def create_dataset(self,
input_files: OneOrMany[str],
data_dir: Optional[str] = None,
shard_size: Optional[int] = None) -> DiskDataset:
"""Creates a `Dataset` from input FASTA files.
At present, FASTA support is limited and only allows for one-hot
featurization, and doesn't allow for sharding.
Parameters
----------
input_files: list
List of fasta files.
data_dir: str, optional
Name of directory where featurized data is stored.
shard_size: int, optional
For now, this argument is ignored and each FASTA file gets its
own shard.
Returns
-------
A `Dataset` object containing a featurized representation of data
from `input_files`.
"""
if isinstance(input_files, str):
input_files = [input_files]
def shard_generator():
for input_file in input_files:
X = encode_fasta_sequence(input_file)
ids = np.ones(len(X))
# (X, y, w, ids)
yield X, None, None, ids
return DiskDataset.create_dataset(shard_generator(), data_dir)
def _to_singletask(dataset, task_dirs):
"""Transforms a multitask dataset to a collection of singletask datasets."""
tasks = dataset.get_task_names()
assert len(tasks) == len(task_dirs)
log("Splitting multitask dataset into singletask datasets",
dataset.verbose)
task_datasets = [
DiskDataset.create_dataset([], task_dirs[task_num], [task])
for (task_num, task) in enumerate(tasks)
]
#task_metadata_rows = {task: [] for task in tasks}
for shard_num, (X, y, w, ids) in enumerate(dataset.itershards()):
log("Processing shard %d" % shard_num, dataset.verbose)
basename = "dataset-%d" % shard_num
for task_num, task in enumerate(tasks):
log("\tTask %s" % task, dataset.verbose)
w_task = w[:, task_num]
y_task = y[:, task_num]
# Extract those datapoints which are present for this task
X_nonzero = X[w_task != 0]
num_datapoints = X_nonzero.shape[0]
y_nonzero = np.reshape(y_task[w_task != 0],
(num_datapoints, 1))
w_nonzero = np.reshape(w_task[w_task != 0],
(num_datapoints, 1))
ids_nonzero = ids[w_task != 0]
task_datasets[task_num].add_shard(X_nonzero, y_nonzero,
w_nonzero, ids_nonzero)
return task_datasets
def featurize(self, input_files, data_dir=None, shard_size=8192):
"""Featurize provided files and write to specified location."""
log("Loading raw samples now.", self.verbose)
log("shard_size: %d" % shard_size, self.verbose)
if not isinstance(input_files, list):
input_files = [input_files]
def shard_generator():
for shard_num, shard in enumerate(
self.get_shards(input_files, shard_size)):
time1 = time.time()
X, valid_inds = self.featurize_shard(shard)
ids, y, w = convert_df_to_numpy(shard, self.tasks,
self.id_field)
# Filter out examples where featurization failed.
ids, y, w = (ids[valid_inds], y[valid_inds], w[valid_inds])
assert len(X) == len(ids) == len(y) == len(w)
time2 = time.time()
log(
"TIMING: featurizing shard %d took %0.3f s" %
(shard_num, time2 - time1), self.verbose)
yield X, y, w, ids
return DiskDataset.create_dataset(shard_generator(), data_dir,
self.tasks)
def _to_singletask(dataset, task_dirs):
"""Transforms a multitask dataset to a collection of singletask datasets."""
tasks = dataset.get_task_names()
assert len(tasks) == len(task_dirs)
log("Splitting multitask dataset into singletask datasets", dataset.verbose)
task_datasets = [DiskDataset.create_dataset([], task_dirs[task_num], [task])
for (task_num, task) in enumerate(tasks)]
#task_metadata_rows = {task: [] for task in tasks}
for shard_num, (X, y, w, ids) in enumerate(dataset.itershards()):
log("Processing shard %d" % shard_num, dataset.verbose)
basename = "dataset-%d" % shard_num
for task_num, task in enumerate(tasks):
log("\tTask %s" % task, dataset.verbose)
w_task = w[:, task_num]
y_task = y[:, task_num]
# Extract those datapoints which are present for this task
X_nonzero = X[w_task != 0]
num_datapoints = X_nonzero.shape[0]
y_nonzero = np.reshape(y_task[w_task != 0], (num_datapoints, 1))
w_nonzero = np.reshape(w_task[w_task != 0], (num_datapoints, 1))
ids_nonzero = ids[w_task != 0]
task_datasets[task_num].add_shard(X_nonzero, y_nonzero, w_nonzero,
ids_nonzero)
return task_datasets
def featurize(self, input_files, data_dir=None, shard_size=8192):
"""Featurize provided files and write to specified location."""
log("Loading raw samples now.", self.verbose)
log("shard_size: %d" % shard_size, self.verbose)
if not isinstance(input_files, list):
input_files = [input_files]
def shard_generator():
for shard_num, shard in enumerate(
self.get_shards(input_files, shard_size)):
time1 = time.time()
X, valid_inds = self.featurize_shard(shard)
ids = shard[self.id_field].values
ids = ids[valid_inds]
if len(self.tasks) > 0:
# Featurize task results iff they exist.
y, w = convert_df_to_numpy(shard, self.tasks, self.id_field)
# Filter out examples where featurization failed.
y, w = (y[valid_inds], w[valid_inds])
assert len(X) == len(ids) == len(y) == len(w)
else:
# For prospective data where results are unknown, it makes
# no sense to have y values or weights.
y, w = (None, None)
assert len(X) == len(ids)
time2 = time.time()
log("TIMING: featurizing shard %d took %0.3f s" %
(shard_num, time2 - time1), self.verbose)
yield X, y, w, ids
return DiskDataset.create_dataset(
shard_generator(), data_dir, self.tasks, verbose=self.verbose)
def create_dataset(self, input_files, data_dir=None, shard_size=8192):
"""Creates and returns a `Dataset` object by featurizing provided files.
Reads in `input_files` and uses `self.featurizer` to featurize the
data in these input files. For large files, automatically shards
into smaller chunks of `shard_size` datapoints for convenience.
Returns a `Dataset` object that contains the featurized dataset.
This implementation assumes that the helper methods `_get_shards`
and `_featurize_shard` are implemented and that each shard
returned by `_get_shards` is a pandas dataframe. You may choose
to reuse or override this method in your subclass implementations.
Parameters
----------
input_files: list
List of input filenames.
data_dir: str, optional
Directory to store featurized dataset.
shard_size: int, optional
Number of examples stored in each shard.
Returns
-------
A `Dataset` object containing a featurized representation of data
from `input_files`.
"""
logger.info("Loading raw samples now.")
logger.info("shard_size: %d" % shard_size)
if not isinstance(input_files, list):
input_files = [input_files]
def shard_generator():
for shard_num, shard in enumerate(
self._get_shards(input_files, shard_size)):
time1 = time.time()
X, valid_inds = self._featurize_shard(shard)
ids = shard[self.id_field].values
ids = ids[valid_inds]
if len(self.tasks) > 0:
# Featurize task results iff they exist.
y, w = _convert_df_to_numpy(shard, self.tasks)
# Filter out examples where featurization failed.
y, w = (y[valid_inds], w[valid_inds])
assert len(X) == len(ids) == len(y) == len(w)
else:
# For prospective data where results are unknown, it
# makes no sense to have y values or weights.
y, w = (None, None)
assert len(X) == len(ids)
time2 = time.time()
logger.info("TIMING: featurizing shard %d took %0.3f s" %
(shard_num, time2 - time1))
yield X, y, w, ids
return DiskDataset.create_dataset(shard_generator(), data_dir,
self.tasks)
def create_dataset(self,
inputs: Sequence[Any],
data_dir: Optional[str] = None,
shard_size: Optional[int] = 8192) -> DiskDataset:
"""Creates and returns a `Dataset` object by featurizing provided files.
Reads in `inputs` and uses `self.featurizer` to featurize the
data in these input files. For large files, automatically shards
into smaller chunks of `shard_size` datapoints for convenience.
Returns a `Dataset` object that contains the featurized dataset.
This implementation assumes that the helper methods `_get_shards`
and `_featurize_shard` are implemented and that each shard
returned by `_get_shards` is a pandas dataframe. You may choose
to reuse or override this method in your subclass implementations.
Parameters
----------
inputs: Sequence[Any]
List of inputs to process. Entries can be arbitrary objects so long as
they are understood by `self.featurizer`
data_dir: str, optional (default None)
Directory to store featurized dataset.
shard_size: int, optional (default 8192)
Number of examples stored in each shard.
Returns
-------
DiskDataset
A `DiskDataset` object containing a featurized representation of data
from `inputs`.
"""
logger.info("Loading raw samples now.")
logger.info("shard_size: %s" % str(shard_size))
if not isinstance(inputs, list):
try:
inputs = list(inputs)
except TypeError:
inputs = [inputs]
def shard_generator():
global_index = 0
for shard_num, shard in enumerate(
self._get_shards(inputs, shard_size)):
time1 = time.time()
X, y, w, ids = self._featurize_shard(shard, global_index)
global_index += len(shard)
time2 = time.time()
logger.info("TIMING: featurizing shard %d took %0.3f s" %
(shard_num, time2 - time1))
yield X, y, w, ids
return DiskDataset.create_dataset(shard_generator(), data_dir,
self.tasks)
def featurize(self, input_files, data_dir=None, shard_size=8192):
"""Featurize provided files and write to specified location.
For large datasets, automatically shards into smaller chunks
for convenience.
Parameters
----------
input_files: list
List of input filenames.
data_dir: str
(Optional) Directory to store featurized dataset.
shard_size: int
(Optional) Number of examples stored in each shard.
"""
log("Loading raw samples now.", self.verbose)
log("shard_size: %d" % shard_size, self.verbose)
if not isinstance(input_files, list):
input_files = [input_files]
def shard_generator():
for shard_num, shard in enumerate(
self.get_shards(input_files, shard_size)):
time1 = time.time()
X, valid_inds = self.featurize_shard(shard)
ids = shard[self.id_field].values
ids = ids[valid_inds]
if len(self.tasks) > 0:
# Featurize task results iff they exist.
y, w = convert_df_to_numpy(shard, self.tasks,
self.id_field)
# Filter out examples where featurization failed.
y, w = (y[valid_inds], w[valid_inds])
assert len(X) == len(ids) == len(y) == len(w)
else:
# For prospective data where results are unknown, it makes
# no sense to have y values or weights.
y, w = (None, None)
assert len(X) == len(ids)
time2 = time.time()
log(
"TIMING: featurizing shard %d took %0.3f s" %
(shard_num, time2 - time1), self.verbose)
yield X, y, w, ids
return DiskDataset.create_dataset(shard_generator(),
data_dir,
self.tasks,
verbose=self.verbose)
def featurize(self, input_files, data_dir=None, shard_size=8192):
"""Featurize provided files and write to specified location."""
log("Loading raw samples now.", self.verbose)
log("shard_size: %d" % shard_size, self.verbose)
if not isinstance(input_files, list):
input_files = [input_files]
def shard_generator():
for shard_num, shard in enumerate(self.get_shards(input_files, shard_size)):
time1 = time.time()
X, valid_inds = self.featurize_shard(shard)
ids, y, w = convert_df_to_numpy(shard, self.tasks, self.id_field)
# Filter out examples where featurization failed.
ids, y, w = (ids[valid_inds], y[valid_inds], w[valid_inds])
assert len(X) == len(ids) == len(y) == len(w)
time2 = time.time()
log("TIMING: featurizing shard %d took %0.3f s" % (shard_num, time2-time1),
self.verbose)
yield X, y, w, ids
return DiskDataset.create_dataset(shard_generator(), data_dir, self.tasks)
def featurize(self, input_files, data_dir=None):
"""Featurizes fasta files.
Parameters
----------
input_files: list
List of fasta files.
data_dir: str
(Optional) Name of directory where featurized data is stored.
"""
if not isinstance(input_files, list):
input_files = [input_files]
def shard_generator():
for input_file in input_files:
X = encode_fasta_sequence(input_file)
ids = np.ones(len(X))
# (X, y, w, ids)
yield X, None, None, ids
return DiskDataset.create_dataset(shard_generator(), data_dir)
def featurize(self, input_files, data_dir=None):
"""Featurizes fasta files.
Parameters
----------
input_files: list
List of fasta files.
data_dir: str
(Optional) Name of directory where featurized data is stored.
"""
if not isinstance(input_files, list):
input_files = [input_files]
def shard_generator():
for input_file in input_files:
X = encode_fasta_sequence(input_file)
ids = np.ones(len(X))
# (X, y, w, ids)
yield X, None, None, ids
return DiskDataset.create_dataset(shard_generator(), data_dir)
def create_dataset(self,
input_files: OneOrMany[str],
data_dir: Optional[str] = None,
shard_size: Optional[int] = 8192) -> DiskDataset:
"""Creates a `Dataset` from input JSON files.
Parameters
----------
input_files: OneOrMany[str]
List of JSON filenames.
data_dir: Optional[str], default None
Name of directory where featurized data is stored.
shard_size: Optional[int], default 8192
Shard size when loading data.
Returns
-------
dataset: dc.data.Dataset
A `Dataset` object containing a featurized representation of data
from `input_files`.
"""
if not isinstance(input_files, list):
try:
if isinstance(input_files, str):
input_files = [input_files]
else:
input_files = list(input_files)
except TypeError:
raise ValueError(
"input_files is of an unrecognized form. Must be one filename or a list of filenames."
)
def shard_generator():
"""Yield X, y, w, and ids for shards."""
for shard_num, shard in enumerate(
self._get_shards(input_files, shard_size)):
time1 = time.time()
X, valid_inds = self._featurize_shard(shard)
if self.id_field:
ids = shard[self.id_field].values
else:
ids = np.ones(len(X))
ids = ids[valid_inds]
if len(self.tasks) > 0:
# Featurize task results if they exist.
y, w = _convert_df_to_numpy(shard, self.tasks)
if self.label_field:
y = shard[self.label_field]
if self.weight_field:
w = shard[self.weight_field]
# Filter out examples where featurization failed.
y, w = (y[valid_inds], w[valid_inds])
assert len(X) == len(ids) == len(y) == len(w)
else:
# For prospective data where results are unknown, it
# makes no sense to have y values or weights.
y, w = (None, None)
assert len(X) == len(ids)
time2 = time.time()
logger.info("TIMING: featurizing shard %d took %0.3f s" %
(shard_num, time2 - time1))
yield X, y, w, ids
return DiskDataset.create_dataset(shard_generator(), data_dir)
def create_dataset(self,
input_files: OneOrMany[str],
data_dir: Optional[str] = None,
shard_size: Optional[int] = None) -> DiskDataset:
"""Creates a `Dataset` from input FASTA files.
At present, FASTA support is limited and doesn't allow for sharding.
Parameters
----------
input_files: List[str]
List of fasta files.
data_dir: str, optional (default None)
Name of directory where featurized data is stored.
shard_size: int, optional (default None)
For now, this argument is ignored and each FASTA file gets its
own shard.
Returns
-------
DiskDataset
A `DiskDataset` object containing a featurized representation of data
from `input_files`.
"""
if isinstance(input_files, str):
input_files = [input_files]
def shard_generator(): # TODO Enable sharding with shard size parameter
for input_file in input_files:
if self.legacy:
X = encode_bio_sequence(input_file)
else:
sequences = _read_file(input_file)
X = self.featurizer(sequences)
ids = np.ones(len(X))
# (X, y, w, ids)
yield X, None, None, ids
def _read_file(input_file: str):
"""
Convert the FASTA file to a numpy array of FASTA-format strings.
"""
# TODO don't convert all sequences into np array (allow shards)
def _generate_sequences(fasta_file, header_mark=">") -> np.ndarray:
"""
Uses a fasta_file to create a numpy array of annotated FASTA-format strings
"""
sequences: np.ndarray = np.array([])
sequence: np.ndarray = np.array([])
header_read = False
for line in fasta_file:
# Check if line is a header
if line.startswith(header_mark): # New header line
header_read = True
sequences = _add_sequence(sequences, sequence)
sequence = np.array([])
elif header_read: # Line contains sequence in FASTA format
if line[-1:] == '\n': # Check last character in string
line = line[0:-1] # Remove last character
sequence = np.append(sequence, line)
sequences = _add_sequence(sequences, sequence) # Add last sequence
return sequences
def _add_sequence(sequences: np.ndarray,
sequence: np.ndarray) -> np.ndarray:
# Handle empty sequence
if sequence is None or len(sequence) <= 0:
# TODO log attempts to add empty sequences every shard
return np.array([])
# Annotate start/stop of sequence
if self.auto_add_annotations:
sequence = np.insert(sequence, 0, "[CLS]")
sequence = np.append(sequence, "[SEP]")
new_sequence = ''.join(sequence)
new_sequences = np.append(sequences, new_sequence)
return new_sequences
with open(input_file, 'r') as f: # Read FASTA file
return _generate_sequences(f)
return DiskDataset.create_dataset(shard_generator(), data_dir)
def create_dataset(self,
inputs: OneOrMany[Any],
data_dir: Optional[str] = None,
shard_size: Optional[int] = 8192) -> Dataset:
"""Creates and returns a `Dataset` object by featurizing provided sdf files.
Parameters
----------
inputs: List
List of inputs to process. Entries can be filenames or arbitrary objects.
Each file should be supported format (.sdf) or compressed folder of
.sdf files
data_dir: str, optional (default None)
Directory to store featurized dataset.
shard_size: int, optional (default 8192)
Number of examples stored in each shard.
Returns
-------
DiskDataset
A `DiskDataset` object containing a featurized representation of data
from `inputs`.
"""
logger.info("Loading raw samples now.")
logger.info("shard_size: %s" % str(shard_size))
# Special case handling of single input
if not isinstance(inputs, list):
inputs = [inputs]
processed_files = []
for input_file in inputs:
filename, extension = os.path.splitext(input_file)
extension = extension.lower()
if extension == ".sdf":
processed_files.append(input_file)
elif extension == ".zip":
zip_dir = tempfile.mkdtemp()
zip_ref = zipfile.ZipFile(input_file, 'r')
zip_ref.extractall(path=zip_dir)
zip_ref.close()
zip_files = [os.path.join(zip_dir, name) for name in zip_ref.namelist()]
for zip_file in zip_files:
_, extension = os.path.splitext(zip_file)
extension = extension.lower()
if extension in [".sdf"]:
processed_files.append(zip_file)
else:
raise ValueError("Unsupported file format")
inputs = processed_files
def shard_generator():
for shard_num, shard in enumerate(self._get_shards(inputs, shard_size)):
time1 = time.time()
X, valid_inds = self._featurize_shard(shard)
ids = shard[self.id_field].values
ids = ids[valid_inds]
if len(self.tasks) > 0:
# Featurize task results iff they exist.
y, w = _convert_df_to_numpy(shard, self.tasks)
# Filter out examples where featurization failed.
y, w = (y[valid_inds], w[valid_inds])
assert len(X) == len(ids) == len(y) == len(w)
else:
# For prospective data where results are unknown, it
# makes no sense to have y values or weights.
y, w = (None, None)
assert len(X) == len(ids)
time2 = time.time()
logger.info("TIMING: featurizing shard %d took %0.3f s" %
(shard_num, time2 - time1))
yield X, y, w, ids
return DiskDataset.create_dataset(shard_generator(), data_dir, self.tasks)
