Skip to content

CLN: res/exp and GH references in frame tests #22730

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 14 commits into from
Oct 8, 2018
Merged

CLN: res/exp and GH references in frame tests #22730

Show file tree
Hide file tree
Changes from 13 commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
f699cd2
Fixturize tests/frame/test_arithmetic
h-vetinari Sep 17, 2018
e903579
Fixturize tests/frame/test_analytics
h-vetinari Sep 23, 2018
be4605d
Clean res/exp in frame/test_apply.py
h-vetinari Sep 23, 2018
a399489
Unify GH references in frame/test_apply.py
h-vetinari Sep 23, 2018
b403a73
Clean up res/exp in frame/test_api.py
h-vetinari Sep 23, 2018
fa0fc2f
Unify GH references in frame/test_api.py
h-vetinari Sep 23, 2018
f56bfde
Clean res/exp in frame/test_arithmetic.py
h-vetinari Sep 23, 2018
f29a839
Unify GH references for frame/test_arithmetic.py
h-vetinari Sep 23, 2018
780dd84
Clean res/exp for frame/test_analytics.py
h-vetinari Sep 23, 2018
0e70a30
Unify GH reference for frame/test_analytics.py
h-vetinari Sep 23, 2018
855a186
Change GH reference formatting (review jreback)
h-vetinari Sep 23, 2018
733b889
Revert "Change GH reference formatting (review jreback)"
h-vetinari Sep 23, 2018
d0c6d37
Merge remote-tracking branch 'upstream/master' into fixturize_frame_t…
h-vetinari Oct 7, 2018
ca36942
Fix typo
h-vetinari Oct 7, 2018
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
66 changes: 33 additions & 33 deletions pandas/tests/frame/test_analytics.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -340,8 +340,8 @@ def test_corr_cov_independent_index_column(self):
assert result.index.equals(result.columns)

def test_corr_invalid_method(self):
# GH PR #22298
df = pd.DataFrame(np.random.normal(size=(10, 2)))
# GH 22298
df = pd. DataFrame(np.random.normal(size=(10, 2)))
Copy link
Contributor

Choose a reason for hiding this comment

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

space added here

msg = ("method must be either 'pearson', 'spearman', "
"or 'kendall'")
with tm.assert_raises_regex(ValueError, msg):
Expand Down Expand Up @@ -548,8 +548,8 @@ def test_describe_categorical(self):

cat = Series(Categorical(["a", "b", "c", "c"]))
df3 = DataFrame({"cat": cat, "s": ["a", "b", "c", "c"]})
res = df3.describe()
tm.assert_numpy_array_equal(res["cat"].values, res["s"].values)
result = df3.describe()
tm.assert_numpy_array_equal(result["cat"].values, result["s"].values)

def test_describe_categorical_columns(self):
# GH 11558
Expand Down Expand Up @@ -620,8 +620,8 @@ def test_describe_timedelta_values(self):
index=['count', 'mean', 'std', 'min', '25%',
'50%', '75%', 'max'])

res = df.describe()
tm.assert_frame_equal(res, expected)
result = df.describe()
tm.assert_frame_equal(result, expected)

exp_repr = (" t1 t2\n"
"count 5 5\n"
Expand All @@ -632,7 +632,7 @@ def test_describe_timedelta_values(self):
"50% 3 days 00:00:00 0 days 03:00:00\n"
"75% 4 days 00:00:00 0 days 04:00:00\n"
"max 5 days 00:00:00 0 days 05:00:00")
assert repr(res) == exp_repr
assert repr(result) == exp_repr

def test_describe_tz_values(self, tz_naive_fixture):
# GH 21332
Expand All @@ -653,8 +653,8 @@ def test_describe_tz_values(self, tz_naive_fixture):
'last', 'mean', 'std', 'min', '25%', '50%',
'75%', 'max']
)
res = df.describe(include='all')
tm.assert_frame_equal(res, expected)
result = df.describe(include='all')
tm.assert_frame_equal(result, expected)

def test_reduce_mixed_frame(self):
# GH 6806
Expand Down Expand Up @@ -684,7 +684,7 @@ def test_count(self, float_frame_with_na, float_frame, float_string_frame):
ct2 = frame.count(0)
assert isinstance(ct2, Series)

# GH #423
# GH 423
df = DataFrame(index=lrange(10))
result = df.count(1)
expected = Series(0, index=df.index)
Expand Down Expand Up @@ -731,7 +731,7 @@ def test_sum(self, float_frame_with_na, mixed_float_frame,
@pytest.mark.parametrize('method', ['sum', 'mean', 'prod', 'var',
'std', 'skew', 'min', 'max'])
def test_stat_operators_attempt_obj_array(self, method):
# GH #676
# GH 676
Copy link
Contributor

Choose a reason for hiding this comment

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

I think these shouldn't have spaced and instead should be gh-676 as then they show up in the viewer cc @gfyoung

Copy link
Member

Choose a reason for hiding this comment

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

The gh-* format is standard for Git commits to GitHub, as those links get parsed. Other formats do not get that same treatment AFAIK. As for the viewer, it doesn't really matter, as I don't believe GitHub parses them inline.

That being said, while my personal preference is to use gh-*, I'm a little unsure as to why we are trying to standardize the references given that they are somewhat moot in the viewer...

Copy link
Contributor Author

Choose a reason for hiding this comment

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

I chose the most common/consistent formatting. Can go to gh- as well...

Copy link
Member

Choose a reason for hiding this comment

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

@h-vetinari : Given that this really doesn't affect anything from a GitHub UI perspective, I am indifferent as to which way you go. Just making sure you're aware that what you're doing is purely aesthetic for our developer eyes. 🙂

Copy link
Contributor Author

Choose a reason for hiding this comment

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

@gfyoung
Hmmm, visually I prefer # GH 1234 over # gh-1234. Didn't see your comment soon enough before I pushed the new commit, reverting.

data = {
'a': [-0.00049987540199591344, -0.0016467257772919831,
0.00067695870775883013],
Expand Down Expand Up @@ -873,7 +873,7 @@ def test_var_std(self, float_frame_with_na, datetime_frame, float_frame,
@pytest.mark.parametrize(
"meth", ['sem', 'var', 'std'])
def test_numeric_only_flag(self, meth):
# GH #9201
# GH 9201
df1 = DataFrame(np.random.randn(5, 3), columns=['foo', 'bar', 'baz'])
# set one entry to a number in str format
df1.loc[0, 'foo'] = '100'
Expand Down Expand Up @@ -1438,12 +1438,12 @@ def test_any_all_extra(self):
(np.any, {'A': pd.Series([1, 2], dtype='category')}, True),

# # Mix
# GH-21484
# GH 21484
# (np.all, {'A': pd.Series([10, 20], dtype='M8[ns]'),
# 'B': pd.Series([10, 20], dtype='m8[ns]')}, True),
])
def test_any_all_np_func(self, func, data, expected):
# https://github.com/pandas-dev/pandas/issues/19976
# GH 19976
data = DataFrame(data)
result = func(data)
assert isinstance(result, np.bool_)
Expand All @@ -1455,7 +1455,7 @@ def test_any_all_np_func(self, func, data, expected):
assert result.item() is expected

def test_any_all_object(self):
# https://github.com/pandas-dev/pandas/issues/19976
# GH 19976
result = np.all(DataFrame(columns=['a', 'b'])).item()
assert result is True

Expand All @@ -1477,7 +1477,7 @@ def test_any_all_level_axis_none_raises(self, method):
# Isin

def test_isin(self):
# GH #4211
# GH 4211
df = DataFrame({'vals': [1, 2, 3, 4], 'ids': ['a', 'b', 'f', 'n'],
'ids2': ['a', 'n', 'c', 'n']},
index=['foo', 'bar', 'baz', 'qux'])
Expand All @@ -1489,7 +1489,7 @@ def test_isin(self):

@pytest.mark.parametrize("empty", [[], Series(), np.array([])])
def test_isin_empty(self, empty):
# see gh-16991
# GH 16991
df = DataFrame({'A': ['a', 'b', 'c'], 'B': ['a', 'e', 'f']})
expected = DataFrame(False, df.index, df.columns)

Expand All @@ -1515,7 +1515,7 @@ def test_isin_dict(self):
tm.assert_frame_equal(result, expected)

def test_isin_with_string_scalar(self):
# GH4763
# GH 4763
df = DataFrame({'vals': [1, 2, 3, 4], 'ids': ['a', 'b', 'f', 'n'],
'ids2': ['a', 'n', 'c', 'n']},
index=['foo', 'bar', 'baz', 'qux'])
Expand All @@ -1541,7 +1541,7 @@ def test_isin_df(self):
tm.assert_frame_equal(result, expected)

def test_isin_tuples(self):
# GH16394
# GH 16394
df = pd.DataFrame({'A': [1, 2, 3], 'B': ['a', 'b', 'f']})
df['C'] = list(zip(df['A'], df['B']))
result = df['C'].isin([(1, 'a')])
Expand Down Expand Up @@ -1751,7 +1751,7 @@ def test_round(self):
expected_rounded['col1'])

def test_numpy_round(self):
# See gh-12600
# GH 12600
df = DataFrame([[1.53, 1.36], [0.06, 7.01]])
out = np.round(df, decimals=0)
expected = DataFrame([[2., 1.], [0., 7.]])
Expand All @@ -1762,7 +1762,7 @@ def test_numpy_round(self):
np.round(df, decimals=0, out=df)

def test_round_mixed_type(self):
# GH11885
# GH 11885
df = DataFrame({'col1': [1.1, 2.2, 3.3, 4.4],
'col2': ['1', 'a', 'c', 'f'],
'col3': date_range('20111111', periods=4)})
Expand All @@ -1777,7 +1777,7 @@ def test_round_mixed_type(self):
tm.assert_frame_equal(df.round({'col3': 1}), df)

def test_round_issue(self):
# GH11611
# GH 11611

df = pd.DataFrame(np.random.random([3, 3]), columns=['A', 'B', 'C'],
index=['first', 'second', 'third'])
Expand All @@ -1794,7 +1794,7 @@ def test_built_in_round(self):
pytest.skip("build in round cannot be overridden "
"prior to Python 3")

# GH11763
# GH 11763
# Here's the test frame we'll be working with
df = DataFrame(
{'col1': [1.123, 2.123, 3.123], 'col2': [1.234, 2.234, 3.234]})
Expand Down Expand Up @@ -1838,7 +1838,7 @@ def test_clip(self, float_frame):
assert (float_frame.values == original.values).all()

def test_inplace_clip(self, float_frame):
# GH #15388
# GH 15388
median = float_frame.median().median()
frame_copy = float_frame.copy()

Expand All @@ -1854,7 +1854,7 @@ def test_inplace_clip(self, float_frame):
assert not (frame_copy.values != median).any()

def test_dataframe_clip(self):
# GH #2747
# GH 2747
df = DataFrame(np.random.randn(1000, 2))

for lb, ub in [(-1, 1), (1, -1)]:
Expand All @@ -1881,7 +1881,7 @@ def test_clip_mixed_numeric(self):

@pytest.mark.parametrize("inplace", [True, False])
def test_clip_against_series(self, inplace):
# GH #6966
# GH 6966

df = DataFrame(np.random.randn(1000, 2))
lb = Series(np.random.randn(1000))
Expand Down Expand Up @@ -1916,7 +1916,7 @@ def test_clip_against_series(self, inplace):
])
def test_clip_against_list_like(self, simple_frame,
inplace, lower, axis, res):
# GH #15390
# GH 15390
original = simple_frame.copy(deep=True)

result = original.clip(lower=lower, upper=[5, 6, 7],
Expand Down Expand Up @@ -1947,12 +1947,12 @@ def test_clip_against_frame(self, axis):

def test_clip_with_na_args(self, float_frame):
"""Should process np.nan argument as None """
# GH # 17276
# GH 17276
tm.assert_frame_equal(float_frame.clip(np.nan), float_frame)
tm.assert_frame_equal(float_frame.clip(upper=np.nan, lower=np.nan),
float_frame)

# GH #19992
# GH 19992
df = DataFrame({'col_0': [1, 2, 3], 'col_1': [4, 5, 6],
'col_2': [7, 8, 9]})

Expand Down Expand Up @@ -2025,7 +2025,7 @@ def test_dot(self):
_np_version_under1p12,
reason="unpredictable return types under numpy < 1.12")
def test_matmul(self):
# matmul test is for GH #10259
# matmul test is for GH 10259
a = DataFrame(np.random.randn(3, 4), index=['a', 'b', 'c'],
columns=['p', 'q', 'r', 's'])
b = DataFrame(np.random.randn(4, 2), index=['p', 'q', 'r', 's'],
Expand Down Expand Up @@ -2139,7 +2139,7 @@ class TestNLargestNSmallest(object):
['b', 'c', 'c']])
@pytest.mark.parametrize('n', range(1, 11))
def test_n(self, df_strings, nselect_method, n, order):
# GH10393
# GH 10393
df = df_strings
if 'b' in order:

Expand Down Expand Up @@ -2190,7 +2190,7 @@ def test_duplicates_on_starter_columns(self, method, expected):
tm.assert_frame_equal(result, expected)

def test_n_identical_values(self):
# GH15297
# GH 15297
df = pd.DataFrame({'a': [1] * 5, 'b': [1, 2, 3, 4, 5]})

result = df.nlargest(3, 'a')
Expand Down Expand Up @@ -2224,7 +2224,7 @@ def test_n_duplicate_index(self, df_duplicates, n, order):
tm.assert_frame_equal(result, expected)

def test_duplicate_keep_all_ties(self):
# see gh-16818
# GH 16818
df = pd.DataFrame({'a': [5, 4, 4, 2, 3, 3, 3, 3],
'b': [10, 9, 8, 7, 5, 50, 10, 20]})
result = df.nlargest(4, 'a', keep='all')
Expand Down
18 changes: 9 additions & 9 deletions pandas/tests/frame/test_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -192,7 +192,7 @@ def test_iteritems(self):
assert isinstance(v, self.klass._constructor_sliced)

def test_items(self):
# issue #17213, #13918
# GH 17213, GH 13918
cols = ['a', 'b', 'c']
df = DataFrame([[1, 2, 3], [4, 5, 6]], columns=cols)
for c, (k, v) in zip(cols, df.items()):
Expand All @@ -213,7 +213,7 @@ def test_iterrows(self, float_frame, float_string_frame):
self._assert_series_equal(v, exp)

def test_iterrows_iso8601(self):
# GH19671
# GH 19671
if self.klass == SparseDataFrame:
pytest.xfail(reason='SparseBlock datetime type not implemented.')

Expand Down Expand Up @@ -354,7 +354,7 @@ def test_axis_aliases(self, float_frame):
assert_series_equal(result, expected)

def test_class_axis(self):
# https://github.com/pandas-dev/pandas/issues/18147
# GH 18147
Copy link
Member

Choose a reason for hiding this comment

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

Generally still ask that you try to minimize your changes as much as possible. Obviously changing comments isn't going to affect any of the code base but it still makes the diffs of your PRs unnecessarily larger, which makes reviews more difficult.

You should always look for logical separation points for smaller PRs, i.e. if you really want to clean up these comments then make a separate PR for that rather than bundling here. For this change please revert this file to master

Copy link
Contributor Author

Choose a reason for hiding this comment

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

IMO these are trivial changes that don't get done otherwise, and what's more I did get asked to do this in several PRs, so I just do it preemptively.

However, I separated the commits between fixturizing and import-cleaning, so you can review the separate commits (almost) as separate PRs.

# no exception and no empty docstring
assert pydoc.getdoc(DataFrame.index)
assert pydoc.getdoc(DataFrame.columns)
Expand All @@ -366,9 +366,9 @@ def test_more_values(self, float_string_frame):
def test_repr_with_mi_nat(self, float_string_frame):
df = self.klass({'X': [1, 2]},
index=[[pd.NaT, pd.Timestamp('20130101')], ['a', 'b']])
res = repr(df)
exp = ' X\nNaT a 1\n2013-01-01 b 2'
assert res == exp
result = repr(df)
expected = ' X\nNaT a 1\n2013-01-01 b 2'
assert result == expected

def test_iteritems_names(self, float_string_frame):
for k, v in compat.iteritems(float_string_frame):
Expand Down Expand Up @@ -418,7 +418,7 @@ def test_values(self, float_frame):
assert (float_frame.values[:, 0] == 5).all()

def test_as_matrix_deprecated(self, float_frame):
# GH18458
# GH 18458
with tm.assert_produces_warning(FutureWarning):
cols = float_frame.columns.tolist()
result = float_frame.as_matrix(columns=cols)
Expand All @@ -439,7 +439,7 @@ def test_transpose_get_view(self, float_frame):
assert (float_frame.values[5:10] == 5).all()

def test_inplace_return_self(self):
# re #1893
# GH 1893

data = DataFrame({'a': ['foo', 'bar', 'baz', 'qux'],
'b': [0, 0, 1, 1],
Expand Down Expand Up @@ -503,7 +503,7 @@ def _check_f(base, f):
_check_f(d.copy(), f)

def test_tab_complete_warning(self, ip):
# https://github.com/pandas-dev/pandas/issues/16409
# GH 16409
pytest.importorskip('IPython', minversion="6.0.0")
from IPython.core.completer import provisionalcompleter

Expand Down
Loading