def indToSub(self, order='F', isOneBased=True, dims=None):
"""
Convert linear indexing to subscript indexing
Parameters
----------
dims : array-like, optional
Maximum dimensions. If not provided, will use dims property.
order : str, 'C' or 'F', default = 'F'
Specifies row-major or column-major array indexing. See numpy.unravel_index.
onebased : boolean, default = True
True if generated subscript indices are to start at 1, False to start at 0
"""
from thunder.rdds.keys import _indToSubConverter
if dims is None:
dims = self.dims.max
converter = _indToSubConverter(dims,
order=order,
isOneBased=isOneBased)
rdd = self.rdd.map(lambda (k, v): (converter(k), v))
return self._constructor(rdd, index=self._index).__finalize__(self)
def check_indtosubResult(indsubParam):
data = indsubParam.indices
converter = _indToSubConverter(dims=indsubParam.dims, order=indsubParam.order, isOneBased=indsubParam.onebased)
results = map(lambda x: converter(x), data)
for res, expected, index in zip(results, indsubParam.subscripts, indsubParam.indices):
assert_equals(expected, res, 'Got subscript %s instead of %s for index:%d, dims:%s' %
(res, expected, index, str(indsubParam.dims)))
def query(self, inds, var='inds', order='F', isOneBased=True):
"""
Extract records with indices matching those provided
Keys will be automatically linearized before matching to provided indices.
This will not affect
Parameters
----------
inds : str, or array-like (2D)
Array of indices, each an array-like of integer indices, or
filename of a MAT file containing a set of indices as a cell array
var : str, optional, default = 'inds'
Variable name if loading from a MAT file
order : str, optional, default = 'F'
Specify ordering for linearizing indices (see subtoind)
onebased : boolean, optional, default = True
Specify zero or one based indexing for linearizing (see subtoind)
Returns
-------
keys : array, shape (n, k) where k is the length of each value
Averaged values
values : array, shape (n, d) where d is the number of keys
Averaged keys
"""
if isinstance(inds, str):
inds = loadMatVar(inds, var)[0]
else:
inds = asarray(inds)
n = len(inds)
from thunder.rdds.keys import _indToSubConverter
converter = _indToSubConverter(dims=self.dims.max,
order=order,
isOneBased=isOneBased)
keys = zeros((n, len(self.dims.count)))
values = zeros((n, len(self.first()[1])))
data = self.subToInd(order=order, isOneBased=isOneBased)
for idx, indList in enumerate(inds):
if len(indList) > 0:
indsSet = set(asarray(indList).flat)
bcInds = self.rdd.context.broadcast(indsSet)
values[idx, :] = data.filterOnKeys(
lambda k: k in bcInds.value).values().mean()
keys[idx, :] = mean(map(lambda k: converter(k), indList),
axis=0)
return keys, values
def query(self, inds, var='inds', order='F', isOneBased=True):
"""
Extract records with indices matching those provided
Keys will be automatically linearized before matching to provided indices.
This will not affect
Parameters
----------
inds : str, or array-like (2D)
Array of indices, each an array-like of integer indices, or
filename of a MAT file containing a set of indices as a cell array
var : str, optional, default = 'inds'
Variable name if loading from a MAT file
order : str, optional, default = 'F'
Specify ordering for linearizing indices (see subtoind)
onebased : boolean, optional, default = True
Specify zero or one based indexing for linearizing (see subtoind)
Returns
-------
keys : array, shape (n, k) where k is the length of each value
Averaged values
values : array, shape (n, d) where d is the number of keys
Averaged keys
"""
if isinstance(inds, str):
inds = loadMatVar(inds, var)[0]
else:
inds = asarray(inds)
n = len(inds)
from thunder.rdds.keys import _indToSubConverter
converter = _indToSubConverter(dims=self.dims.max, order=order, isOneBased=isOneBased)
keys = zeros((n, len(self.dims.count)))
values = zeros((n, len(self.first()[1])))
data = self.subToInd(order=order, isOneBased=isOneBased)
for idx, indList in enumerate(inds):
if len(indList) > 0:
indsSet = set(asarray(indList).flat)
bcInds = self.rdd.context.broadcast(indsSet)
values[idx, :] = data.filterOnKeys(lambda k: k in bcInds.value).values().mean()
keys[idx, :] = mean(map(lambda k: converter(k), indList), axis=0)
return keys, values
def indToSub(self, order='F', isOneBased=True, dims=None):
"""
Convert linear indexing to subscript indexing
Parameters
----------
dims : array-like, optional
Maximum dimensions. If not provided, will use dims property.
order : str, 'C' or 'F', default = 'F'
Specifies row-major or column-major array indexing. See numpy.unravel_index.
onebased : boolean, default = True
True if generated subscript indices are to start at 1, False to start at 0
"""
from thunder.rdds.keys import _indToSubConverter
if dims is None:
dims = self.dims.max
converter = _indToSubConverter(dims, order=order, isOneBased=isOneBased)
rdd = self.rdd.map(lambda (k, v): (converter(k), v))
return self._constructor(rdd, index=self._index).__finalize__(self)
def test_ind_to_sub_array(self):
inds = range(1, 13)
converter = _indToSubConverter(dims=[2, 3, 2])
subs = map(lambda x: converter(x), inds)
assert(allclose(subs, array([(1, 1, 1), (2, 1, 1), (1, 2, 1), (2, 2, 1), (1, 3, 1), (2, 3, 1),
(1, 1, 2), (2, 1, 2), (1, 2, 2), (2, 2, 2), (1, 3, 2), (2, 3, 2)])))