8000 TST/CLN: clean up indexes/multi/test_unique_and_duplicates by h-vetinari · Pull Request #21900 · pandas-dev/pandas · GitHub
[go: up one dir, main page]
Skip to content

TST/CLN: clean up indexes/multi/test_unique_and_duplicates #21900

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 5 commits into from
Jul 16, 2018
Merged

TST/CLN: clean up indexes/multi/test_unique_and_duplicates #21900

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
6774684
TST/CLN: clean up indexes/multi/test_unique_and_duplicates
h-vetinari Jul 13, 2018
0ef988f
Reorder tests for more legible diff; trigger rerun of failed build
h-vetinari Jul 14, 2018
2a3221c
Incorporate review (jreback)
h-vetinari Jul 14, 2018
d93a9a9
Conform naming scheme for duplicated tests to Series/DF
h-vetinari Jul 14, 2018
fce0d56
Further cleanup
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
Further cleanup
  • Loading branch information
@h-vetinari
h-vetinari committed Jul 14, 2018
commit fce0d564b2c2db625cbb97b2c10e7dd21aaae037
98 changes: 48 additions & 50 deletions pandas/tests/indexes/multi/test_duplicates.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,55 +2,54 @@

import warnings
from itertools import product
import pytest

import numpy as np
import pandas as pd
import pandas.util.testing as tm
import pytest

from pandas.compat import range, u
from pandas import MultiIndex, DatetimeIndex
from pandas._libs import hashtable
import pandas.util.testing as tm


@pytest.mark.parametrize('names', [None, ['first', 'second']])
def test_unique(names):
mi = pd.MultiIndex.from_arrays([[1, 2, 1, 2], [1, 1, 1, 2]],
names=names)
mi = MultiIndex.from_arrays([[1, 2, 1, 2], [1, 1, 1, 2]], names=names)

res = mi.unique()
exp = pd.MultiIndex.from_arrays([[1, 2, 2], [1, 1, 2]], names=mi.names)
exp = MultiIndex.from_arrays([[1, 2, 2], [1, 1, 2]], names=mi.names)
tm.assert_index_equal(res, exp)

mi = pd.MultiIndex.from_arrays([list('aaaa'), list('abab')],
names=names)
mi = MultiIndex.from_arrays([list('aaaa'), list('abab')],
names=names)
res = mi.unique()
exp = pd.MultiIndex.from_arrays([list('aa'), list('ab')],
names=mi.names)
exp = MultiIndex.from_arrays([list('aa'), list('ab')], names=mi.names)
tm.assert_index_equal(res, exp)

mi = pd.MultiIndex.from_arrays([list('aaaa'), list('aaaa')],
names=names)
mi = MultiIndex.from_arrays([list('aaaa'), list('aaaa')], names=names)
res = mi.unique()
exp = pd.MultiIndex.from_arrays([['a'], ['a']], names=mi.names)
exp = MultiIndex.from_arrays([['a'], ['a']], names=mi.names)
tm.assert_index_equal(res, exp)

# GH #20568 - empty MI
mi = pd.MultiIndex.from_arrays([[], []], names=names)
mi = MultiIndex.from_arrays([[], []], names=names)
res = mi.unique()
tm.assert_index_equal(mi, res)


def test_unique_datetimelike():
idx1 = pd.DatetimeIndex(['2015-01-01', '2015-01-01', '2015-01-01',
'2015-01-01', 'NaT', 'NaT'])
idx2 = pd.DatetimeIndex(['2015-01-01', '2015-01-01', '2015-01-02',
'2015-01-02', 'NaT', '2015-01-01'],
tz='Asia/Tokyo')
result = pd.MultiIndex.from_arrays([idx1, idx2]).unique()

eidx1 = pd.DatetimeIndex(['2015-01-01', '2015-01-01', 'NaT', 'NaT'])
eidx2 = pd.DatetimeIndex(['2015-01-01', '2015-01-02',
'NaT', '2015-01-01'],
tz='Asia/Tokyo')
exp = pd.MultiIndex.from_arrays([eidx1, eidx2])
idx1 = DatetimeIndex(['2015-01-01', '2015-01-01', '2015-01-01',
'2015-01-01', 'NaT', 'NaT'])
idx2 = DatetimeIndex(['2015-01-01', '2015-01-01', '2015-01-02',
'2015-01-02', 'NaT', '2015-01-01'],
tz='Asia/Tokyo')
result = MultiIndex.from_arrays([idx1, idx2]).unique()

eidx1 = DatetimeIndex(['2015-01-01', '2015-01-01', 'NaT', 'NaT'])
eidx2 = DatetimeIndex(['2015-01-01', '2015-01-02',
'NaT', '2015-01-01'],
tz='Asia/Tokyo')
exp = MultiIndex.from_arrays([eidx1, eidx2])
tm.assert_index_equal(result, exp)


Expand All @@ -62,14 +61,14 @@ def test_unique_level(idx, level):
tm.assert_index_equal(result, expected)

# With already unique level
mi = pd.MultiIndex.from_arrays([[1, 3, 2, 4], [1, 3, 2, 5]],
names=['first', 'second'])
mi = MultiIndex.from_arrays([[1, 3, 2, 4], [1, 3, 2, 5]],
names=['first', 'second'])
result = mi.unique(level=level)
expected = mi.get_level_values(level)
tm.assert_index_equal(result, expected)

# With empty MI
mi = pd.MultiIndex.from_arrays([[], []], names=['first', 'second'])
mi = MultiIndex.from_arrays([[], []], names=['first', 'second'])
result = mi.unique(level=level)
expected = mi.get_level_values(level)

Expand All @@ -88,11 +87,11 @@ def test_duplicate_multiindex_labels():
# GH 17464
# Make sure that a MultiIndex with duplicate levels throws a ValueError
with pytest.raises(ValueError):
mi = pd.MultiIndex([['A'] * 10, range(10)], [[0] * 10, range(10)])
mi = MultiIndex([['A'] * 10, range(10)], [[0] * 10, range(10)])

# And that using set_levels with duplicate levels fails
mi = pd.MultiIndex.from_arrays([['A', 'A', 'B', 'B', 'B'],
[1, 2, 1, 2, 3]])
mi = MultiIndex.from_arrays([['A', 'A', 'B', 'B', 'B'],
[1, 2, 1, 2, 3]])
with pytest.raises(ValueError):
mi.set_levels([['A', 'B', 'A', 'A', 'B'], [2, 1, 3, -2, 5]],
inplace=True)
Expand All @@ -102,11 +101,11 @@ def test_duplicate_multiindex_labels():
[1, 'a', 1]])
def test_duplicate_level_names(names):
# GH18872, GH19029
mi = pd.MultiIndex.from_product([[0, 1]] * 3, names=names)
mi = MultiIndex.from_product([[0, 1]] * 3, names=names)
assert mi.names == names

# With .rename()
mi = pd.MultiIndex.from_product([[0, 1]] * 3)
mi = MultiIndex.from_product([[0, 1]] * 3)
mi = mi.rename(names)
assert mi.names == names

Expand All @@ -118,7 +117,7 @@ def test_duplicate_level_names(names):

def test_duplicate_meta_data():
# GH 10115
mi = pd.MultiIndex(
mi = MultiIndex(
levels=[[0, 1], [0, 1, 2]],
labels=[[0, 0, 0, 0, 1, 1, 1],
[0, 1, 2, 0, 0, 1, 2]])
Expand All @@ -138,9 +137,9 @@ def test_has_duplicates(idx, idx_dup):
assert not idx_dup.is_unique
assert idx_dup.has_duplicates

mi = pd.MultiIndex(levels=[[0, 1], [0, 1, 2]],
labels=[[0, 0, 0, 0, 1, 1, 1],
[0, 1, 2, 0, 0, 1, 2]])
mi = MultiIndex(levels=[[0, 1], [0, 1, 2]],
labels=[[0, 0, 0, 0, 1, 1, 1],
[0, 1, 2, 0, 0, 1, 2]])
assert not mi.is_unique
assert mi.has_duplicates

Expand All @@ -166,7 +165,7 @@ def test_has_duplicates_from_tuples():
(u('x'), u('out'), u('z'), 33, u('y'), u('in'), u('z'), 123),
(u('x'), u('out'), u('z'), 12, u('y'), u('in'), u('z'), 144)]

mi = pd.MultiIndex.from_tuples(t)
mi = MultiIndex.from_tuples(t)
assert not mi.has_duplicates


Expand All @@ -189,18 +188,18 @@ def check(nlevels, with_nulls):
levels = [level] * nlevels + [[0, 1]]

# no dups
mi = pd.MultiIndex(levels=levels, labels=labels)
mi = MultiIndex(levels=levels, labels=labels)
assert not mi.has_duplicates

# with a dup
if with_nulls:
def f(a):
return np.insert(a, 1000, a[0])
labels = list(map(f, labels))
mi = pd.MultiIndex(levels=levels, labels=labels)
mi = MultiIndex(levels=levels, labels=labels)
else:
values = mi.values.tolist()
mi = pd.MultiIndex.from_tuples(values + [values[0]])
mi = MultiIndex.from_tuples(values + [values[0]])

assert mi.has_duplicates

Expand Down Expand Up @@ -229,23 +228,22 @@ def test_duplicated_large(keep):
n, k = 200, 5000
levels = [np.arange(n), tm.makeStringIndex(n), 1000 + np.arange(n)]
labels = [np.random.choice(n, k * n) for lev in levels]
mi = pd.MultiIndex(levels=levels, labels=labels)
mi = MultiIndex(levels=levels, labels=labels)

result = mi.duplicated(keep=keep)
expected = pd._libs.hashtable.duplicated_object(mi.values, keep=keep)
expected = hashtable.duplicated_object(mi.values, keep=keep)
tm.assert_numpy_array_equal(result, expected)


def test_get_duplicates():
# GH5873
for a in [101, 102]:
mi = pd.MultiIndex.from_arrays([[101, a], [3.5, np.nan]])
mi = MultiIndex.from_arrays([[101, a], [3.5, np.nan]])
assert not mi.has_duplicates

with warnings.catch_warnings(record=True):
# Deprecated - see GH20239
assert mi.get_duplicates().equals(pd.MultiIndex.from_arrays(
[[], []]))
assert mi.get_duplicates().equals(MultiIndex.from_arrays([[], []]))

tm.assert_numpy_array_equal(mi.duplicated(),
np.zeros(2, dtype='bool'))
Expand All @@ -254,14 +252,14 @@ def test_get_duplicates():
for m in range(1, 5): # 2nd level shape
# all possible unique combinations, including nan
lab = product(range(-1, n), range(-1, m))
mi = pd.MultiIndex(levels=[list('abcde')[:n], list('WXYZ')[:m]],
labels=np.random.permutation(list(lab)).T)
mi = MultiIndex(levels=[list('abcde')[:n], list('WXYZ')[:m]],
labels=np.random.permutation(list(lab)).T)
assert len(mi) == (n + 1) * (m + 1)
assert not mi.has_duplicates

with warnings.catch_warnings(record=True):
# Deprecated - see GH20239
assert mi.get_duplicates().equals(pd.MultiIndex.from_arrays(
assert mi.get_duplicates().equals(MultiIndex.from_arrays(
[[], []]))

tm.assert_numpy_array_equal(mi.duplicated(),
Expand Down
0