def loadSeriesLocal(self,
dataFilePath,
inputFormat='npy',
minPartitions=None,
keyFilePath=None,
varName=None):
"""
Load a Series object from a local file (either npy or MAT format).
File should contain a 1d or 2d matrix, where each row
of the input matrix is a record.
Keys can be provided in a separate file (with variable name 'keys', for MAT files).
If not provided, linear indices will be used for keys.
Parameters
----------
dataFilePath: str
File to import
varName : str, optional, default = None
Variable name to load (for MAT files only)
keyFilePath : str, optional, default = None
File containing the keys for each record as another 1d or 2d array
minPartitions : Int, optional, default = 1
Number of partitions for RDD
"""
checkParams(inputFormat, ['mat', 'npy'])
from thunder.rdds.fileio.seriesloader import SeriesLoader
loader = SeriesLoader(self._sc, minPartitions=minPartitions)
if inputFormat.lower() == 'mat':
if varName is None:
raise Exception(
'Must provide variable name for loading MAT files')
data = loader.fromMatLocal(dataFilePath, varName, keyFilePath)
else:
data = loader.fromNpyLocal(dataFilePath, keyFilePath)
return data
def loadSeriesLocal(self, datafile, inputformat='npy', minPartitions=None, keyfile=None, varname=None):
"""
Load a Series object from a local file (either npy or MAT format).
File should contain a 1d or 2d matrix, where each row
of the input matrix is a record.
Keys can be provided in a separate file (with variable name 'keys', for MAT files).
If not provided, linear indices will be used for keys.
Parameters
----------
datafile : str
File to import
varname : str, optional, default = None
Variable name to load (for MAT files only)
keyfile : str, optional, default = None
File containing the keys for each record as another 1d or 2d array
minPartitions : Int, optional, default = 1
Number of partitions for RDD
"""
checkparams(inputformat, ['mat', 'npy'])
from thunder.rdds.fileio.seriesloader import SeriesLoader
loader = SeriesLoader(self._sc, minPartitions=minPartitions)
if inputformat.lower() == 'mat':
if varname is None:
raise Exception('Must provide variable name for loading MAT files')
data = loader.fromMatLocal(datafile, varname, keyfile)
else:
data = loader.fromNpyLocal(datafile, keyfile)
return data
def loadSeries(self, dataPath, nkeys=None, nvalues=None, inputFormat='binary', minPartitions=None,
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.
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)
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
