class TestSparseDataFrameAnalytics(object):
def setup_method(self, method):
self.data = {
'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, dtype=float),
'D': [0, 1, 2, 3, 4, 5, nan, nan, nan, nan]
}
self.dates = bdate_range('1/1/2011', periods=10)
self.frame = SparseDataFrame(self.data, index=self.dates)
def test_cumsum(self):
expected = SparseDataFrame(self.frame.to_dense().cumsum())
result = self.frame.cumsum()
tm.assert_sp_frame_equal(result, expected)
result = self.frame.cumsum(axis=None)
tm.assert_sp_frame_equal(result, expected)
result = self.frame.cumsum(axis=0)
tm.assert_sp_frame_equal(result, expected)
def test_numpy_cumsum(self):
result = np.cumsum(self.frame)
expected = SparseDataFrame(self.frame.to_dense().cumsum())
tm.assert_sp_frame_equal(result, expected)
msg = "the 'dtype' parameter is not supported"
tm.assert_raises_regex(ValueError,
msg,
np.cumsum,
self.frame,
dtype=np.int64)
msg = "the 'out' parameter is not supported"
tm.assert_raises_regex(ValueError,
msg,
np.cumsum,
self.frame,
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', 'min',
'max'
]
for func in funcs:
getattr(np, func)(self.frame)
class TestSparseDataFrameAnalytics(tm.TestCase):
def setUp(self):
self.data = {'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, dtype=float),
'D': [0, 1, 2, 3, 4, 5, nan, nan, nan, nan]}
self.dates = bdate_range('1/1/2011', periods=10)
self.frame = SparseDataFrame(self.data, index=self.dates)
def test_cumsum(self):
expected = SparseDataFrame(self.frame.to_dense().cumsum())
result = self.frame.cumsum()
tm.assert_sp_frame_equal(result, expected)
result = self.frame.cumsum(axis=None)
tm.assert_sp_frame_equal(result, expected)
result = self.frame.cumsum(axis=0)
tm.assert_sp_frame_equal(result, expected)
def test_numpy_cumsum(self):
result = np.cumsum(self.frame)
expected = SparseDataFrame(self.frame.to_dense().cumsum())
tm.assert_sp_frame_equal(result, expected)
msg = "the 'dtype' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.cumsum,
self.frame, dtype=np.int64)
msg = "the 'out' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.cumsum,
self.frame, 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', 'min', 'max']
for func in funcs:
getattr(np, func)(self.frame)
class TestSparseDataFrameAnalytics(object):
def setup_method(self, method):
self.data = {
'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, dtype=float),
'D': [0, 1, 2, 3, 4, 5, nan, nan, nan, nan]
}
self.dates = bdate_range('1/1/2011', periods=10)
self.frame = SparseDataFrame(self.data, index=self.dates)
def test_cumsum(self):
expected = SparseDataFrame(self.frame.to_dense().cumsum())
result = self.frame.cumsum()
tm.assert_sp_frame_equal(result, expected)
result = self.frame.cumsum(axis=None)
tm.assert_sp_frame_equal(result, expected)
result = self.frame.cumsum(axis=0)
tm.assert_sp_frame_equal(result, expected)
def test_numpy_cumsum(self):
result = np.cumsum(self.frame)
expected = SparseDataFrame(self.frame.to_dense().cumsum())
tm.assert_sp_frame_equal(result, expected)
msg = "the 'dtype' parameter is not supported"
tm.assert_raises_regex(ValueError,
msg,
np.cumsum,
self.frame,
dtype=np.int64)
msg = "the 'out' parameter is not supported"
tm.assert_raises_regex(ValueError,
msg,
np.cumsum,
self.frame,
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', 'min',
'max'
]
for func in funcs:
getattr(np, func)(self.frame)
@pytest.mark.xfail(reason='Wrong SparseBlock initialization ' '(GH 17386)')
def test_quantile(self):
# GH 17386
data = [[1, 1], [2, 10], [3, 100], [nan, nan]]
q = 0.1
sparse_df = SparseDataFrame(data)
result = sparse_df.quantile(q)
dense_df = DataFrame(data)
dense_expected = dense_df.quantile(q)
sparse_expected = SparseSeries(dense_expected)
tm.assert_series_equal(result, dense_expected)
tm.assert_sp_series_equal(result, sparse_expected)
@pytest.mark.xfail(reason='Wrong SparseBlock initialization ' '(GH 17386)')
def test_quantile_multi(self):
# GH 17386
data = [[1, 1], [2, 10], [3, 100], [nan, nan]]
q = [0.1, 0.5]
sparse_df = SparseDataFrame(data)
result = sparse_df.quantile(q)
dense_df = DataFrame(data)
dense_expected = dense_df.quantile(q)
sparse_expected = SparseDataFrame(dense_expected)
tm.assert_frame_equal(result, dense_expected)
tm.assert_sp_frame_equal(result, sparse_expected)
class TestSparseDataFrameAnalytics(object):
def setup_method(self, method):
self.data = {'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, dtype=float),
'D': [0, 1, 2, 3, 4, 5, nan, nan, nan, nan]}
self.dates = bdate_range('1/1/2011', periods=10)
self.frame = SparseDataFrame(self.data, index=self.dates)
def test_cumsum(self):
expected = SparseDataFrame(self.frame.to_dense().cumsum())
result = self.frame.cumsum()
tm.assert_sp_frame_equal(result, expected)
result = self.frame.cumsum(axis=None)
tm.assert_sp_frame_equal(result, expected)
result = self.frame.cumsum(axis=0)
tm.assert_sp_frame_equal(result, expected)
def test_numpy_cumsum(self):
result = np.cumsum(self.frame)
expected = SparseDataFrame(self.frame.to_dense().cumsum())
tm.assert_sp_frame_equal(result, expected)
msg = "the 'dtype' parameter is not supported"
tm.assert_raises_regex(ValueError, msg, np.cumsum,
self.frame, dtype=np.int64)
msg = "the 'out' parameter is not supported"
tm.assert_raises_regex(ValueError, msg, np.cumsum,
self.frame, 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', 'min', 'max']
for func in funcs:
getattr(np, func)(self.frame)
@pytest.mark.xfail(reason='Wrong SparseBlock initialization '
'(GH 17386)')
def test_quantile(self):
# GH 17386
data = [[1, 1], [2, 10], [3, 100], [nan, nan]]
q = 0.1
sparse_df = SparseDataFrame(data)
result = sparse_df.quantile(q)
dense_df = DataFrame(data)
dense_expected = dense_df.quantile(q)
sparse_expected = SparseSeries(dense_expected)
tm.assert_series_equal(result, dense_expected)
tm.assert_sp_series_equal(result, sparse_expected)
@pytest.mark.xfail(reason='Wrong SparseBlock initialization '
'(GH 17386)')
def test_quantile_multi(self):
# GH 17386
data = [[1, 1], [2, 10], [3, 100], [nan, nan]]
q = [0.1, 0.5]
sparse_df = SparseDataFrame(data)
result = sparse_df.quantile(q)
dense_df = DataFrame(data)
dense_expected = dense_df.quantile(q)
sparse_expected = SparseDataFrame(dense_expected)
tm.assert_frame_equal(result, dense_expected)
tm.assert_sp_frame_equal(result, sparse_expected)
def test_assign_with_sparse_frame(self):
# GH 19163
df = pd.DataFrame({"a": [1, 2, 3]})
res = df.to_sparse(fill_value=False).assign(newcol=False)
exp = df.assign(newcol=False).to_sparse(fill_value=False)
tm.assert_sp_frame_equal(res, exp)
for column in res.columns:
assert type(res[column]) is SparseSeries
