def test_valid(self):
sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)
sp_valid = sp.valid()
assert_almost_equal(sp_valid, sp.to_dense().valid())
self.assert_(sp_valid.index.equals(sp.to_dense().valid().index))
self.assertEquals(len(sp_valid.sp_values), 2)
def test_abs(self):
s = SparseSeries([1, 2, -3], name='x')
expected = SparseSeries([1, 2, 3], name='x')
result = s.abs()
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = np.abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
s = SparseSeries([1, -2, 2, -3], fill_value=-2, name='x')
expected = SparseSeries([1, 2, 3], sparse_index=s.sp_index,
fill_value=2, name='x')
result = s.abs()
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = np.abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
def test_valid(self):
sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)
sp_valid = sp.valid()
assert_almost_equal(sp_valid, sp.to_dense().valid())
self.assert_(sp_valid.index.equals(sp.to_dense().valid().index))
self.assertEquals(len(sp_valid.sp_values), 2)
def setUp(self):
arr, index = _test_data1()
date_index = DateRange("1/1/2011", periods=len(index))
self.bseries = SparseSeries(arr, index=index, kind="block")
self.bseries.name = "bseries"
self.ts = self.bseries
self.btseries = SparseSeries(arr, index=date_index, kind="block")
self.iseries = SparseSeries(arr, index=index, kind="integer")
arr, index = _test_data2()
self.bseries2 = SparseSeries(arr, index=index, kind="block")
self.iseries2 = SparseSeries(arr, index=index, kind="integer")
arr, index = _test_data1_zero()
self.zbseries = SparseSeries(arr, index=index, kind="block", fill_value=0)
self.ziseries = SparseSeries(arr, index=index, kind="integer", fill_value=0)
arr, index = _test_data2_zero()
self.zbseries2 = SparseSeries(arr, index=index, kind="block", fill_value=0)
self.ziseries2 = SparseSeries(arr, index=index, kind="integer", fill_value=0)
def test_fill_value_when_combine_const(self):
# GH12723
s = SparseSeries([0, 1, np.nan, 3, 4, 5], index=np.arange(6))
exp = s.fillna(0).add(2)
res = s.add(2, fill_value=0)
self.assert_series_equal(res, exp)
def test_fill_value_when_combine_const(self):
# GH12723
s = SparseSeries([0, 1, np.nan, 3, 4, 5], index=np.arange(6))
exp = s.fillna(0).add(2)
res = s.add(2, fill_value=0)
self.assert_series_equal(res, exp)
def test_sparseseries_roundtrip(self):
# GH 13999
for kind in ['integer', 'block']:
for fill in [1, np.nan, 0]:
arr = SparseArray([np.nan, 1, np.nan, 2, 3],
kind=kind,
fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
arr = SparseArray([0, 0, 0, 1, 1, 2],
dtype=np.int64,
kind=kind,
fill_value=fill)
res = SparseArray(SparseSeries(arr), dtype=np.int64)
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
for fill in [True, False, np.nan]:
arr = SparseArray([True, False, True, True],
dtype=np.bool,
kind=kind,
fill_value=fill)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
res = SparseArray(SparseSeries(arr))
tm.assert_sp_array_equal(arr, res)
def setUp(self):
arr, index = _test_data1()
date_index = bdate_range('1/1/2011', periods=len(index))
self.bseries = SparseSeries(arr, index=index, kind='block',
name='bseries')
self.ts = self.bseries
self.btseries = SparseSeries(arr, index=date_index, kind='block')
self.iseries = SparseSeries(arr, index=index, kind='integer',
name='iseries')
arr, index = _test_data2()
self.bseries2 = SparseSeries(arr, index=index, kind='block')
self.iseries2 = SparseSeries(arr, index=index, kind='integer')
arr, index = _test_data1_zero()
self.zbseries = SparseSeries(arr, index=index, kind='block',
fill_value=0, name='zbseries')
self.ziseries = SparseSeries(arr, index=index, kind='integer',
fill_value=0)
arr, index = _test_data2_zero()
self.zbseries2 = SparseSeries(arr, index=index, kind='block',
fill_value=0)
self.ziseries2 = SparseSeries(arr, index=index, kind='integer',
fill_value=0)
def setUp(self):
arr, index = _test_data1()
self.bseries = SparseSeries(arr, index=index, kind='block',
name='bseries')
arr, index = _test_data1_zero()
self.zbseries = SparseSeries(arr, index=index, kind='block',
fill_value=0, name='zbseries')
def test_constructor(self):
# test setup guys
self.assertTrue(np.isnan(self.bseries.fill_value))
tm.assertIsInstance(self.bseries.sp_index, BlockIndex)
self.assertTrue(np.isnan(self.iseries.fill_value))
tm.assertIsInstance(self.iseries.sp_index, IntIndex)
self.assertEqual(self.zbseries.fill_value, 0)
assert_equal(self.zbseries.values.values,
self.bseries.to_dense().fillna(0).values)
# pass SparseSeries
def _check_const(sparse, name):
# use passed series name
result = SparseSeries(sparse)
tm.assert_sp_series_equal(result, sparse)
self.assertEqual(sparse.name, name)
self.assertEqual(result.name, name)
# use passed name
result = SparseSeries(sparse, name='x')
tm.assert_sp_series_equal(result, sparse, check_names=False)
self.assertEqual(result.name, 'x')
_check_const(self.bseries, 'bseries')
_check_const(self.iseries, 'iseries')
_check_const(self.zbseries, 'zbseries')
# Sparse time series works
date_index = bdate_range('1/1/2000', periods=len(self.bseries))
s5 = SparseSeries(self.bseries, index=date_index)
tm.assertIsInstance(s5, SparseSeries)
# pass Series
bseries2 = SparseSeries(self.bseries.to_dense())
assert_equal(self.bseries.sp_values, bseries2.sp_values)
# pass dict?
# don't copy the data by default
values = np.ones(self.bseries.npoints)
sp = SparseSeries(values, sparse_index=self.bseries.sp_index)
sp.sp_values[:5] = 97
self.assertEqual(values[0], 97)
self.assertEqual(len(sp), 20)
self.assertEqual(sp.shape, (20, ))
# but can make it copy!
sp = SparseSeries(values, sparse_index=self.bseries.sp_index,
copy=True)
sp.sp_values[:5] = 100
self.assertEqual(values[0], 97)
self.assertEqual(len(sp), 20)
self.assertEqual(sp.shape, (20, ))
def _check_const(sparse, name):
# use passed series name
result = SparseSeries(sparse)
tm.assert_sp_series_equal(result, sparse)
self.assertEqual(sparse.name, name)
self.assertEqual(result.name, name)
# use passed name
result = SparseSeries(sparse, name='x')
tm.assert_sp_series_equal(result, sparse, check_names=False)
self.assertEqual(result.name, 'x')
def test_constructor_scalar(self):
data = 5
sp = SparseSeries(data, np.arange(100))
sp = sp.reindex(np.arange(200))
self.assertTrue((sp.ix[:99] == data).all())
self.assertTrue(isnull(sp.ix[100:]).all())
data = np.nan
sp = SparseSeries(data, np.arange(100))
self.assertEqual(len(sp), 100)
self.assertEqual(sp.shape, (100, ))
def test_constructor_scalar(self):
data = 5
sp = SparseSeries(data, np.arange(100))
sp = sp.reindex(np.arange(200))
self.assertTrue((sp.ix[:99] == data).all())
self.assertTrue(isnull(sp.ix[100:]).all())
data = np.nan
sp = SparseSeries(data, np.arange(100))
self.assertEqual(len(sp), 100)
self.assertEqual(sp.shape, (100, ))
def _check(values, index1, index2, fill_value):
first_series = SparseSeries(values, sparse_index=index1,
fill_value=fill_value)
reindexed = first_series.sparse_reindex(index2)
self.assert_(reindexed.sp_index is index2)
int_indices1 = index1.to_int_index().indices
int_indices2 = index2.to_int_index().indices
expected = Series(values, index=int_indices1)
expected = expected.reindex(int_indices2).fillna(fill_value)
assert_almost_equal(expected.values, reindexed.sp_values)
def test_dropna(self):
sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)
sp_valid = sp.valid()
assert_almost_equal(sp_valid.values, sp.to_dense().valid().values)
self.assert_(sp_valid.index.equals(sp.to_dense().valid().index))
self.assertEquals(len(sp_valid.sp_values), 2)
result = self.bseries.dropna()
expected = self.bseries.to_dense().dropna()
self.assert_(not isinstance(result, SparseSeries))
tm.assert_series_equal(result, expected)
def _check(values, index1, index2, fill_value):
first_series = SparseSeries(values,
sparse_index=index1,
fill_value=fill_value)
reindexed = first_series.sparse_reindex(index2)
self.assert_(reindexed.sp_index is index2)
int_indices1 = index1.to_int_index().indices
int_indices2 = index2.to_int_index().indices
expected = Series(values, index=int_indices1)
expected = expected.reindex(int_indices2).fillna(fill_value)
assert_almost_equal(expected.values, reindexed.sp_values)
def setUp(self):
arr, index = _test_data1()
self.bseries = SparseSeries(arr,
index=index,
kind='block',
name='bseries')
arr, index = _test_data1_zero()
self.zbseries = SparseSeries(arr,
index=index,
kind='block',
fill_value=0,
name='zbseries')
def test_sparse_reindex(self):
length = 10
def _check(values, index1, index2, fill_value):
first_series = SparseSeries(values,
sparse_index=index1,
fill_value=fill_value)
reindexed = first_series.sparse_reindex(index2)
self.assertIs(reindexed.sp_index, index2)
int_indices1 = index1.to_int_index().indices
int_indices2 = index2.to_int_index().indices
expected = Series(values, index=int_indices1)
expected = expected.reindex(int_indices2).fillna(fill_value)
tm.assert_almost_equal(expected.values, reindexed.sp_values)
# make sure level argument asserts
# TODO: expected is not used anywhere...remove?
expected = expected.reindex(int_indices2).fillna(
fill_value) # noqa
def _check_with_fill_value(values, first, second, fill_value=nan):
i_index1 = IntIndex(length, first)
i_index2 = IntIndex(length, second)
b_index1 = i_index1.to_block_index()
b_index2 = i_index2.to_block_index()
_check(values, i_index1, i_index2, fill_value)
_check(values, b_index1, b_index2, fill_value)
def _check_all(values, first, second):
_check_with_fill_value(values, first, second, fill_value=nan)
_check_with_fill_value(values, first, second, fill_value=0)
index1 = [2, 4, 5, 6, 8, 9]
values1 = np.arange(6.)
_check_all(values1, index1, [2, 4, 5])
_check_all(values1, index1, [2, 3, 4, 5, 6, 7, 8, 9])
_check_all(values1, index1, [0, 1])
_check_all(values1, index1, [0, 1, 7, 8, 9])
_check_all(values1, index1, [])
first_series = SparseSeries(values1,
sparse_index=IntIndex(length, index1),
fill_value=nan)
with tm.assertRaisesRegexp(TypeError,
'new index must be a SparseIndex'):
reindexed = first_series.sparse_reindex(0) # noqa
def test_abs(self):
s = SparseSeries([1, 2, -3], name='x')
expected = SparseSeries([1, 2, 3], name='x')
result = s.abs()
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = np.abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
def test_numpy_take(self):
sp = SparseSeries([1.0, 2.0, 3.0])
indices = [1, 2]
tm.assert_series_equal(np.take(sp, indices, axis=0).to_dense(),
np.take(sp.to_dense(), indices, axis=0))
msg = "the 'out' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.take,
sp, indices, out=np.empty(sp.shape))
msg = "the 'mode' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.take,
sp, indices, mode='clip')
def test_abs(self):
s = SparseSeries([1, 2, -3], name='x')
expected = SparseSeries([1, 2, 3], name='x')
result = s.abs()
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = np.abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
def test_sparse_reindex(self):
length = 10
def _check(values, index1, index2, fill_value):
first_series = SparseSeries(values, sparse_index=index1,
fill_value=fill_value)
reindexed = first_series.sparse_reindex(index2)
self.assertIs(reindexed.sp_index, index2)
int_indices1 = index1.to_int_index().indices
int_indices2 = index2.to_int_index().indices
expected = Series(values, index=int_indices1)
expected = expected.reindex(int_indices2).fillna(fill_value)
tm.assert_almost_equal(expected.values, reindexed.sp_values)
# make sure level argument asserts
# TODO: expected is not used anywhere...remove?
expected = expected.reindex(int_indices2).fillna(fill_value) # noqa
def _check_with_fill_value(values, first, second, fill_value=nan):
i_index1 = IntIndex(length, first)
i_index2 = IntIndex(length, second)
b_index1 = i_index1.to_block_index()
b_index2 = i_index2.to_block_index()
_check(values, i_index1, i_index2, fill_value)
_check(values, b_index1, b_index2, fill_value)
def _check_all(values, first, second):
_check_with_fill_value(values, first, second, fill_value=nan)
_check_with_fill_value(values, first, second, fill_value=0)
index1 = [2, 4, 5, 6, 8, 9]
values1 = np.arange(6.)
_check_all(values1, index1, [2, 4, 5])
_check_all(values1, index1, [2, 3, 4, 5, 6, 7, 8, 9])
_check_all(values1, index1, [0, 1])
_check_all(values1, index1, [0, 1, 7, 8, 9])
_check_all(values1, index1, [])
first_series = SparseSeries(values1,
sparse_index=IntIndex(length, index1),
fill_value=nan)
with tm.assertRaisesRegexp(TypeError,
'new index must be a SparseIndex'):
reindexed = first_series.sparse_reindex(0) # noqa
def test_homogenize(self):
def _check_matches(indices, expected):
data = {}
for i, idx in enumerate(indices):
data[i] = SparseSeries(idx.to_int_index().indices,
sparse_index=idx)
homogenized = spf.homogenize(data)
for k, v in homogenized.iteritems():
assert (v.sp_index.equals(expected))
indices1 = [
BlockIndex(10, [2], [7]),
BlockIndex(10, [1, 6], [3, 4]),
BlockIndex(10, [0], [10])
]
expected1 = BlockIndex(10, [2, 6], [2, 3])
_check_matches(indices1, expected1)
indices2 = [BlockIndex(10, [2], [7]), BlockIndex(10, [2], [7])]
expected2 = indices2[0]
_check_matches(indices2, expected2)
# must have NaN fill value
data = {
'a': SparseSeries(np.arange(7),
sparse_index=expected2,
fill_value=0)
}
nose.tools.assert_raises(Exception, spf.homogenize, data)
def test_constructor_dtype(self):
arr = SparseSeries([np.nan, 1, 2, np.nan])
self.assertEqual(arr.dtype, np.float64)
self.assertTrue(np.isnan(arr.fill_value))
arr = SparseSeries([np.nan, 1, 2, np.nan], fill_value=0)
self.assertEqual(arr.dtype, np.float64)
self.assertEqual(arr.fill_value, 0)
arr = SparseSeries([0, 1, 2, 4], dtype=np.int64)
self.assertEqual(arr.dtype, np.int64)
self.assertTrue(np.isnan(arr.fill_value))
arr = SparseSeries([0, 1, 2, 4], fill_value=0, dtype=np.int64)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
def _check_frame_ops(self, frame):
def _compare_to_dense(a, b, da, db, op):
sparse_result = op(a, b)
dense_result = op(da, db)
fill = sparse_result.default_fill_value
dense_result = dense_result.to_sparse(fill_value=fill)
tm.assert_sp_frame_equal(sparse_result,
dense_result,
exact_indices=False)
if isinstance(a, DataFrame) and isinstance(db, DataFrame):
mixed_result = op(a, db)
tm.assertIsInstance(mixed_result, SparseDataFrame)
tm.assert_sp_frame_equal(mixed_result,
sparse_result,
exact_indices=False)
opnames = ['add', 'sub', 'mul', 'truediv', 'floordiv']
ops = [getattr(operator, name) for name in opnames]
fidx = frame.index
# time series operations
series = [
frame['A'], frame['B'], frame['C'], frame['D'],
frame['A'].reindex(fidx[:7]), frame['A'].reindex(fidx[::2]),
SparseSeries([], index=[])
]
for op in opnames:
_compare_to_dense(frame, frame[::2], frame.to_dense(),
frame[::2].to_dense(), getattr(operator, op))
# 2304, no auto-broadcasting
for i, s in enumerate(series):
f = lambda a, b: getattr(a, op)(b, axis='index')
_compare_to_dense(frame, s, frame.to_dense(), s.to_dense(), f)
# rops are not implemented
# _compare_to_dense(s, frame, s.to_dense(),
# frame.to_dense(), f)
# cross-sectional operations
series = [
frame.xs(fidx[0]),
frame.xs(fidx[3]),
frame.xs(fidx[5]),
frame.xs(fidx[7]),
frame.xs(fidx[5])[:2]
]
for op in ops:
for s in series:
_compare_to_dense(frame, s, frame.to_dense(), s, op)
_compare_to_dense(s, frame, s, frame.to_dense(), op)
# it works!
result = self.frame + self.frame.loc[:, ['A', 'B']] # noqa
def test_dropna(self):
sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)
sp_valid = sp.valid()
expected = sp.to_dense().valid()
expected = expected[expected != 0]
exp_arr = pd.SparseArray(expected.values, fill_value=0, kind='block')
tm.assert_sp_array_equal(sp_valid.values, exp_arr)
self.assert_index_equal(sp_valid.index, expected.index)
self.assertEqual(len(sp_valid.sp_values), 2)
result = self.bseries.dropna()
expected = self.bseries.to_dense().dropna()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
def test_dropna(self):
sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)
sp_valid = sp.valid()
expected = sp.to_dense().valid()
expected = expected[expected != 0]
tm.assert_almost_equal(sp_valid.values, expected.values)
self.assertTrue(sp_valid.index.equals(expected.index))
self.assertEqual(len(sp_valid.sp_values), 2)
result = self.bseries.dropna()
expected = self.bseries.to_dense().dropna()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
def test_dropna(self):
sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)
sp_valid = sp.valid()
expected = sp.to_dense().valid()
expected = expected[expected != 0]
tm.assert_almost_equal(sp_valid.values, expected.values)
self.assertTrue(sp_valid.index.equals(expected.index))
self.assertEqual(len(sp_valid.sp_values), 2)
result = self.bseries.dropna()
expected = self.bseries.to_dense().dropna()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
def test_dropna(self):
sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)
sp_valid = sp.valid()
expected = sp.to_dense().valid()
expected = expected[expected != 0]
exp_arr = pd.SparseArray(expected.values, fill_value=0, kind='block')
tm.assert_sp_array_equal(sp_valid.values, exp_arr)
self.assert_index_equal(sp_valid.index, expected.index)
self.assertEqual(len(sp_valid.sp_values), 2)
result = self.bseries.dropna()
expected = self.bseries.to_dense().dropna()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
def test_homogenize(self):
def _check_matches(indices, expected):
data = {}
for i, idx in enumerate(indices):
data[i] = SparseSeries(idx.to_int_index().indices,
sparse_index=idx)
homogenized = spf.homogenize(data)
for k, v in compat.iteritems(homogenized):
assert (v.sp_index.equals(expected))
indices1 = [
BlockIndex(10, [2], [7]),
BlockIndex(10, [1, 6], [3, 4]),
BlockIndex(10, [0], [10])
]
expected1 = BlockIndex(10, [2, 6], [2, 3])
_check_matches(indices1, expected1)
indices2 = [BlockIndex(10, [2], [7]), BlockIndex(10, [2], [7])]
expected2 = indices2[0]
_check_matches(indices2, expected2)
# must have NaN fill value
data = {
'a': SparseSeries(np.arange(7),
sparse_index=expected2,
fill_value=0)
}
with tm.assertRaisesRegexp(TypeError, "NaN fill value"):
spf.homogenize(data)
def _check(values, index1, index2, fill_value):
first_series = SparseSeries(values, sparse_index=index1,
fill_value=fill_value)
reindexed = first_series.sparse_reindex(index2)
self.assertIs(reindexed.sp_index, index2)
int_indices1 = index1.to_int_index().indices
int_indices2 = index2.to_int_index().indices
expected = Series(values, index=int_indices1)
expected = expected.reindex(int_indices2).fillna(fill_value)
tm.assert_almost_equal(expected.values, reindexed.sp_values)
# make sure level argument asserts
# TODO: expected is not used anywhere...remove?
expected = expected.reindex(int_indices2).fillna(fill_value) # noqa
def _check(values, index1, index2, fill_value):
first_series = SparseSeries(values, sparse_index=index1,
fill_value=fill_value)
reindexed = first_series.sparse_reindex(index2)
self.assertIs(reindexed.sp_index, index2)
int_indices1 = index1.to_int_index().indices
int_indices2 = index2.to_int_index().indices
expected = Series(values, index=int_indices1)
expected = expected.reindex(int_indices2).fillna(fill_value)
tm.assert_almost_equal(expected.values, reindexed.sp_values)
# make sure level argument asserts
# TODO: expected is not used anywhere...remove?
expected = expected.reindex(int_indices2).fillna(fill_value) # noqa
def test_constructor(self):
# test setup guys
self.assertTrue(np.isnan(self.bseries.fill_value))
tm.assertIsInstance(self.bseries.sp_index, BlockIndex)
self.assertTrue(np.isnan(self.iseries.fill_value))
tm.assertIsInstance(self.iseries.sp_index, IntIndex)
self.assertEqual(self.zbseries.fill_value, 0)
assert_equal(self.zbseries.values.values,
self.bseries.to_dense().fillna(0).values)
# pass SparseSeries
def _check_const(sparse, name):
# use passed series name
result = SparseSeries(sparse)
tm.assert_sp_series_equal(result, sparse)
self.assertEqual(sparse.name, name)
self.assertEqual(result.name, name)
# use passed name
result = SparseSeries(sparse, name='x')
tm.assert_sp_series_equal(result, sparse, check_names=False)
self.assertEqual(result.name, 'x')
_check_const(self.bseries, 'bseries')
_check_const(self.iseries, 'iseries')
_check_const(self.zbseries, 'zbseries')
# Sparse time series works
date_index = bdate_range('1/1/2000', periods=len(self.bseries))
s5 = SparseSeries(self.bseries, index=date_index)
tm.assertIsInstance(s5, SparseSeries)
# pass Series
bseries2 = SparseSeries(self.bseries.to_dense())
assert_equal(self.bseries.sp_values, bseries2.sp_values)
# pass dict?
# don't copy the data by default
values = np.ones(self.bseries.npoints)
sp = SparseSeries(values, sparse_index=self.bseries.sp_index)
sp.sp_values[:5] = 97
self.assertEqual(values[0], 97)
self.assertEqual(len(sp), 20)
self.assertEqual(sp.shape, (20, ))
# but can make it copy!
sp = SparseSeries(values,
sparse_index=self.bseries.sp_index,
copy=True)
sp.sp_values[:5] = 100
self.assertEqual(values[0], 97)
self.assertEqual(len(sp), 20)
self.assertEqual(sp.shape, (20, ))
def test_from_coo_long_repr(self):
# GH 13114
# test it doesn't raise error. Formatting is tested in test_format
tm._skip_if_no_scipy()
import scipy.sparse
sparse = SparseSeries.from_coo(scipy.sparse.rand(350, 18))
repr(sparse)
def test_from_coo_long_repr(self):
# GH 13114
# test it doesn't raise error. Formatting is tested in test_format
tm._skip_if_no_scipy()
import scipy.sparse
sparse = SparseSeries.from_coo(scipy.sparse.rand(350, 18))
repr(sparse)
def _check_matches(indices, expected):
data = {}
for i, idx in enumerate(indices):
data[i] = SparseSeries(idx.to_int_index().indices,
sparse_index=idx)
homogenized = spf.homogenize(data)
for k, v in compat.iteritems(homogenized):
assert (v.sp_index.equals(expected))
def test_shift(self):
series = SparseSeries([nan, 1.0, 2.0, 3.0, nan, nan], index=np.arange(6))
shifted = series.shift(0)
self.assert_(shifted is not series)
assert_sp_series_equal(shifted, series)
f = lambda s: s.shift(1)
_dense_series_compare(series, f)
f = lambda s: s.shift(-2)
_dense_series_compare(series, f)
series = SparseSeries([nan, 1.0, 2.0, 3.0, nan, nan], index=DateRange("1/1/2000", periods=6))
f = lambda s: s.shift(2, timeRule="WEEKDAY")
_dense_series_compare(series, f)
f = lambda s: s.shift(2, offset=datetools.bday)
_dense_series_compare(series, f)
def test_cumsum(self):
result = self.bseries.cumsum()
expected = SparseSeries(self.bseries.to_dense().cumsum())
tm.assert_sp_series_equal(result, expected)
# TODO: gh-12855 - return a SparseSeries here
result = self.zbseries.cumsum()
expected = self.zbseries.to_dense().cumsum()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
def _read_sparse_series(self, group, where=None):
index = self._read_index(group, 'index')
sp_values = _read_array(group, 'sp_values')
sp_index = self._read_index(group, 'sp_index')
name = getattr(group._v_attrs, 'name', None)
fill_value = getattr(group._v_attrs, 'fill_value', None)
kind = getattr(group._v_attrs, 'kind', 'block')
return SparseSeries(sp_values, index=index, sparse_index=sp_index,
kind=kind, fill_value=fill_value,
name=name)
def test_density(self):
df = SparseSeries([nan, nan, nan, 0, 1, 2, 3, 4, 5, 6])
self.assertEqual(df.density, 0.7)
df = SparseDataFrame({'A': [nan, nan, nan, 0, 1, 2, 3, 4, 5, 6],
'B': [0, 1, 2, nan, nan, nan, 3, 4, 5, 6],
'C': np.arange(10),
'D': [0, 1, 2, 3, 4, 5, nan, nan, nan, nan]})
self.assertEqual(df.density, 0.75)
def test_shift(self):
series = SparseSeries([nan, 1., 2., 3., nan, nan], index=np.arange(6))
shifted = series.shift(0)
self.assertIsNot(shifted, series)
tm.assert_sp_series_equal(shifted, series)
f = lambda s: s.shift(1)
_dense_series_compare(series, f)
f = lambda s: s.shift(-2)
_dense_series_compare(series, f)
series = SparseSeries([nan, 1., 2., 3., nan, nan],
index=bdate_range('1/1/2000', periods=6))
f = lambda s: s.shift(2, freq='B')
_dense_series_compare(series, f)
f = lambda s: s.shift(2, freq=datetools.bday)
_dense_series_compare(series, f)
def test_shift(self):
series = SparseSeries([nan, 1., 2., 3., nan, nan], index=np.arange(6))
shifted = series.shift(0)
self.assert_(shifted is not series)
assert_sp_series_equal(shifted, series)
f = lambda s: s.shift(1)
_dense_series_compare(series, f)
f = lambda s: s.shift(-2)
_dense_series_compare(series, f)
series = SparseSeries([nan, 1., 2., 3., nan, nan],
index=DateRange('1/1/2000', periods=6))
f = lambda s: s.shift(2, timeRule='WEEKDAY')
_dense_series_compare(series, f)
f = lambda s: s.shift(2, offset=datetools.bday)
_dense_series_compare(series, f)
def test_shift(self):
series = SparseSeries([nan, 1., 2., 3., nan, nan], index=np.arange(6))
shifted = series.shift(0)
self.assertIsNot(shifted, series)
tm.assert_sp_series_equal(shifted, series)
f = lambda s: s.shift(1)
_dense_series_compare(series, f)
f = lambda s: s.shift(-2)
_dense_series_compare(series, f)
series = SparseSeries([nan, 1., 2., 3., nan, nan],
index=bdate_range('1/1/2000', periods=6))
f = lambda s: s.shift(2, freq='B')
_dense_series_compare(series, f)
f = lambda s: s.shift(2, freq=datetools.bday)
_dense_series_compare(series, f)
def test_take(self):
def _compare_with_dense(sp):
dense = sp.to_dense()
def _compare(idx):
dense_result = dense.take(idx).values
sparse_result = sp.take(idx)
assert_almost_equal(dense_result, sparse_result)
_compare([1.0, 2.0, 3.0, 4.0, 5.0, 0.0])
_compare([7, 2, 9, 0, 4])
_compare([3, 6, 3, 4, 7])
self._check_all(_compare_with_dense)
self.assertRaises(Exception, self.bseries.take, [-1, 0])
self.assertRaises(Exception, self.bseries.take, [0, len(self.bseries) + 1])
# Corner case
sp = SparseSeries(np.ones(10.0) * nan)
assert_almost_equal(sp.take([0, 1, 2, 3, 4]), np.repeat(nan, 5))
def test_constructor(self):
# test setup guys
self.assert_(np.isnan(self.bseries.fill_value))
self.assert_(isinstance(self.bseries.sp_index, BlockIndex))
self.assert_(np.isnan(self.iseries.fill_value))
self.assert_(isinstance(self.iseries.sp_index, IntIndex))
self.assertEquals(self.zbseries.fill_value, 0)
assert_equal(self.zbseries.values, self.bseries.to_dense().fillna(0))
# pass SparseSeries
s2 = SparseSeries(self.bseries)
s3 = SparseSeries(self.iseries)
s4 = SparseSeries(self.zbseries)
assert_sp_series_equal(s2, self.bseries)
assert_sp_series_equal(s3, self.iseries)
assert_sp_series_equal(s4, self.zbseries)
# Sparse time series works
date_index = DateRange('1/1/2000', periods=len(self.bseries))
s5 = SparseSeries(self.bseries, index=date_index)
self.assert_(isinstance(s5, SparseTimeSeries))
# pass Series
bseries2 = SparseSeries(self.bseries.to_dense())
assert_equal(self.bseries.sp_values, bseries2.sp_values)
# pass dict?
# don't copy the data by default
values = np.ones(len(self.bseries.sp_values))
sp = SparseSeries(values, sparse_index=self.bseries.sp_index)
sp.sp_values[:5] = 97
self.assert_(values[0] == 97)
# but can make it copy!
sp = SparseSeries(values, sparse_index=self.bseries.sp_index,
copy=True)
sp.sp_values[:5] = 100
self.assert_(values[0] == 97)
def _check_frame_ops(self, frame):
fill = frame.default_fill_value
def _compare_to_dense(a, b, da, db, op):
sparse_result = op(a, b)
dense_result = op(da, db)
dense_result = dense_result.to_sparse(fill_value=fill)
assert_sp_frame_equal(sparse_result,
dense_result,
exact_indices=False)
if isinstance(a, DataFrame) and isinstance(db, DataFrame):
mixed_result = op(a, db)
self.assert_(isinstance(mixed_result, SparseDataFrame))
assert_sp_frame_equal(mixed_result,
sparse_result,
exact_indices=False)
opnames = ['add', 'sub', 'mul', 'truediv', 'floordiv']
ops = [getattr(operator, name) for name in opnames]
fidx = frame.index
# time series operations
series = [
frame['A'], frame['B'], frame['C'], frame['D'],
frame['A'].reindex(fidx[:7]), frame['A'].reindex(fidx[::2]),
SparseSeries([], index=[])
]
for op in ops:
_compare_to_dense(frame, frame[::2], frame.to_dense(),
frame[::2].to_dense(), op)
for s in series:
_compare_to_dense(frame, s, frame.to_dense(), s.to_dense(), op)
_compare_to_dense(s, frame, s.to_dense(), frame.to_dense(), op)
# cross-sectional operations
series = [
frame.xs(fidx[0]),
frame.xs(fidx[3]),
frame.xs(fidx[5]),
frame.xs(fidx[7]),
frame.xs(fidx[5])[:2]
]
for op in ops:
for s in series:
_compare_to_dense(frame, s, frame.to_dense(), s, op)
_compare_to_dense(s, frame, s, frame.to_dense(), op)
def test_reindex(self):
def _compare_with_series(sps, new_index):
spsre = sps.reindex(new_index)
series = sps.to_dense()
seriesre = series.reindex(new_index)
seriesre = seriesre.to_sparse(fill_value=sps.fill_value)
tm.assert_sp_series_equal(spsre, seriesre)
tm.assert_series_equal(spsre.to_dense(), seriesre.to_dense())
_compare_with_series(self.bseries, self.bseries.index[::2])
_compare_with_series(self.bseries, list(self.bseries.index[::2]))
_compare_with_series(self.bseries, self.bseries.index[:10])
_compare_with_series(self.bseries, self.bseries.index[5:])
_compare_with_series(self.zbseries, self.zbseries.index[::2])
_compare_with_series(self.zbseries, self.zbseries.index[:10])
_compare_with_series(self.zbseries, self.zbseries.index[5:])
# special cases
same_index = self.bseries.reindex(self.bseries.index)
tm.assert_sp_series_equal(self.bseries, same_index)
self.assertIsNot(same_index, self.bseries)
# corner cases
sp = SparseSeries([], index=[])
# TODO: sp_zero is not used anywhere...remove?
sp_zero = SparseSeries([], index=[], fill_value=0) # noqa
_compare_with_series(sp, np.arange(10))
# with copy=False
reindexed = self.bseries.reindex(self.bseries.index, copy=True)
reindexed.sp_values[:] = 1.
self.assertTrue((self.bseries.sp_values != 1.).all())
reindexed = self.bseries.reindex(self.bseries.index, copy=False)
reindexed.sp_values[:] = 1.
tm.assert_numpy_array_equal(self.bseries.sp_values, np.repeat(1., 10))
def test_take(self):
def _compare_with_dense(sp):
dense = sp.to_dense()
def _compare(idx):
dense_result = dense.take(idx).values
sparse_result = sp.take(idx)
assert_almost_equal(dense_result, sparse_result)
_compare([1., 2., 3., 4., 5., 0.])
_compare([7, 2, 9, 0, 4])
_compare([3, 6, 3, 4, 7])
self._check_all(_compare_with_dense)
self.assertRaises(Exception, self.bseries.take, [-1, 0])
self.assertRaises(Exception, self.bseries.take,
[0, len(self.bseries) + 1])
# Corner case
sp = SparseSeries(np.ones(10.) * nan)
assert_almost_equal(sp.take([0, 1, 2, 3, 4]), np.repeat(nan, 5))
def test_reindex(self):
def _compare_with_series(sps, new_index):
spsre = sps.reindex(new_index)
series = sps.to_dense()
seriesre = series.reindex(new_index)
seriesre = seriesre.to_sparse(fill_value=sps.fill_value)
assert_sp_series_equal(spsre, seriesre)
assert_series_equal(spsre.to_dense(), seriesre.to_dense())
_compare_with_series(self.bseries, self.bseries.index[::2])
_compare_with_series(self.bseries, list(self.bseries.index[::2]))
_compare_with_series(self.bseries, self.bseries.index[:10])
_compare_with_series(self.bseries, self.bseries.index[5:])
_compare_with_series(self.zbseries, self.zbseries.index[::2])
_compare_with_series(self.zbseries, self.zbseries.index[:10])
_compare_with_series(self.zbseries, self.zbseries.index[5:])
# special cases
same_index = self.bseries.reindex(self.bseries.index)
assert_sp_series_equal(self.bseries, same_index)
self.assert_(same_index is not self.bseries)
# corner cases
sp = SparseSeries([], index=[])
sp_zero = SparseSeries([], index=[], fill_value=0)
_compare_with_series(sp, np.arange(10))
# with copy=False
reindexed = self.bseries.reindex(self.bseries.index, copy=True)
reindexed.sp_values[:] = 1.
self.assert_((self.bseries.sp_values != 1.).all())
reindexed = self.bseries.reindex(self.bseries.index, copy=False)
reindexed.sp_values[:] = 1.
self.assert_((self.bseries.sp_values == 1.).all())
def test_numpy_take(self):
sp = SparseSeries([1.0, 2.0, 3.0])
indices = [1, 2]
tm.assert_series_equal(
np.take(sp, indices, axis=0).to_dense(),
np.take(sp.to_dense(), indices, axis=0))
msg = "the 'out' parameter is not supported"
tm.assertRaisesRegexp(ValueError,
msg,
np.take,
sp,
indices,
out=np.empty(sp.shape))
msg = "the 'mode' parameter is not supported"
tm.assertRaisesRegexp(ValueError,
msg,
np.take,
sp,
indices,
mode='clip')
def test_take(self):
def _compare_with_dense(sp):
dense = sp.to_dense()
def _compare(idx):
dense_result = dense.take(idx).values
sparse_result = sp.take(idx)
self.assertIsInstance(sparse_result, SparseSeries)
tm.assert_almost_equal(dense_result,
sparse_result.values.values)
_compare([1., 2., 3., 4., 5., 0.])
_compare([7, 2, 9, 0, 4])
_compare([3, 6, 3, 4, 7])
self._check_all(_compare_with_dense)
self.assertRaises(Exception, self.bseries.take,
[0, len(self.bseries) + 1])
# Corner case
sp = SparseSeries(np.ones(10) * nan)
exp = pd.Series(np.repeat(nan, 5))
tm.assert_series_equal(sp.take([0, 1, 2, 3, 4]), exp)
class TestSparseSeriesAnalytics(tm.TestCase):
def setUp(self):
arr, index = _test_data1()
self.bseries = SparseSeries(arr,
index=index,
kind='block',
name='bseries')
arr, index = _test_data1_zero()
self.zbseries = SparseSeries(arr,
index=index,
kind='block',
fill_value=0,
name='zbseries')
def test_cumsum(self):
result = self.bseries.cumsum()
expected = SparseSeries(self.bseries.to_dense().cumsum())
tm.assert_sp_series_equal(result, expected)
# TODO: gh-12855 - return a SparseSeries here
result = self.zbseries.cumsum()
expected = self.zbseries.to_dense().cumsum()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
def test_numpy_cumsum(self):
result = np.cumsum(self.bseries)
expected = SparseSeries(self.bseries.to_dense().cumsum())
tm.assert_sp_series_equal(result, expected)
# TODO: gh-12855 - return a SparseSeries here
result = np.cumsum(self.zbseries)
expected = self.zbseries.to_dense().cumsum()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
msg = "the 'dtype' parameter is not supported"
tm.assertRaisesRegexp(ValueError,
msg,
np.cumsum,
self.bseries,
dtype=np.int64)
msg = "the 'out' parameter is not supported"
tm.assertRaisesRegexp(ValueError,
msg,
np.cumsum,
self.zbseries,
out=result)
class TestSparseSeriesAnalytics(tm.TestCase):
def setUp(self):
arr, index = _test_data1()
self.bseries = SparseSeries(arr, index=index, kind='block',
name='bseries')
arr, index = _test_data1_zero()
self.zbseries = SparseSeries(arr, index=index, kind='block',
fill_value=0, name='zbseries')
def test_cumsum(self):
result = self.bseries.cumsum()
expected = SparseSeries(self.bseries.to_dense().cumsum())
tm.assert_sp_series_equal(result, expected)
# TODO: gh-12855 - return a SparseSeries here
result = self.zbseries.cumsum()
expected = self.zbseries.to_dense().cumsum()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
def test_numpy_cumsum(self):
result = np.cumsum(self.bseries)
expected = SparseSeries(self.bseries.to_dense().cumsum())
tm.assert_sp_series_equal(result, expected)
# TODO: gh-12855 - return a SparseSeries here
result = np.cumsum(self.zbseries)
expected = self.zbseries.to_dense().cumsum()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
msg = "the 'dtype' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.cumsum,
self.bseries, dtype=np.int64)
msg = "the 'out' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.cumsum,
self.zbseries, out=result)
def test_numpy_func_call(self):
# no exception should be raised even though
# numpy passes in 'axis=None' or `axis=-1'
funcs = ['sum', 'cumsum', 'var', 'mean',
'prod', 'cumprod', 'std', 'argsort',
'argmin', 'argmax', 'min', 'max']
for func in funcs:
for series in ('bseries', 'zbseries'):
getattr(np, func)(getattr(self, series))
class TestSparseSeriesAnalytics(tm.TestCase):
def setUp(self):
arr, index = _test_data1()
self.bseries = SparseSeries(arr, index=index, kind='block',
name='bseries')
arr, index = _test_data1_zero()
self.zbseries = SparseSeries(arr, index=index, kind='block',
fill_value=0, name='zbseries')
def test_cumsum(self):
result = self.bseries.cumsum()
expected = SparseSeries(self.bseries.to_dense().cumsum())
tm.assert_sp_series_equal(result, expected)
# TODO: gh-12855 - return a SparseSeries here
result = self.zbseries.cumsum()
expected = self.zbseries.to_dense().cumsum()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
def test_numpy_cumsum(self):
result = np.cumsum(self.bseries)
expected = SparseSeries(self.bseries.to_dense().cumsum())
tm.assert_sp_series_equal(result, expected)
# TODO: gh-12855 - return a SparseSeries here
result = np.cumsum(self.zbseries)
expected = self.zbseries.to_dense().cumsum()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
msg = "the 'dtype' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.cumsum,
self.bseries, dtype=np.int64)
msg = "the 'out' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.cumsum,
self.zbseries, out=result)
class TestSparseSeries(tm.TestCase, SharedWithSparse):
_multiprocess_can_split_ = True
def setUp(self):
arr, index = _test_data1()
date_index = bdate_range('1/1/2011', periods=len(index))
self.bseries = SparseSeries(arr, index=index, kind='block',
name='bseries')
self.ts = self.bseries
self.btseries = SparseSeries(arr, index=date_index, kind='block')
self.iseries = SparseSeries(arr, index=index, kind='integer',
name='iseries')
arr, index = _test_data2()
self.bseries2 = SparseSeries(arr, index=index, kind='block')
self.iseries2 = SparseSeries(arr, index=index, kind='integer')
arr, index = _test_data1_zero()
self.zbseries = SparseSeries(arr, index=index, kind='block',
fill_value=0, name='zbseries')
self.ziseries = SparseSeries(arr, index=index, kind='integer',
fill_value=0)
arr, index = _test_data2_zero()
self.zbseries2 = SparseSeries(arr, index=index, kind='block',
fill_value=0)
self.ziseries2 = SparseSeries(arr, index=index, kind='integer',
fill_value=0)
def test_constructor_dtype(self):
arr = SparseSeries([np.nan, 1, 2, np.nan])
self.assertEqual(arr.dtype, np.float64)
self.assertTrue(np.isnan(arr.fill_value))
arr = SparseSeries([np.nan, 1, 2, np.nan], fill_value=0)
self.assertEqual(arr.dtype, np.float64)
self.assertEqual(arr.fill_value, 0)
arr = SparseSeries([0, 1, 2, 4], dtype=np.int64)
self.assertEqual(arr.dtype, np.int64)
self.assertTrue(np.isnan(arr.fill_value))
arr = SparseSeries([0, 1, 2, 4], fill_value=0, dtype=np.int64)
self.assertEqual(arr.dtype, np.int64)
self.assertEqual(arr.fill_value, 0)
def test_iteration_and_str(self):
[x for x in self.bseries]
str(self.bseries)
def test_TimeSeries_deprecation(self):
# deprecation TimeSeries, #10890
with tm.assert_produces_warning(FutureWarning):
pd.SparseTimeSeries(1, index=pd.date_range('20130101', periods=3))
def test_construct_DataFrame_with_sp_series(self):
# it works!
df = DataFrame({'col': self.bseries})
# printing & access
df.iloc[:1]
df['col']
df.dtypes
str(df)
tm.assert_sp_series_equal(df['col'], self.bseries, check_names=False)
result = df.iloc[:, 0]
tm.assert_sp_series_equal(result, self.bseries, check_names=False)
# blocking
expected = Series({'col': 'float64:sparse'})
result = df.ftypes
tm.assert_series_equal(expected, result)
def test_series_density(self):
# GH2803
ts = Series(np.random.randn(10))
ts[2:-2] = nan
sts = ts.to_sparse()
density = sts.density # don't die
self.assertEqual(density, 4 / 10.0)
def test_sparse_to_dense(self):
arr, index = _test_data1()
series = self.bseries.to_dense()
assert_equal(series, arr)
series = self.bseries.to_dense(sparse_only=True)
assert_equal(series, arr[np.isfinite(arr)])
series = self.iseries.to_dense()
assert_equal(series, arr)
arr, index = _test_data1_zero()
series = self.zbseries.to_dense()
assert_equal(series, arr)
series = self.ziseries.to_dense()
assert_equal(series, arr)
def test_to_dense_fill_value(self):
s = pd.Series([1, np.nan, np.nan, 3, np.nan])
res = SparseSeries(s).to_dense()
tm.assert_series_equal(res, s)
res = SparseSeries(s, fill_value=0).to_dense()
tm.assert_series_equal(res, s)
s = pd.Series([1, np.nan, 0, 3, 0])
res = SparseSeries(s, fill_value=0).to_dense()
tm.assert_series_equal(res, s)
res = SparseSeries(s, fill_value=0).to_dense()
tm.assert_series_equal(res, s)
s = pd.Series([np.nan, np.nan, np.nan, np.nan, np.nan])
res = SparseSeries(s).to_dense()
tm.assert_series_equal(res, s)
s = pd.Series([np.nan, np.nan, np.nan, np.nan, np.nan])
res = SparseSeries(s, fill_value=0).to_dense()
tm.assert_series_equal(res, s)
def test_dense_to_sparse(self):
series = self.bseries.to_dense()
bseries = series.to_sparse(kind='block')
iseries = series.to_sparse(kind='integer')
tm.assert_sp_series_equal(bseries, self.bseries)
tm.assert_sp_series_equal(iseries, self.iseries, check_names=False)
self.assertEqual(iseries.name, self.bseries.name)
self.assertEqual(len(series), len(bseries))
self.assertEqual(len(series), len(iseries))
self.assertEqual(series.shape, bseries.shape)
self.assertEqual(series.shape, iseries.shape)
# non-NaN fill value
series = self.zbseries.to_dense()
zbseries = series.to_sparse(kind='block', fill_value=0)
ziseries = series.to_sparse(kind='integer', fill_value=0)
tm.assert_sp_series_equal(zbseries, self.zbseries)
tm.assert_sp_series_equal(ziseries, self.ziseries, check_names=False)
self.assertEqual(ziseries.name, self.zbseries.name)
self.assertEqual(len(series), len(zbseries))
self.assertEqual(len(series), len(ziseries))
self.assertEqual(series.shape, zbseries.shape)
self.assertEqual(series.shape, ziseries.shape)
def test_to_dense_preserve_name(self):
assert (self.bseries.name is not None)
result = self.bseries.to_dense()
self.assertEqual(result.name, self.bseries.name)
def test_constructor(self):
# test setup guys
self.assertTrue(np.isnan(self.bseries.fill_value))
tm.assertIsInstance(self.bseries.sp_index, BlockIndex)
self.assertTrue(np.isnan(self.iseries.fill_value))
tm.assertIsInstance(self.iseries.sp_index, IntIndex)
self.assertEqual(self.zbseries.fill_value, 0)
assert_equal(self.zbseries.values.values,
self.bseries.to_dense().fillna(0).values)
# pass SparseSeries
def _check_const(sparse, name):
# use passed series name
result = SparseSeries(sparse)
tm.assert_sp_series_equal(result, sparse)
self.assertEqual(sparse.name, name)
self.assertEqual(result.name, name)
# use passed name
result = SparseSeries(sparse, name='x')
tm.assert_sp_series_equal(result, sparse, check_names=False)
self.assertEqual(result.name, 'x')
_check_const(self.bseries, 'bseries')
_check_const(self.iseries, 'iseries')
_check_const(self.zbseries, 'zbseries')
# Sparse time series works
date_index = bdate_range('1/1/2000', periods=len(self.bseries))
s5 = SparseSeries(self.bseries, index=date_index)
tm.assertIsInstance(s5, SparseSeries)
# pass Series
bseries2 = SparseSeries(self.bseries.to_dense())
assert_equal(self.bseries.sp_values, bseries2.sp_values)
# pass dict?
# don't copy the data by default
values = np.ones(self.bseries.npoints)
sp = SparseSeries(values, sparse_index=self.bseries.sp_index)
sp.sp_values[:5] = 97
self.assertEqual(values[0], 97)
self.assertEqual(len(sp), 20)
self.assertEqual(sp.shape, (20, ))
# but can make it copy!
sp = SparseSeries(values, sparse_index=self.bseries.sp_index,
copy=True)
sp.sp_values[:5] = 100
self.assertEqual(values[0], 97)
self.assertEqual(len(sp), 20)
self.assertEqual(sp.shape, (20, ))
def test_constructor_scalar(self):
data = 5
sp = SparseSeries(data, np.arange(100))
sp = sp.reindex(np.arange(200))
self.assertTrue((sp.ix[:99] == data).all())
self.assertTrue(isnull(sp.ix[100:]).all())
data = np.nan
sp = SparseSeries(data, np.arange(100))
self.assertEqual(len(sp), 100)
self.assertEqual(sp.shape, (100, ))
def test_constructor_ndarray(self):
pass
def test_constructor_nonnan(self):
arr = [0, 0, 0, nan, nan]
sp_series = SparseSeries(arr, fill_value=0)
assert_equal(sp_series.values.values, arr)
self.assertEqual(len(sp_series), 5)
self.assertEqual(sp_series.shape, (5, ))
# GH 9272
def test_constructor_empty(self):
sp = SparseSeries()
self.assertEqual(len(sp.index), 0)
self.assertEqual(sp.shape, (0, ))
def test_copy_astype(self):
cop = self.bseries.astype(np.float64)
self.assertIsNot(cop, self.bseries)
self.assertIs(cop.sp_index, self.bseries.sp_index)
self.assertEqual(cop.dtype, np.float64)
cop2 = self.iseries.copy()
tm.assert_sp_series_equal(cop, self.bseries)
tm.assert_sp_series_equal(cop2, self.iseries)
# test that data is copied
cop[:5] = 97
self.assertEqual(cop.sp_values[0], 97)
self.assertNotEqual(self.bseries.sp_values[0], 97)
# correct fill value
zbcop = self.zbseries.copy()
zicop = self.ziseries.copy()
tm.assert_sp_series_equal(zbcop, self.zbseries)
tm.assert_sp_series_equal(zicop, self.ziseries)
# no deep copy
view = self.bseries.copy(deep=False)
view.sp_values[:5] = 5
self.assertTrue((self.bseries.sp_values[:5] == 5).all())
def test_shape(self):
# GH 10452
self.assertEqual(self.bseries.shape, (20, ))
self.assertEqual(self.btseries.shape, (20, ))
self.assertEqual(self.iseries.shape, (20, ))
self.assertEqual(self.bseries2.shape, (15, ))
self.assertEqual(self.iseries2.shape, (15, ))
self.assertEqual(self.zbseries2.shape, (15, ))
self.assertEqual(self.ziseries2.shape, (15, ))
def test_astype(self):
self.assertRaises(Exception, self.bseries.astype, np.int64)
def test_kind(self):
self.assertEqual(self.bseries.kind, 'block')
self.assertEqual(self.iseries.kind, 'integer')
def test_to_frame(self):
# GH 9850
s = pd.SparseSeries([1, 2, 0, nan, 4, nan, 0], name='x')
exp = pd.SparseDataFrame({'x': [1, 2, 0, nan, 4, nan, 0]})
tm.assert_sp_frame_equal(s.to_frame(), exp)
exp = pd.SparseDataFrame({'y': [1, 2, 0, nan, 4, nan, 0]})
tm.assert_sp_frame_equal(s.to_frame(name='y'), exp)
s = pd.SparseSeries([1, 2, 0, nan, 4, nan, 0], name='x', fill_value=0)
exp = pd.SparseDataFrame({'x': [1, 2, 0, nan, 4, nan, 0]},
default_fill_value=0)
tm.assert_sp_frame_equal(s.to_frame(), exp)
exp = pd.DataFrame({'y': [1, 2, 0, nan, 4, nan, 0]})
tm.assert_frame_equal(s.to_frame(name='y').to_dense(), exp)
def test_pickle(self):
def _test_roundtrip(series):
unpickled = self.round_trip_pickle(series)
tm.assert_sp_series_equal(series, unpickled)
tm.assert_series_equal(series.to_dense(), unpickled.to_dense())
self._check_all(_test_roundtrip)
def _check_all(self, check_func):
check_func(self.bseries)
check_func(self.iseries)
check_func(self.zbseries)
check_func(self.ziseries)
def test_getitem(self):
def _check_getitem(sp, dense):
for idx, val in compat.iteritems(dense):
tm.assert_almost_equal(val, sp[idx])
for i in range(len(dense)):
tm.assert_almost_equal(sp[i], dense[i])
# j = np.float64(i)
# assert_almost_equal(sp[j], dense[j])
# API change 1/6/2012
# negative getitem works
# for i in xrange(len(dense)):
# assert_almost_equal(sp[-i], dense[-i])
_check_getitem(self.bseries, self.bseries.to_dense())
_check_getitem(self.btseries, self.btseries.to_dense())
_check_getitem(self.zbseries, self.zbseries.to_dense())
_check_getitem(self.iseries, self.iseries.to_dense())
_check_getitem(self.ziseries, self.ziseries.to_dense())
# exception handling
self.assertRaises(Exception, self.bseries.__getitem__,
len(self.bseries) + 1)
# index not contained
self.assertRaises(Exception, self.btseries.__getitem__,
self.btseries.index[-1] + BDay())
def test_get_get_value(self):
tm.assert_almost_equal(self.bseries.get(10), self.bseries[10])
self.assertIsNone(self.bseries.get(len(self.bseries) + 1))
dt = self.btseries.index[10]
result = self.btseries.get(dt)
expected = self.btseries.to_dense()[dt]
tm.assert_almost_equal(result, expected)
tm.assert_almost_equal(self.bseries.get_value(10), self.bseries[10])
def test_set_value(self):
idx = self.btseries.index[7]
self.btseries.set_value(idx, 0)
self.assertEqual(self.btseries[idx], 0)
self.iseries.set_value('foobar', 0)
self.assertEqual(self.iseries.index[-1], 'foobar')
self.assertEqual(self.iseries['foobar'], 0)
def test_getitem_slice(self):
idx = self.bseries.index
res = self.bseries[::2]
tm.assertIsInstance(res, SparseSeries)
expected = self.bseries.reindex(idx[::2])
tm.assert_sp_series_equal(res, expected)
res = self.bseries[:5]
tm.assertIsInstance(res, SparseSeries)
tm.assert_sp_series_equal(res, self.bseries.reindex(idx[:5]))
res = self.bseries[5:]
tm.assert_sp_series_equal(res, self.bseries.reindex(idx[5:]))
# negative indices
res = self.bseries[:-3]
tm.assert_sp_series_equal(res, self.bseries.reindex(idx[:-3]))
def test_take(self):
def _compare_with_dense(sp):
dense = sp.to_dense()
def _compare(idx):
dense_result = dense.take(idx).values
sparse_result = sp.take(idx)
self.assertIsInstance(sparse_result, SparseSeries)
tm.assert_almost_equal(dense_result,
sparse_result.values.values)
_compare([1., 2., 3., 4., 5., 0.])
_compare([7, 2, 9, 0, 4])
_compare([3, 6, 3, 4, 7])
self._check_all(_compare_with_dense)
self.assertRaises(Exception, self.bseries.take,
[0, len(self.bseries) + 1])
# Corner case
sp = SparseSeries(np.ones(10) * nan)
exp = pd.Series(np.repeat(nan, 5))
tm.assert_series_equal(sp.take([0, 1, 2, 3, 4]), exp)
def test_setitem(self):
self.bseries[5] = 7.
self.assertEqual(self.bseries[5], 7.)
def test_setslice(self):
self.bseries[5:10] = 7.
tm.assert_series_equal(self.bseries[5:10].to_dense(),
Series(7., index=range(5, 10),
name=self.bseries.name))
def test_operators(self):
def _check_op(a, b, op):
sp_result = op(a, b)
adense = a.to_dense() if isinstance(a, SparseSeries) else a
bdense = b.to_dense() if isinstance(b, SparseSeries) else b
dense_result = op(adense, bdense)
tm.assert_almost_equal(sp_result.to_dense(), dense_result)
def check(a, b):
_check_op(a, b, operator.add)
_check_op(a, b, operator.sub)
_check_op(a, b, operator.truediv)
_check_op(a, b, operator.floordiv)
_check_op(a, b, operator.mul)
_check_op(a, b, lambda x, y: operator.add(y, x))
_check_op(a, b, lambda x, y: operator.sub(y, x))
_check_op(a, b, lambda x, y: operator.truediv(y, x))
_check_op(a, b, lambda x, y: operator.floordiv(y, x))
_check_op(a, b, lambda x, y: operator.mul(y, x))
# NaN ** 0 = 1 in C?
# _check_op(a, b, operator.pow)
# _check_op(a, b, lambda x, y: operator.pow(y, x))
check(self.bseries, self.bseries)
check(self.iseries, self.iseries)
check(self.bseries, self.iseries)
check(self.bseries, self.bseries2)
check(self.bseries, self.iseries2)
check(self.iseries, self.iseries2)
# scalar value
check(self.bseries, 5)
# zero-based
check(self.zbseries, self.zbseries * 2)
check(self.zbseries, self.zbseries2)
check(self.ziseries, self.ziseries2)
# with dense
result = self.bseries + self.bseries.to_dense()
tm.assert_sp_series_equal(result, self.bseries + self.bseries)
def test_binary_operators(self):
# skipping for now #####
raise nose.SkipTest("skipping sparse binary operators test")
def _check_inplace_op(iop, op):
tmp = self.bseries.copy()
expected = op(tmp, self.bseries)
iop(tmp, self.bseries)
tm.assert_sp_series_equal(tmp, expected)
inplace_ops = ['add', 'sub', 'mul', 'truediv', 'floordiv', 'pow']
for op in inplace_ops:
_check_inplace_op(getattr(operator, "i%s" % op),
getattr(operator, op))
def test_abs(self):
s = SparseSeries([1, 2, -3], name='x')
expected = SparseSeries([1, 2, 3], name='x')
result = s.abs()
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
result = np.abs(s)
tm.assert_sp_series_equal(result, expected)
self.assertEqual(result.name, 'x')
def test_reindex(self):
def _compare_with_series(sps, new_index):
spsre = sps.reindex(new_index)
series = sps.to_dense()
seriesre = series.reindex(new_index)
seriesre = seriesre.to_sparse(fill_value=sps.fill_value)
tm.assert_sp_series_equal(spsre, seriesre)
tm.assert_series_equal(spsre.to_dense(), seriesre.to_dense())
_compare_with_series(self.bseries, self.bseries.index[::2])
_compare_with_series(self.bseries, list(self.bseries.index[::2]))
_compare_with_series(self.bseries, self.bseries.index[:10])
_compare_with_series(self.bseries, self.bseries.index[5:])
_compare_with_series(self.zbseries, self.zbseries.index[::2])
_compare_with_series(self.zbseries, self.zbseries.index[:10])
_compare_with_series(self.zbseries, self.zbseries.index[5:])
# special cases
same_index = self.bseries.reindex(self.bseries.index)
tm.assert_sp_series_equal(self.bseries, same_index)
self.assertIsNot(same_index, self.bseries)
# corner cases
sp = SparseSeries([], index=[])
# TODO: sp_zero is not used anywhere...remove?
sp_zero = SparseSeries([], index=[], fill_value=0) # noqa
_compare_with_series(sp, np.arange(10))
# with copy=False
reindexed = self.bseries.reindex(self.bseries.index, copy=True)
reindexed.sp_values[:] = 1.
self.assertTrue((self.bseries.sp_values != 1.).all())
reindexed = self.bseries.reindex(self.bseries.index, copy=False)
reindexed.sp_values[:] = 1.
tm.assert_numpy_array_equal(self.bseries.sp_values, np.repeat(1., 10))
def test_sparse_reindex(self):
length = 10
def _check(values, index1, index2, fill_value):
first_series = SparseSeries(values, sparse_index=index1,
fill_value=fill_value)
reindexed = first_series.sparse_reindex(index2)
self.assertIs(reindexed.sp_index, index2)
int_indices1 = index1.to_int_index().indices
int_indices2 = index2.to_int_index().indices
expected = Series(values, index=int_indices1)
expected = expected.reindex(int_indices2).fillna(fill_value)
tm.assert_almost_equal(expected.values, reindexed.sp_values)
# make sure level argument asserts
# TODO: expected is not used anywhere...remove?
expected = expected.reindex(int_indices2).fillna(fill_value) # noqa
def _check_with_fill_value(values, first, second, fill_value=nan):
i_index1 = IntIndex(length, first)
i_index2 = IntIndex(length, second)
b_index1 = i_index1.to_block_index()
b_index2 = i_index2.to_block_index()
_check(values, i_index1, i_index2, fill_value)
_check(values, b_index1, b_index2, fill_value)
def _check_all(values, first, second):
_check_with_fill_value(values, first, second, fill_value=nan)
_check_with_fill_value(values, first, second, fill_value=0)
index1 = [2, 4, 5, 6, 8, 9]
values1 = np.arange(6.)
_check_all(values1, index1, [2, 4, 5])
_check_all(values1, index1, [2, 3, 4, 5, 6, 7, 8, 9])
_check_all(values1, index1, [0, 1])
_check_all(values1, index1, [0, 1, 7, 8, 9])
_check_all(values1, index1, [])
first_series = SparseSeries(values1,
sparse_index=IntIndex(length, index1),
fill_value=nan)
with tm.assertRaisesRegexp(TypeError,
'new index must be a SparseIndex'):
reindexed = first_series.sparse_reindex(0) # noqa
def test_repr(self):
# TODO: These aren't used
bsrepr = repr(self.bseries) # noqa
isrepr = repr(self.iseries) # noqa
def test_iter(self):
pass
def test_truncate(self):
pass
def test_fillna(self):
pass
def test_groupby(self):
pass
def test_reductions(self):
def _compare_with_dense(obj, op):
sparse_result = getattr(obj, op)()
series = obj.to_dense()
dense_result = getattr(series, op)()
self.assertEqual(sparse_result, dense_result)
to_compare = ['count', 'sum', 'mean', 'std', 'var', 'skew']
def _compare_all(obj):
for op in to_compare:
_compare_with_dense(obj, op)
_compare_all(self.bseries)
self.bseries.sp_values[5:10] = np.NaN
_compare_all(self.bseries)
_compare_all(self.zbseries)
self.zbseries.sp_values[5:10] = np.NaN
_compare_all(self.zbseries)
series = self.zbseries.copy()
series.fill_value = 2
_compare_all(series)
nonna = Series(np.random.randn(20)).to_sparse()
_compare_all(nonna)
nonna2 = Series(np.random.randn(20)).to_sparse(fill_value=0)
_compare_all(nonna2)
def test_dropna(self):
sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)
sp_valid = sp.valid()
expected = sp.to_dense().valid()
expected = expected[expected != 0]
tm.assert_almost_equal(sp_valid.values, expected.values)
self.assertTrue(sp_valid.index.equals(expected.index))
self.assertEqual(len(sp_valid.sp_values), 2)
result = self.bseries.dropna()
expected = self.bseries.to_dense().dropna()
self.assertNotIsInstance(result, SparseSeries)
tm.assert_series_equal(result, expected)
def test_homogenize(self):
def _check_matches(indices, expected):
data = {}
for i, idx in enumerate(indices):
data[i] = SparseSeries(idx.to_int_index().indices,
sparse_index=idx)
homogenized = spf.homogenize(data)
for k, v in compat.iteritems(homogenized):
assert (v.sp_index.equals(expected))
indices1 = [BlockIndex(10, [2], [7]), BlockIndex(10, [1, 6], [3, 4]),
BlockIndex(10, [0], [10])]
expected1 = BlockIndex(10, [2, 6], [2, 3])
_check_matches(indices1, expected1)
indices2 = [BlockIndex(10, [2], [7]), BlockIndex(10, [2], [7])]
expected2 = indices2[0]
_check_matches(indices2, expected2)
# must have NaN fill value
data = {'a': SparseSeries(np.arange(7), sparse_index=expected2,
fill_value=0)}
with tm.assertRaisesRegexp(TypeError, "NaN fill value"):
spf.homogenize(data)
def test_fill_value_corner(self):
cop = self.zbseries.copy()
cop.fill_value = 0
result = self.bseries / cop
self.assertTrue(np.isnan(result.fill_value))
cop2 = self.zbseries.copy()
cop2.fill_value = 1
result = cop2 / cop
self.assertTrue(np.isnan(result.fill_value))
def test_fill_value_when_combine_const(self):
# GH12723
s = SparseSeries([0, 1, np.nan, 3, 4, 5], index=np.arange(6))
exp = s.fillna(0).add(2)
res = s.add(2, fill_value=0)
self.assert_series_equal(res, exp)
def test_shift(self):
series = SparseSeries([nan, 1., 2., 3., nan, nan], index=np.arange(6))
shifted = series.shift(0)
self.assertIsNot(shifted, series)
tm.assert_sp_series_equal(shifted, series)
f = lambda s: s.shift(1)
_dense_series_compare(series, f)
f = lambda s: s.shift(-2)
_dense_series_compare(series, f)
series = SparseSeries([nan, 1., 2., 3., nan, nan],
index=bdate_range('1/1/2000', periods=6))
f = lambda s: s.shift(2, freq='B')
_dense_series_compare(series, f)
f = lambda s: s.shift(2, freq=datetools.bday)
_dense_series_compare(series, f)
def test_shift_nan(self):
# GH 12908
orig = pd.Series([np.nan, 2, np.nan, 4, 0, np.nan, 0])
sparse = orig.to_sparse()
tm.assert_sp_series_equal(sparse.shift(0), orig.shift(0).to_sparse())
tm.assert_sp_series_equal(sparse.shift(1), orig.shift(1).to_sparse())
tm.assert_sp_series_equal(sparse.shift(2), orig.shift(2).to_sparse())
tm.assert_sp_series_equal(sparse.shift(3), orig.shift(3).to_sparse())
tm.assert_sp_series_equal(sparse.shift(-1), orig.shift(-1).to_sparse())
tm.assert_sp_series_equal(sparse.shift(-2), orig.shift(-2).to_sparse())
tm.assert_sp_series_equal(sparse.shift(-3), orig.shift(-3).to_sparse())
tm.assert_sp_series_equal(sparse.shift(-4), orig.shift(-4).to_sparse())
sparse = orig.to_sparse(fill_value=0)
tm.assert_sp_series_equal(sparse.shift(0),
orig.shift(0).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(1),
orig.shift(1).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(2),
orig.shift(2).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(3),
orig.shift(3).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(-1),
orig.shift(-1).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(-2),
orig.shift(-2).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(-3),
orig.shift(-3).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(-4),
orig.shift(-4).to_sparse(fill_value=0))
def test_shift_dtype(self):
# GH 12908
orig = pd.Series([1, 2, 3, 4], dtype=np.int64)
sparse = orig.to_sparse()
tm.assert_sp_series_equal(sparse.shift(0), orig.shift(0).to_sparse())
tm.assert_sp_series_equal(sparse.shift(1), orig.shift(1).to_sparse())
tm.assert_sp_series_equal(sparse.shift(2), orig.shift(2).to_sparse())
tm.assert_sp_series_equal(sparse.shift(3), orig.shift(3).to_sparse())
tm.assert_sp_series_equal(sparse.shift(-1), orig.shift(-1).to_sparse())
tm.assert_sp_series_equal(sparse.shift(-2), orig.shift(-2).to_sparse())
tm.assert_sp_series_equal(sparse.shift(-3), orig.shift(-3).to_sparse())
tm.assert_sp_series_equal(sparse.shift(-4), orig.shift(-4).to_sparse())
def test_shift_dtype_fill_value(self):
# GH 12908
orig = pd.Series([1, 0, 0, 4], dtype=np.int64)
sparse = orig.to_sparse(fill_value=0)
tm.assert_sp_series_equal(sparse.shift(0),
orig.shift(0).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(1),
orig.shift(1).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(2),
orig.shift(2).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(3),
orig.shift(3).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(-1),
orig.shift(-1).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(-2),
orig.shift(-2).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(-3),
orig.shift(-3).to_sparse(fill_value=0))
tm.assert_sp_series_equal(sparse.shift(-4),
orig.shift(-4).to_sparse(fill_value=0))
def test_cumsum(self):
result = self.bseries.cumsum()
expected = self.bseries.to_dense().cumsum()
tm.assertIsInstance(result, SparseSeries)
self.assertEqual(result.name, self.bseries.name)
tm.assert_series_equal(result.to_dense(), expected)
result = self.zbseries.cumsum()
expected = self.zbseries.to_dense().cumsum()
tm.assertIsInstance(result, Series)
tm.assert_series_equal(result, expected)
def test_combine_first(self):
s = self.bseries
result = s[::2].combine_first(s)
result2 = s[::2].combine_first(s.to_dense())
expected = s[::2].to_dense().combine_first(s.to_dense())
expected = expected.to_sparse(fill_value=s.fill_value)
tm.assert_sp_series_equal(result, result2)
tm.assert_sp_series_equal(result, expected)
class TestSparseSeries(TestCase, test_series.CheckNameIntegration):
def setUp(self):
arr, index = _test_data1()
date_index = DateRange("1/1/2011", periods=len(index))
self.bseries = SparseSeries(arr, index=index, kind="block")
self.bseries.name = "bseries"
self.ts = self.bseries
self.btseries = SparseSeries(arr, index=date_index, kind="block")
self.iseries = SparseSeries(arr, index=index, kind="integer")
arr, index = _test_data2()
self.bseries2 = SparseSeries(arr, index=index, kind="block")
self.iseries2 = SparseSeries(arr, index=index, kind="integer")
arr, index = _test_data1_zero()
self.zbseries = SparseSeries(arr, index=index, kind="block", fill_value=0)
self.ziseries = SparseSeries(arr, index=index, kind="integer", fill_value=0)
arr, index = _test_data2_zero()
self.zbseries2 = SparseSeries(arr, index=index, kind="block", fill_value=0)
self.ziseries2 = SparseSeries(arr, index=index, kind="integer", fill_value=0)
def test_construct_DataFrame_with_sp_series(self):
# it works!
df = DataFrame({"col": self.bseries})
def test_sparse_to_dense(self):
arr, index = _test_data1()
series = self.bseries.to_dense()
assert_equal(series, arr)
series = self.bseries.to_dense(sparse_only=True)
assert_equal(series, arr[np.isfinite(arr)])
series = self.iseries.to_dense()
assert_equal(series, arr)
arr, index = _test_data1_zero()
series = self.zbseries.to_dense()
assert_equal(series, arr)
series = self.ziseries.to_dense()
assert_equal(series, arr)
def test_dense_to_sparse(self):
series = self.bseries.to_dense()
bseries = series.to_sparse(kind="block")
iseries = series.to_sparse(kind="integer")
assert_sp_series_equal(bseries, self.bseries)
assert_sp_series_equal(iseries, self.iseries)
# non-NaN fill value
series = self.zbseries.to_dense()
zbseries = series.to_sparse(kind="block", fill_value=0)
ziseries = series.to_sparse(kind="integer", fill_value=0)
assert_sp_series_equal(zbseries, self.zbseries)
assert_sp_series_equal(ziseries, self.ziseries)
def test_to_dense_preserve_name(self):
assert self.bseries.name is not None
result = self.bseries.to_dense()
self.assertEquals(result.name, self.bseries.name)
def test_constructor(self):
# test setup guys
self.assert_(np.isnan(self.bseries.fill_value))
self.assert_(isinstance(self.bseries.sp_index, BlockIndex))
self.assert_(np.isnan(self.iseries.fill_value))
self.assert_(isinstance(self.iseries.sp_index, IntIndex))
self.assertEquals(self.zbseries.fill_value, 0)
assert_equal(self.zbseries.values, self.bseries.to_dense().fillna(0))
# pass SparseSeries
s2 = SparseSeries(self.bseries)
s3 = SparseSeries(self.iseries)
s4 = SparseSeries(self.zbseries)
assert_sp_series_equal(s2, self.bseries)
assert_sp_series_equal(s3, self.iseries)
assert_sp_series_equal(s4, self.zbseries)
# Sparse time series works
date_index = DateRange("1/1/2000", periods=len(self.bseries))
s5 = SparseSeries(self.bseries, index=date_index)
self.assert_(isinstance(s5, SparseTimeSeries))
# pass Series
bseries2 = SparseSeries(self.bseries.to_dense())
assert_equal(self.bseries.sp_values, bseries2.sp_values)
# pass dict?
# don't copy the data by default
values = np.ones(len(self.bseries.sp_values))
sp = SparseSeries(values, sparse_index=self.bseries.sp_index)
sp.sp_values[:5] = 97
self.assert_(values[0] == 97)
# but can make it copy!
sp = SparseSeries(values, sparse_index=self.bseries.sp_index, copy=True)
sp.sp_values[:5] = 100
self.assert_(values[0] == 97)
def test_constructor_ndarray(self):
pass
def test_constructor_nonnan(self):
arr = [0, 0, 0, nan, nan]
sp_series = SparseSeries(arr, fill_value=0)
assert_equal(sp_series.values, arr)
def test_copy_astype(self):
cop = self.bseries.astype(np.float_)
self.assert_(cop is not self.bseries)
self.assert_(cop.sp_index is self.bseries.sp_index)
self.assert_(cop.dtype == np.float64)
cop2 = self.iseries.copy()
assert_sp_series_equal(cop, self.bseries)
assert_sp_series_equal(cop2, self.iseries)
# test that data is copied
cop.sp_values[:5] = 97
self.assert_(cop.sp_values[0] == 97)
self.assert_(self.bseries.sp_values[0] != 97)
# correct fill value
zbcop = self.zbseries.copy()
zicop = self.ziseries.copy()
assert_sp_series_equal(zbcop, self.zbseries)
assert_sp_series_equal(zicop, self.ziseries)
# no deep copy
view = self.bseries.copy(deep=False)
view.sp_values[:5] = 5
self.assert_((self.bseries.sp_values[:5] == 5).all())
def test_astype(self):
self.assertRaises(Exception, self.bseries.astype, np.int64)
def test_kind(self):
self.assertEquals(self.bseries.kind, "block")
self.assertEquals(self.iseries.kind, "integer")
def test_pickle(self):
def _test_roundtrip(series):
pickled = pickle.dumps(series, protocol=pickle.HIGHEST_PROTOCOL)
unpickled = pickle.loads(pickled)
assert_sp_series_equal(series, unpickled)
assert_series_equal(series.to_dense(), unpickled.to_dense())
self._check_all(_test_roundtrip)
def _check_all(self, check_func):
check_func(self.bseries)
check_func(self.iseries)
check_func(self.zbseries)
check_func(self.ziseries)
def test_getitem(self):
def _check_getitem(sp, dense):
for idx, val in dense.iteritems():
assert_almost_equal(val, sp[idx])
for i in xrange(len(dense)):
assert_almost_equal(sp[i], dense[i])
# j = np.float64(i)
# assert_almost_equal(sp[j], dense[j])
# API change 1/6/2012
# negative getitem works
# for i in xrange(len(dense)):
# assert_almost_equal(sp[-i], dense[-i])
_check_getitem(self.bseries, self.bseries.to_dense())
_check_getitem(self.btseries, self.btseries.to_dense())
_check_getitem(self.zbseries, self.zbseries.to_dense())
_check_getitem(self.iseries, self.iseries.to_dense())
_check_getitem(self.ziseries, self.ziseries.to_dense())
# exception handling
self.assertRaises(Exception, self.bseries.__getitem__, len(self.bseries) + 1)
# index not contained
self.assertRaises(Exception, self.btseries.__getitem__, self.btseries.index[-1] + BDay())
def test_get_get_value(self):
assert_almost_equal(self.bseries.get(10), self.bseries[10])
self.assert_(self.bseries.get(len(self.bseries) + 1) is None)
dt = self.btseries.index[10]
result = self.btseries.get(dt)
expected = self.btseries.to_dense()[dt]
assert_almost_equal(result, expected)
assert_almost_equal(self.bseries.get_value(10), self.bseries[10])
def test_set_value(self):
idx = self.btseries.index[7]
res = self.btseries.set_value(idx, 0)
self.assert_(res is not self.btseries)
self.assertEqual(res[idx], 0)
res = self.iseries.set_value("foobar", 0)
self.assert_(res is not self.iseries)
self.assert_(res.index[-1] == "foobar")
self.assertEqual(res["foobar"], 0)
def test_getitem_slice(self):
idx = self.bseries.index
res = self.bseries[::2]
self.assert_(isinstance(res, SparseSeries))
assert_sp_series_equal(res, self.bseries.reindex(idx[::2]))
res = self.bseries[:5]
self.assert_(isinstance(res, SparseSeries))
assert_sp_series_equal(res, self.bseries.reindex(idx[:5]))
res = self.bseries[5:]
assert_sp_series_equal(res, self.bseries.reindex(idx[5:]))
# negative indices
res = self.bseries[:-3]
assert_sp_series_equal(res, self.bseries.reindex(idx[:-3]))
def test_take(self):
def _compare_with_dense(sp):
dense = sp.to_dense()
def _compare(idx):
dense_result = dense.take(idx).values
sparse_result = sp.take(idx)
self.assert_(isinstance(sparse_result, SparseSeries))
assert_almost_equal(dense_result, sparse_result.values)
_compare([1.0, 2.0, 3.0, 4.0, 5.0, 0.0])
_compare([7, 2, 9, 0, 4])
_compare([3, 6, 3, 4, 7])
self._check_all(_compare_with_dense)
self.assertRaises(Exception, self.bseries.take, [-1, 0])
self.assertRaises(Exception, self.bseries.take, [0, len(self.bseries) + 1])
# Corner case
sp = SparseSeries(np.ones(10.0) * nan)
assert_almost_equal(sp.take([0, 1, 2, 3, 4]), np.repeat(nan, 5))
def test_setitem(self):
self.assertRaises(Exception, self.bseries.__setitem__, 5, 7.0)
self.assertRaises(Exception, self.iseries.__setitem__, 5, 7.0)
def test_setslice(self):
self.assertRaises(Exception, self.bseries.__setslice__, 5, 10, 7.0)
def test_operators(self):
def _check_op(a, b, op):
sp_result = op(a, b)
adense = a.to_dense() if isinstance(a, SparseSeries) else a
bdense = b.to_dense() if isinstance(b, SparseSeries) else b
dense_result = op(adense, bdense)
assert_almost_equal(sp_result.to_dense(), dense_result)
def check(a, b):
_check_op(a, b, operator.add)
_check_op(a, b, operator.sub)
_check_op(a, b, operator.truediv)
_check_op(a, b, operator.floordiv)
_check_op(a, b, operator.mul)
_check_op(a, b, lambda x, y: operator.add(y, x))
_check_op(a, b, lambda x, y: operator.sub(y, x))
_check_op(a, b, lambda x, y: operator.truediv(y, x))
_check_op(a, b, lambda x, y: operator.floordiv(y, x))
_check_op(a, b, lambda x, y: operator.mul(y, x))
# NaN ** 0 = 1 in C?
# _check_op(a, b, operator.pow)
# _check_op(a, b, lambda x, y: operator.pow(y, x))
check(self.bseries, self.bseries)
check(self.iseries, self.iseries)
check(self.bseries, self.iseries)
check(self.bseries, self.bseries2)
check(self.bseries, self.iseries2)
check(self.iseries, self.iseries2)
# scalar value
check(self.bseries, 5)
# zero-based
check(self.zbseries, self.zbseries * 2)
check(self.zbseries, self.zbseries2)
check(self.ziseries, self.ziseries2)
# with dense
result = self.bseries + self.bseries.to_dense()
assert_sp_series_equal(result, self.bseries + self.bseries)
# @dec.knownfailureif(True, 'Known NumPy failer as of 1.5.1')
def test_operators_corner2(self):
raise nose.SkipTest("known failer on numpy 1.5.1")
# NumPy circumvents __r*__ operations
val = np.float64(3.0)
result = val - self.zbseries
assert_sp_series_equal(result, 3 - self.zbseries)
def test_binary_operators(self):
def _check_inplace_op(op):
tmp = self.bseries.copy()
self.assertRaises(NotImplementedError, op, tmp, self.bseries)
inplace_ops = ["iadd", "isub", "imul", "itruediv", "ifloordiv", "ipow"]
for op in inplace_ops:
_check_inplace_op(getattr(operator, op))
def test_reindex(self):
def _compare_with_series(sps, new_index):
spsre = sps.reindex(new_index)
series = sps.to_dense()
seriesre = series.reindex(new_index)
seriesre = seriesre.to_sparse(fill_value=sps.fill_value)
assert_sp_series_equal(spsre, seriesre)
assert_series_equal(spsre.to_dense(), seriesre.to_dense())
_compare_with_series(self.bseries, self.bseries.index[::2])
_compare_with_series(self.bseries, list(self.bseries.index[::2]))
_compare_with_series(self.bseries, self.bseries.index[:10])
_compare_with_series(self.bseries, self.bseries.index[5:])
_compare_with_series(self.zbseries, self.zbseries.index[::2])
_compare_with_series(self.zbseries, self.zbseries.index[:10])
_compare_with_series(self.zbseries, self.zbseries.index[5:])
# special cases
same_index = self.bseries.reindex(self.bseries.index)
assert_sp_series_equal(self.bseries, same_index)
self.assert_(same_index is not self.bseries)
# corner cases
sp = SparseSeries([], index=[])
sp_zero = SparseSeries([], index=[], fill_value=0)
_compare_with_series(sp, np.arange(10))
# with copy=False
reindexed = self.bseries.reindex(self.bseries.index, copy=True)
reindexed.sp_values[:] = 1.0
self.assert_((self.bseries.sp_values != 1.0).all())
reindexed = self.bseries.reindex(self.bseries.index, copy=False)
reindexed.sp_values[:] = 1.0
self.assert_((self.bseries.sp_values == 1.0).all())
def test_sparse_reindex(self):
length = 10
def _check(values, index1, index2, fill_value):
first_series = SparseSeries(values, sparse_index=index1, fill_value=fill_value)
reindexed = first_series.sparse_reindex(index2)
self.assert_(reindexed.sp_index is index2)
int_indices1 = index1.to_int_index().indices
int_indices2 = index2.to_int_index().indices
expected = Series(values, index=int_indices1)
expected = expected.reindex(int_indices2).fillna(fill_value)
assert_almost_equal(expected.values, reindexed.sp_values)
# make sure level argument asserts
expected = expected.reindex(int_indices2).fillna(fill_value)
def _check_with_fill_value(values, first, second, fill_value=nan):
i_index1 = IntIndex(length, first)
i_index2 = IntIndex(length, second)
b_index1 = i_index1.to_block_index()
b_index2 = i_index2.to_block_index()
_check(values, i_index1, i_index2, fill_value)
_check(values, b_index1, b_index2, fill_value)
def _check_all(values, first, second):
_check_with_fill_value(values, first, second, fill_value=nan)
_check_with_fill_value(values, first, second, fill_value=0)
index1 = [2, 4, 5, 6, 8, 9]
values1 = np.arange(6.0)
_check_all(values1, index1, [2, 4, 5])
_check_all(values1, index1, [2, 3, 4, 5, 6, 7, 8, 9])
_check_all(values1, index1, [0, 1])
_check_all(values1, index1, [0, 1, 7, 8, 9])
_check_all(values1, index1, [])
def test_repr(self):
bsrepr = repr(self.bseries)
isrepr = repr(self.iseries)
def test_iter(self):
pass
def test_truncate(self):
pass
def test_fillna(self):
pass
def test_groupby(self):
pass
def test_reductions(self):
def _compare_with_dense(obj, op):
sparse_result = getattr(obj, op)()
series = obj.to_dense()
dense_result = getattr(series, op)()
self.assertEquals(sparse_result, dense_result)
to_compare = ["count", "sum", "mean", "std", "var", "skew"]
def _compare_all(obj):
for op in to_compare:
_compare_with_dense(obj, op)
_compare_all(self.bseries)
self.bseries.sp_values[5:10] = np.NaN
_compare_all(self.bseries)
_compare_all(self.zbseries)
self.zbseries.sp_values[5:10] = np.NaN
_compare_all(self.zbseries)
series = self.zbseries.copy()
series.fill_value = 2
_compare_all(series)
def test_dropna(self):
sp = SparseSeries([0, 0, 0, nan, nan, 5, 6], fill_value=0)
sp_valid = sp.valid()
assert_almost_equal(sp_valid.values, sp.to_dense().valid().values)
self.assert_(sp_valid.index.equals(sp.to_dense().valid().index))
self.assertEquals(len(sp_valid.sp_values), 2)
result = self.bseries.dropna()
expected = self.bseries.to_dense().dropna()
self.assert_(not isinstance(result, SparseSeries))
tm.assert_series_equal(result, expected)
def test_homogenize(self):
def _check_matches(indices, expected):
data = {}
for i, idx in enumerate(indices):
data[i] = SparseSeries(idx.to_int_index().indices, sparse_index=idx)
homogenized = spf.homogenize(data)
for k, v in homogenized.iteritems():
assert v.sp_index.equals(expected)
indices1 = [BlockIndex(10, [2], [7]), BlockIndex(10, [1, 6], [3, 4]), BlockIndex(10, [0], [10])]
expected1 = BlockIndex(10, [2, 6], [2, 3])
_check_matches(indices1, expected1)
indices2 = [BlockIndex(10, [2], [7]), BlockIndex(10, [2], [7])]
expected2 = indices2[0]
_check_matches(indices2, expected2)
# must have NaN fill value
data = {"a": SparseSeries(np.arange(7), sparse_index=expected2, fill_value=0)}
nose.tools.assert_raises(Exception, spf.homogenize, data)
def test_fill_value_corner(self):
cop = self.zbseries.copy()
cop.fill_value = 0
result = self.bseries / cop
self.assert_(np.isnan(result.fill_value))
cop2 = self.zbseries.copy()
cop2.fill_value = 1
result = cop2 / cop
self.assert_(np.isnan(result.fill_value))
def test_shift(self):
series = SparseSeries([nan, 1.0, 2.0, 3.0, nan, nan], index=np.arange(6))
shifted = series.shift(0)
self.assert_(shifted is not series)
assert_sp_series_equal(shifted, series)
f = lambda s: s.shift(1)
_dense_series_compare(series, f)
f = lambda s: s.shift(-2)
_dense_series_compare(series, f)
series = SparseSeries([nan, 1.0, 2.0, 3.0, nan, nan], index=DateRange("1/1/2000", periods=6))
f = lambda s: s.shift(2, timeRule="WEEKDAY")
_dense_series_compare(series, f)
f = lambda s: s.shift(2, offset=datetools.bday)
_dense_series_compare(series, f)
def test_cumsum(self):
result = self.bseries.cumsum()
expected = self.bseries.to_dense().cumsum()
self.assert_(isinstance(result, SparseSeries))
self.assertEquals(result.name, self.bseries.name)
assert_series_equal(result.to_dense(), expected)
result = self.zbseries.cumsum()
expected = self.zbseries.to_dense().cumsum()
self.assert_(isinstance(result, Series))
assert_series_equal(result, expected)
def test_combine_first(self):
s = self.bseries
result = s[::2].combine_first(s)
result2 = s[::2].combine_first(s.to_dense())
expected = s[::2].to_dense().combine_first(s.to_dense())
expected = expected.to_sparse(fill_value=s.fill_value)
assert_sp_series_equal(result, result2)
assert_sp_series_equal(result, expected)
def test_from_coo_nodense_index(self):
ss = SparseSeries.from_coo(self.coo_matrices[0], dense_index=False)
check = self.sparse_series[2]
check = check.dropna().to_sparse()
tm.assert_sp_series_equal(ss, check)
def test_from_coo_dense_index(self):
ss = SparseSeries.from_coo(self.coo_matrices[0], dense_index=True)
check = self.sparse_series[2]
tm.assert_sp_series_equal(ss, check)