def _simple_new(cls, data, sp_index, fill_value):
if not isinstance(sp_index, SparseIndex):
# caller must pass SparseIndex
raise ValueError('sp_index must be a SparseIndex')
if fill_value is None:
if sp_index.ngaps > 0:
# has missing hole
fill_value = np.nan
else:
fill_value = na_value_for_dtype(data.dtype)
if (is_integer_dtype(data) and is_float(fill_value)
and sp_index.ngaps > 0):
# if float fill_value is being included in dense repr,
# convert values to float
data = data.astype(float)
result = data.view(cls)
if not isinstance(sp_index, SparseIndex):
# caller must pass SparseIndex
raise ValueError('sp_index must be a SparseIndex')
result.sp_index = sp_index
result._fill_value = fill_value
return result
def _simple_new(cls, data, sp_index, fill_value):
if not isinstance(sp_index, SparseIndex):
# caller must pass SparseIndex
raise ValueError('sp_index must be a SparseIndex')
if fill_value is None:
if sp_index.ngaps > 0:
# has missing hole
fill_value = np.nan
else:
fill_value = na_value_for_dtype(data.dtype)
if (is_integer_dtype(data) and is_float(fill_value) and
sp_index.ngaps > 0):
# if float fill_value is being included in dense repr,
# convert values to float
data = data.astype(float)
result = data.view(cls)
if not isinstance(sp_index, SparseIndex):
# caller must pass SparseIndex
raise ValueError('sp_index must be a SparseIndex')
result.sp_index = sp_index
result._fill_value = fill_value
return result
def test_na_value_for_dtype():
for dtype in [np.dtype('M8[ns]'), np.dtype('m8[ns]'),
DatetimeTZDtype('datetime64[ns, US/Eastern]')]:
assert na_value_for_dtype(dtype) is NaT
for dtype in ['u1', 'u2', 'u4', 'u8',
'i1', 'i2', 'i4', 'i8']:
assert na_value_for_dtype(np.dtype(dtype)) == 0
for dtype in ['bool']:
assert na_value_for_dtype(np.dtype(dtype)) is False
for dtype in ['f2', 'f4', 'f8']:
assert np.isnan(na_value_for_dtype(np.dtype(dtype)))
for dtype in ['O']:
assert np.isnan(na_value_for_dtype(np.dtype(dtype)))
def test_na_value_for_dtype():
for dtype in [np.dtype('M8[ns]'), np.dtype('m8[ns]'),
DatetimeTZDtype('datetime64[ns, US/Eastern]')]:
assert na_value_for_dtype(dtype) is NaT
for dtype in ['u1', 'u2', 'u4', 'u8',
'i1', 'i2', 'i4', 'i8']:
assert na_value_for_dtype(np.dtype(dtype)) == 0
for dtype in ['bool']:
assert na_value_for_dtype(np.dtype(dtype)) is False
for dtype in ['f2', 'f4', 'f8']:
assert np.isnan(na_value_for_dtype(np.dtype(dtype)))
for dtype in ['O']:
assert np.isnan(na_value_for_dtype(np.dtype(dtype)))
def make_sparse(arr, kind='block', fill_value=None):
"""
Convert ndarray to sparse format
Parameters
----------
arr : ndarray
kind : {'block', 'integer'}
fill_value : NaN or another value
Returns
-------
(sparse_values, index) : (ndarray, SparseIndex)
"""
arr = _sanitize_values(arr)
if arr.ndim > 1:
raise TypeError("expected dimension <= 1 data")
if fill_value is None:
fill_value = na_value_for_dtype(arr.dtype)
if isnull(fill_value):
mask = notnull(arr)
else:
# For str arrays in NumPy 1.12.0, operator!= below isn't
# element-wise but just returns False if fill_value is not str,
# so cast to object comparison to be safe
if is_string_dtype(arr):
arr = arr.astype(object)
mask = arr != fill_value
length = len(arr)
if length != mask.size:
# the arr is a SparseArray
indices = mask.sp_index.indices
else:
indices = mask.nonzero()[0].astype(np.int32)
index = _make_index(length, indices, kind)
sparsified_values = arr[mask]
return sparsified_values, index, fill_value
def make_sparse(arr, kind='block', fill_value=None):
"""
Convert ndarray to sparse format
Parameters
----------
arr : ndarray
kind : {'block', 'integer'}
fill_value : NaN or another value
Returns
-------
(sparse_values, index) : (ndarray, SparseIndex)
"""
arr = _sanitize_values(arr)
if arr.ndim > 1:
raise TypeError("expected dimension <= 1 data")
if fill_value is None:
fill_value = na_value_for_dtype(arr.dtype)
if isnull(fill_value):
mask = notnull(arr)
else:
# For str arrays in NumPy 1.12.0, operator!= below isn't
# element-wise but just returns False if fill_value is not str,
# so cast to object comparison to be safe
if is_string_dtype(arr):
arr = arr.astype(object)
mask = arr != fill_value
length = len(arr)
if length != mask.size:
# the arr is a SparseArray
indices = mask.sp_index.indices
else:
indices = mask.nonzero()[0].astype(np.int32)
index = _make_index(length, indices, kind)
sparsified_values = arr[mask]
return sparsified_values, index, fill_value
def make_sparse(arr, kind='block', fill_value=None):
"""
Convert ndarray to sparse format
Parameters
----------
arr : ndarray
kind : {'block', 'integer'}
fill_value : NaN or another value
Returns
-------
(sparse_values, index) : (ndarray, SparseIndex)
"""
arr = _sanitize_values(arr)
if arr.ndim > 1:
raise TypeError("expected dimension <= 1 data")
if fill_value is None:
fill_value = na_value_for_dtype(arr.dtype)
if isnull(fill_value):
mask = notnull(arr)
else:
mask = arr != fill_value
length = len(arr)
if length != mask.size:
# the arr is a SparseArray
indices = mask.sp_index.indices
else:
indices = np.arange(length, dtype=np.int32)[mask]
index = _make_index(length, indices, kind)
sparsified_values = arr[mask]
return sparsified_values, index, fill_value
def make_sparse(arr, kind='block', fill_value=None):
"""
Convert ndarray to sparse format
Parameters
----------
arr : ndarray
kind : {'block', 'integer'}
fill_value : NaN or another value
Returns
-------
(sparse_values, index) : (ndarray, SparseIndex)
"""
arr = _sanitize_values(arr)
if arr.ndim > 1:
raise TypeError("expected dimension <= 1 data")
if fill_value is None:
fill_value = na_value_for_dtype(arr.dtype)
if isnull(fill_value):
mask = notnull(arr)
else:
mask = arr != fill_value
length = len(arr)
if length != mask.size:
# the arr is a SparseArray
indices = mask.sp_index.indices
else:
indices = np.arange(length, dtype=np.int32)[mask]
index = _make_index(length, indices, kind)
sparsified_values = arr[mask]
return sparsified_values, index, fill_value
