def create_file_reader(input_files,
topology,
featurizer,
chunk_size=1000,
**kw):
r"""
Creates a (possibly featured) file reader by a number of input files and either a topology file or a featurizer.
Parameters
----------
:param input_files:
A single input file or a list of input files.
:param topology:
A topology file. If given, the featurizer argument can be None.
:param featurizer:
A featurizer. If given, the topology file can be None.
:param chunk_size:
The chunk size with which the corresponding reader gets initialized.
:return: Returns the reader.
"""
from pyemma.coordinates.data.numpy_filereader import NumPyFileReader
from pyemma.coordinates.data.py_csv_reader import PyCSVReader
from pyemma.coordinates.data import FeatureReader
from pyemma.coordinates.data.fragmented_trajectory_reader import FragmentedTrajectoryReader
# fragmented trajectories
if (isinstance(input_files, (list, tuple)) and len(input_files) > 0
and any(isinstance(item, (list, tuple)) for item in input_files)):
return FragmentedTrajectoryReader(input_files, topology, chunk_size,
featurizer)
# normal trajectories
if (isinstance(input_files, string_types)
or (isinstance(input_files, (list, tuple)) and
(any(isinstance(item, string_types)
for item in input_files) or len(input_files) is 0))):
reader = None
# check: if single string create a one-element list
if isinstance(input_files, string_types):
input_list = [input_files]
elif len(input_files) > 0 and all(
isinstance(item, string_types) for item in input_files):
input_list = input_files
else:
if len(input_files) is 0:
raise ValueError("The passed input list should not be empty.")
else:
raise ValueError(
"The passed list did not exclusively contain strings or was a list of lists "
"(fragmented trajectory).")
# TODO: this does not handle suffixes like .xyz.gz (rare)
_, suffix = os.path.splitext(input_list[0])
# check: do all files have the same file type? If not: raise ValueError.
if all(item.endswith(suffix) for item in input_list):
# do all the files exist? If not: Raise value error
all_exist = True
err_msg = ""
for item in input_list:
if not os.path.isfile(item):
err_msg += "\n" if len(err_msg) > 0 else ""
err_msg += "File %s did not exist or was no file" % item
all_exist = False
if not all_exist:
raise ValueError(
"Some of the given input files were directories"
" or did not exist:\n%s" % err_msg)
if all_exist:
from mdtraj.formats.registry import FormatRegistry
# CASE 1.1: file types are MD files
if suffix in list(FormatRegistry.loaders.keys()):
# check: do we either have a featurizer or a topology file name? If not: raise ValueError.
# create a MD reader with file names and topology
if not featurizer and not topology:
raise ValueError(
"The input files were MD files which makes it mandatory to have either a "
"featurizer or a topology file.")
reader = FeatureReader(input_list,
featurizer=featurizer,
topologyfile=topology,
chunksize=chunk_size)
else:
if suffix in ['.npy', '.npz']:
reader = NumPyFileReader(input_list,
chunksize=chunk_size)
# otherwise we assume that given files are ascii tabulated data
else:
reader = PyCSVReader(input_list,
chunksize=chunk_size,
**kw)
else:
raise ValueError(
"Not all elements in the input list were of the type %s!" %
suffix)
else:
raise ValueError("Input \"%s\" was no string or list of strings." %
input)
return reader
def _get_reader_instance(self, instance_number):
if instance_number == 0:
return DataInMemory(self.data)
elif instance_number == 1:
return FeatureReader(self.data_feature_reader,
topologyfile=self.topfile)
def create_file_reader(input_files, topology, featurizer, chunksize=None, **kw):
r"""
Creates a (possibly featured) file reader by a number of input files and either a topology file or a featurizer.
Parameters
----------
:param input_files:
A single input file or a list of input files.
:param topology:
A topology file. If given, the featurizer argument can be None.
:param featurizer:
A featurizer. If given, the topology file can be None.
:param chunksize:
The chunk size with which the corresponding reader gets initialized.
:return: Returns the reader.
"""
from pyemma.coordinates.data.numpy_filereader import NumPyFileReader
from pyemma.coordinates.data.py_csv_reader import PyCSVReader
from pyemma.coordinates.data import FeatureReader
from pyemma.coordinates.data.fragmented_trajectory_reader import FragmentedTrajectoryReader
# fragmented trajectories
if (isinstance(input_files, (list, tuple)) and len(input_files) > 0 and
any(isinstance(item, (list, tuple)) for item in input_files)):
return FragmentedTrajectoryReader(input_files, topology, chunksize, featurizer)
# normal trajectories
if (isinstance(input_files, (Path, str))
or (isinstance(input_files, (list, tuple))
and (any(isinstance(item, (Path, str)) for item in input_files)
or len(input_files) == 0))):
# check: if single string create a one-element list
if isinstance(input_files, (Path, str)):
input_list = [input_files]
elif len(input_files) > 0 and all(isinstance(item, (Path, str)) for item in input_files):
input_list = input_files
else:
if len(input_files) == 0:
raise ValueError("The passed input list should not be empty.")
else:
raise ValueError("The passed list did not exclusively contain strings or was a list of lists "
"(fragmented trajectory).")
# convert to list of paths
input_list = [Path(f) for f in input_list]
# TODO: this does not handle suffixes like .xyz.gz (rare)
suffix = input_list[0].suffix
# check: do all files have the same file type? If not: raise ValueError.
if all(item.suffix == suffix for item in input_list):
# do all the files exist? If not: Raise value error
all_exist = True
from six import StringIO
err_msg = StringIO()
for item in input_list:
if not item.is_file():
err_msg.write('\n' if err_msg.tell() > 0 else "")
err_msg.write('File %s did not exist or was no file' % item)
all_exist = False
if not all_exist:
raise ValueError('Some of the given input files were directories'
' or did not exist:\n%s' % err_msg.getvalue())
featurizer_or_top_provided = featurizer is not None or topology is not None
# we need to check for h5 first, because of mdtraj custom HDF5 traj format (which is deprecated).
if suffix in ('.h5', '.hdf5') and not featurizer_or_top_provided:
# This check is potentially expensive for lots of files, we also re-open the file twice (causing atime updates etc.)
# So we simply require that no featurizer option is given.
# and not all((_is_mdtraj_hdf5_file(f) for f in input_files)):
from pyemma.coordinates.data.h5_reader import H5Reader
reader = H5Reader(filenames=input_files, chunk_size=chunksize, **kw)
# CASE 1.1: file types are MD files
elif FeatureReader.supports_format(suffix):
# check: do we either have a featurizer or a topology file name? If not: raise ValueError.
# create a MD reader with file names and topology
if not featurizer_or_top_provided:
raise ValueError('The input files were MD files which makes it mandatory to have either a '
'Featurizer or a topology file.')
if suffix in ('.pdb', '.pdb.gz'):
raise ValueError('PyEMMA can not read PDB-fake-trajectories. '
'Please consider using a sane trajectory format (e.g. xtc, dcd).')
reader = FeatureReader(input_list, featurizer=featurizer, topologyfile=topology,
chunksize=chunksize)
elif suffix in ('.npy', '.npz'):
reader = NumPyFileReader(input_list, chunksize=chunksize)
# otherwise we assume that given files are ascii tabulated data
else:
reader = PyCSVReader(input_list, chunksize=chunksize, **kw)
else:
raise ValueError('Not all elements in the input list were of the type %s!' % suffix)
else:
raise ValueError('Input "{}" was no string or list of strings.'.format(input_files))
return reader