8000 TST/CLN: Fixturize frame/test_analytics by h-vetinari · Pull Request #22733 · pandas-dev/pandas · GitHub
[go: up one dir, main page]

Skip to content

TST/CLN: Fixturize frame/test_analytics #22733

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

Merged
merged 15 commits into from
Oct 6, 2018
Merged
Changes from 1 commit
Commits
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
Prev Previous commit
Next Next commit
Pure copy/paste of _check_stat_op and _check_bool_op
  • Loading branch information
h-vetinari committed Sep 25, 2018
commit 7ac476ec50d3a9b44112c078a61f9455efe93c07
280 changes: 141 additions & 139 deletions pandas/tests/frame/test_analytics.py
Original file line number Diff line number Diff line change
Expand Up @@ -25,6 +25,147 @@
import pandas.util._test_decorators as td


def _check_stat_op(self, name, alternative, main_frame, float_frame,
float_string_frame, has_skipna=True,
has_numeric_only=False, check_dtype=True,
check_dates=False, check_less_precise=False,
skipna_alternative=None):

f = getattr(main_frame, name)

if check_dates:
df = DataFrame({'b': date_range('1/1/2001', periods=2)})
_f = getattr(df, name)
result = _f()
assert isinstance(result, Series)

df['a'] = lrange(len(df))
result = getattr(df, name)()
assert isinstance(result, Series)
assert len(result)

if has_skipna:
def wrapper(x):
return alternative(x.values)

skipna_wrapper = tm._make_skipna_wrapper(alternative,
skipna_alternative)
result0 = f(axis=0, skipna=False)
result1 = f(axis=1, skipna=False)
tm.assert_series_equal(result0, main_frame.apply(wrapper),
check_dtype=check_dtype,
check_less_precise=check_less_precise)
# HACK: win32
tm.assert_series_equal(result1, main_frame.apply(wrapper, axis=1),
check_dtype=False,
check_less_precise=check_less_precise)
else:
skipna_wrapper = alternative

result0 = f(axis=0)
result1 = f(axis=1)
tm.assert_series_equal(result0, main_frame.apply(skipna_wrapper),
check_dtype=check_dtype,
check_less_precise=check_less_precise)
if name in ['sum', 'prod']:
expected = main_frame.apply(skipna_wrapper, axis=1)
tm.assert_series_equal(result1, expected, check_dtype=False,
check_less_precise=check_less_precise)

# check dtypes
if check_dtype:
lcd_dtype = main_frame.values.dtype
assert lcd_dtype == result0.dtype
assert lcd_dtype == result1.dtype

# bad axis
tm.assert_raises_regex(ValueError, 'No axis named 2', f, axis=2)
# make sure works on mixed-type frame
getattr(float_string_frame, name)(axis=0)
getattr(float_string_frame, name)(axis=1)

if has_numeric_only:
getattr(float_string_frame, name)(axis=0, numeric_only=True)
getattr(float_string_frame, name)(axis=1, numeric_only=True)
getattr(float_frame, name)(axis=0, numeric_only=False)
getattr(float_frame, name)(axis=1, numeric_only=False)

# all NA case
if has_skipna:
all_na = float_frame * np.NaN
r0 = getattr(all_na, name)(axis=0)
r1 = getattr(all_na, name)(axis=1)
if name in ['sum', 'prod']:
unit = int(name == 'prod')
expected = pd.Series(unit, index=r0.index, dtype=r0.dtype)
tm.assert_series_equal(r0, expected)
expected = pd.Series(unit, index=r1.index, dtype=r1.dtype)
tm.assert_series_equal(r1, expected)


def _check_bool_op(self, name, alternative, frame, float_string_frame,
has_skipna=True, has_bool_only=False):

f = getattr(frame, name)

if has_skipna:
def skipna_wrapper(x):
nona = x.dropna().values
return alternative(nona)

def wrapper(x):
return alternative(x.values)

result0 = f(axis=0, skipna=False)
result1 = f(axis=1, skipna=False)
tm.assert_series_equal(result0, frame.apply(wrapper))
tm.assert_series_equal(result1, frame.apply(wrapper, axis=1),
check_dtype=False) # HACK: win32
else:
skipna_wrapper = alternative
wrapper = alternative

result0 = f(axis=0)
result1 = f(axis=1)
tm.assert_series_equal(result0, frame.apply(skipna_wrapper))
tm.assert_series_equal(result1, frame.apply(skipna_wrapper, axis=1),
check_dtype=False)

# bad axis
pytest.raises(ValueError, f, axis=2)

# make sure works on mixed-type frame
mixed = float_string_frame
mixed['_bool_'] = np.random.randn(len(mixed)) > 0
getattr(mixed, name)(axis=0)
getattr(mixed, name)(axis=1)

class NonzeroFail(object):

def __nonzero__(self):
raise ValueError

mixed['_nonzero_fail_'] = NonzeroFail()

if has_bool_only:
getattr(mixed, name)(axis=0, bool_only=True)
getattr(mixed, name)(axis=1, bool_only=True)
getattr(frame, name)(axis=0, bool_only=False)
getattr(frame, name)(axis=1, bool_only=False)

# all NA case
if has_skipna:
all_na = frame * np.NaN
r0 = getattr(all_na, name)(axis=0)
r1 = getattr(all_na, name)(axis=1)
if name == 'any':
assert not r0.any()
assert not r1.any()
else:
assert r0.all()
assert r1.all()


class TestDataFrameAnalytics():

# ---------------------------------------------------------------------=
Expand Down Expand Up @@ -803,83 +944,6 @@ def alt(x):
assert kurt.name is None
assert kurt2.name == 'bar'

def _check_stat_op(self, name, alternative, main_frame, float_frame,
float_string_frame, has_skipna=True,
has_numeric_only=False, check_dtype=True,
check_dates=False, check_less_precise=False,
skipna_alternative=None):

f = getattr(main_frame, name)

if check_dates:
df = DataFrame({'b': date_range('1/1/2001', periods=2)})
_f = getattr(df, name)
result = _f()
assert isinstance(result, Series)

df['a'] = lrange(len(df))
result = getattr(df, name)()
assert isinstance(result, Series)
assert len(result)

if has_skipna:
def wrapper(x):
return alternative(x.values)

skipna_wrapper = tm._make_skipna_wrapper(alternative,
skipna_alternative)
result0 = f(axis=0, skipna=False)
result1 = f(axis=1, skipna=False)
tm.assert_series_equal(result0, main_frame.apply(wrapper),
check_dtype=check_dtype,
check_less_precise=check_less_precise)
# HACK: win32
tm.assert_series_equal(result1, main_frame.apply(wrapper, axis=1),
check_dtype=False,
check_less_precise=check_less_precise)
else:
skipna_wrapper = alternative

result0 = f(axis=0)
result1 = f(axis=1)
tm.assert_series_equal(result0, main_frame.apply(skipna_wrapper),
check_dtype=check_dtype,
check_less_precise=check_less_precise)
if name in ['sum', 'prod']:
expected = main_frame.apply(skipna_wrapper, axis=1)
tm.assert_series_equal(result1, expected, check_dtype=False,
check_less_precise=check_less_precise)

# check dtypes
if check_dtype:
lcd_dtype = main_frame.values.dtype
assert lcd_dtype == result0.dtype
assert lcd_dtype == result1.dtype

# bad axis
tm.assert_raises_regex(ValueError, 'No axis named 2', f, axis=2)
# make sure works on mixed-type frame
getattr(float_string_frame, name)(axis=0)
getattr(float_string_frame, name)(axis=1)

if has_numeric_only:
getattr(float_string_frame, name)(axis=0, numeric_only=True)
getattr(float_string_frame, name)(axis=1, numeric_only=True)
getattr(float_frame, name)(axis=0, numeric_only=False)
getattr(float_frame, name)(axis=1, numeric_only=False)

# all NA case
if has_skipna:
all_na = float_frame * np.NaN
r0 = getattr(all_na, name)(axis=0)
r1 = getattr(all_na, name)(axis=1)
if name in ['sum', 'prod']:
unit = int(name == 'prod')
expected = pd.Series(unit, index=r0.index, dtype=r0.dtype)
tm.assert_series_equal(r0, expected)
expected = pd.Series(unit, index=r1.index, dtype=r1.dtype)
tm.assert_series_equal(r1, expected)

@pytest.mark.parametrize("dropna, expected", [
(True, {'A': [12],
'B': [10.0],
Expand Down Expand Up @@ -1336,68 +1400,6 @@ def test_any_all_level_axis_none_raises(self, method):
with tm.assert_raises_regex(ValueError, xpr):
getattr(df, method)(axis=None, level='out')

def _check_bool_op(self, name, alternative, frame, float_string_frame,
has_skipna=True, has_bool_only=False):

f = getattr(frame, name)

if has_skipna:
def skipna_wrapper(x):
nona = x.dropna().values
return alternative(nona)

def wrapper(x):
return alternative(x.values)

result0 = f(axis=0, skipna=False)
result1 = f(axis=1, skipna=False)
tm.assert_series_equal(result0, frame.apply(wrapper))
tm.assert_series_equal(result1, frame.apply(wrapper, axis=1),
check_dtype=False) # HACK: win32
else:
skipna_wrapper = alternative
wrapper = alternative

result0 = f(axis=0)
result1 = f(axis=1)
tm.assert_series_equal(result0, frame.apply(skipna_wrapper))
tm.assert_series_equal(result1, frame.apply(skipna_wrapper, axis=1),
check_dtype=False)

# bad axis
pytest.raises(ValueError, f, axis=2)

# make sure works on mixed-type frame
mixed = float_string_frame
mixed['_bool_'] = np.random.randn(len(mixed)) > 0
getattr(mixed, name)(axis=0)
getattr(mixed, name)(axis=1)

class NonzeroFail(object):

def __nonzero__(self):
raise ValueError

mixed['_nonzero_fail_'] = NonzeroFail()

if has_bool_only:
getattr(mixed, name)(axis=0, bool_only=True)
getattr(mixed, name)(axis=1, bool_only=True)
getattr(frame, name)(axis=0, bool_only=False)
getattr(frame, name)(axis=1, bool_only=False)

# all NA case
if has_skipna:
all_na = frame * np.NaN
r0 = getattr(all_na, name)(axis=0)
r1 = getattr(all_na, name)(axis=1)
if name == 'any':
assert not r0.any()
assert not r1.any()
else:
assert r0.all()
assert r1.all()

# ----------------------------------------------------------------------
# Isin

Expand Down
0