Python pandas.util.testing.assert_sp_frame_equal() Examples
The following are 30
code examples of pandas.util.testing.assert_sp_frame_equal().
You can vote up the ones you like or vote down the ones you don't like,
and go to the original project or source file by following the links above each example.
You may also want to check out all available functions/classes of the module
pandas.util.testing
, or try the search function
.
.
Example #1
| Source File: test_indexing.py From vnpy_crypto with MIT License | 6 votes |
|
def test_take_fill_value(self):
orig = pd.DataFrame([[1, np.nan, 0],
[2, 3, np.nan],
[0, np.nan, 4],
[0, np.nan, 5]],
columns=list('xyz'))
sparse = orig.to_sparse(fill_value=0)
exp = orig.take([0]).to_sparse(fill_value=0)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(sparse.take([0]), exp)
exp = orig.take([0, 1]).to_sparse(fill_value=0)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(sparse.take([0, 1]), exp)
exp = orig.take([-1, -2]).to_sparse(fill_value=0)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(sparse.take([-1, -2]), exp)
Example #2
| Source File: test_indexing.py From recruit with Apache License 2.0 | 6 votes |
|
def test_reindex(self):
orig = pd.DataFrame([[1, np.nan, 0],
[2, 3, np.nan],
[0, np.nan, 4],
[0, np.nan, 5]],
index=list('ABCD'), columns=list('xyz'))
sparse = orig.to_sparse()
res = sparse.reindex(['A', 'C', 'B'])
exp = orig.reindex(['A', 'C', 'B']).to_sparse()
tm.assert_sp_frame_equal(res, exp)
orig = pd.DataFrame([[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan]],
index=list('ABCD'), columns=list('xyz'))
sparse = orig.to_sparse()
res = sparse.reindex(['A', 'C', 'B'])
exp = orig.reindex(['A', 'C', 'B']).to_sparse()
tm.assert_sp_frame_equal(res, exp)
Example #3
| Source File: test_indexing.py From recruit with Apache License 2.0 | 6 votes |
|
def test_take_fill_value(self):
orig = pd.DataFrame([[1, np.nan, 0],
[2, 3, np.nan],
[0, np.nan, 4],
[0, np.nan, 5]],
columns=list('xyz'))
sparse = orig.to_sparse(fill_value=0)
exp = orig.take([0]).to_sparse(fill_value=0)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(sparse.take([0]), exp)
exp = orig.take([0, 1]).to_sparse(fill_value=0)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(sparse.take([0, 1]), exp)
exp = orig.take([-1, -2]).to_sparse(fill_value=0)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(sparse.take([-1, -2]), exp)
Example #4
| Source File: test_indexing.py From vnpy_crypto with MIT License | 6 votes |
|
def test_reindex(self):
orig = pd.DataFrame([[1, np.nan, 0],
[2, 3, np.nan],
[0, np.nan, 4],
[0, np.nan, 5]],
index=list('ABCD'), columns=list('xyz'))
sparse = orig.to_sparse()
res = sparse.reindex(['A', 'C', 'B'])
exp = orig.reindex(['A', 'C', 'B']).to_sparse()
tm.assert_sp_frame_equal(res, exp)
orig = pd.DataFrame([[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan]],
index=list('ABCD'), columns=list('xyz'))
sparse = orig.to_sparse()
res = sparse.reindex(['A', 'C', 'B'])
exp = orig.reindex(['A', 'C', 'B']).to_sparse()
tm.assert_sp_frame_equal(res, exp)
Example #5
| Source File: test_series.py From vnpy_crypto with MIT License | 6 votes |
|
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)
Example #6
| Source File: test_subclass.py From recruit with Apache License 2.0 | 6 votes |
|
def test_subclass_sparse_slice(self):
rows = [[1.0, 2.0, 3.0], [4.0, 5.0, 6.0], [7.0, 8.0, 9.0]]
ssdf = tm.SubclassedSparseDataFrame(rows)
ssdf.testattr = "testattr"
tm.assert_sp_frame_equal(ssdf.loc[:2],
tm.SubclassedSparseDataFrame(rows[:3]))
tm.assert_sp_frame_equal(ssdf.iloc[:2],
tm.SubclassedSparseDataFrame(rows[:2]))
tm.assert_sp_frame_equal(ssdf[:2],
tm.SubclassedSparseDataFrame(rows[:2]))
assert ssdf.loc[:2].testattr == "testattr"
assert ssdf.iloc[:2].testattr == "testattr"
assert ssdf[:2].testattr == "testattr"
tm.assert_sp_series_equal(ssdf.loc[1],
tm.SubclassedSparseSeries(rows[1]),
check_names=False,
check_kind=False)
tm.assert_sp_series_equal(ssdf.iloc[1],
tm.SubclassedSparseSeries(rows[1]),
check_names=False,
check_kind=False)
Example #7
| Source File: test_indexing.py From vnpy_crypto with MIT License | 6 votes |
|
def test_getitem(self):
orig = pd.DataFrame([[1, np.nan, np.nan],
[2, 3, np.nan],
[np.nan, np.nan, 4],
[0, np.nan, 5]],
columns=list('xyz'))
sparse = orig.to_sparse()
tm.assert_sp_series_equal(sparse['x'], orig['x'].to_sparse())
tm.assert_sp_frame_equal(sparse[['x']], orig[['x']].to_sparse())
tm.assert_sp_frame_equal(sparse[['z', 'x']],
orig[['z', 'x']].to_sparse())
tm.assert_sp_frame_equal(sparse[[True, False, True, True]],
orig[[True, False, True, True]].to_sparse())
tm.assert_sp_frame_equal(sparse.iloc[[1, 2]],
orig.iloc[[1, 2]].to_sparse())
Example #8
| Source File: test_series.py From recruit with Apache License 2.0 | 6 votes |
|
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)
Example #9
| Source File: test_subclass.py From recruit with Apache License 2.0 | 6 votes |
|
def test_subclass_sparse_to_frame(self):
s = tm.SubclassedSparseSeries([1, 2], index=list('ab'), name='xxx')
res = s.to_frame()
exp_arr = pd.SparseArray([1, 2], dtype=np.int64, kind='block',
fill_value=0)
exp = tm.SubclassedSparseDataFrame({'xxx': exp_arr},
index=list('ab'),
default_fill_value=0)
tm.assert_sp_frame_equal(res, exp)
# create from int dict
res = tm.SubclassedSparseDataFrame({'xxx': [1, 2]},
index=list('ab'),
default_fill_value=0)
tm.assert_sp_frame_equal(res, exp)
s = tm.SubclassedSparseSeries([1.1, 2.1], index=list('ab'),
name='xxx')
res = s.to_frame()
exp = tm.SubclassedSparseDataFrame({'xxx': [1.1, 2.1]},
index=list('ab'))
tm.assert_sp_frame_equal(res, exp)
Example #10
| Source File: test_to_from_scipy.py From recruit with Apache License 2.0 | 6 votes |
|
def test_from_scipy_correct_ordering(spmatrix):
# GH 16179
arr = np.arange(1, 5).reshape(2, 2)
try:
spm = spmatrix(arr)
assert spm.dtype == arr.dtype
except (TypeError, AssertionError):
# If conversion to sparse fails for this spmatrix type and arr.dtype,
# then the combination is not currently supported in NumPy, so we
# can just skip testing it thoroughly
return
sdf = SparseDataFrame(spm)
expected = SparseDataFrame(arr)
tm.assert_sp_frame_equal(sdf, expected)
tm.assert_frame_equal(sdf.to_dense(), expected.to_dense())
Example #11
| Source File: test_frame.py From recruit with Apache License 2.0 | 6 votes |
|
def test_constructor_ndarray(self, float_frame):
# no index or columns
sp = SparseDataFrame(float_frame.values)
# 1d
sp = SparseDataFrame(float_frame['A'].values, index=float_frame.index,
columns=['A'])
tm.assert_sp_frame_equal(sp, float_frame.reindex(columns=['A']))
# raise on level argument
pytest.raises(TypeError, float_frame.reindex, columns=['A'],
level=1)
# wrong length index / columns
with pytest.raises(ValueError, match="^Index length"):
SparseDataFrame(float_frame.values, index=float_frame.index[:-1])
with pytest.raises(ValueError, match="^Column length"):
SparseDataFrame(float_frame.values,
columns=float_frame.columns[:-1])
# GH 9272
Example #12
| Source File: test_frame.py From recruit with Apache License 2.0 | 6 votes |
|
def test_notna(self):
# GH 8276
df = pd.SparseDataFrame({'A': [np.nan, np.nan, 1, 2, np.nan],
'B': [0, np.nan, np.nan, 2, np.nan]})
res = df.notna()
exp = pd.SparseDataFrame({'A': [False, False, True, True, False],
'B': [True, False, False, True, False]},
default_fill_value=False)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(res, exp)
# if fill_value is not nan, True can be included in sp_values
df = pd.SparseDataFrame({'A': [0, 0, 1, 2, np.nan],
'B': [0, np.nan, 0, 2, np.nan]},
default_fill_value=0.)
res = df.notna()
assert isinstance(res, pd.SparseDataFrame)
exp = pd.DataFrame({'A': [True, True, True, True, False],
'B': [True, False, True, True, False]})
tm.assert_frame_equal(res.to_dense(), exp)
Example #13
| Source File: test_frame.py From recruit with Apache License 2.0 | 6 votes |
|
def test_isna(self):
# GH 8276
df = pd.SparseDataFrame({'A': [np.nan, np.nan, 1, 2, np.nan],
'B': [0, np.nan, np.nan, 2, np.nan]})
res = df.isna()
exp = pd.SparseDataFrame({'A': [True, True, False, False, True],
'B': [False, True, True, False, True]},
default_fill_value=True)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(res, exp)
# if fill_value is not nan, True can be included in sp_values
df = pd.SparseDataFrame({'A': [0, 0, 1, 2, np.nan],
'B': [0, np.nan, 0, 2, np.nan]},
default_fill_value=0.)
res = df.isna()
assert isinstance(res, pd.SparseDataFrame)
exp = pd.DataFrame({'A': [False, False, False, False, True],
'B': [False, True, False, False, True]})
tm.assert_frame_equal(res.to_dense(), exp)
Example #14
| Source File: test_frame.py From recruit with Apache License 2.0 | 6 votes |
|
def test_astype_bool(self):
sparse = pd.SparseDataFrame({'A': SparseArray([0, 2, 0, 4],
fill_value=0,
dtype=np.int64),
'B': SparseArray([0, 5, 0, 7],
fill_value=0,
dtype=np.int64)},
default_fill_value=0)
assert sparse['A'].dtype == SparseDtype(np.int64)
assert sparse['B'].dtype == SparseDtype(np.int64)
res = sparse.astype(SparseDtype(bool, False))
exp = pd.SparseDataFrame({'A': SparseArray([False, True, False, True],
dtype=np.bool,
fill_value=False,
kind='integer'),
'B': SparseArray([False, True, False, True],
dtype=np.bool,
fill_value=False,
kind='integer')},
default_fill_value=False)
tm.assert_sp_frame_equal(res, exp)
assert res['A'].dtype == SparseDtype(np.bool)
assert res['B'].dtype == SparseDtype(np.bool)
Example #15
| Source File: test_frame.py From recruit with Apache License 2.0 | 6 votes |
|
def test_transpose(self, float_frame, float_frame_int_kind,
float_frame_dense,
float_frame_fill0, float_frame_fill0_dense,
float_frame_fill2, float_frame_fill2_dense):
def _check(frame, orig):
transposed = frame.T
untransposed = transposed.T
tm.assert_sp_frame_equal(frame, untransposed)
tm.assert_frame_equal(frame.T.to_dense(), orig.T)
tm.assert_frame_equal(frame.T.T.to_dense(), orig.T.T)
tm.assert_sp_frame_equal(frame, frame.T.T, exact_indices=False)
_check(float_frame, float_frame_dense)
_check(float_frame_int_kind, float_frame_dense)
_check(float_frame_fill0, float_frame_fill0_dense)
_check(float_frame_fill2, float_frame_fill2_dense)
Example #16
| Source File: test_indexing.py From recruit with Apache License 2.0 | 6 votes |
|
def test_getitem(self):
orig = pd.DataFrame([[1, np.nan, np.nan],
[2, 3, np.nan],
[np.nan, np.nan, 4],
[0, np.nan, 5]],
columns=list('xyz'))
sparse = orig.to_sparse()
tm.assert_sp_series_equal(sparse['x'], orig['x'].to_sparse())
tm.assert_sp_frame_equal(sparse[['x']], orig[['x']].to_sparse())
tm.assert_sp_frame_equal(sparse[['z', 'x']],
orig[['z', 'x']].to_sparse())
tm.assert_sp_frame_equal(sparse[[True, False, True, True]],
orig[[True, False, True, True]].to_sparse())
tm.assert_sp_frame_equal(sparse.iloc[[1, 2]],
orig.iloc[[1, 2]].to_sparse())
Example #17
| Source File: test_indexing.py From vnpy_crypto with MIT License | 5 votes |
|
def test_reindex_fill_value(self):
orig = pd.DataFrame([[1, np.nan, 0],
[2, 3, np.nan],
[0, np.nan, 4],
[0, np.nan, 5]],
index=list('ABCD'), columns=list('xyz'))
sparse = orig.to_sparse(fill_value=0)
res = sparse.reindex(['A', 'C', 'B'])
exp = orig.reindex(['A', 'C', 'B']).to_sparse(fill_value=0)
tm.assert_sp_frame_equal(res, exp)
# all missing
orig = pd.DataFrame([[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan],
[np.nan, np.nan, np.nan]],
index=list('ABCD'), columns=list('xyz'))
sparse = orig.to_sparse(fill_value=0)
res = sparse.reindex(['A', 'C', 'B'])
exp = orig.reindex(['A', 'C', 'B']).to_sparse(fill_value=0)
tm.assert_sp_frame_equal(res, exp)
# all fill_value
orig = pd.DataFrame([[0, 0, 0],
[0, 0, 0],
[0, 0, 0],
[0, 0, 0]],
index=list('ABCD'), columns=list('xyz'))
sparse = orig.to_sparse(fill_value=0)
res = sparse.reindex(['A', 'C', 'B'])
exp = orig.reindex(['A', 'C', 'B']).to_sparse(fill_value=0)
tm.assert_sp_frame_equal(res, exp)
Example #18
| Source File: test_indexing.py From vnpy_crypto with MIT License | 5 votes |
|
def test_loc_slice(self):
orig = pd.DataFrame([[1, np.nan, np.nan],
[2, 3, np.nan],
[np.nan, np.nan, 4]],
columns=list('xyz'))
sparse = orig.to_sparse()
tm.assert_sp_frame_equal(sparse.loc[2:], orig.loc[2:].to_sparse())
Example #19
| Source File: test_frame.py From recruit with Apache License 2.0 | 5 votes |
|
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
Example #20
| Source File: test_frame.py From recruit with Apache License 2.0 | 5 votes |
|
def test_numpy_cumsum(self, float_frame):
result = np.cumsum(float_frame)
expected = SparseDataFrame(float_frame.to_dense().cumsum())
tm.assert_sp_frame_equal(result, expected)
msg = "the 'dtype' parameter is not supported"
with pytest.raises(ValueError, match=msg):
np.cumsum(float_frame, dtype=np.int64)
msg = "the 'out' parameter is not supported"
with pytest.raises(ValueError, match=msg):
np.cumsum(float_frame, out=result)
Example #21
| Source File: test_frame.py From recruit with Apache License 2.0 | 5 votes |
|
def test_cumsum(self, float_frame):
expected = SparseDataFrame(float_frame.to_dense().cumsum())
result = float_frame.cumsum()
tm.assert_sp_frame_equal(result, expected)
result = float_frame.cumsum(axis=None)
tm.assert_sp_frame_equal(result, expected)
result = float_frame.cumsum(axis=0)
tm.assert_sp_frame_equal(result, expected)
Example #22
| Source File: test_frame.py From recruit with Apache License 2.0 | 5 votes |
|
def test_numeric_op_scalar(self):
df = pd.DataFrame({'A': [nan, nan, 0, 1, ],
'B': [0, 1, 2, nan],
'C': [1., 2., 3., 4.],
'D': [nan, nan, nan, nan]})
sparse = df.to_sparse()
tm.assert_sp_frame_equal(sparse + 1, (df + 1).to_sparse())
Example #23
| Source File: test_combine_concat.py From vnpy_crypto with MIT License | 5 votes |
|
def test_concat_axis1(self):
val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
val2 = np.array([3, np.nan, 4, 0, 0])
sparse1 = pd.SparseSeries(val1, name='x')
sparse2 = pd.SparseSeries(val2, name='y')
res = pd.concat([sparse1, sparse2], axis=1)
exp = pd.concat([pd.Series(val1, name='x'),
pd.Series(val2, name='y')], axis=1)
exp = pd.SparseDataFrame(exp)
tm.assert_sp_frame_equal(res, exp)
Example #24
| Source File: test_combine_concat.py From vnpy_crypto with MIT License | 5 votes |
|
def test_concat_different_fill_value(self):
# 1st fill_value will be used
sparse = self.dense1.to_sparse()
sparse2 = self.dense2.to_sparse(fill_value=0)
res = pd.concat([sparse, sparse2])
exp = pd.concat([self.dense1, self.dense2]).to_sparse()
tm.assert_sp_frame_equal(res, exp)
res = pd.concat([sparse2, sparse])
exp = pd.concat([self.dense2, self.dense1]).to_sparse(fill_value=0)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(res, exp)
Example #25
| Source File: test_frame.py From recruit with Apache License 2.0 | 5 votes |
|
def test_combine_first_with_dense(self):
# We could support this if we allow
# pd.core.dtypes.cast.find_common_type to special case SparseDtype
# but I don't think that's worth it.
df = self.frame
result = df[::2].combine_first(df.to_dense())
expected = df[::2].to_dense().combine_first(df.to_dense())
expected = expected.to_sparse(fill_value=df.default_fill_value)
tm.assert_sp_frame_equal(result, expected)
Example #26
| Source File: test_frame.py From recruit with Apache License 2.0 | 5 votes |
|
def test_combine_first(self, float_frame):
df = float_frame
result = df[::2].combine_first(df)
expected = df[::2].to_dense().combine_first(df.to_dense())
expected = expected.to_sparse(fill_value=df.default_fill_value)
tm.assert_sp_frame_equal(result, expected)
Example #27
| Source File: test_combine_concat.py From vnpy_crypto with MIT License | 5 votes |
|
def test_concat_series(self):
# fill_value = np.nan
sparse = self.dense1.to_sparse()
sparse2 = self.dense2.to_sparse()
for col in ['A', 'D']:
res = pd.concat([sparse, sparse2[col]])
exp = pd.concat([self.dense1, self.dense2[col]]).to_sparse()
tm.assert_sp_frame_equal(res, exp)
res = pd.concat([sparse2[col], sparse])
exp = pd.concat([self.dense2[col], self.dense1]).to_sparse()
tm.assert_sp_frame_equal(res, exp)
# fill_value = 0
sparse = self.dense1.to_sparse(fill_value=0)
sparse2 = self.dense2.to_sparse(fill_value=0)
for col in ['C', 'D']:
res = pd.concat([sparse, sparse2[col]])
exp = pd.concat([self.dense1,
self.dense2[col]]).to_sparse(fill_value=0)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(res, exp)
res = pd.concat([sparse2[col], sparse])
exp = pd.concat([self.dense2[col],
self.dense1]).to_sparse(fill_value=0)
exp._default_fill_value = np.nan
tm.assert_sp_frame_equal(res, exp)
Example #28
| Source File: test_frame.py From recruit with Apache License 2.0 | 5 votes |
|
def test_numpy_transpose(self):
sdf = SparseDataFrame([1, 2, 3], index=[1, 2, 3], columns=['a'])
result = np.transpose(np.transpose(sdf))
tm.assert_sp_frame_equal(result, sdf)
msg = "the 'axes' parameter is not supported"
with pytest.raises(ValueError, match=msg):
np.transpose(sdf, axes=1)
Example #29
| Source File: test_series.py From vnpy_crypto with MIT License | 5 votes |
|
def test_concat_axis1(self):
val1 = np.array([1, 2, np.nan, np.nan, 0, np.nan])
val2 = np.array([3, np.nan, 4, 0, 0])
sparse1 = pd.SparseSeries(val1, name='x')
sparse2 = pd.SparseSeries(val2, name='y')
res = pd.concat([sparse1, sparse2], axis=1)
exp = pd.concat([pd.Series(val1, name='x'),
pd.Series(val2, name='y')], axis=1)
exp = pd.SparseDataFrame(exp)
tm.assert_sp_frame_equal(res, exp)
Example #30
| Source File: test_format.py From vnpy_crypto with MIT License | 5 votes |
|
def test_sparse_repr_after_set(self):
# GH 15488
sdf = pd.SparseDataFrame([[np.nan, 1], [2, np.nan]])
res = sdf.copy()
# Ignore the warning
with pd.option_context('mode.chained_assignment', None):
sdf[0][1] = 2 # This line triggers the bug
repr(sdf)
tm.assert_sp_frame_equal(sdf, res)
