def fromArraysAsImages(self, arrays):
"""Create a Series object from a sequence of numpy ndarrays resident in memory on the driver.
The arrays will be interpreted as though each represents a single time point - effectively the same
as if converting Images to a Series, with each array representing a volume image at a particular
point in time. Thus in the resulting Series, the value of the record with key (0,0,0) will be
array([arrays[0][0,0,0], arrays[1][0,0,0],... arrays[n][0,0,0]).
The dimensions of the resulting Series will be *opposite* that of the passed numpy array. Their dtype will not
be changed.
"""
# if passed a single array, cast it to a sequence of length 1
if isinstance(arrays, ndarray):
arrays = [arrays]
# check that shapes of passed arrays are consistent
shape = arrays[0].shape
dtype = arrays[0].dtype
for ary in arrays:
if not ary.shape == shape:
raise ValueError("Inconsistent array shapes: first array had shape %s, but other array has shape %s" %
(str(shape), str(ary.shape)))
if not ary.dtype == dtype:
raise ValueError("Inconsistent array dtypes: first array had dtype %s, but other array has dtype %s" %
(str(dtype), str(ary.dtype)))
# get indices so that fastest index changes first
shapeiters = (xrange(n) for n in shape)
keys = [idx[::-1] for idx in itertools.product(*shapeiters)]
values = vstack([ary.ravel() for ary in arrays]).T
dims = Dimensions.fromTuple(shape[::-1])
return Series(self.sc.parallelize(zip(keys, values), self.minPartitions), dims=dims, dtype=str(dtype))
def __init__(self, rdd, dims=None, nrecords=None, dtype=None):
super(Images, self).__init__(rdd, nrecords=nrecords, dtype=dtype)
if dims and not isinstance(dims, Dimensions):
try:
dims = Dimensions.fromTuple(dims)
except:
raise TypeError("Images dims parameter must be castable to Dimensions object, got: %s" % str(dims))
self._dims = dims
def populateParamsFromFirstRecord(self):
record = super(Images, self).populateParamsFromFirstRecord()
self._dims = Dimensions.fromTuple(record[1].shape)
return record
def populateParamsFromFirstRecord(self):
record = super(SimpleBlocks, self).populateParamsFromFirstRecord()
self._dims = Dimensions.fromTuple(record[0].origShape)
return record