Skip to content
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

TST: Move some Series ctor tests to SharedWithSparse #17050

Merged
merged 6 commits into from
Jul 22, 2017
Merged
Show file tree
Hide file tree
Changes from 4 commits
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
2 changes: 1 addition & 1 deletion doc/source/whatsnew/v0.21.0.txt
Original file line number Diff line number Diff line change
Expand Up @@ -282,7 +282,7 @@ Groupby/Resample/Rolling

Sparse
^^^^^^
- Bug in ``SparseSeries`` raises ``AttributeError`` when a dictionary is passed in as data (:issue:`16777`)
- Bug in ``SparseSeries`` raises ``AttributeError`` when a dictionary is passed in as data (:issue:`16905`)
Copy link
Contributor

Choose a reason for hiding this comment

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

oh typo from before?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Yea, #16960



Reshaping
Expand Down
78 changes: 77 additions & 1 deletion pandas/tests/series/test_api.py
Original file line number Diff line number Diff line change
@@ -1,12 +1,13 @@
# coding=utf-8
# pylint: disable-msg=E1101,W0612
from collections import OrderedDict

import pytest

import numpy as np
import pandas as pd

from pandas import Index, Series, DataFrame, date_range
from pandas import Index, Series, SparseSeries, DataFrame, date_range
from pandas.core.indexes.datetimes import Timestamp

from pandas.compat import range
Expand All @@ -21,6 +22,10 @@

class SharedWithSparse(object):

def _assert_series_equal(self, left, right):
Copy link
Contributor

Choose a reason for hiding this comment

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

why don't we instead define this in the Mixin classes? (and add a NotImplemented one here)?

"""Dispatch to series class dependent assertion"""
raise NotImplementedError

def test_scalarop_preserve_name(self):
result = self.ts * 2
assert result.name == self.ts.name
Expand Down Expand Up @@ -117,9 +122,80 @@ def test_to_sparse_pass_name(self):
result = self.ts.to_sparse()
assert result.name == self.ts.name

def test_constructor_dict(self):
d = {'a': 0., 'b': 1., 'c': 2.}
result = self.series_klass(d)
expected = self.series_klass(d, index=sorted(d.keys()))
self._assert_series_equal(result, expected)

result = self.series_klass(d, index=['b', 'c', 'd', 'a'])
expected = self.series_klass([1, 2, np.nan, 0],
index=['b', 'c', 'd', 'a'])
self._assert_series_equal(result, expected)

def test_constructor_subclass_dict(self):
data = tm.TestSubDict((x, 10.0 * x) for x in range(10))
series = self.series_klass(data)
expected = self.series_klass(dict(compat.iteritems(data)))
self._assert_series_equal(series, expected)

def test_constructor_ordereddict(self):
# GH3283
data = OrderedDict(
('col%s' % i, np.random.random()) for i in range(12))

series = self.series_klass(data)
expected = self.series_klass(list(data.values()), list(data.keys()))
self._assert_series_equal(series, expected)

# Test with subclass
class A(OrderedDict):
pass

series = self.series_klass(A(data))
self._assert_series_equal(series, expected)

def test_constructor_dict_multiindex(self):
d = {('a', 'a'): 0., ('b', 'a'): 1., ('b', 'c'): 2.}
_d = sorted(d.items())
result = self.series_klass(d)
expected = self.series_klass(
[x[1] for x in _d],
index=pd.MultiIndex.from_tuples([x[0] for x in _d]))
self._assert_series_equal(result, expected)

d['z'] = 111.
_d.insert(0, ('z', d['z']))
result = self.series_klass(d)
expected = self.series_klass([x[1] for x in _d],
index=pd.Index([x[0] for x in _d],
tupleize_cols=False))
result = result.reindex(index=expected.index)
self._assert_series_equal(result, expected)

def test_constructor_dict_timedelta_index(self):
# GH #12169 : Resample category data with timedelta index
# construct Series from dict as data and TimedeltaIndex as index
# will result NaN in result Series data
expected = self.series_klass(
data=['A', 'B', 'C'],
index=pd.to_timedelta([0, 10, 20], unit='s')
)

result = self.series_klass(
data={pd.to_timedelta(0, unit='s'): 'A',
pd.to_timedelta(10, unit='s'): 'B',
pd.to_timedelta(20, unit='s'): 'C'},
index=pd.to_timedelta([0, 10, 20], unit='s')
)
self._assert_series_equal(result, expected)


class TestSeriesMisc(TestData, SharedWithSparse):

series_klass = Series
_assert_series_equal = staticmethod(tm.assert_series_equal)

def test_tab_completion(self):
# GH 9910
s = Series(list('abcd'))
Expand Down
65 changes: 1 addition & 64 deletions pandas/tests/series/test_constructors.py
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,7 @@
from pandas._libs import lib
from pandas._libs.tslib import iNaT

from pandas.compat import lrange, range, zip, OrderedDict, long
from pandas import compat
from pandas.compat import lrange, range, zip, long
from pandas.util.testing import assert_series_equal
import pandas.util.testing as tm

Expand Down Expand Up @@ -605,48 +604,6 @@ def test_constructor_dict(self):
expected.iloc[1] = 1
assert_series_equal(result, expected)

def test_constructor_dict_multiindex(self):
check = lambda result, expected: tm.assert_series_equal(
result, expected, check_dtype=True, check_series_type=True)
d = {('a', 'a'): 0., ('b', 'a'): 1., ('b', 'c'): 2.}
_d = sorted(d.items())
ser = Series(d)
expected = Series([x[1] for x in _d],
index=MultiIndex.from_tuples([x[0] for x in _d]))
check(ser, expected)

d['z'] = 111.
_d.insert(0, ('z', d['z']))
ser = Series(d)
expected = Series([x[1] for x in _d], index=Index(
[x[0] for x in _d], tupleize_cols=False))
ser = ser.reindex(index=expected.index)
check(ser, expected)

def test_constructor_dict_timedelta_index(self):
# GH #12169 : Resample category data with timedelta index
# construct Series from dict as data and TimedeltaIndex as index
# will result NaN in result Series data
expected = Series(
data=['A', 'B', 'C'],
index=pd.to_timedelta([0, 10, 20], unit='s')
)

result = Series(
data={pd.to_timedelta(0, unit='s'): 'A',
pd.to_timedelta(10, unit='s'): 'B',
pd.to_timedelta(20, unit='s'): 'C'},
index=pd.to_timedelta([0, 10, 20], unit='s')
)
# this should work
assert_series_equal(result, expected)

def test_constructor_subclass_dict(self):
data = tm.TestSubDict((x, 10.0 * x) for x in range(10))
series = Series(data)
refseries = Series(dict(compat.iteritems(data)))
assert_series_equal(refseries, series)

def test_constructor_dict_datetime64_index(self):
# GH 9456

Expand All @@ -670,26 +627,6 @@ def create_data(constructor):
assert_series_equal(result_datetime, expected)
assert_series_equal(result_Timestamp, expected)

def test_orderedDict_ctor(self):
# GH3283
import pandas
import random
data = OrderedDict([('col%s' % i, random.random()) for i in range(12)])
s = pandas.Series(data)
assert all(s.values == list(data.values()))

def test_orderedDict_subclass_ctor(self):
# GH3283
import pandas
import random

class A(OrderedDict):
pass

data = A([('col%s' % i, random.random()) for i in range(12)])
s = pandas.Series(data)
assert all(s.values == list(data.values()))

def test_constructor_list_of_tuples(self):
data = [(1, 1), (2, 2), (2, 3)]
s = Series(data)
Expand Down
6 changes: 4 additions & 2 deletions pandas/tests/sparse/test_frame.py
Original file line number Diff line number Diff line change
Expand Up @@ -1002,12 +1002,14 @@ def _check(frame, orig):

shifted = frame.shift(2, freq='B')
exp = orig.shift(2, freq='B')
exp = exp.to_sparse(frame.default_fill_value)
exp = exp.to_sparse(frame.default_fill_value,
kind=frame.default_kind)
tm.assert_frame_equal(shifted, exp)

shifted = frame.shift(2, freq=BDay())
exp = orig.shift(2, freq=BDay())
exp = exp.to_sparse(frame.default_fill_value)
exp = exp.to_sparse(frame.default_fill_value,
kind=frame.default_kind)
tm.assert_frame_equal(shifted, exp)

self._check_all(_check)
Expand Down
20 changes: 20 additions & 0 deletions pandas/tests/sparse/test_series.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
# pylint: disable-msg=E1101,W0612

import operator
from datetime import datetime

import pytest

from numpy import nan
Expand Down Expand Up @@ -58,6 +60,9 @@ def _test_data2_zero():

class TestSparseSeries(SharedWithSparse):

series_klass = SparseSeries
_assert_series_equal = staticmethod(tm.assert_sp_series_equal)
Copy link
Contributor Author

Choose a reason for hiding this comment

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

This doesn't look as good, but avoids *args, **kwargs passing and retains docstring.

Copy link
Contributor

Choose a reason for hiding this comment

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

hmm, I like that actually.

The only thing is we are using self._assert_series_equal, which is a tiny bit annoying, when in the rest of the codebase we are using tm.assert_series_equal (or tm.assert_sp_series_equal.

any ideas on a better / more consistent way would be good. (maybe add a comment to this effect in the sub-classes about this)

Copy link
Contributor Author

@kernc kernc Jul 21, 2017

Choose a reason for hiding this comment

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

def setup_method():
    pd.util.testing.assert_series_equal = whatever

J/k. I have nothing better.


def setup_method(self, method):
arr, index = _test_data1()

Expand Down Expand Up @@ -1379,3 +1384,18 @@ def test_numpy_func_call(self):
for func in funcs:
for series in ('bseries', 'zbseries'):
getattr(np, func)(getattr(self, series))


@pytest.mark.parametrize(
'datetime_type', (np.datetime64,
pd.Timestamp,
lambda x: datetime.strptime(x, '%Y-%m-%d')))
def test_constructor_dict_datetime64_index(datetime_type):
# GH 9456
dates = ['1984-02-19', '1988-11-06', '1989-12-03', '1990-03-15']
values = [42544017.198965244, 1234565, 40512335.181958228, -1]

result = SparseSeries(dict(zip(map(datetime_type, dates), values)))
expected = SparseSeries(values, map(pd.Timestamp, dates))

tm.assert_sp_series_equal(result, expected)