def unit_to_dtype(ds):
"""
>>> unit_to_dtype('int32')
dtype('int32')
>>> unit_to_dtype('float64')
dtype('float64')
>>> unit_to_dtype('?int64')
dtype('float64')
>>> unit_to_dtype('string')
dtype('O')
>>> unit_to_dtype('?datetime')
dtype('<M8[us]')
"""
if isinstance(ds, str):
ds = dshape(ds)
if isinstance(ds, DataShape):
ds = ds.measure
if isinstance(ds, Option) and isscalar(ds) and isnumeric(ds):
return unit_to_dtype(str(ds).replace('int', 'float').replace('?', ''))
if isinstance(ds, Option) and isinstance(
ds.ty,
(type(date_), type(datetime_), type(string), type(timedelta_))):
ds = ds.ty
if ds == string:
return np.dtype('O')
return to_numpy_dtype(ds)
def unit_to_dtype(ds):
"""
>>> unit_to_dtype('int32')
dtype('int32')
>>> unit_to_dtype('float64')
dtype('float64')
>>> unit_to_dtype('?int64')
dtype('float64')
>>> unit_to_dtype('string')
dtype('O')
>>> unit_to_dtype('?datetime')
dtype('<M8[us]')
"""
if isinstance(ds, str):
ds = dshape(ds)
if isinstance(ds, DataShape):
ds = ds.measure
if isinstance(ds, Option) and isscalar(ds) and isnumeric(ds):
return unit_to_dtype(str(ds).replace('int', 'float').replace('?', ''))
if isinstance(ds, Option) and isinstance(ds.ty, (type(date_),
type(datetime_), type(string), type(timedelta_))):
ds = ds.ty
if ds == string:
return np.dtype('O')
return to_numpy_dtype(ds)
def unit_to_dtype(ds):
""" Convert a datashape Unit instance into a numpy dtype
Parameters
----------
ds : DataShape
The DataShape instance to convert
Returns
-------
np.dtype
Examples
--------
>>> unit_to_dtype('int32')
dtype('int32')
>>> unit_to_dtype('float64')
dtype('float64')
>>> unit_to_dtype('?int64')
dtype('float64')
>>> unit_to_dtype('string')
dtype('O')
>>> unit_to_dtype('?datetime')
dtype('<M8[us]')
"""
if isinstance(ds, str):
ds = dshape(ds)
if isinstance(ds, DataShape):
ds = ds.measure
if isinstance(ds, Option) and isscalar(ds) and isnumeric(ds):
if isinstance(ds.ty, Decimal):
str_np_dtype = str(ds.ty.to_numpy_dtype()).replace('int', 'float')
if str_np_dtype == 'float8': # not a valid dtype, so increase
str_np_dtype = 'float16'
return unit_to_dtype(str_np_dtype)
return unit_to_dtype(str(ds).replace('int', 'float').replace('?', ''))
if isinstance(ds, Option) and isinstance(
ds.ty, (Date, DateTime, String, TimeDelta)
):
ds = ds.ty
if ds == string:
return np.dtype('O')
return to_numpy_dtype(ds)
def unit_to_dtype(ds):
"""
>>> unit_to_dtype('int32')
dtype('int32')
>>> unit_to_dtype('float64')
dtype('float64')
>>> unit_to_dtype('?int64')
dtype('float64')
>>> unit_to_dtype('string')
dtype('O')
"""
if isinstance(ds, str):
ds = dshape(ds)[0]
if isinstance(ds, Option) and isscalar(ds) and isnumeric(ds):
return unit_to_dtype(str(ds).replace('int', 'float').replace('?', ''))
if isinstance(ds, Option) and ds.ty in (date_, datetime_, string):
ds = ds.ty
return to_numpy_dtype(ds)
def unit_to_dtype(ds):
"""
>>> unit_to_dtype('int32')
dtype('int32')
>>> unit_to_dtype('float64')
dtype('float64')
>>> unit_to_dtype('?int64')
dtype('float64')
>>> unit_to_dtype('string')
dtype('O')
"""
if isinstance(ds, str):
ds = dshape(ds)[0]
if isinstance(ds, Option) and isscalar(ds) and isnumeric(ds):
return unit_to_dtype(str(ds).replace('int', 'float').replace('?', ''))
if isinstance(ds, Option) and ds.ty in (date_, datetime_, string):
ds = ds.ty
return to_numpy_dtype(ds)
""" Vector norm
See np.linalg.norm
"""
if ord is None or ord == 'fro':
ord = 2
if ord == inf:
return max(abs(expr), axis=axis, keepdims=keepdims)
elif ord == -inf:
return min(abs(expr), axis=axis, keepdims=keepdims)
elif ord == 1:
return sum(abs(expr), axis=axis, keepdims=keepdims)
elif ord % 2 == 0:
return sum(expr**ord, axis=axis, keepdims=keepdims)**(1.0 / ord)
return sum(abs(expr)**ord, axis=axis, keepdims=keepdims)**(1.0 / ord)
dshape_method_list.extend([
(iscollection, set([count, nelements])),
(lambda ds:
(iscollection(ds) and
(isstring(ds) or isnumeric(ds) or isboolean(ds) or isdatelike(ds))),
set([min, max])),
(lambda ds: len(ds.shape) == 1, set([nrows, nunique])),
(lambda ds: iscollection(ds) and isboolean(ds), set([any, all])),
(lambda ds: iscollection(ds) and (isnumeric(ds) or isboolean(ds)),
set([mean, sum, std, var, vnorm])),
])
method_properties.update([nrows])
See np.linalg.norm
"""
if ord is None or ord == 'fro':
ord = 2
if ord == inf:
return max(abs(expr), axis=axis, keepdims=keepdims)
elif ord == -inf:
return min(abs(expr), axis=axis, keepdims=keepdims)
elif ord == 1:
return sum(abs(expr), axis=axis, keepdims=keepdims)
elif ord % 2 == 0:
return sum(expr ** ord, axis=axis, keepdims=keepdims) ** (1.0 / ord)
return sum(abs(expr) ** ord, axis=axis, keepdims=keepdims) ** (1.0 / ord)
dshape_method_list.extend([
(iscollection, set([count, nelements])),
(lambda ds: (iscollection(ds) and
(isstring(ds) or isnumeric(ds) or isboolean(ds) or
isdatelike(ds) or isinstance(ds, TimeDelta))),
set([min, max])),
(lambda ds: len(ds.shape) == 1,
set([nrows, nunique])),
(lambda ds: iscollection(ds) and isboolean(ds),
set([any, all])),
(lambda ds: iscollection(ds) and (isnumeric(ds) or isboolean(ds)),
set([mean, sum, std, var, vnorm])),
])
method_properties.update([nrows])
else:
left, right = axes, axes
if isinstance(left, int):
left = (left, )
if isinstance(right, int):
right = (right, )
if isinstance(left, list):
left = tuple(left)
if isinstance(right, list):
right = tuple(right)
return TensorDot(lhs, rhs, left, right)
@copydoc(TensorDot)
def dot(lhs, rhs):
return tensordot(lhs, rhs)
from datashape.predicates import isnumeric, isboolean
from .expressions import dshape_method_list, method_properties
dshape_method_list.extend([
(lambda ds: ndim(ds) > 1, set([transpose])),
(lambda ds: ndim(ds) == 2, set([T])),
(lambda ds: ndim(ds) >= 1 and (isnumeric(ds) or isboolean(ds)), set([dot]))
])
method_properties.add(T)
child = children[0]
else:
child = common_subexpression(*children)
if axis is None:
axis = tuple(range(ndim(child)))
if isinstance(axis, (set, list)):
axis = tuple(axis)
if not isinstance(axis, tuple):
axis = (axis,)
return Summary(child, names, values, keepdims=keepdims, axis=axis)
summary.__doc__ = Summary.__doc__
from datashape.predicates import iscollection, isboolean, isnumeric
from .expressions import dshape_method_list, method_properties
dshape_method_list.extend([
(iscollection, set([count, min, max, nelements])),
(lambda ds: len(ds.shape) == 1,
set([nrows, nunique])),
(lambda ds: iscollection(ds) and isboolean(ds),
set([any, all, sum])),
(lambda ds: iscollection(ds) and isnumeric(ds),
set([mean, sum, mean, min, max, std, var])),
])
method_properties.update([nrows])
def test_time():
assert not isnumeric('time')
else:
left, right = axes, axes
if isinstance(left, int):
left = (left,)
if isinstance(right, int):
right = (right,)
if isinstance(left, list):
left = tuple(left)
if isinstance(right, list):
right = tuple(right)
return TensorDot(lhs, rhs, left, right)
tensordot.__doc__ = TensorDot.__doc__
def dot(lhs, rhs):
return tensordot(lhs, rhs)
from datashape.predicates import isnumeric, isboolean
from .expressions import dshape_method_list, method_properties
dshape_method_list.extend([
(lambda ds: ndim(ds) > 1, set([transpose])),
(lambda ds: ndim(ds) == 2, set([T])),
(lambda ds: ndim(ds) >= 1 and (isnumeric(ds) or isboolean(ds)), set([dot]))
])
method_properties.add(T)
""" Vector norm
See np.linalg.norm
"""
if ord is None or ord == 'fro':
ord = 2
if ord == inf:
return max(abs(expr), axis=axis, keepdims=keepdims)
elif ord == -inf:
return min(abs(expr), axis=axis, keepdims=keepdims)
elif ord == 1:
return sum(abs(expr), axis=axis, keepdims=keepdims)
elif ord % 2 == 0:
return sum(expr**ord, axis=axis, keepdims=keepdims)**(1. / ord)
else:
return sum(abs(expr)**ord, axis=axis, keepdims=keepdims)**(1. / ord)
from datashape.predicates import iscollection, isboolean, isnumeric
from .expressions import dshape_method_list, method_properties
dshape_method_list.extend([
(iscollection, set([count, min, max, nelements])),
(lambda ds: len(ds.shape) == 1, set([nrows, nunique])),
(lambda ds: iscollection(ds) and isboolean(ds), set([any, all, sum])),
(lambda ds: iscollection(ds) and isnumeric(ds),
set([mean, sum, mean, min, max, std, var, vnorm])),
])
method_properties.update([nrows])
