def unpack_distribution(self, p_dense, p_sparse=None):
"""
convenience routine to translate a distribution from a dense array
to a dictionary, using this state enumeration
"""
p_indices = numpy.arange(numpy.size(p_dense))
# convert from list of coordinate vectors to list of states
p_states = domain.to_iter(self.states(p_indices))
if p_sparse is None:
p_sparse = statistics.Distribution()
for index, state in itertools.izip(p_indices, p_states):
value = p_dense[index]
if value != 0.0:
p_sparse[state] = value
return p_sparse
def to_dense(self, shape, origin=None):
"""
Returns dense version of distribution for given array shape and origin
"""
if origin is None:
origin = (0, ) * len(shape)
states = set(domain.to_iter(domain.from_rect(shape, origin=origin)))
states &= set(self.iterkeys())
p_dense = numpy.zeros(shape, dtype=numpy.float)
origin = numpy.asarray(origin)
for state in states:
probability = self[state]
shifted_state = tuple(numpy.asarray(state) + origin)
p_dense[shifted_state] += probability
return p_dense
def to_dense(self, shape, origin=None):
"""
Returns dense version of distribution for given array shape and origin
"""
if origin is None:
origin = (0, )*len(shape)
states = set(domain.to_iter(domain.from_rect(shape, origin=origin)))
states &= set(self.iterkeys())
p_dense = numpy.zeros(shape, dtype=numpy.float)
origin = numpy.asarray(origin)
for state in states:
probability = self[state]
shifted_state = tuple(numpy.asarray(state) + origin)
p_dense[shifted_state] += probability
return p_dense
def map_distribution(f, p, g=None):
"""
map_distribution(f, p [, g]) -> mapping
Returns a copy of the mapping p, with each key replaced by its
image under f. Any duplicate image keys are merged, with the value of
the merged key equal to the sum of the values.
It is expected that f returns tuples or scalars, and behaves in a
reasonable way when given vector state array arguments.
If g is supplied, it is used instead of addition to reduce the values of
duplicate image keys. If given, g must have a reduce method of the form
g.reduce(probabilities) -> reduced_probability
for example, setting g to a numpy ufunc would be fine.
"""
# all this nonsense actually does something fairly straight forward
# see 'map_distribution_simple' for a reference implementation that
# avoids numpy operations
num_items = len(p)
if num_items == 0:
return {}
if g is None:
g = numpy.add
s, v = domain.from_mapping(p)
fs = numpy.asarray(f(s))
# handle case where f returns scalar arguments, say
# this might be a touch flakey
if len(fs.shape) != 2:
fs = fs * numpy.ones((1, s.shape[1]))
# sort image states using lexical ordering on coords, then
# apply same ordering to values
order = numpy.lexsort(fs)
sfs = fs[:, order]
sv = v[order]
# figure out the indices of the first instance of each state
not_equal_adj = numpy.logical_or.reduce(sfs[:, :-1] != sfs[:, 1:])
not_equal_adj = numpy.concatenate(([True], not_equal_adj))
# extract the unique image states under f
usfs = sfs[:, not_equal_adj]
# convert back from arrya representation to iterator of state tuples
unique_image_states = domain.to_iter(usfs)
# determine start and end indices of each equivalence class of
# values in the sorted values array, where values are equivalent if
# they are associated with states that agree under the transform f
class_begin = numpy.nonzero(not_equal_adj)[0]
class_end = numpy.concatenate((class_begin[1:], [num_items]))
# construct the resulting mapped probability distribution
# each image state s maps to the values in its equivalence class,
# reduced by g
p_mapped = {}
for s, i, j in itertools.izip(unique_image_states, class_begin, class_end):
p_mapped[s] = g.reduce(sv[i:j])
return p_mapped
def map_distribution(f, p, g=None):
"""
map_distribution(f, p [, g]) -> mapping
Returns a copy of the mapping p, with each key replaced by its
image under f. Any duplicate image keys are merged, with the value of
the merged key equal to the sum of the values.
It is expected that f returns tuples or scalars, and behaves in a
reasonable way when given vector state array arguments.
If g is supplied, it is used instead of addition to reduce the values of
duplicate image keys. If given, g must have a reduce method of the form
g.reduce(probabilities) -> reduced_probability
for example, setting g to a numpy ufunc would be fine.
"""
# all this nonsense actually does something fairly straight forward
# see 'map_distribution_simple' for a reference implementation that
# avoids numpy operations
num_items = len(p)
if num_items == 0:
return {}
if g is None:
g = numpy.add
s, v = domain.from_mapping(p)
fs = numpy.asarray(f(s))
# handle case where f returns scalar arguments, say
# this might be a touch flakey
if len(fs.shape) != 2:
fs = fs*numpy.ones((1, s.shape[1]))
# sort image states using lexical ordering on coords, then
# apply same ordering to values
order = numpy.lexsort(fs)
sfs = fs[:, order]
sv = v[order]
# figure out the indices of the first instance of each state
not_equal_adj = numpy.logical_or.reduce(sfs[:, :-1] != sfs[:, 1:])
not_equal_adj = numpy.concatenate(([True], not_equal_adj))
# extract the unique image states under f
usfs = sfs[:, not_equal_adj]
# convert back from arrya representation to iterator of state tuples
unique_image_states = domain.to_iter(usfs)
# determine start and end indices of each equivalence class of
# values in the sorted values array, where values are equivalent if
# they are associated with states that agree under the transform f
class_begin = numpy.nonzero(not_equal_adj)[0]
class_end = numpy.concatenate((class_begin[1:], [num_items]))
# construct the resulting mapped probability distribution
# each image state s maps to the values in its equivalence class,
# reduced by g
p_mapped = {}
for s, i, j in itertools.izip(unique_image_states, class_begin, class_end):
p_mapped[s] = g.reduce(sv[i:j])
return p_mapped