def test_sort():
tm.assert_frame_equal(compute(t.sort('amount'), df), pdsort(df, 'amount'))
tm.assert_frame_equal(compute(t.sort('amount', ascending=True), df),
pdsort(df, 'amount', ascending=True))
tm.assert_frame_equal(compute(t.sort(['amount', 'id']), df),
pdsort(df, ['amount', 'id']))
def test_sort():
tm.assert_frame_equal(compute(t.sort('amount'), df),
pdsort(df, 'amount'))
tm.assert_frame_equal(compute(t.sort('amount', ascending=True), df),
pdsort(df, 'amount', ascending=True))
tm.assert_frame_equal(compute(t.sort(['amount', 'id']), df),
pdsort(df, ['amount', 'id']))
def test_outer_join():
left = [(1, 'Alice', 100),
(2, 'Bob', 200),
(4, 'Dennis', 400)]
left = DataFrame(left, columns=['id', 'name', 'amount'])
right = [('NYC', 1),
('Boston', 1),
('LA', 3),
('Moscow', 4)]
right = DataFrame(right, columns=['city', 'id'])
lsym = symbol('lsym', 'var * {id: int, name: string, amount: real}')
rsym = symbol('rsym', 'var * {city: string, id: int}')
convert = lambda df: set(df.to_records(index=False).tolist())
assert (convert(compute(join(lsym, rsym), {lsym: left, rsym: right})) ==
set([(1, 'Alice', 100, 'NYC'),
(1, 'Alice', 100, 'Boston'),
(4, 'Dennis', 400, 'Moscow')]))
assert (convert(compute(join(lsym, rsym, how='left'),
{lsym: left, rsym: right})) ==
set([(1, 'Alice', 100, 'NYC'),
(1, 'Alice', 100, 'Boston'),
(2, 'Bob', 200, np.nan),
(4, 'Dennis', 400, 'Moscow')]))
df = compute(join(lsym, rsym, how='right'), {lsym: left, rsym: right})
expected = DataFrame([(1., 'Alice', 100., 'NYC'),
(1., 'Alice', 100., 'Boston'),
(3., np.nan, np.nan, 'lsymA'),
(4., 'Dennis', 400., 'Moscow')],
columns=['id', 'name', 'amount', 'city'])
result = pdsort(df, 'id').to_records(index=False)
expected = pdsort(expected, 'id').to_records(index=False)
np.array_equal(result, expected)
df = compute(join(lsym, rsym, how='outer'), {lsym: left, rsym: right})
expected = DataFrame([(1., 'Alice', 100., 'NYC'),
(1., 'Alice', 100., 'Boston'),
(2., 'Bob', 200., np.nan),
(3., np.nan, np.nan, 'LA'),
(4., 'Dennis', 400., 'Moscow')],
columns=['id', 'name', 'amount', 'city'])
result = pdsort(df, 'id').to_records(index=False)
expected = pdsort(expected, 'id').to_records(index=False)
np.array_equal(result, expected)