def test_sub_to_ind_array(self):
subs = [(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)]
data_local = map(lambda x: (x, array([1.0])), subs)
dims = [2, 3, 2]
inds = map(lambda x: x[0], subtoind(data_local, dims))
assert(allclose(inds, array(range(1, 13))))
def calc(self, data):
"""Calculate averages. Keys (tuples) are converted
into linear indices based on their dimensions
Parameters
----------
data : RDD of (tuple, array) pairs, each array of shape (ncols,)
Data to compute averages from
Returns
-------
ts : array, shape (n, ncols)
"""
dims = getdims(data)
data = subtoind(data, dims.max)
# loop over indices, averaging time series
ts = zeros((self.n, len(data.first()[1])))
for i in range(0, self.n):
if len(self.inds[i]) > 0:
ts[i, :] = self.select(
data, i).map(lambda (k, x): x).sum() / len(self.inds[i])
return ts
def calc(self, data):
"""Calculate averages. Keys (tuples) are converted
into linear indices based on their dimensions
Parameters
----------
data : RDD of (tuple, array) pairs, each array of shape (ncols,)
Data to compute averages from
Returns
-------
self : returns an instance of self.
"""
dims = getdims(data)
data = subtoind(data, dims.max)
# loop over indices, computing average keys and average values
keys = zeros((self.n, len(dims.count())))
values = zeros((self.n, len(data.first()[1])))
for idx, indlist in enumerate(self.inds):
if len(indlist) > 0:
values[idx, :] = self.select(data, idx).map(lambda (k, x): x).sum() / len(indlist)
keys[idx, :] = mean(map(lambda (k, v): k, indtosub(map(lambda k: (k, 0), indlist), dims.max)), axis=0)
self.keys = keys
self.values = values
return self
def calc(self, data):
"""Calculate averages. Keys (tuples) are converted
into linear indices based on their dimensions
Parameters
----------
data : RDD of (tuple, array) pairs, each array of shape (ncols,)
Data to compute averages from
Returns
-------
self : returns an instance of self.
"""
dims = getdims(data)
data = subtoind(data, dims.max)
# loop over indices, computing average keys and average values
keys = zeros((self.n, len(dims.count())))
values = zeros((self.n, len(data.first()[1])))
for idx, indlist in enumerate(self.inds):
if len(indlist) > 0:
values[idx, :] = self.select(
data, idx).map(lambda (k, x): x).sum() / len(indlist)
keys[idx, :] = mean(map(
lambda (k, v): k,
indtosub(map(lambda k: (k, 0), indlist), dims.max)),
axis=0)
self.keys = keys
self.values = values
return self
def check_subtoind_result(si_param):
# attach dummy value 'x' to subscripts to match expected input to subtoind
data = map(lambda d: (d, 'x'), si_param.subscripts)
results = subtoind(data, si_param.dims, order=si_param.order, onebased=si_param.onebased)
# check results individually to highlight specific failures
for res, expected, subscript in zip(results, si_param.indices, si_param.subscripts):
assert_equals(expected, res[0], 'Got index %d instead of %d for subscript:%s, dims:%s' %
(res[0], expected, str(subscript), str(si_param.dims)))
def test_sub_to_ind_array(self):
subs = [(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)]
data_local = map(lambda x: (x, array([1.0])), subs)
dims = [2, 3, 2]
inds = map(lambda x: x[0], subtoind(data_local, dims))
assert (allclose(inds, array(range(1, 13))))
def test_sub_to_ind_rdd(self):
subs = [(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)]
data_local = map(lambda x: (x, array([1.0])), subs)
data = self.sc.parallelize(data_local)
dims = [2, 3, 2]
inds = subtoind(data, dims).map(lambda (k, _): k).collect()
assert(allclose(inds, array(range(1, 13))))
def test_sub_to_ind_rdd(self):
subs = [(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)]
data_local = map(lambda x: (x, array([1.0])), subs)
data = self.sc.parallelize(data_local)
dims = [2, 3, 2]
inds = subtoind(data, dims).map(lambda (k, _): k).collect()
assert (allclose(inds, array(range(1, 13))))
def check_subtoind_result(si_param):
# attach dummy value 'x' to subscripts to match expected input to subtoind
data = map(lambda d: (d, 'x'), si_param.subscripts)
results = subtoind(data,
si_param.dims,
order=si_param.order,
onebased=si_param.onebased)
# check results individually to highlight specific failures
for res, expected, subscript in zip(results, si_param.indices,
si_param.subscripts):
assert_equals(
expected, res[0],
'Got index %d instead of %d for subscript:%s, dims:%s' %
(res[0], expected, str(subscript), str(si_param.dims)))
def calc(self, data):
"""Calculate averages. Keys (tuples) are converted
into linear indices based on their dimensions
Parameters
----------
data : RDD of (tuple, array) pairs, each array of shape (ncols,)
Data to compute averages from
Returns
-------
ts : array, shape (n, ncols)
"""
dims = getdims(data)
data = subtoind(data, dims.max)
# loop over indices, averaging time series
ts = zeros((self.n, len(data.first()[1])))
for i in range(0, self.n):
ts[i, :] = self.select(data, i).map(lambda (k, x): x).sum() / len(self.inds[i])
return ts
