def saveAsBinarySeries(self, outputDirPath, overwrite=False):
"""Writes out Series-formatted data.
Subclasses are *not* expected to override this method.
Parameters
----------
outputdirname : string path or URI to directory to be created
Output files will be written underneath outputdirname. This directory must not yet exist
(unless overwrite is True), and must be no more than one level beneath an existing directory.
It will be created as a result of this call.
overwrite : bool
If true, outputdirname and all its contents will be deleted and recreated as part
of this call.
"""
from thunder.rdds.fileio.writers import getParallelWriterForPath
from thunder.rdds.fileio.seriesloader import writeSeriesConfig
from thunder.utils.aws import AWSCredentials
if not overwrite:
self._checkOverwrite(outputDirPath)
overwrite = True # prevent additional downstream checks for this path
awsCredentialsOverride = AWSCredentials.fromContext(self.rdd.ctx)
writer = getParallelWriterForPath(outputDirPath)(outputDirPath, overwrite=overwrite,
awsCredentialsOverride=awsCredentialsOverride)
binseriesRdd = self.toBinarySeries()
binseriesRdd.foreach(writer.writerFcn)
writeSeriesConfig(outputDirPath, len(self.dims), self.nimages, keyType='int16', valueType=self.dtype,
overwrite=overwrite, awsCredentialsOverride=awsCredentialsOverride)
def _checkOverwrite(self, outputDirPath):
""" Checks for existence of outputDirPath, raising ValueError if it already exists """
from thunder.utils.aws import AWSCredentials
from thunder.utils.common import raiseErrorIfPathExists
awsCredentialOverride = AWSCredentials.fromContext(self.rdd.ctx)
raiseErrorIfPathExists(outputDirPath,
awsCredentialsOverride=awsCredentialOverride)
def __init__(self, sparkContext):
"""Initialize a new ImagesLoader object.
Parameters
----------
sparkcontext: SparkContext
The pyspark SparkContext object used by the current Thunder environment.
"""
from thunder.utils.aws import AWSCredentials
self.sc = sparkContext
self.awsCredentialsOverride = AWSCredentials.fromContext(sparkContext)
def setAWSCredentials(self, awsAccessKeyId, awsSecretAccessKey):
"""
Manually set AWS access credentials to be used by Thunder.
Provided for hosted cloud environments without filesystem access. If
launching a cluster using the thunder-ec2 script, credentials will be
configured automatically (inside core-site.xml and ~/.boto), so this
method should not need to be called.
Parameters
----------
awsAccessKeyId : string
AWS public key, usually starts with "AKIA"
awsSecretAccessKey : string
AWS private key
"""
from thunder.utils.aws import AWSCredentials
self._credentials = AWSCredentials(awsAccessKeyId, awsSecretAccessKey)
self._credentials.setOnContext(self._sc)
def saveAsPngs(self, outputDirPath, cmap=None, vmin=None, vmax=None, filePrefix="export", overwrite=False,
collectToDriver=True):
"""
Write out basic png files for two-dimensional image data.
Files will be written into a newly-created directory given by outputdirname.
Parameters
----------
outputDirPath : string
Path to output directory to be created. Exception will be thrown if this directory already
exists, unless overwrite is True. Directory must be one level below an existing directory.
filePrefix : string
String to prepend to all filenames. Files will be named <fileprefix>-00000.png, <fileprefix>-00001.png, etc
overwrite : bool
If true, the directory given by outputdirname will first be deleted if it already exists.
collectToDriver : bool, default True
If true, images will be collect()'ed at the driver first before being written out, allowing
for use of a local filesystem at the expense of network overhead. If false, images will be written
in parallel by each executor, presumably to a distributed or networked filesystem.
"""
dims = self.dims
if not len(dims) == 2:
raise ValueError("Only two-dimensional images can be exported as .png files; image is %d-dimensional." %
len(dims))
from matplotlib.pyplot import imsave
from io import BytesIO
from thunder.rdds.fileio.writers import getParallelWriterForPath, getCollectedFileWriterForPath
from thunder.utils.aws import AWSCredentials
def toFilenameAndPngBuf(kv):
key, img = kv
fname = filePrefix+"-"+"%05d.png" % int(key)
bytebuf = BytesIO()
imsave(bytebuf, img, vmin, vmax, cmap=cmap, format="png")
return fname, bytebuf.getvalue()
bufRdd = self.rdd.map(toFilenameAndPngBuf)
awsCredentials = AWSCredentials.fromContext(self.rdd.ctx)
if collectToDriver:
writer = getCollectedFileWriterForPath(outputDirPath)(outputDirPath, overwrite=overwrite,
awsCredentialsOverride=awsCredentials)
writer.writeCollectedFiles(bufRdd.collect())
else:
writer = getParallelWriterForPath(outputDirPath)(outputDirPath, overwrite=overwrite,
awsCredentialsOverride=awsCredentials)
bufRdd.foreach(writer.writerFcn)
def saveAsBinaryImages(self,
outputDirPath,
prefix="image",
overwrite=False):
"""
Write out images or volumes as flat binary files.
Files will be written into a newly-created directory given by outputdirname.
Parameters
----------
outputDirPath : string
Path to output directory to be created. Exception will be thrown if this directory already
exists, unless overwrite is True. Directory must be one level below an existing directory.
prefix : string
String to prepend to all filenames. Files will be named <fileprefix>-00000.bin, <fileprefix>-00001.bin, etc
overwrite : bool
If true, the directory given by outputdirname will first be deleted if it already exists.
"""
from thunder.rdds.fileio.writers import getParallelWriterForPath
from thunder.rdds.fileio.imagesloader import writeBinaryImagesConfig
from thunder.utils.aws import AWSCredentials
import StringIO
dimsTotal = list(asarray(self.dims.max) - asarray(self.dims.min) + 1)
def toFilenameAndBinaryBuf(kv):
key, img = kv
fname = prefix + "-" + "%05d.bin" % int(key)
buf = StringIO.StringIO()
buf.write(img.transpose().copy().tostring())
val = buf.getvalue()
buf.close()
return fname, val
bufRdd = self.rdd.map(toFilenameAndBinaryBuf)
awsCredentials = AWSCredentials.fromContext(self.rdd.ctx)
writer = getParallelWriterForPath(outputDirPath)(
outputDirPath,
overwrite=overwrite,
awsCredentialsOverride=awsCredentials)
bufRdd.foreach(writer.writerFcn)
writeBinaryImagesConfig(outputDirPath,
dims=dimsTotal,
dtype=self.dtype,
overwrite=overwrite,
awsCredentialsOverride=awsCredentials)
def __init__(self, sparkContext, minPartitions=None):
"""Initialize a new SeriesLoader object.
Parameters
----------
sparkcontext: SparkContext
The pyspark SparkContext object used by the current Thunder environment.
minPartitions: int
minimum number of partitions to use when loading data. (Used by fromText, fromMatLocal, and fromNpyLocal)
"""
from thunder.utils.aws import AWSCredentials
self.sc = sparkContext
self.minPartitions = minPartitions
self.awsCredentialsOverride = AWSCredentials.fromContext(sparkContext)
def __init__(self, sparkContext, minPartitions=None):
"""Initialize a new SeriesLoader object.
Parameters
----------
sparkcontext: SparkContext
The pyspark SparkContext object used by the current Thunder environment.
minPartitions: int
minimum number of partitions to use when loading data. (Used by fromText, fromMatLocal, and fromNpyLocal)
"""
from thunder.utils.aws import AWSCredentials
self.sc = sparkContext
self.minPartitions = minPartitions
self.awsCredentialsOverride = AWSCredentials.fromContext(sparkContext)
def saveAsBinaryImages(self, outputDirPath, prefix="image", overwrite=False):
"""
Write out images or volumes as flat binary files.
Files will be written into a newly-created directory given by outputdirname.
Parameters
----------
outputDirPath : string
Path to output directory to be created. Exception will be thrown if this directory already
exists, unless overwrite is True. Directory must be one level below an existing directory.
prefix : string
String to prepend to all filenames. Files will be named <fileprefix>-00000.bin, <fileprefix>-00001.bin, etc
overwrite : bool
If true, the directory given by outputdirname will first be deleted if it already exists.
"""
from thunder.rdds.fileio.writers import getParallelWriterForPath
from thunder.rdds.fileio.imagesloader import writeBinaryImagesConfig
from thunder.utils.aws import AWSCredentials
import StringIO
dimsTotal = list(asarray(self.dims.max)-asarray(self.dims.min)+1)
def toFilenameAndBinaryBuf(kv):
key, img = kv
fname = prefix+"-"+"%05d.bin" % int(key)
buf = StringIO.StringIO()
buf.write(img.transpose().copy().tostring())
val = buf.getvalue()
buf.close()
return fname, val
bufRdd = self.rdd.map(toFilenameAndBinaryBuf)
awsCredentials = AWSCredentials.fromContext(self.rdd.ctx)
writer = getParallelWriterForPath(outputDirPath)(outputDirPath, overwrite=overwrite,
awsCredentialsOverride=awsCredentials)
bufRdd.foreach(writer.writerFcn)
writeBinaryImagesConfig(outputDirPath, dims=dimsTotal, dtype=self.dtype,
overwrite=overwrite, awsCredentialsOverride=awsCredentials)
def setAWSCredentials(self, awsAccessKeyId, awsSecretAccessKey):
"""
Manually set AWS access credentials to be used by Thunder.
Provided for hosted cloud environments without filesystem access. If
launching a cluster using the thunder-ec2 script, credentials will be
configured automatically (inside core-site.xml and ~/.boto), so this
method should not need to be called.
Parameters
----------
awsAccessKeyId : string
AWS public key, usually starts with "AKIA"
awsSecretAccessKey : string
AWS private key
"""
from thunder.utils.aws import AWSCredentials
self._credentials = AWSCredentials(awsAccessKeyId, awsSecretAccessKey)
self._credentials.setOnContext(self._sc)
def __init__(self, awsCredentialsOverride=None):
"""Initialization; validates that AWS keys are available as environment variables.
Will let boto library look up credentials itself according to its own rules - e.g. first looking for
AWS_ACCESS_KEY_ID and AWS_SECRET_ACCESS_KEY, then going through several possible config files and finally
looking for a ~/.aws/credentials .ini-formatted file. See boto docs:
http://boto.readthedocs.org/en/latest/boto_config_tut.html
However, if an AWSCredentials object is provided, its `awsAccessKeyId` and `awsSecretAccessKey` attributes
will be used instead of those found by the standard boto credential lookup process.
"""
if not _haveBoto:
raise ValueError("The boto package does not appear to be available; boto is required for BotoReader")
self.awsCredentialsOverride = awsCredentialsOverride if awsCredentialsOverride else AWSCredentials()
class ThunderContext():
"""
Wrapper for a SparkContext that provides an entry point for loading and saving.
Also supports creation of example datasets, and loading example
data both locally and from EC2.
Attributes
----------
`_sc` : SparkContext
Spark context for Spark functionality
`_credentials` : AWSCredentials object, optional, default = None
Stores public and private keys for AWS services. Typically available through
configuration files, and but can optionally be set using :func:`ThunderContext.setAWSCredentials()`.
"""
def __init__(self, sparkcontext):
self._sc = sparkcontext
self._credentials = None
@classmethod
def start(cls, *args, **kwargs):
"""
Starts a ThunderContext using the same arguments as SparkContext
"""
from pyspark import SparkContext
return ThunderContext(SparkContext(*args, **kwargs))
def addPyFile(self, path):
"""
Adds a .zip or .py or .egg dependency for all tasks to be executed
as part of this context.
Uses the corresponding SparkContext method.
Parameters
----------
path : str
Path to a file as either a local file, file in HDFS, or URI.
"""
self._sc.addPyFile(path)
def stop(self):
"""
Shut down the context
"""
self._sc.stop()
def loadSeries(self, dataPath, nkeys=None, nvalues=None, inputFormat='binary', minPartitions=None,
maxPartitionSize='32mb', confFilename='conf.json', keyType=None, valueType=None, keyPath=None,
varName=None):
"""
Loads a Series object from data stored as binary, text, npy, or mat.
For binary and text, supports single files or multiple files stored on a local file system,
a networked file system (mounted and available on all cluster nodes), Amazon S3, or HDFS.
For local formats (npy and mat) only local file systems currently supported.
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
nkeys: int, optional (required if `inputFormat` is 'text'), default = None
Number of keys per record (e.g. 3 for (x, y, z) coordinate keys). Must be specified for
text data; can be specified here or in a configuration file for binary data.
nvalues: int, optional (required if `inputFormat` is 'text')
Number of values per record. Must be specified here or in a configuration file for binary data.
inputFormat: {'text', 'binary', 'npy', 'mat'}. optional, default = 'binary'
inputFormat of data to be read.
minPartitions: int, optional, default = SparkContext.minParallelism
Minimum number of Spark partitions to use, only for text.
maxPartitionSize : int, optional, default = '32mb'
Maximum size of partitions as a Java-style memory string, e.g. '32mb' or '64mb',
indirectly controls the number of Spark partitions, only for binary.
confFilename: string, optional, default 'conf.json'
Path to JSON file with configuration options including 'nkeys', 'nvalues',
'keyType', and 'valueType'. If a file is not found at the given path, then the base
directory in 'dataPath' will be checked. Parameters will override the conf file.
keyType: string or numpy dtype, optional, default = None
Numerical type of keys, will override conf file.
valueType: string or numpy dtype, optional, default = None
Numerical type of values, will override conf file.
keyPath: string, optional, default = None
Path to file with keys when loading from npy or mat.
varName : str, optional, default = None
Variable name to load (for MAT files only)
Returns
-------
data: thunder.rdds.Series
A Series object, wrapping an RDD, with (n-tuples of ints) : (numpy array) pairs
"""
checkParams(inputFormat, ['text', 'binary', 'npy', 'mat'])
from thunder.rdds.fileio.seriesloader import SeriesLoader
loader = SeriesLoader(self._sc, minPartitions=minPartitions)
if inputFormat.lower() == 'binary':
data = loader.fromBinary(dataPath, confFilename=confFilename, nkeys=nkeys, nvalues=nvalues,
keyType=keyType, valueType=valueType, maxPartitionSize=maxPartitionSize)
elif inputFormat.lower() == 'text':
if nkeys is None:
raise Exception('Must provide number of keys per record for loading from text')
data = loader.fromText(dataPath, nkeys=nkeys)
elif inputFormat.lower() == 'npy':
data = loader.fromNpyLocal(dataPath, keyPath)
else:
if varName is None:
raise Exception('Must provide variable name for loading MAT files')
data = loader.fromMatLocal(dataPath, varName, keyPath)
return data
def loadImages(self, dataPath, dims=None, dtype=None, inputFormat='stack', ext=None,
startIdx=None, stopIdx=None, recursive=False, nplanes=None, npartitions=None,
renumber=False, confFilename='conf.json'):
"""
Loads an Images object from data stored as a binary image stack, tif, or png files.
Supports single files or multiple files, stored on a local file system, a networked file sytem
(mounted and available on all nodes), Amazon S3, or Google Storage.
HDFS is not currently supported for image file data.
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
dims: tuple of positive int, optional (required if inputFormat is 'stack')
Image dimensions. Binary stack data will be interpreted as a multidimensional array
with the given dimensions, and should be stored in row-major order (Fortran or Matlab convention),
where the first dimension changes most rapidly. For 'png' or 'tif' data dimensions
will be read from the image file headers.
inputFormat: str, optional, default = 'stack'
Expected format of the input data: 'stack', 'png', or 'tif'. 'stack' indicates flat binary stacks.
'png' or 'tif' indicate image format. Page of a multipage tif file will be extend along
the third dimension. Separate files interpreted as distinct records, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default = None
File extension, default will be "bin" if inputFormat=="stack", "tif" for inputFormat=='tif',
and 'png' for inputFormat=="png".
dtype: string or numpy dtype, optional, default = 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string.
Ignored for 'tif' or 'png' (data will be inferred from image formats).
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position). These parameters give the starting
and final index after lexicographic sorting.
stopIdx: nonnegative int, optional, default = None
See startIdx.
recursive: boolean, optional, default = False
If true, will recursively descend directories rooted at dataPath, loading all files
in the tree with an appropriate extension.
nplanes: positive integer, optional, default = None
Subdivide individual image files. Every `nplanes` from each file will be considered a new record.
With nplanes=None (the default), a single file will be considered as representing a single record.
If the number of records per file is not the same across all files, then `renumber` should be set
to True to ensure consistent keys.
npartitions: positive int, optional, default = None
Specify number of partitions for the RDD, if unspecified will use 1 partition per image.
renumber: boolean, optional, default = False
Recalculate keys for records after images are loading. Only necessary if different files contain
different number of records (e.g. due to specifying nplanes). See Images.renumber().
confFilename : string, optional, default = 'conf.json'
Name of conf file if using to specify parameters for binary stack data
Returns
-------
data: thunder.rdds.Images
An Images object, wrapping an RDD of with (int) : (numpy array) pairs
"""
checkParams(inputFormat, ['stack', 'png', 'tif', 'tif-stack'])
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
# Checking StartIdx is smaller or equal to StopIdx
if startIdx is not None and stopIdx is not None and startIdx > stopIdx:
raise Exception("Error. startIdx {} is larger than stopIdx {}".inputFormat(startIdx, stopIdx))
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
if inputFormat.lower() == 'stack':
data = loader.fromStack(dataPath, dims=dims, dtype=dtype, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions,
confFilename=confFilename)
elif inputFormat.lower().startswith('tif'):
data = loader.fromTif(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx, recursive=recursive,
nplanes=nplanes, npartitions=npartitions)
else:
if nplanes:
raise NotImplementedError("nplanes argument is not supported for png files")
data = loader.fromPng(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx, recursive=recursive,
npartitions=npartitions)
if not renumber:
return data
else:
return data.renumber()
def loadSeriesFromArray(self, values, index=None, npartitions=None):
"""
Load Series data from a local array
Parameters
----------
values : list or ndarray
A list of 1d numpy arrays, or a single 2d numpy array
index : array-like, optional, deafult = None
Index to set for Series object, if None will use linear indices.
npartitions : position int, optional, default = None
Number of partitions for RDD, if unspecified will use
default parallelism.
"""
from numpy import ndarray, asarray
from thunder.rdds.fileio.seriesloader import SeriesLoader
loader = SeriesLoader(self._sc)
if not npartitions:
npartitions = self._sc.defaultParallelism
if isinstance(values, list):
values = asarray(values)
if isinstance(values, ndarray) and values.ndim > 1:
values = list(values)
data = loader.fromArrays(values, npartitions=npartitions)
if index:
data.index = index
return data
def loadImagesFromArray(self, values, npartitions=None):
"""
Load Images data from a local array
Parameters
----------
values : list or ndarray
A list of 2d or 3d numpy arrays,
or a single 3d or 4d numpy array
npartitions : position int, optional, default = None
Number of partitions for RDD, if unspecified will use
default parallelism.
"""
from numpy import ndarray, asarray
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if isinstance(values, list):
values = asarray(values)
if isinstance(values, ndarray) and values.ndim > 2:
values = list(values)
if not npartitions:
npartitions = self._sc.defaultParallelism
return loader.fromArrays(values, npartitions=npartitions)
def loadImagesOCP(self, bucketName, resolution, server='ocp.me', startIdx=None, stopIdx=None,
minBound=None, maxBound=None):
"""
Load Images from OCP (Open Connectome Project).
The OCP is a web service for access to EM brain images and other neural image data.
The web-service can be accessed at http://www.openconnectomeproject.org/.
Parameters
----------
bucketName: string
Token name for the project in OCP. This name should exist on the server from which data is loaded.
resolution: nonnegative int
Resolution of the data in OCP
server: string, optional, default = 'ocp.me'
Name of the OCP server with the specified token.
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position).
stopIdx: nonnegative int, optional
See startIdx.
minBound, maxBound: tuple of nonnegative int, optional, default = None
X,Y,Z bounds of the data to fetch from OCP. minBound contains the (xMin,yMin,zMin) while
maxBound contains (xMax,yMax,zMax).
Returns
-------
data: thunder.rdds.Images
An Images object, wrapping an RDD of with (int) : (numpy array) pairs
"""
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
# Checking StartIdx is smaller or equal to StopIdx
if startIdx is not None and stopIdx is not None and startIdx > stopIdx:
raise Exception("Error. startIdx {} is larger than stopIdx {}".format(startIdx, stopIdx))
data = loader.fromOCP(bucketName, resolution=resolution, server=server, startIdx=startIdx,
stopIdx=stopIdx, minBound=minBound, maxBound=maxBound)
return data
def loadImagesAsSeries(self, dataPath, dims=None, inputFormat='stack', ext=None, dtype='int16',
blockSize="150M", blockSizeUnits="pixels", startIdx=None, stopIdx=None,
shuffle=True, recursive=False, nplanes=None, npartitions=None,
renumber=False, confFilename='conf.json'):
"""
Load Images data as Series data.
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
dims: tuple of positive int, optional (required if inputFormat is 'stack')
Image dimensions. Binary stack data will be interpreted as a multidimensional array
with the given dimensions, and should be stored in row-major order (Fortran or Matlab convention),
where the first dimension changes most rapidly. For 'png' or 'tif' data dimensions
will be read from the image file headers.
inputFormat: str, optional, default = 'stack'
Expected format of the input data: 'stack', 'png', or 'tif'. 'stack' indicates flat binary stacks.
'png' or 'tif' indicate image formats. Page of a multipage tif file will be extend along
the third dimension. Separate files interpreted as distinct records, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default = None
File extension, default will be "bin" if inputFormat=="stack", "tif" for inputFormat=='tif',
and 'png' for inputFormat=="png".
dtype: string or numpy dtype. optional, default 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string.
Ignored for 'tif' or 'png' (data will be inferred from image formats).
blockSize: string or positive int, optional, default "150M"
Requested size of blocks (e.g "64M", "512k", "2G"). If shuffle=True, can also be a
tuple of int specifying the number of pixels or splits per dimension. Indirectly
controls the number of Spark partitions, with one partition per block.
blockSizeUnits: string, either "pixels" or "splits", default "pixels"
Units for interpreting a tuple passed as blockSize when shuffle=True.
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position). These parameters give the starting
and final index after lexicographic sorting.
stopIdx: nonnegative int, optional, default = None
See startIdx.
shuffle: boolean, optional, default = True
Controls whether the conversion from Images to Series formats will use of a Spark shuffle-based method.
recursive: boolean, optional, default = False
If true, will recursively descend directories rooted at dataPath, loading all files
in the tree with an appropriate extension.
nplanes: positive integer, optional, default = None
Subdivide individual image files. Every `nplanes` from each file will be considered a new record.
With nplanes=None (the default), a single file will be considered as representing a single record.
If the number of records per file is not the same across all files, then `renumber` should be set
to True to ensure consistent keys.
npartitions: positive int, optional, default = None
Specify number of partitions for the RDD, if unspecified will use 1 partition per image.
renumber: boolean, optional, default = False
Recalculate keys for records after images are loading. Only necessary if different files contain
different number of records (e.g. due to specifying nplanes). See Images.renumber().
confFilename : string, optional, default = 'conf.json'
Name of conf file if using to specify parameters for binary stack data
Returns
-------
data: thunder.rdds.Series
A Series object, wrapping an RDD, with (n-tuples of ints) : (numpy array) pairs.
Keys will be n-tuples of int, with n given by dimensionality of the images, and correspond
to indexes into the image arrays. Value will have length equal to the number of image files.
With each image contributing one point to this value array, with ordering given by
the lexicographic ordering of image file names.
"""
checkParams(inputFormat, ['stack', 'tif', 'tif-stack'])
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
if shuffle:
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputFormat.lower() == 'stack':
images = loader.fromStack(dataPath, dims, dtype=dtype, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions,
confFilename=confFilename)
else:
# tif / tif stack
images = loader.fromTif(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions)
if renumber:
images = images.renumber()
return images.toBlocks(blockSize, units=blockSizeUnits).toSeries()
else:
from thunder.rdds.fileio.seriesloader import SeriesLoader
if nplanes is not None:
raise NotImplementedError("nplanes is not supported with shuffle=False")
if npartitions is not None:
raise NotImplementedError("npartitions is not supported with shuffle=False")
if renumber:
raise NotImplementedError("renumber is not supported with shuffle=False")
loader = SeriesLoader(self._sc)
if inputFormat.lower() == 'stack':
return loader.fromStack(dataPath, dims, ext=ext, dtype=dtype, blockSize=blockSize,
startIdx=startIdx, stopIdx=stopIdx, recursive=recursive)
else:
# tif / tif stack
return loader.fromTif(dataPath, ext=ext, blockSize=blockSize,
startIdx=startIdx, stopIdx=stopIdx, recursive=recursive)
def convertImagesToSeries(self, dataPath, outputDirPath, dims=None, inputFormat='stack', ext=None,
dtype='int16', blockSize="150M", blockSizeUnits="pixels", startIdx=None, stopIdx=None,
shuffle=True, overwrite=False, recursive=False, nplanes=None, npartitions=None,
renumber=False, confFilename='conf.json'):
"""
Write out Images data as Series data, saved in a flat binary format.
The resulting files may subsequently be read in using ThunderContext.loadSeries().
Loading Series data directly will likely be faster than converting image data
to a Series object through loadImagesAsSeries().
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
outputDirPath: string
Path to directory to write Series file output. May be either a path on the local file system
or a URI-like format, such as "local/directory", "s3n:///my-s3-bucket/data/",
or "file:///mnt/another/directory/". If the directory exists and 'overwrite' is True,
the existing directory and all its contents will be deleted and overwritten.
dims: tuple of positive int, optional (required if inputFormat is 'stack')
Image dimensions. Binary stack data will be interpreted as a multidimensional array
with the given dimensions, and should be stored in row-major order (Fortran or Matlab convention),
where the first dimension changes most rapidly. For 'png' or 'tif' data dimensions
will be read from the image file headers.
inputFormat: str, optional, default = 'stack'
Expected format of the input data: 'stack', 'png', or 'tif'. 'stack' indicates flat binary stacks.
'png' or 'tif' indicate image formats. Page of a multipage tif file will be extend along
the third dimension. Separate files interpreted as distinct records, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default = None
File extension, default will be "bin" if inputFormat=="stack", "tif" for inputFormat=='tif',
and 'png' for inputFormat=="png".
dtype: string or numpy dtype. optional, default 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string.
Ignored for 'tif' or 'png' (data will be inferred from image formats).
blockSize: string or positive int, optional, default "150M"
Requested size of blocks (e.g "64M", "512k", "2G"). If shuffle=True, can also be a
tuple of int specifying the number of pixels or splits per dimension. Indirectly
controls the number of Spark partitions, with one partition per block.
blockSizeUnits: string, either "pixels" or "splits", default "pixels"
Units for interpreting a tuple passed as blockSize when shuffle=True.
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position). These parameters give the starting
and final index after lexicographic sorting.
stopIdx: nonnegative int, optional, default = None
See startIdx.
shuffle: boolean, optional, default = True
Controls whether the conversion from Images to Series formats will use of a Spark shuffle-based method.
overwrite: boolean, optional, default False
If true, the directory specified by outputDirPath will be deleted (recursively) if it
already exists. (Use with caution.)
recursive: boolean, optional, default = False
If true, will recursively descend directories rooted at dataPath, loading all files
in the tree with an appropriate extension.
nplanes: positive integer, optional, default = None
Subdivide individual image files. Every `nplanes` from each file will be considered a new record.
With nplanes=None (the default), a single file will be considered as representing a single record.
If the number of records per file is not the same across all files, then `renumber` should be set
to True to ensure consistent keys.
npartitions: positive int, optional, default = None
Specify number of partitions for the RDD, if unspecified will use 1 partition per image.
renumber: boolean, optional, default = False
Recalculate keys for records after images are loading. Only necessary if different files contain
different number of records (e.g. due to specifying nplanes). See Images.renumber().
confFilename : string, optional, default = 'conf.json'
Name of conf file if using to specify parameters for binary stack data
"""
checkParams(inputFormat, ['stack', 'tif', 'tif-stack'])
if not overwrite:
raiseErrorIfPathExists(outputDirPath, awsCredentialsOverride=self._credentials)
overwrite = True # prevent additional downstream checks for this path
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
if shuffle:
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputFormat.lower() == 'stack':
images = loader.fromStack(dataPath, dims, ext=ext, dtype=dtype, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions,
confFilename=confFilename)
else:
# 'tif' or 'tif-stack'
images = loader.fromTif(dataPath, ext=ext, startIdx=startIdx, stopIdx=stopIdx,
recursive=recursive, nplanes=nplanes, npartitions=npartitions)
if renumber:
images = images.renumber()
images.toBlocks(blockSize, units=blockSizeUnits).saveAsBinarySeries(outputDirPath, overwrite=overwrite)
else:
from thunder.rdds.fileio.seriesloader import SeriesLoader
if nplanes is not None:
raise NotImplementedError("nplanes is not supported with shuffle=False")
if npartitions is not None:
raise NotImplementedError("npartitions is not supported with shuffle=False")
loader = SeriesLoader(self._sc)
if inputFormat.lower() == 'stack':
loader.saveFromStack(dataPath, outputDirPath, dims, ext=ext, dtype=dtype,
blockSize=blockSize, overwrite=overwrite, startIdx=startIdx,
stopIdx=stopIdx, recursive=recursive)
else:
# 'tif' or 'tif-stack'
loader.saveFromTif(dataPath, outputDirPath, ext=ext, blockSize=blockSize,
startIdx=startIdx, stopIdx=stopIdx, overwrite=overwrite,
recursive=recursive)
def makeExample(self, dataset=None, **opts):
"""
Make an example data set for testing analyses.
Options include 'pca', 'factor', 'kmeans', 'ica', 'sources'
See thunder.utils.datasets for detailed options.
Parameters
----------
dataset : str
Which dataset to generate
Returns
-------
data : RDD of (tuple, array) pairs
Generated dataset
"""
from thunder.utils.datasets import DATASET_MAKERS
if dataset is None:
return sorted(DATASET_MAKERS.keys())
checkParams(dataset, DATASET_MAKERS.keys())
return DataSets.make(self._sc, dataset, **opts)
def loadExample(self, dataset=None):
"""
Load a local example data set for testing analyses.
Some of these data sets are extremely downsampled and should be considered
useful only for testing the API. If called with None,
will return list of available datasets.
Parameters
----------
dataset : str
Which dataset to load
Returns
-------
data : Data object
Generated dataset as a Thunder data objects (e.g Series or Images)
"""
import atexit
import shutil
import tempfile
from pkg_resources import resource_listdir, resource_filename
DATASETS = {
'iris': 'iris',
'fish-series': 'fish/series',
'fish-images': 'fish/images',
'mouse-series': 'mouse/series',
'mouse-images': 'mouse/images',
'mouse-params': 'mouse/params'
}
if dataset is None:
return sorted(DATASETS.keys())
checkParams(dataset, DATASETS.keys())
if 'ec2' in self._sc.master:
tmpdir = os.path.join('/root/thunder/python/thunder/utils', 'data', DATASETS[dataset])
else:
tmpdir = tempfile.mkdtemp()
atexit.register(shutil.rmtree, tmpdir)
def copyLocal(target):
files = resource_listdir('thunder.utils.data', target)
for f in files:
path = resource_filename('thunder.utils.data', os.path.join(target, f))
shutil.copy(path, tmpdir)
copyLocal(DATASETS[dataset])
npartitions = self._sc.defaultParallelism
if dataset == "iris":
return self.loadSeries(tmpdir)
elif dataset == "fish-series":
return self.loadSeries(tmpdir).astype('float')
elif dataset == "fish-images":
return self.loadImages(tmpdir, inputFormat="tif", npartitions=npartitions)
elif dataset == "mouse-series":
return self.loadSeries(tmpdir).astype('float')
elif dataset == "mouse-images":
return self.loadImages(tmpdir, npartitions=npartitions)
elif dataset == "mouse-params":
return self.loadParams(os.path.join(tmpdir, 'covariates.json'))
def loadExampleS3(self, dataset=None):
"""
Load an example data set from S3.
Info on the included datasets can be found at the CodeNeuro data repository
(http://datasets.codeneuro.org/). If called with None, will return
list of available datasets.
Parameters
----------
dataset : str
Which dataset to load
Returns
-------
data : a Data object (usually a Series or Images)
The dataset as one of Thunder's data objects
params : dict
Parameters or metadata for dataset
"""
DATASETS = {
'ahrens.lab/direction.selectivity': 'ahrens.lab/direction.selectivity/1/',
'ahrens.lab/optomotor.response': 'ahrens.lab/optomotor.response/1/',
'svoboda.lab/tactile.navigation': 'svoboda.lab/tactile.navigation/1/'
}
if dataset is None:
return DATASETS.keys()
if 'local' in self._sc.master:
raise Exception("Must be running on an EC2 cluster to load this example data set")
checkParams(dataset, DATASETS.keys())
basePath = 's3n://neuro.datasets/'
dataPath = DATASETS[dataset]
data = self.loadSeries(basePath + dataPath + 'series')
params = self.loadParams(basePath + dataPath + 'params/covariates.json')
return data, params
def loadJSON(self, path):
"""
Generic function for loading JSON from a path, handling local file systems and S3 or GS
Parameters
----------
path : str
Path to a file, can be on a local file system or an S3 or GS bucket
Returns
-------
A string with the JSON
"""
import json
from thunder.rdds.fileio.readers import getFileReaderForPath, FileNotFoundError
reader = getFileReaderForPath(path)(awsCredentialsOverride=self._credentials)
try:
buffer = reader.read(path)
except FileNotFoundError:
raise Exception("Cannot find file %s" % path)
return json.loads(buffer)
def loadParams(self, path):
"""
Load a file with parameters from a local file system or S3 or GS.
Assumes file is JSON with basic types (strings, integers, doubles, lists),
in either a single dict or list of dict-likes, and each dict has at least
a "name" field and a "value" field.
Useful for loading generic meta data, parameters, covariates, etc.
Parameters
----------
path : str
Path to file, can be on a local file system or an S3 or GS bucket
Returns
-------
A dict or list with the parameters
"""
blob = self.loadJSON(path)
return Params(blob)
def loadSources(self, path):
"""
Load a file with sources from a local file system or S3 or GS.
Parameters
----------
path : str
Path to file, can be on a local file system or an S3 or GS bucket
Returns
-------
A SourceModel
See also
--------
SourceExtraction
"""
from thunder import SourceExtraction
blob = self.loadJSON(path)
return SourceExtraction.deserialize(blob)
def export(self, data, filename, outputFormat=None, overwrite=False, varname=None):
"""
Export local array data to a variety of formats.
Can write to a local file sytem or S3 or GS (destination inferred from filename schema).
S3 or GS writing useful for persisting arrays when working in an environment without
accessible local storage.
Parameters
----------
data : array-like
The data to export
filename : str
Output location (path/to/file.ext)
outputFormat : str, optional, default = None
Ouput format ("npy", "mat", or "txt"), if not provided will
try to infer from file extension.
overwrite : boolean, optional, default = False
Whether to overwrite if directory or file already exists
varname : str, optional, default = None
Variable name for writing "mat" formatted files
"""
from numpy import save, savetxt, asarray
from scipy.io import savemat
from StringIO import StringIO
from thunder.rdds.fileio.writers import getFileWriterForPath
path, file, outputFormat = handleFormat(filename, outputFormat)
checkParams(outputFormat, ["npy", "mat", "txt"])
clazz = getFileWriterForPath(filename)
writer = clazz(path, file, overwrite=overwrite, awsCredentialsOverride=self._credentials)
stream = StringIO()
if outputFormat == "mat":
varname = os.path.splitext(file)[0] if varname is None else varname
savemat(stream, mdict={varname: data}, oned_as='column', do_compression='true')
if outputFormat == "npy":
save(stream, data)
if outputFormat == "txt":
if asarray(data).ndim > 2:
raise Exception("Cannot write data with more than two dimensions to text")
savetxt(stream, data)
stream.seek(0)
writer.writeFile(stream.buf)
def setAWSCredentials(self, awsAccessKeyId, awsSecretAccessKey):
"""
Manually set AWS access credentials to be used by Thunder.
Provided for hosted cloud environments without filesystem access. If
launching a cluster using the thunder-ec2 script, credentials will be
configured automatically (inside core-site.xml and ~/.boto), so this
method should not need to be called.
Parameters
----------
awsAccessKeyId : string
AWS public key, usually starts with "AKIA"
awsSecretAccessKey : string
AWS private key
"""
from thunder.utils.aws import AWSCredentials
self._credentials = AWSCredentials(awsAccessKeyId, awsSecretAccessKey)
self._credentials.setOnContext(self._sc)
def _checkOverwrite(self, outputDirPath):
""" Checks for existence of outputDirPath, raising ValueError if it already exists """
from thunder.utils.aws import AWSCredentials
from thunder.utils.common import raiseErrorIfPathExists
awsCredentialOverride = AWSCredentials.fromContext(self.rdd.ctx)
raiseErrorIfPathExists(outputDirPath, awsCredentialsOverride=awsCredentialOverride)
def saveAsBinarySeries(self, outputDirPath, overwrite=False):
"""
Writes out Series-formatted data.
This method (Series.saveAsBinarySeries) writes out binary series files using the current partitioning
of this Series object. (That is, if mySeries.rdd.getNumPartitions() == 5, then 5 files will be written
out, one per partition.) The records will not be resorted; the file names for each partition will be
taken from the key of the first Series record in that partition. If the Series object is already
sorted and no records have been removed by filtering, then the resulting output should be equivalent
to what one would get from calling myImages.saveAsBinarySeries().
If all one wishes to do is to save out Images data in a binary series format, then
tsc.convertImagesToSeries() will likely be more efficient than
tsc.loadImages().toSeries().saveAsBinarySeries().
Parameters
----------
outputDirPath : string path or URI to directory to be created
Output files will be written underneath outputdirname. This directory must not yet exist
(unless overwrite is True), and must be no more than one level beneath an existing directory.
It will be created as a result of this call.
overwrite : bool
If true, outputdirname and all its contents will be deleted and recreated as part
of this call.
"""
import cStringIO as StringIO
import struct
from thunder.rdds.imgblocks.blocks import SimpleBlocks
from thunder.rdds.fileio.writers import getParallelWriterForPath
from thunder.rdds.fileio.seriesloader import writeSeriesConfig
from thunder.utils.aws import AWSCredentials
if not overwrite:
self._checkOverwrite(outputDirPath)
overwrite = True # prevent additional downstream checks for this path
def partitionToBinarySeries(kvIter):
""" Collects all Series records in a partition into a single binary series record. """
keypacker = None
firstKey = None
buf = StringIO.StringIO()
for seriesKey, series in kvIter:
if keypacker is None:
keypacker = struct.Struct('h'*len(seriesKey))
firstKey = seriesKey
# print >> sys.stderr, seriesKey, series, series.tostring().encode('hex')
buf.write(keypacker.pack(*seriesKey))
buf.write(series.tostring())
val = buf.getvalue()
buf.close()
# we might have an empty partition, in which case firstKey will still be None
if firstKey is None:
return iter([])
else:
label = SimpleBlocks.getBinarySeriesNameForKey(firstKey) + ".bin"
return iter([(label, val)])
awsCredentials = AWSCredentials.fromContext(self.rdd.ctx)
writer = getParallelWriterForPath(outputDirPath)(outputDirPath, overwrite=overwrite,
awsCredentialsOverride=awsCredentials)
binseriesrdd = self.rdd.mapPartitions(partitionToBinarySeries)
binseriesrdd.foreach(writer.writerFcn)
# TODO: all we really need here are the number of keys and number of values, which could in principle
# be cached in _nkeys and _nvals attributes, removing the need for this .first() call in most cases.
firstKey, firstVal = self.first()
writeSeriesConfig(outputDirPath, len(firstKey), len(firstVal), keyType='int16', valueType=self.dtype,
overwrite=overwrite, awsCredentialsOverride=awsCredentials)
def saveAsPngs(self,
outputDirPath,
cmap=None,
vmin=None,
vmax=None,
filePrefix="export",
overwrite=False,
collectToDriver=True):
"""
Write out basic png files for two-dimensional image data.
Files will be written into a newly-created directory given by outputdirname.
Parameters
----------
outputDirPath : string
Path to output directory to be created. Exception will be thrown if this directory already
exists, unless overwrite is True. Directory must be one level below an existing directory.
filePrefix : string
String to prepend to all filenames. Files will be named <fileprefix>-00000.png, <fileprefix>-00001.png, etc
overwrite : bool
If true, the directory given by outputdirname will first be deleted if it already exists.
collectToDriver : bool, default True
If true, images will be collect()'ed at the driver first before being written out, allowing
for use of a local filesystem at the expense of network overhead. If false, images will be written
in parallel by each executor, presumably to a distributed or networked filesystem.
"""
dims = self.dims
if not len(dims) == 2:
raise ValueError(
"Only two-dimensional images can be exported as .png files; image is %d-dimensional."
% len(dims))
from matplotlib.pyplot import imsave
from io import BytesIO
from thunder.rdds.fileio.writers import getParallelWriterForPath, getCollectedFileWriterForPath
from thunder.utils.aws import AWSCredentials
def toFilenameAndPngBuf(kv):
key, img = kv
fname = filePrefix + "-" + "%05d.png" % int(key)
bytebuf = BytesIO()
imsave(bytebuf, img, vmin, vmax, cmap=cmap, format="png")
return fname, bytebuf.getvalue()
bufRdd = self.rdd.map(toFilenameAndPngBuf)
awsCredentials = AWSCredentials.fromContext(self.rdd.ctx)
if collectToDriver:
writer = getCollectedFileWriterForPath(outputDirPath)(
outputDirPath,
overwrite=overwrite,
awsCredentialsOverride=awsCredentials)
writer.writeCollectedFiles(bufRdd.collect())
else:
writer = getParallelWriterForPath(outputDirPath)(
outputDirPath,
overwrite=overwrite,
awsCredentialsOverride=awsCredentials)
bufRdd.foreach(writer.writerFcn)
class ThunderContext():
"""
Wrapper for a SparkContext that provides an entry point for loading and saving.
Also supports creation of example datasets, and loading example
data both locally and from EC2.
"""
def __init__(self, sparkcontext):
self._sc = sparkcontext
self._credentials = None
@classmethod
def start(cls, *args, **kwargs):
"""
Starts a ThunderContext using the same arguments as SparkContext
"""
from pyspark import SparkContext
return ThunderContext(SparkContext(*args, **kwargs))
def addPyFile(self, path):
"""
Adds a .zip or .py or .egg dependency for all tasks to be executed
as part of this context.
Uses the corresponding SparkContext method.
Parameters
----------
path : str
Path to a file as either a local file, file in HDFS, or URI.
"""
self._sc.addPyFile(path)
def stop(self):
"""
Shut down the context
"""
self._sc.stop()
def loadSeries(self,
dataPath,
nkeys=None,
nvalues=None,
inputFormat='binary',
minPartitions=None,
maxPartitionSize='32mb',
confFilename='conf.json',
keyType=None,
valueType=None,
keyPath=None,
varName=None):
"""
Loads a Series object from data stored as binary, text, npy, or mat.
For binary and text, supports single files or multiple files stored on a local file system,
a networked file system (mounted and available on all cluster nodes), Amazon S3, or HDFS.
For local formats (npy and mat) only local file systems currently supported.
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
nkeys: int, optional (required if `inputFormat` is 'text'), default = None
Number of keys per record (e.g. 3 for (x, y, z) coordinate keys). Must be specified for
text data; can be specified here or in a configuration file for binary data.
nvalues: int, optional (required if `inputFormat` is 'text')
Number of values per record. Must be specified here or in a configuration file for binary data.
inputFormat: {'text', 'binary', 'npy', 'mat'}. optional, default = 'binary'
inputFormat of data to be read.
minPartitions: int, optional, default = SparkContext.minParallelism
Minimum number of Spark partitions to use, only for text.
maxPartitionSize : int, optional, default = '32mb'
Maximum size of partitions as a Java-style memory string, e.g. '32mb' or '64mb',
indirectly controls the number of Spark partitions, only for binary.
confFilename: string, optional, default 'conf.json'
Path to JSON file with configuration options including 'nkeys', 'nvalues',
'keyType', and 'valueType'. If a file is not found at the given path, then the base
directory in 'dataPath' will be checked. Parameters will override the conf file.
keyType: string or numpy dtype, optional, default = None
Numerical type of keys, will override conf file.
valueType: string or numpy dtype, optional, default = None
Numerical type of values, will override conf file.
keyPath: string, optional, default = None
Path to file with keys when loading from npy or mat.
varName : str, optional, default = None
Variable name to load (for MAT files only)
Returns
-------
data: thunder.rdds.Series
A Series object, wrapping an RDD, with (n-tuples of ints) : (numpy array) pairs
"""
checkParams(inputFormat, ['text', 'binary', 'npy', 'mat'])
from thunder.rdds.fileio.seriesloader import SeriesLoader
loader = SeriesLoader(self._sc, minPartitions=minPartitions)
if inputFormat.lower() == 'binary':
data = loader.fromBinary(dataPath,
confFilename=confFilename,
nkeys=nkeys,
nvalues=nvalues,
keyType=keyType,
valueType=valueType,
maxPartitionSize=maxPartitionSize)
elif inputFormat.lower() == 'text':
if nkeys is None:
raise Exception(
'Must provide number of keys per record for loading from text'
)
data = loader.fromText(dataPath, nkeys=nkeys)
elif inputFormat.lower() == 'npy':
data = loader.fromNpyLocal(dataPath, keyPath)
else:
if varName is None:
raise Exception(
'Must provide variable name for loading MAT files')
data = loader.fromMatLocal(dataPath, varName, keyPath)
return data
def loadImages(self,
dataPath,
dims=None,
dtype=None,
inputFormat='stack',
ext=None,
startIdx=None,
stopIdx=None,
recursive=False,
nplanes=None,
npartitions=None,
renumber=False,
confFilename='conf.json'):
"""
Loads an Images object from data stored as a binary image stack, tif, or png files.
Supports single files or multiple files, stored on a local file system, a networked file sytem
(mounted and available on all nodes), Amazon S3, or Google Storage.
HDFS is not currently supported for image file data.
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
dims: tuple of positive int, optional (required if inputFormat is 'stack')
Image dimensions. Binary stack data will be interpreted as a multidimensional array
with the given dimensions, and should be stored in row-major order (Fortran or Matlab convention),
where the first dimension changes most rapidly. For 'png' or 'tif' data dimensions
will be read from the image file headers.
inputFormat: str, optional, default = 'stack'
Expected format of the input data: 'stack', 'png', or 'tif'. 'stack' indicates flat binary stacks.
'png' or 'tif' indicate image format. Page of a multipage tif file will be extend along
the third dimension. Separate files interpreted as distinct records, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default = None
File extension, default will be "bin" if inputFormat=="stack", "tif" for inputFormat=='tif',
and 'png' for inputFormat=="png".
dtype: string or numpy dtype, optional, default = 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string.
Ignored for 'tif' or 'png' (data will be inferred from image formats).
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position). These parameters give the starting
and final index after lexicographic sorting.
stopIdx: nonnegative int, optional, default = None
See startIdx.
recursive: boolean, optional, default = False
If true, will recursively descend directories rooted at dataPath, loading all files
in the tree with an appropriate extension.
nplanes: positive integer, optional, default = None
Subdivide individual image files. Every `nplanes` from each file will be considered a new record.
With nplanes=None (the default), a single file will be considered as representing a single record.
If the number of records per file is not the same across all files, then `renumber` should be set
to True to ensure consistent keys.
npartitions: positive int, optional, default = None
Specify number of partitions for the RDD, if unspecified will use as many partitions
as available cores
renumber: boolean, optional, default = False
Recalculate keys for records after images are loading. Only necessary if different files contain
different number of records (e.g. due to specifying nplanes). See Images.renumber().
confFilename : string, optional, default = 'conf.json'
Name of conf file if using to specify parameters for binary stack data
Returns
-------
data: thunder.rdds.Images
An Images object, wrapping an RDD of with (int) : (numpy array) pairs
"""
checkParams(inputFormat, ['stack', 'png', 'tif', 'tif-stack'])
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if npartitions is None:
npartitions = self._sc.defaultParallelism
# Checking StartIdx is smaller or equal to StopIdx
if startIdx is not None and stopIdx is not None and startIdx > stopIdx:
raise Exception(
"Error. startIdx {} is larger than stopIdx {}".inputFormat(
startIdx, stopIdx))
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
if inputFormat.lower() == 'stack':
data = loader.fromStack(dataPath,
dims=dims,
dtype=dtype,
ext=ext,
startIdx=startIdx,
stopIdx=stopIdx,
recursive=recursive,
nplanes=nplanes,
npartitions=npartitions,
confFilename=confFilename)
elif inputFormat.lower().startswith('tif'):
data = loader.fromTif(dataPath,
ext=ext,
startIdx=startIdx,
stopIdx=stopIdx,
recursive=recursive,
nplanes=nplanes,
npartitions=npartitions)
else:
if nplanes:
raise NotImplementedError(
"nplanes argument is not supported for png files")
data = loader.fromPng(dataPath,
ext=ext,
startIdx=startIdx,
stopIdx=stopIdx,
recursive=recursive,
npartitions=npartitions)
if not renumber:
return data
else:
return data.renumber()
def loadSeriesFromArray(self, values, index=None, npartitions=None):
"""
Load Series data from a local array
Parameters
----------
values : list or ndarray
A list of 1d numpy arrays, or a single 2d numpy array
index : array-like, optional, deafult = None
Index to set for Series object, if None will use linear indices.
npartitions : position int, optional, default = None
Number of partitions for RDD, if unspecified will use
default parallelism.
"""
from numpy import ndarray, asarray
from thunder.rdds.fileio.seriesloader import SeriesLoader
loader = SeriesLoader(self._sc)
if not npartitions:
npartitions = self._sc.defaultParallelism
if isinstance(values, list):
values = asarray(values)
if isinstance(values, ndarray) and values.ndim > 1:
values = list(values)
data = loader.fromArrays(values, npartitions=npartitions)
if index:
data.index = index
return data
def loadImagesFromArray(self, values, npartitions=None):
"""
Load Images data from a local array
Parameters
----------
values : list or ndarray
A list of 2d or 3d numpy arrays,
or a single 3d or 4d numpy array
npartitions : position int, optional, default = None
Number of partitions for RDD, if unspecified will use
default parallelism.
"""
from numpy import ndarray, asarray
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if isinstance(values, list):
values = asarray(values)
if isinstance(values, ndarray) and values.ndim > 2:
values = list(values)
if not npartitions:
npartitions = self._sc.defaultParallelism
return loader.fromArrays(values, npartitions=npartitions)
def loadImagesOCP(self,
bucketName,
resolution,
server='ocp.me',
startIdx=None,
stopIdx=None,
minBound=None,
maxBound=None):
"""
Load Images from OCP (Open Connectome Project).
The OCP is a web service for access to EM brain images and other neural image data.
The web-service can be accessed at http://www.openconnectomeproject.org/.
Parameters
----------
bucketName: string
Token name for the project in OCP. This name should exist on the server from which data is loaded.
resolution: nonnegative int
Resolution of the data in OCP
server: string, optional, default = 'ocp.me'
Name of the OCP server with the specified token.
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position).
stopIdx: nonnegative int, optional
See startIdx.
minBound, maxBound: tuple of nonnegative int, optional, default = None
X,Y,Z bounds of the data to fetch from OCP. minBound contains the (xMin,yMin,zMin) while
maxBound contains (xMax,yMax,zMax).
Returns
-------
data: thunder.rdds.Images
An Images object, wrapping an RDD of with (int) : (numpy array) pairs
"""
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
# Checking StartIdx is smaller or equal to StopIdx
if startIdx is not None and stopIdx is not None and startIdx > stopIdx:
raise Exception(
"Error. startIdx {} is larger than stopIdx {}".format(
startIdx, stopIdx))
data = loader.fromOCP(bucketName,
resolution=resolution,
server=server,
startIdx=startIdx,
stopIdx=stopIdx,
minBound=minBound,
maxBound=maxBound)
return data
def loadImagesAsSeries(self,
dataPath,
dims=None,
inputFormat='stack',
ext=None,
dtype='int16',
blockSize="150M",
blockSizeUnits="pixels",
startIdx=None,
stopIdx=None,
recursive=False,
nplanes=None,
npartitions=None,
renumber=False,
confFilename='conf.json'):
"""
Load Images data as Series data.
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
dims: tuple of positive int, optional (required if inputFormat is 'stack')
Image dimensions. Binary stack data will be interpreted as a multidimensional array
with the given dimensions, and should be stored in row-major order (Fortran or Matlab convention),
where the first dimension changes most rapidly. For 'png' or 'tif' data dimensions
will be read from the image file headers.
inputFormat: str, optional, default = 'stack'
Expected format of the input data: 'stack', 'png', or 'tif'. 'stack' indicates flat binary stacks.
'png' or 'tif' indicate image formats. Page of a multipage tif file will be extend along
the third dimension. Separate files interpreted as distinct records, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default = None
File extension, default will be "bin" if inputFormat=="stack", "tif" for inputFormat=='tif',
and 'png' for inputFormat=="png".
dtype: string or numpy dtype. optional, default 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string.
Ignored for 'tif' or 'png' (data will be inferred from image formats).
blockSize: string or positive int, optional, default "150M"
Requested size of blocks (e.g "64M", "512k", "2G"). If shuffle=True, can also be a
tuple of int specifying the number of pixels or splits per dimension. Indirectly
controls the number of Spark partitions, with one partition per block.
blockSizeUnits: string, either "pixels" or "splits", default "pixels"
Units for interpreting a tuple passed as blockSize when shuffle=True.
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position). These parameters give the starting
and final index after lexicographic sorting.
stopIdx: nonnegative int, optional, default = None
See startIdx.
recursive: boolean, optional, default = False
If true, will recursively descend directories rooted at dataPath, loading all files
in the tree with an appropriate extension.
nplanes: positive integer, optional, default = None
Subdivide individual image files. Every `nplanes` from each file will be considered a new record.
With nplanes=None (the default), a single file will be considered as representing a single record.
If the number of records per file is not the same across all files, then `renumber` should be set
to True to ensure consistent keys.
npartitions: positive int, optional, default = None
Specify number of partitions for the RDD, if unspecified will use 1 partition per image.
renumber: boolean, optional, default = False
Recalculate keys for records after images are loading. Only necessary if different files contain
different number of records (e.g. due to specifying nplanes). See Images.renumber().
confFilename : string, optional, default = 'conf.json'
Name of conf file if using to specify parameters for binary stack data
Returns
-------
data: thunder.rdds.Series
A Series object, wrapping an RDD, with (n-tuples of ints) : (numpy array) pairs.
Keys will be n-tuples of int, with n given by dimensionality of the images, and correspond
to indexes into the image arrays. Value will have length equal to the number of image files.
With each image contributing one point to this value array, with ordering given by
the lexicographic ordering of image file names.
"""
checkParams(inputFormat, ['stack', 'tif', 'tif-stack'])
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputFormat.lower() == 'stack':
images = loader.fromStack(dataPath,
dims,
dtype=dtype,
ext=ext,
startIdx=startIdx,
stopIdx=stopIdx,
recursive=recursive,
nplanes=nplanes,
npartitions=npartitions,
confFilename=confFilename)
else:
# tif / tif stack
images = loader.fromTif(dataPath,
ext=ext,
startIdx=startIdx,
stopIdx=stopIdx,
recursive=recursive,
nplanes=nplanes,
npartitions=npartitions)
if renumber:
images = images.renumber()
return images.toBlocks(blockSize, units=blockSizeUnits).toSeries()
def convertImagesToSeries(self,
dataPath,
outputDirPath,
dims=None,
inputFormat='stack',
ext=None,
dtype='int16',
blockSize="150M",
blockSizeUnits="pixels",
startIdx=None,
stopIdx=None,
overwrite=False,
recursive=False,
nplanes=None,
npartitions=None,
renumber=False,
confFilename='conf.json'):
"""
Write out Images data as Series data, saved in a flat binary format.
The resulting files may subsequently be read in using ThunderContext.loadSeries().
Loading Series data directly will likely be faster than converting image data
to a Series object through loadImagesAsSeries().
Parameters
----------
dataPath: string
Path to data files or directory, as either a local filesystem path or a URI.
May include a single '*' wildcard in the filename. Examples of valid dataPaths include
'local/directory/*.stack", "s3n:///my-s3-bucket/data/", or "file:///mnt/another/directory/".
outputDirPath: string
Path to directory to write Series file output. May be either a path on the local file system
or a URI-like format, such as "local/directory", "s3n:///my-s3-bucket/data/",
or "file:///mnt/another/directory/". If the directory exists and 'overwrite' is True,
the existing directory and all its contents will be deleted and overwritten.
dims: tuple of positive int, optional (required if inputFormat is 'stack')
Image dimensions. Binary stack data will be interpreted as a multidimensional array
with the given dimensions, and should be stored in row-major order (Fortran or Matlab convention),
where the first dimension changes most rapidly. For 'png' or 'tif' data dimensions
will be read from the image file headers.
inputFormat: str, optional, default = 'stack'
Expected format of the input data: 'stack', 'png', or 'tif'. 'stack' indicates flat binary stacks.
'png' or 'tif' indicate image formats. Page of a multipage tif file will be extend along
the third dimension. Separate files interpreted as distinct records, with ordering
given by lexicographic sorting of file names.
ext: string, optional, default = None
File extension, default will be "bin" if inputFormat=="stack", "tif" for inputFormat=='tif',
and 'png' for inputFormat=="png".
dtype: string or numpy dtype. optional, default 'int16'
Data type of the image files to be loaded, specified as a numpy "dtype" string.
Ignored for 'tif' or 'png' (data will be inferred from image formats).
blockSize: string or positive int, optional, default "150M"
Requested size of blocks (e.g "64M", "512k", "2G"). If shuffle=True, can also be a
tuple of int specifying the number of pixels or splits per dimension. Indirectly
controls the number of Spark partitions, with one partition per block.
blockSizeUnits: string, either "pixels" or "splits", default "pixels"
Units for interpreting a tuple passed as blockSize when shuffle=True.
startIdx: nonnegative int, optional, default = None
Convenience parameters to read only a subset of input files. Uses python slice conventions
(zero-based indexing with exclusive final position). These parameters give the starting
and final index after lexicographic sorting.
stopIdx: nonnegative int, optional, default = None
See startIdx.
overwrite: boolean, optional, default False
If true, the directory specified by outputDirPath will be deleted (recursively) if it
already exists. (Use with caution.)
recursive: boolean, optional, default = False
If true, will recursively descend directories rooted at dataPath, loading all files
in the tree with an appropriate extension.
nplanes: positive integer, optional, default = None
Subdivide individual image files. Every `nplanes` from each file will be considered a new record.
With nplanes=None (the default), a single file will be considered as representing a single record.
If the number of records per file is not the same across all files, then `renumber` should be set
to True to ensure consistent keys.
npartitions: positive int, optional, default = None
Specify number of partitions for the RDD, if unspecified will use 1 partition per image.
renumber: boolean, optional, default = False
Recalculate keys for records after images are loading. Only necessary if different files contain
different number of records (e.g. due to specifying nplanes). See Images.renumber().
confFilename : string, optional, default = 'conf.json'
Name of conf file if using to specify parameters for binary stack data
"""
checkParams(inputFormat, ['stack', 'tif', 'tif-stack'])
if not overwrite:
raiseErrorIfPathExists(outputDirPath,
awsCredentialsOverride=self._credentials)
overwrite = True # prevent additional downstream checks for this path
if not ext:
ext = DEFAULT_EXTENSIONS.get(inputFormat.lower(), None)
from thunder.rdds.fileio.imagesloader import ImagesLoader
loader = ImagesLoader(self._sc)
if inputFormat.lower() == 'stack':
images = loader.fromStack(dataPath,
dims,
ext=ext,
dtype=dtype,
startIdx=startIdx,
stopIdx=stopIdx,
recursive=recursive,
nplanes=nplanes,
npartitions=npartitions,
confFilename=confFilename)
else:
# 'tif' or 'tif-stack'
images = loader.fromTif(dataPath,
ext=ext,
startIdx=startIdx,
stopIdx=stopIdx,
recursive=recursive,
nplanes=nplanes,
npartitions=npartitions)
if renumber:
images = images.renumber()
images.toBlocks(blockSize, units=blockSizeUnits).saveAsBinarySeries(
outputDirPath, overwrite=overwrite)
def makeExample(self, dataset=None, **opts):
"""
Make an example data set for testing analyses.
Options include 'pca', 'factor', 'kmeans', 'ica', 'sources'
See thunder.utils.datasets for detailed options.
Parameters
----------
dataset : str
Which dataset to generate
Returns
-------
data : RDD of (tuple, array) pairs
Generated dataset
"""
from thunder.utils.datasets import DATASET_MAKERS
if dataset is None:
return sorted(DATASET_MAKERS.keys())
checkParams(dataset, DATASET_MAKERS.keys())
return DataSets.make(self._sc, dataset, **opts)
def loadExample(self, dataset=None):
"""
Load a local example data set for testing analyses.
Some of these data sets are extremely downsampled and should be considered
useful only for testing the API. If called with None,
will return list of available datasets.
Parameters
----------
dataset : str
Which dataset to load
Returns
-------
data : Data object
Generated dataset as a Thunder data objects (e.g Series or Images)
"""
import atexit
import shutil
import tempfile
from pkg_resources import resource_listdir, resource_filename
DATASETS = {
'iris': 'iris',
'fish-series': 'fish/series',
'fish-images': 'fish/images',
'mouse-series': 'mouse/series',
'mouse-images': 'mouse/images',
'mouse-params': 'mouse/params'
}
if dataset is None:
return sorted(DATASETS.keys())
checkParams(dataset, DATASETS.keys())
if 'ec2' in self._sc.master:
tmpdir = os.path.join('/root/thunder/thunder/utils', 'data',
DATASETS[dataset])
else:
tmpdir = tempfile.mkdtemp()
atexit.register(shutil.rmtree, tmpdir)
def copyLocal(target):
files = resource_listdir('thunder.utils.data', target)
for f in files:
path = resource_filename('thunder.utils.data',
os.path.join(target, f))
shutil.copy(path, tmpdir)
copyLocal(DATASETS[dataset])
npartitions = self._sc.defaultParallelism
if dataset == "iris":
return self.loadSeries(tmpdir)
elif dataset == "fish-series":
return self.loadSeries(tmpdir).astype('float')
elif dataset == "fish-images":
return self.loadImages(tmpdir,
inputFormat="tif",
npartitions=npartitions)
elif dataset == "mouse-series":
return self.loadSeries(tmpdir).astype('float')
elif dataset == "mouse-images":
return self.loadImages(tmpdir, npartitions=npartitions)
elif dataset == "mouse-params":
return self.loadParams(os.path.join(tmpdir, 'covariates.json'))
def loadExampleS3(self, dataset=None):
"""
Load an example data set from S3.
Info on the included datasets can be found at the CodeNeuro data repository
(http://datasets.codeneuro.org/). If called with None, will return
list of available datasets.
Parameters
----------
dataset : str
Which dataset to load
Returns
-------
data : a Data object (usually a Series or Images)
The dataset as one of Thunder's data objects
params : dict
Parameters or metadata for dataset
"""
DATASETS = {
'ahrens.lab/direction.selectivity':
'ahrens.lab/direction.selectivity/1/',
'ahrens.lab/optomotor.response':
'ahrens.lab/optomotor.response/1/',
'svoboda.lab/tactile.navigation':
'svoboda.lab/tactile.navigation/1/'
}
if dataset is None:
return DATASETS.keys()
if 'local' in self._sc.master:
raise Exception(
"Must be running on an EC2 cluster to load this example data set"
)
checkParams(dataset, DATASETS.keys())
basePath = 's3n://neuro.datasets/'
dataPath = DATASETS[dataset]
data = self.loadSeries(basePath + dataPath + 'series')
params = self.loadParams(basePath + dataPath +
'params/covariates.json')
return data, params
def loadJSON(self, path):
"""
Generic function for loading JSON from a path, handling local file systems and S3 or GS
Parameters
----------
path : str
Path to a file, can be on a local file system or an S3 or GS bucket
Returns
-------
A string with the JSON
"""
import json
from thunder.rdds.fileio.readers import getFileReaderForPath, FileNotFoundError
from thunder.utils.serializable import _decode_dict
reader = getFileReaderForPath(path)(
awsCredentialsOverride=self._credentials)
try:
buffer = reader.read(path)
except FileNotFoundError:
raise Exception("Cannot find file %s" % path)
return json.loads(buffer, object_hook=_decode_dict)
def loadParams(self, path):
"""
Load a file with parameters from a local file system or S3 or GS.
Assumes file is JSON with basic types (strings, integers, doubles, lists),
in either a single dict or list of dict-likes, and each dict has at least
a "name" field and a "value" field.
Useful for loading generic meta data, parameters, covariates, etc.
Parameters
----------
path : str
Path to file, can be on a local file system or an S3 or GS bucket
Returns
-------
A dict or list with the parameters
"""
blob = self.loadJSON(path)
return Params(blob)
def loadSources(self, path):
"""
Load a file with sources from a local file system or S3 or GS.
Parameters
----------
path : str
Path to file, can be on a local file system or an S3 or GS bucket
Returns
-------
A SourceModel
See also
--------
SourceExtraction
"""
from thunder import SourceExtraction
blob = self.loadJSON(path)
return SourceExtraction.deserialize(blob)
def export(self,
data,
filename,
outputFormat=None,
overwrite=False,
varname=None):
"""
Export local array data to a variety of formats.
Can write to a local file sytem or S3 or GS (destination inferred from filename schema).
S3 or GS writing useful for persisting arrays when working in an environment without
accessible local storage.
Parameters
----------
data : array-like
The data to export
filename : str
Output location (path/to/file.ext)
outputFormat : str, optional, default = None
Ouput format ("npy", "mat", or "txt"), if not provided will
try to infer from file extension.
overwrite : boolean, optional, default = False
Whether to overwrite if directory or file already exists
varname : str, optional, default = None
Variable name for writing "mat" formatted files
"""
from numpy import save, savetxt, asarray
from scipy.io import savemat
from StringIO import StringIO
from thunder.rdds.fileio.writers import getFileWriterForPath
path, file, outputFormat = handleFormat(filename, outputFormat)
checkParams(outputFormat, ["npy", "mat", "txt"])
clazz = getFileWriterForPath(filename)
writer = clazz(path,
file,
overwrite=overwrite,
awsCredentialsOverride=self._credentials)
stream = StringIO()
if outputFormat == "mat":
varname = os.path.splitext(file)[0] if varname is None else varname
savemat(stream,
mdict={varname: data},
oned_as='column',
do_compression='true')
if outputFormat == "npy":
save(stream, data)
if outputFormat == "txt":
if asarray(data).ndim > 2:
raise Exception(
"Cannot write data with more than two dimensions to text")
savetxt(stream, data)
stream.seek(0)
writer.writeFile(stream.buf)
def setAWSCredentials(self, awsAccessKeyId, awsSecretAccessKey):
"""
Manually set AWS access credentials to be used by Thunder.
Provided for hosted cloud environments without filesystem access. If
launching a cluster using the thunder-ec2 script, credentials will be
configured automatically (inside core-site.xml and ~/.boto), so this
method should not need to be called.
Parameters
----------
awsAccessKeyId : string
AWS public key, usually starts with "AKIA"
awsSecretAccessKey : string
AWS private key
"""
from thunder.utils.aws import AWSCredentials
self._credentials = AWSCredentials(awsAccessKeyId, awsSecretAccessKey)
self._credentials.setOnContext(self._sc)