Skip to content

BUG: unstack fails in PeriodIndex #7041

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 1 commit into from
May 10, 2014
Merged

BUG: unstack fails in PeriodIndex #7041

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
1 change: 1 addition & 0 deletions doc/source/release.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -487,6 +487,7 @@ Bug Fixes
views; mark ``is_copy`` on ``xs` only if its an actual copy (and not a view) (:issue:`7084`)
- Bug in DatetimeIndex creation from string ndarray with ``dayfirst=True`` (:issue:`5917`)
- Bug in ``MultiIndex.from_arrays`` created from ``DatetimeIndex`` doesn't preserve ``freq`` and ``tz`` (:issue:`7090`)
- Bug in ``unstack`` raises ``ValueError`` when ``MultiIndex`` contains ``PeriodIndex`` (:issue:`4342`)

pandas 0.13.1
-------------
Expand Down
8 changes: 6 additions & 2 deletions pandas/core/reshape.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
import pandas.algos as algos

from pandas.core.index import Index, MultiIndex
from pandas.tseries.period import PeriodIndex


class _Unstacker(object):
Expand Down Expand Up @@ -81,8 +82,11 @@ def __init__(self, values, index, level=-1, value_columns=None):
labels = index.labels

def _make_index(lev, lab):
i = lev.__class__(_make_index_array_level(lev.values, lab))
i.name = lev.name
if isinstance(lev, PeriodIndex):
Copy link
Contributor

Choose a reason for hiding this comment

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

what does this fail with? (before the change)

Copy link
Member Author

Choose a reason for hiding this comment

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

Resulted in ValueError because PeriodIndex cannot be created without freq.

i = lev.copy()
else:
i = lev.__class__(_make_index_array_level(lev.values, lab))
i.name = lev.name
return i

self.new_index_levels = [_make_index(lev, lab)
Expand Down
6 changes: 4 additions & 2 deletions pandas/tests/test_categorical.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,7 @@
from pandas.tseries.period import PeriodIndex
from pandas.util.testing import assert_almost_equal
import pandas.core.common as com
from pandas.tseries.period import PeriodIndex

import pandas.util.testing as tm

Expand Down Expand Up @@ -183,7 +184,7 @@ def test_empty_print(self):

def test_periodindex(self):
idx1 = PeriodIndex(['2014-01', '2014-01', '2014-02', '2014-02',
'2014-03', '2014-03'], freq='M')
'2014-03', '2014-03'], freq='M')
cat1 = Categorical.from_array(idx1)

exp_arr = np.array([0, 0, 1, 1, 2, 2])
Expand All @@ -192,8 +193,9 @@ def test_periodindex(self):
self.assert_numpy_array_equal(cat1.labels, exp_arr)
self.assert_(cat1.levels.equals(exp_idx))


idx2 = PeriodIndex(['2014-03', '2014-03', '2014-02', '2014-01',
'2014-03', '2014-01'], freq='M')
'2014-03', '2014-01'], freq='M')
cat2 = Categorical.from_array(idx2)

exp_arr = np.array([2, 2, 1, 0, 2, 0])
Expand Down
80 changes: 80 additions & 0 deletions pandas/tests/test_multilevel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -964,6 +964,86 @@ def test_stack_unstack_multiple(self):
expected = self.ymd.unstack(2).unstack(1).dropna(axis=1, how='all')
assert_frame_equal(unstacked, expected.ix[:, unstacked.columns])

def test_unstack_period_series(self):
# GH 4342
idx1 = pd.PeriodIndex(['2013-01', '2013-01', '2013-02', '2013-02',
'2013-03', '2013-03'], freq='M', name='period')
idx2 = Index(['A', 'B'] * 3, name='str')
value = [1, 2, 3, 4, 5, 6]

idx = MultiIndex.from_arrays([idx1, idx2])
s = Series(value, index=idx)

result1 = s.unstack()
result2 = s.unstack(level=1)
result3 = s.unstack(level=0)

e_idx = pd.PeriodIndex(['2013-01', '2013-02', '2013-03'], freq='M', name='period')
expected = DataFrame({'A': [1, 3, 5], 'B': [2, 4, 6]}, index=e_idx,
columns=['A', 'B'])
expected.columns.name = 'str'

assert_frame_equal(result1, expected)
assert_frame_equal(result2, expected)
assert_frame_equal(result3, expected.T)

idx1 = pd.PeriodIndex(['2013-01', '2013-01', '2013-02', '2013-02',
'2013-03', '2013-03'], freq='M', name='period1')

idx2 = pd.PeriodIndex(['2013-12', '2013-11', '2013-10', '2013-09',
'2013-08', '2013-07'], freq='M', name='period2')
idx = pd.MultiIndex.from_arrays([idx1, idx2])
s = Series(value, index=idx)

result1 = s.unstack()
result2 = s.unstack(level=1)
result3 = s.unstack(level=0)

e_idx = pd.PeriodIndex(['2013-01', '2013-02', '2013-03'], freq='M', name='period1')
e_cols = pd.PeriodIndex(['2013-07', '2013-08', '2013-09', '2013-10',
'2013-11', '2013-12'], freq='M', name='period2')
expected = DataFrame([[np.nan, np.nan, np.nan, np.nan, 2, 1],
[np.nan, np.nan, 4, 3, np.nan, np.nan],
[6, 5, np.nan, np.nan, np.nan, np.nan]],
index=e_idx, columns=e_cols)

assert_frame_equal(result1, expected)
assert_frame_equal(result2, expected)
assert_frame_equal(result3, expected.T)

def test_unstack_period_frame(self):
# GH 4342
idx1 = pd.PeriodIndex(['2014-01', '2014-02', '2014-02', '2014-02', '2014-01', '2014-01'],
freq='M', name='period1')
idx2 = pd.PeriodIndex(['2013-12', '2013-12', '2014-02', '2013-10', '2013-10', '2014-02'],
freq='M', name='period2')
value = {'A': [1, 2, 3, 4, 5, 6], 'B': [6, 5, 4, 3, 2, 1]}
idx = pd.MultiIndex.from_arrays([idx1, idx2])
df = pd.DataFrame(value, index=idx)

result1 = df.unstack()
result2 = df.unstack(level=1)
result3 = df.unstack(level=0)

e_1 = pd.PeriodIndex(['2014-01', '2014-02'], freq='M', name='period1')
e_2 = pd.PeriodIndex(['2013-10', '2013-12', '2014-02', '2013-10',
'2013-12', '2014-02'], freq='M', name='period2')
e_cols = pd.MultiIndex.from_arrays(['A A A B B B'.split(), e_2])
expected = DataFrame([[5, 1, 6, 2, 6, 1], [4, 2, 3, 3, 5, 4]],
index=e_1, columns=e_cols)

assert_frame_equal(result1, expected)
assert_frame_equal(result2, expected)

e_1 = pd.PeriodIndex(['2014-01', '2014-02', '2014-01',
'2014-02'], freq='M', name='period1')
e_2 = pd.PeriodIndex(['2013-10', '2013-12', '2014-02'], freq='M', name='period2')
e_cols = pd.MultiIndex.from_arrays(['A A B B'.split(), e_1])
expected = DataFrame([[5, 4, 2, 3], [1, 2, 6, 5], [6, 3, 1, 4]],
index=e_2, columns=e_cols)

assert_frame_equal(result3, expected)

def test_stack_multiple_bug(self):
""" bug when some uniques are not present in the data #3170"""
id_col = ([1] * 3) + ([2] * 3)
Expand Down
2 changes: 1 addition & 1 deletion pandas/tseries/tests/test_period.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2177,7 +2177,7 @@ def test_slice_keep_name(self):

def test_factorize(self):
idx1 = PeriodIndex(['2014-01', '2014-01', '2014-02', '2014-02',
'2014-03', '2014-03'], freq='M')
'2014-03', '2014-03'], freq='M')

exp_arr = np.array([0, 0, 1, 1, 2, 2])
exp_idx = PeriodIndex(['2014-01', '2014-02', '2014-03'], freq='M')
Expand Down