21220)
#21223
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.
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
Changes from 9 commits
91a3f16
64e6e66
8939fad
b09ffb7
1a0e5a2
59b487d
0d14cc2
12da2ce
2d689ad
687568b
7ed9688
2ce56e7
ac9d5a1
fdf324c
e896a91
69d8bda
f7b333f
c4c988c
d099fd6
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -11,7 +11,7 @@ | |
import pandas.compat as compat | ||
|
||
from pandas import (Categorical, DataFrame, | ||
Index, MultiIndex, Timedelta) | ||
Index, MultiIndex, Timedelta, Series) | ||
from pandas.core.arrays.categorical import _recode_for_categories | ||
from pandas.core.frame import _merge_doc | ||
from pandas.core.dtypes.common import ( | ||
|
@@ -492,6 +492,8 @@ def __init__(self, left, right, how='inner', on=None, | |
left_index=False, right_index=False, sort=True, | ||
suffixes=('_x', '_y'), copy=True, indicator=False, | ||
validate=None): | ||
left = validate_operand(left) | ||
right = validate_operand(right) | ||
self.left = self.orig_left = left | ||
self.right = self.orig_right = right | ||
self.how = how | ||
|
@@ -518,13 +520,6 @@ def __init__(self, left, right, how='inner', on=None, | |
raise ValueError( | ||
'indicator option can only accept boolean or string arguments') | ||
|
||
if not isinstance(left, DataFrame): | ||
raise ValueError('can not merge DataFrame with instance of ' | ||
'type {left}'.format(left=type(left))) | ||
if not isinstance(right, DataFrame): | ||
raise ValueError('can not merge DataFrame with instance of ' | ||
'type {right}'.format(right=type(right))) | ||
|
||
if not is_bool(left_index): | ||
raise ValueError( | ||
'left_index parameter must be of type bool, not ' | ||
|
@@ -1639,3 +1634,16 @@ def _should_fill(lname, rname): | |
|
||
def _any(x): | ||
return x is not None and com._any_not_none(*x) | ||
|
||
|
||
def validate_operand(obj): | ||
if isinstance(obj, DataFrame): | ||
return obj | ||
elif isinstance(obj, Series): | ||
if obj.name is None: | ||
raise ValueError('Cannot merge a Series without a name') | ||
else: | ||
return obj.to_frame() | ||
else: | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. just raise, and more like
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Thanks - done - updated the statement and made into a TypeError There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Is there a reason you changed this to TypeError? There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. @jorisvandenbossche Thanks - I thought TypeError is more relevant for the statement below, as the message is telling the user "only objects of type Series or DataFrame can be merged" There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I don't think the one is necessarily much better than the other in this case, so I would personally rather keep it as it was to be conservative. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Although eg There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Ok - not changing then and keeping it (i.e. TypeError) |
||
raise ValueError('Cannot merge a DataFrame or a Series with ' | ||
'instance of type {obj}'.format(obj=type(obj))) |
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -230,7 +230,9 @@ def test_join_on_fails_with_different_column_counts(self): | |
|
||
def test_join_on_fails_with_wrong_object_type(self): | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. can you parameterize this test |
||
# GH12081 | ||
wrongly_typed = [Series([0, 1]), 2, 'str', None, np.array([0, 1])] | ||
wrongly_typed = [2, 'str', None, np.array([0, 1])] | ||
# GH21220 - merging of Series and DataFrame is now allowed | ||
# Edited the test to remove the Series object from 'wrongly_typed' | ||
df = DataFrame({'a': [1, 1]}) | ||
|
||
for obj in wrongly_typed: | ||
|
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -1864,3 +1864,42 @@ def test_merge_index_types(index): | |
OrderedDict([('left_data', [1, 2]), ('right_data', [1.0, 2.0])]), | ||
index=index) | ||
assert_frame_equal(result, expected) | ||
|
||
|
||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. also parameterize this as much as possible. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. done |
||
@pytest.mark.parametrize("on,left_on,right_on,left_index,right_index,nms,nm", [ | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. can you format this so it lines up, its pretty unreadable now There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Thanks - done |
||
(['outer', 'inner'], None, None, False, False, | ||
['outer', 'inner'], 'B'), | ||
(None, None, None, True, True, ['outer', 'inner'], | ||
'B'), | ||
(None, ['outer', 'inner'], None, False, True, None, | ||
'B'), | ||
(None, None, ['outer', 'inner'], True, False, None, | ||
'B'), | ||
(['outer', 'inner'], None, None, False, False, | ||
['outer', 'inner'], None), | ||
(None, None, None, True, True, ['outer', 'inner'], | ||
None), | ||
(None, ['outer', 'inner'], None, False, True, None, | ||
None), | ||
(None, None, ['outer', 'inner'], True, False, None, | ||
None), | ||
]) | ||
def test_merge_series(on, left_on, right_on, left_index, right_index, nms, nm): | ||
# GH 21220 | ||
a = pd.DataFrame({"A": [1, 2, 3, 4]}, | ||
index=pd.MultiIndex.from_product([['a', 'b'], [0, 1]], | ||
names=['outer', 'inner'])) | ||
b = pd.Series([1, 2, 3, 4], | ||
index=pd.MultiIndex.from_product([['a', 'b'], [1, 2]], | ||
names=['outer', 'inner']), name=nm) | ||
expected = pd.DataFrame({"A": [2, 4], "B": [1, 3]}, | ||
index=pd.MultiIndex.from_product([['a', 'b'], [1]], | ||
names=nms)) | ||
if nm is not None: | ||
result = pd.merge(a, b, on=on, left_on=left_on, right_on=right_on, | ||
left_index=left_index, right_index=right_index) | ||
tm.assert_frame_equal(result, expected) | ||
else: | ||
with tm.assert_raises_regex(ValueError, 'a Series without a name'): | ||
result = pd.merge(a, b, on=on, left_on=left_on, right_on=right_on, | ||
left_index=left_index, right_index=right_index) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this won't render, use
:func:`merge`
. also not clear what the change is from a user POV hereThere was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks - updated the comment as:
:func:`merge` now directly allows merge between objects of type ``DataFrame`` and ``Series`` with a name, without need to convert the ``Series`` object into a ``DataFrame`` beforehand (:issue:`21220`)