8000 TST/CLN: series.duplicated; parametrisation; fix warning by h-vetinari · Pull Request #21899 · pandas-dev/pandas · GitHub
[go: up one dir, main page]
Skip to content

TST/CLN: series.duplicated; parametrisation; fix warning #21899

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 7 commits into from
Jul 16, 2018
Merged

TST/CLN: series.duplicated; parametrisation; fix warning #21899

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
4ca9dee
TST/CLN: series.duplicated; parametrisation; fix warning
h-vetinari Jul 13, 2018
c06442b
Incorporate review (jreback)
h-vetinari Jul 14, 2018
92d708c
Split off duplicates/unique tests into separate file
h-vetinari Jul 14, 2018
12d2888
Change tests away from classes; reorder conftest.py
h-vetinari Jul 14, 2018
c9a3f71
Typos
h-vetinari Jul 14, 2018
d34b7d1
Further cleanup
h-vetinari Jul 14, 2018
e640040
Remove space
h-vetinari Jul 14, 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
Prev Previous commit
Next Next commit
Change tests away from classes; reorder conftest.py
  • Loading branch information
@h-vetinari
h-vetinari committed Jul 14, 2018
commit 12d288835e8660f8a2981f59ada78baea16c6bc1
33 changes: 15 additions & 18 deletions pandas/conftest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -248,7 +248,19 @@ def tz_aware_fixture(request):
return request.param


@pytest.fixture(params=[str, 'str', 'U'])
UNSIGNED_INT_DTYPES = ["uint8", "uint16", "uint32", "uint64"]
SIGNED_INT_DTYPES = [int, "int8", "int16", "int32", "int64"]
Copy link
Contributor

Choose a reason for hiding this comment

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

@gfyoung this is ok? it follows our existing pattern?

Copy link
Contributor Author
@h-vetinari h-vetinari Jul 14, 2018 •
edited
Loading

Choose a reason for hiding this comment

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

@jreback @gfyoung I only added COMPLEX_DTYPES, STRING_DTYPES (which was just giving names to existing collections) and ALL_NUMPY_DTYPES - the rest was just reordering.

ALL_INT_DTYPES = UNSIGNED_INT_DTYPES + SIGNED_INT_DTYPES

FLOAT_DTYPES = [float, "float32", "float64"]
COMPLEX_DTYPES = [complex, "complex64", "complex128"]
STRING_DTYPES = [str, 'str', 'U']

ALL_REAL_DTYPES = FLOAT_DTYPES + ALL_INT_DTYPES
ALL_NUMPY_DTYPES = ALL_REAL_DTYPES + STRING_DTYPES + COMPLEX_DTYPES


@pytest.fixture(params=STRING_DTYPES)
def string_dtype(request):
"""Parametrized fixture for string dtypes.

Expand All @@ -259,9 +271,6 @@ def string_dtype(request):
return request.param


FLOAT_DTYPES = [float, "float32", "float64"]


@pytest.fixture(params=FLOAT_DTYPES)
def float_dtype(request):
"""
Expand All @@ -274,7 +283,7 @@ def float_dtype(request):
return request.param


@pytest.fixture(params=[complex, "complex64", "complex128"])
@pytest.fixture(params=COMPLEX_DTYPES)
def complex_dtype(request):
"""
Parameterized fixture for complex dtypes.
Expand All @@ -286,11 +295,6 @@ def complex_dtype(request):
return request.param


UNSIGNED_INT_DTYPES = ["uint8", "uint16", "uint32", "uint64"]
SIGNED_INT_DTYPES = [int, "int8", "int16", "int32", "int64"]
ALL_INT_DTYPES = UNSIGNED_INT_DTYPES + SIGNED_INT_DTYPES


@pytest.fixture(params=SIGNED_INT_DTYPES)
def sint_dtype(request):
"""
Expand Down Expand Up @@ -337,13 +341,6 @@ def any_int_dtype(request):
return request.param


FLOAT_DTYPES = [float, "float32", "float64"]
COMPLEX_DTYPES = [complex, "complex64", "complex128"]
STRING_DTYPES = [str, 'str', 'U']
ALL_REAL_DTYPES = FLOAT_DTYPES + ALL_INT_DTYPES
ALL_NUMPY_DTYPES = ALL_REAL_DTYPES + STRING_DTYPES + COMPLEX_DTYPES


@pytest.fixture(params=ALL_REAL_DTYPES)
def any_real_dtype(request):
"""
Expand All @@ -367,7 +364,7 @@ def any_real_dtype(request):
@pytest.fixture(params=ALL_NUMPY_DTYPES)
def any_numpy_dtype(request):
"""
Parameterized fixture for any integer dtypes.
Parameterized fixture for any numpy dtypes.

* int8
* uint8
Expand Down
257 changes: 130 additions & 127 deletions pandas/tests/series/test_duplicates.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,133 +10,136 @@

from pandas.util.testing import assert_series_equal
import pandas.util.testing as tm
Copy link
Contributor

Choose a reason for hiding this comment

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

use tm; don’t import assert_series_equal

from .common import TestData


class TestSeriesDuplicates(TestData):

def test_value_counts_nunique(self):

# basics.rst doc example
series = Series(np.random.randn(500))
series[20:500] = np.nan
series[10:20] = 5000
result = series.nunique()
assert result == 11

# GH 18051
s = pd.Series(pd.Categorical([]))
assert s.nunique() == 0
s = pd.Series(pd.Categorical([np.nan]))
assert s.nunique() == 0

def test_unique(self):

# 714 also, dtype=float
s = Series([1.2345] * 100)
s[::2] = np.nan
result = s.unique()
assert len(result) == 2

s = Series([1.2345] * 100, dtype='f4')
s[::2] = np.nan
result = s.unique()
assert len(result) == 2

# NAs in object arrays #714
s = Series(['foo'] * 100, dtype='O')
s[::2] = np.nan
result = s.unique()
assert len(result) == 2

# decision about None
s = Series([1, 2, 3, None, None, None], dtype=object)
result = s.unique()
expected = np.array([1, 2, 3, None], dtype=object)
tm.assert_numpy_array_equal(result, expected)

# GH 18051
s = pd.Series(pd.Categorical([]))
tm.assert_categorical_equal(s.unique(), pd.Categorical([]),
check_dtype=False)
s = pd.Series(pd.Categorical([np.nan]))
tm.assert_categorical_equal(s.unique(), pd.Categorical([np.nan]),
check_dtype=False)

def test_unique_data_ownership(self):
# it works! #1807
Series(Series(["a", "c", "b"]).unique()).sort_values()

def test_is_unique(self):
# GH11946
s = Series(np.random.randint(0, 10, size=1000))
assert not s.is_unique
s = Series(np.arange(1000))
assert s.is_unique

def test_is_unique_class_ne(self, capsys):
# GH 20661
class Foo(object):
def __init__(self, val):
self._value = val

def __ne__(self, other):
raise Exception("NEQ not supported")

li = [Foo(i) for i in range(5)]
s = pd.Series(li, index=[i for i in range(5)])
_, err = capsys.readouterr()
s.is_unique
_, err = capsys.readouterr()
assert len(err) == 0

@pytest.mark.parametrize(
'keep, expected',
[
('first', Series([False, False, False, False, True, True, False])),
('last', Series([False, True, True, False, False, False, False])),
(False, Series([False, True, True, False, True, True, False]))
])
def test_drop_duplicates_non_bool(self, any_numpy_dtype, keep, expected):
tc = Series([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype(any_numpy_dtype))

assert_series_equal(tc.duplicated(keep=keep), expected)
assert_series_equal(tc.drop_duplicates(keep=keep), tc[~expected])
sc = tc.copy()
sc.drop_duplicates(keep=keep, inplace=True)
assert_series_equal(sc, tc[~expected])

@pytest.mark.parametrize('keep, expected',
[('first', Series([False, False, True, True])),
('last', Series([True, True, False, False])),
(False, Series([True, True, True, True]))])
def test_drop_duplicates_bool(self, keep, expected):
tc = Series([True, False, True, False])

assert_series_equal(tc.duplicated(keep=keep), expected)
assert_series_equal(tc.drop_duplicates(keep=keep), tc[~expected])
sc = tc.copy()
sc.drop_duplicates(keep=keep, inplace=True)
assert_series_equal(sc, tc[~expected])

@pytest.mark.parametrize('keep, expected', [
('first', Series([False, False, True, False, True], name='name')),
('last', Series([True, True, False, False, False], name='name')),
(False, Series([True, True, True, False, True], name='name'))
])
def test_duplicated_keep(self, keep, expected):
s = Series(['a', 'b', 'b', 'c', 'a'], name='name')

result = s.duplicated(keep=keep)
tm.assert_series_equal(result, expected)

@pytest.mark.parametrize('keep, expected', [
('first', Series([False, False, True, False, True])),
('last', Series([True, True, False, False, False])),
(False, Series([True, True, True, False, True]))
def test_value_counts_nunique():
# basics.rst doc example
series = Series(np.random.randn(500))
series[20:500] = np.nan
series[10:20] = 5000
result = series.nunique()
assert result == 11

# GH 18051
s = pd.Series(pd.Categorical([]))
assert s.nunique() == 0
s = pd.Series(pd.Categorical([np.nan]))
assert s.nunique() == 0


def test_unique():
# GH714 also, dtype=float
s = Series([1.2345] * 100)
s[::2] = np.nan
result = s.unique()
assert len(result) == 2

s = Series([1.2345] * 100, dtype='f4')
s[::2] = np.nan
result = s.unique()
assert len(result) == 2

# NAs in object arrays #714
s = Series(['foo'] * 100, dtype='O')
s[::2] = np.nan
result = s.unique()
assert len(result) == 2

# decision about None
s = Series([1, 2, 3, None, None, None], dtype=object)
result = s.unique()
expected = np.array([1, 2, 3, None], dtype=object)
tm.assert_numpy_array_equal(result, expected)

# GH 18051
s = pd.Series(pd.Categorical([]))
tm.assert_categorical_equal(s.unique(), pd.Categorical([]),
check_dtype=False)
s = pd.Series(pd.Categorical([np.nan]))
tm.assert_categorical_equal(s.unique(), pd.Categorical([np.nan]),
check_dtype=False)


def test_unique_data_ownership():
# it works! #1807
Series(Series(["a", "c", "b"]).unique()).sort_values()


def test_is_unique():
# GH11946
s = Series(np.random.randint(0, 10, size=1000))
assert not s.is_unique
s = Series(np.arange(1000))
assert s.is_unique


def test_is_unique_class_ne(capsys):
# GH 20661
class Foo(object):
def __init__(self, val):
self._value = val

def __ne__(self, other):
raise Exception("NEQ not supported")

li = [Foo(i) for i in range(5)]
s = pd.Series(li, index=[i for i in range(5)])
_, err = capsys.readouterr()
s.is_unique
_, err = capsys.readouterr()
assert len(err) == 0


@pytest.mark.parametrize(
'keep, expected',
[
('first', Series([False, False, False, False, True, True, False])),
('last', Series([False, True, True, False, False, False, False])),
(False, Series([False, True, True, False, True, True, False]))
])
def test_duplicated_nan_none(self, keep, expected):
s = Series([np.nan, 3, 3, None, np.nan], dtype=object)

result = s.duplicated(keep=keep)
tm.assert_series_equal(result, expected)
def test_drop_duplicates_non_bool(any_numpy_dtype, keep, expected):
tc = Series([1, 2, 3, 5, 3, 2, 4], dtype=np.dtype(any_numpy_dtype))

assert_series_equal(tc.duplicated(keep=keep), expected)
assert_series_equal(tc.drop_duplicates(keep=keep), tc[~expected])
sc = tc.copy()
sc.drop_duplicates(keep=keep, inplace=True)
assert_series_equal(sc, tc[~expected])


@pytest.mark.parametrize('keep, expected',
[('first', Series([False, False, True, True])),
('last', Series([True, True, False, False])),
(False, Series([True, True, True, True]))])
def test_drop_duplicates_bool(keep, expected):
tc = Series([True, False, True, False])

assert_series_equal(tc.duplicated(keep=keep), expected)
assert_series_equal(tc.drop_duplicates(keep=keep), tc[~expected])
sc = tc.copy()
sc.drop_duplicates(keep=keep, inplace=True)
assert_series_equal(sc, tc[~expected])


@pytest.mark.parametrize('keep, expected', [
('first', Series([False, False, True, False, True], name='name')),
('last', Series([True, True, False, False, False], name='name')),
(False, Series([True, True, True, False, True], name='name'))
])
def test_duplicated_keep(keep, expected):
s = Series(['a', 'b', 'b', 'c', 'a'], name='name')

result = s.duplicated(keep=keep)
tm.assert_series_equal(result, expected)


@pytest.mark.parametrize('keep, expected', [
('first', Series([False, False, True, False, True])),
('last', Series([True, True, False, False, False])),
(False, Series([True, True, True, False, True]))
])
def test_duplicated_nan_none(keep, expected):
s = Series([np.nan, 3, 3, None, np.nan], dtype=object)

result = s.duplicated(keep=keep)
tm.assert_series_equal(result, expected)
0