def cli_info(command, raw_args):
"""CLI interface to predict
"""
assert command == "info"
parser = argparse.ArgumentParser('kipoi {}'.format(command),
description="Prints dataloader" +
" keyword arguments.")
add_model(parser)
add_dataloader(parser, with_args=False)
args = parser.parse_args(raw_args)
# --------------------------------------------
# load model & dataloader
model = kipoi.get_model(args.model, args.source)
if args.dataloader is not None:
dl_info = "dataloader '{0}' from source '{1}'".format(str(args.dataloader), str(args.dataloader_source))
Dl = kipoi.get_dataloader_factory(args.dataloader, args.dataloader_source)
else:
dl_info = "default dataloader for model '{0}' from source '{1}'".format(str(model.name), str(args.source))
Dl = model.default_dataloader
print("-" * 80)
print("Displaying keyword arguments for {0}".format(dl_info))
print(Dl.print_args())
print("-" * 80)
def cli_test(command, raw_args):
"""Runs test on the model
"""
assert command == "test"
# setup the arg-parsing
parser = argparse.ArgumentParser('kipoi {}'.format(command),
description='script to test model zoo submissions')
add_model(parser, source="dir")
parser.add_argument('--batch_size', type=int, default=32,
help='Batch size to use in prediction')
parser.add_argument("-i", "--install_req", action='store_true',
help="Install required packages from requirements.txt")
args = parser.parse_args(raw_args)
# --------------------------------------------
if args.install_req:
kipoi.pipeline.install_model_requirements(args.model,
args.source,
and_dataloaders=True)
mh = kipoi.get_model(args.model, args.source)
if not mh._sufficient_deps(mh.dependencies):
# model requirements should be installed
logger.warn("Required package '{0}' for model type: {1} is not listed in the dependencies".
format(mh.MODEL_PACKAGE, mh.type))
# Load the test files from model source
# with cd(mh.source_dir):
mh.pipeline.predict_example(batch_size=args.batch_size)
# if not match:
# # logger.error("Expected targets don't match model predictions")
# raise Exception("Expected targets don't match model predictions")
logger.info('Successfully ran test_predict')
def cli_test(command, raw_args):
"""Runs test on the model
"""
assert command == "test"
# setup the arg-parsing
parser = argparse.ArgumentParser(
'kipoi {}'.format(command),
description='script to test model zoo submissions. Example usage:\n'
'`kipoi test model/directory`, where `model/directory` is the '
'path to a directory containing a model.yaml file.')
add_model(parser, source="dir")
parser.add_argument('--batch_size',
type=int,
default=32,
help='Batch size to use in prediction')
args = parser.parse_args(raw_args)
# --------------------------------------------
mh = kipoi.get_model(args.model, args.source)
if not mh._sufficient_deps(mh.dependencies):
# model requirements should be installed
logger.warn(
"Required package '{0}' for model type: {1} is not listed in the dependencies"
.format(mh.MODEL_PACKAGE, mh.type))
# Load the test files from model source
# with cd(mh.source_dir):
mh.pipeline.predict_example(batch_size=args.batch_size)
# if not match:
# # logger.error("Expected targets don't match model predictions")
# raise Exception("Expected targets don't match model predictions")
logger.info('Successfully ran test_predict')
def cli_info(command, raw_args):
"""CLI interface to predict
"""
assert command == "info"
parser = argparse.ArgumentParser('kipoi {}'.format(command),
description="Prints dataloader" +
" keyword arguments.")
parser.add_argument("-i", "--install_req", action='store_true',
help="Install required packages from requirements.txt")
add_model(parser)
add_dataloader(parser, with_args=False)
args = parser.parse_args(raw_args)
# --------------------------------------------
# install args
if args.install_req:
kipoi.pipeline.install_model_requirements(args.model,
args.source,
and_dataloaders=True)
# load model & dataloader
model = kipoi.get_model(args.model, args.source)
if args.dataloader is not None:
dl_info = "dataloader '{0}' from source '{1}'".format(str(args.dataloader), str(args.dataloader_source))
Dl = kipoi.get_dataloader_factory(args.dataloader, args.dataloader_source)
else:
dl_info = "default dataloader for model '{0}' from source '{1}'".format(str(model.name), str(args.source))
Dl = model.default_dataloader
print("-" * 80)
print("Displaying keyword arguments for {0}".format(dl_info))
print(kipoi.print_dl_kwargs(Dl))
print("-" * 80)
def cli_get_example(command, raw_args):
"""Downloads the example files to the desired directory
"""
assert command == "get-example"
# setup the arg-parsing
parser = argparse.ArgumentParser('kipoi {}'.format(command),
description='Get example files')
add_model(parser, source="kipoi")
parser.add_argument("-o", "--output", default="example", required=False,
help="Output directory where to store the examples. Default: 'example'")
args = parser.parse_args(raw_args)
# --------------------------------------------
md = kipoi.get_model_descr(args.model, args.source)
src = kipoi.get_source(args.source)
# load the default dataloader
if isinstance(md.default_dataloader, kipoi.specs.DataLoaderImport):
with cd(src.get_model_dir(args.model)):
dl_descr = md.default_dataloader.get()
else:
# load from directory
# attach the default dataloader already to the model
dl_descr = kipoi.get_dataloader_descr(os.path.join(args.model, md.default_dataloader),
source=args.source)
kwargs = dl_descr.download_example(output_dir=args.output, dry_run=False)
logger.info("Example files downloaded to: {}".format(args.output))
logger.info("use the following dataloader kwargs:")
print(json.dumps(kwargs))
def cli_info(command, raw_args):
"""CLI interface to predict
"""
assert command == "info"
parser = argparse.ArgumentParser('kipoi {}'.format(command),
description="Prints dataloader" +
" keyword arguments.")
add_model(parser)
add_dataloader(parser, with_args=False)
args = parser.parse_args(raw_args)
# --------------------------------------------
# load model & dataloader
md = kipoi.get_model_descr(args.model, args.source)
src = kipoi.get_source(args.source)
# load the default dataloader
try:
if isinstance(md.default_dataloader, kipoi.specs.DataLoaderImport):
with cd(src.get_model_dir(args.model)):
dl_descr = md.default_dataloader.get()
else:
# load from directory
# attach the default dataloader already to the model
dl_descr = kipoi.get_dataloader_descr(os.path.join(
args.model, md.default_dataloader),
source=args.source)
# if kipoiseq is not installed you get an ImportError
except ImportError:
dl_descr = None
print("-" * 80)
print("'{0}' from source '{1}'".format(str(args.model), str(args.source)))
print("")
print("Model information")
print("-----------")
print(md.info.get_config_as_yaml())
if dl_descr:
print("Dataloader arguments")
print("--------------------")
dl_descr.print_args()
print("--------------------\n")
print("Run `kipoi get-example {} -o example` to download example files.\n".
format(args.model))
def cli_get_example(command, raw_args):
"""Downloads the example files to the desired directory
"""
assert command == "get-example"
# setup the arg-parsing
parser = argparse.ArgumentParser('kipoi {}'.format(command),
description='Get example files')
add_model(parser, source="kipoi")
parser.add_argument("-o", "--output", default="example", required=False,
help="Output directory where to store the examples. Default: 'example'")
args = parser.parse_args(raw_args)
# --------------------------------------------
mh = kipoi.get_model(args.model, args.source)
kwargs = mh.default_dataloader.download_example(output_dir=args.output, dry_run=False)
logger.info("Example files downloaded to: {}".format(args.output))
logger.info("use the following dataloader kwargs:")
print(json.dumps(kwargs))
def cli_score_variants(command, raw_args):
"""CLI interface to predict
"""
AVAILABLE_FORMATS = ["tsv", "hdf5", "h5"]
import pybedtools
assert command == "score_variants"
parser = argparse.ArgumentParser(
'kipoi postproc {}'.format(command),
description='Predict effect of SNVs using ISM.')
add_model(parser)
add_dataloader(parser, with_args=True)
parser.add_argument('-v', '--vcf_path', help='Input VCF.')
# TODO - rename path to fpath
parser.add_argument('-a',
'--out_vcf_fpath',
help='Output annotated VCF file path.',
default=None)
parser.add_argument('--batch_size',
type=int,
default=32,
help='Batch size to use in prediction')
parser.add_argument(
"-n",
"--num_workers",
type=int,
default=0,
help="Number of parallel workers for loading the dataset")
parser.add_argument("-i",
"--install_req",
action='store_true',
help="Install required packages from requirements.txt")
parser.add_argument(
'-r',
'--restriction_bed',
default=None,
help="Regions for prediction can only be subsets of this bed file")
parser.add_argument(
'-o',
'--output',
required=False,
help=
"Additional output file. File format is inferred from the file path ending"
+ ". Available file formats are: {0}".format(
",".join(AVAILABLE_FORMATS)))
parser.add_argument(
'-s',
"--scoring",
default="diff",
nargs="+",
help=
"Scoring method to be used. Only scoring methods selected in the model yaml file are"
"available except for `diff` which is always available. Select scoring function by the"
"`name` tag defined in the model yaml file.")
parser.add_argument(
'-k',
"--scoring_kwargs",
default="",
nargs="+",
help=
"JSON definition of the kwargs for the scoring functions selected in --scoring. The "
"definiton can either be in JSON in the command line or the path of a .json file. The "
"individual JSONs are expected to be supplied in the same order as the labels defined in "
"--scoring. If the defaults or no arguments should be used define '{}' for that respective "
"scoring method.")
args = parser.parse_args(raw_args)
# extract args for kipoi.variant_effects.predict_snvs
vcf_path = args.vcf_path
out_vcf_fpath = args.out_vcf_fpath
dataloader_arguments = parse_json_file_str(args.dataloader_args)
# infer the file format
args.file_format = args.output.split(".")[-1]
if args.file_format not in AVAILABLE_FORMATS:
logger.error("File ending: {0} for file {1} not from {2}".format(
args.file_format, args.output, AVAILABLE_FORMATS))
sys.exit(1)
if args.file_format in ["hdf5", "h5"]:
# only if hdf5 output is used
import deepdish
# Check that all the folders exist
file_exists(args.vcf_path, logger)
dir_exists(os.path.dirname(args.out_vcf_fpath), logger)
if args.output is not None:
dir_exists(os.path.dirname(args.output), logger)
# --------------------------------------------
# install args
if args.install_req:
kipoi.pipeline.install_model_requirements(args.model,
args.source,
and_dataloaders=True)
# load model & dataloader
model = kipoi.get_model(args.model, args.source)
if args.dataloader is not None:
Dl = kipoi.get_dataloader_factory(args.dataloader,
args.dataloader_source)
else:
Dl = model.default_dataloader
if not os.path.exists(vcf_path):
raise Exception("VCF file does not exist: %s" % vcf_path)
if not isinstance(args.scoring, list):
args.scoring = [args.scoring]
dts = _get_scoring_fns(model, args.scoring, args.scoring_kwargs)
# Load effect prediction related model info
model_info = kipoi.postprocessing.variant_effects.ModelInfoExtractor(
model, Dl)
# Select the appropriate region generator
if args.restriction_bed is not None:
# Select the restricted SNV-centered region generator
pbd = pybedtools.BedTool(args.restriction_bed)
vcf_to_region = kipoi.postprocessing.variant_effects.SnvPosRestrictedRg(
model_info, pbd)
logger.info(
'Restriction bed file defined. Only variants in defined regions will be tested.'
'Only defined regions will be tested.')
elif model_info.requires_region_definition:
# Select the SNV-centered region generator
vcf_to_region = kipoi.postprocessing.variant_effects.SnvCenteredRg(
model_info)
logger.info('Using variant-centered sequence generation.')
else:
# No regions can be defined for the given model, VCF overlap will be inferred, hence tabixed VCF is necessary
vcf_to_region = None
# Make sure that the vcf is tabixed
vcf_path = kipoi.postprocessing.variant_effects.ensure_tabixed_vcf(
vcf_path)
logger.info(
'Dataloader does not accept definition of a regions bed-file. Only VCF-variants that lie within'
'produced regions can be predicted')
if model_info.use_seq_only_rc:
logger.info(
'Model SUPPORTS simple reverse complementation of input DNA sequences.'
)
else:
logger.info(
'Model DOES NOT support simple reverse complementation of input DNA sequences.'
)
# Get a vcf output writer if needed
if out_vcf_fpath is not None:
logger.info('Annotated VCF will be written to %s.' %
str(out_vcf_fpath))
vcf_writer = kipoi.postprocessing.variant_effects.VcfWriter(
model, vcf_path, out_vcf_fpath)
else:
vcf_writer = None
keep_predictions = args.output is not None
res = kipoi.postprocessing.variant_effects.predict_snvs(
model,
Dl,
vcf_path,
batch_size=args.batch_size,
num_workers=args.num_workers,
dataloader_args=dataloader_arguments,
vcf_to_region=vcf_to_region,
evaluation_function_kwargs={"diff_types": dts},
sync_pred_writer=vcf_writer,
return_predictions=keep_predictions)
# tabular files
if args.output is not None:
if args.file_format in ["tsv"]:
for i, k in enumerate(res):
# Remove an old file if it is still there...
if i == 0:
try:
os.unlink(args.output)
except Exception:
pass
with open(args.output, "w") as ofh:
ofh.write("KPVEP_%s\n" % k.upper())
res[k].to_csv(args.output, sep="\t", mode="a")
if args.file_format in ["hdf5", "h5"]:
deepdish.io.save(args.output, res)
logger.info('Successfully predicted samples')
def cli_predict(command, raw_args):
"""CLI interface to predict
"""
assert command == "predict"
parser = argparse.ArgumentParser('kipoi {}'.format(command),
description='Run the model prediction.')
add_model(parser)
add_dataloader(parser, with_args=True)
parser.add_argument('--batch_size', type=int, default=32,
help='Batch size to use in prediction')
parser.add_argument("-n", "--num_workers", type=int, default=0,
help="Number of parallel workers for loading the dataset")
parser.add_argument("-i", "--install_req", action='store_true',
help="Install required packages from requirements.txt")
parser.add_argument("-k", "--keep_inputs", action='store_true',
help="Keep the inputs in the output file. ")
parser.add_argument("-l", "--layer",
help="Which output layer to use to make the predictions. If specified," +
"`model.predict_activation_on_batch` will be invoked instead of `model.predict_on_batch`")
parser.add_argument('-o', '--output', required=True, nargs="+",
help="Output files. File format is inferred from the file path ending. Available file formats are: " +
", ".join(["." + k for k in writers.FILE_SUFFIX_MAP]))
args = parser.parse_args(raw_args)
dataloader_kwargs = parse_json_file_str(args.dataloader_args)
# setup the files
if not isinstance(args.output, list):
args.output = [args.output]
for o in args.output:
ending = o.split('.')[-1]
if ending not in writers.FILE_SUFFIX_MAP:
logger.error("File ending: {0} for file {1} not from {2}".
format(ending, o, writers.FILE_SUFFIX_MAP))
sys.exit(1)
dir_exists(os.path.dirname(o), logger)
# --------------------------------------------
# install args
if args.install_req:
kipoi.pipeline.install_model_requirements(args.model,
args.source,
and_dataloaders=True)
# load model & dataloader
model = kipoi.get_model(args.model, args.source)
if args.dataloader is not None:
Dl = kipoi.get_dataloader_factory(args.dataloader, args.dataloader_source)
else:
Dl = model.default_dataloader
dataloader_kwargs = kipoi.pipeline.validate_kwargs(Dl, dataloader_kwargs)
dl = Dl(**dataloader_kwargs)
# setup batching
it = dl.batch_iter(batch_size=args.batch_size,
num_workers=args.num_workers)
# Setup the writers
use_writers = []
for output in args.output:
ending = output.split('.')[-1]
W = writers.FILE_SUFFIX_MAP[ending]
logger.info("Using {0} for file {1}".format(W.__name__, output))
if ending == "tsv":
assert W == writers.TsvBatchWriter
use_writers.append(writers.TsvBatchWriter(file_path=output, nested_sep="/"))
elif ending == "bed":
assert W == writers.BedBatchWriter
use_writers.append(writers.BedBatchWriter(file_path=output,
dataloader_schema=dl.output_schema.metadata,
header=True))
elif ending in ["hdf5", "h5"]:
assert W == writers.HDF5BatchWriter
use_writers.append(writers.HDF5BatchWriter(file_path=output))
else:
logger.error("Unknown file format: {0}".format(ending))
sys.exit(1)
# Loop through the data, make predictions, save the output
for i, batch in enumerate(tqdm(it)):
# validate the data schema in the first iteration
if i == 0 and not Dl.output_schema.compatible_with_batch(batch):
logger.warn("First batch of data is not compatible with the dataloader schema.")
# make the prediction
if args.layer is None:
pred_batch = model.predict_on_batch(batch['inputs'])
else:
pred_batch = model.predict_activation_on_batch(batch['inputs'], layer=args.layer)
# write out the predictions, metadata (, inputs, targets)
output_batch = prepare_batch(batch, pred_batch, keep_inputs=args.keep_inputs)
for writer in use_writers:
writer.batch_write(output_batch)
for writer in use_writers:
writer.close()
logger.info('Done! Predictions stored in {0}'.format(",".join(args.output)))
def cli_test(command, raw_args):
"""Runs test on the model
"""
assert command == "test"
# setup the arg-parsing
parser = argparse.ArgumentParser('kipoi {}'.format(command),
description='script to test model zoo submissions. Example usage:\n'
'`kipoi test model/directory`, where `model/directory` is the '
'path to a directory containing a model.yaml file.')
add_model(parser, source="dir")
parser.add_argument('--batch_size', type=int, default=32,
help='Batch size to use in prediction')
parser.add_argument("-o", "--output", default=None, required=False,
help="Output hdf5 file")
parser.add_argument("-s", "--skip-expect", action='store_true',
help="Skip validating the expected predictions if test.expect field is specified under model.yaml")
parser.add_argument("-e", "--expect", default=None,
help="File path to the hdf5 file of predictions produced by kipoi test -o file.h5 "
"or kipoi predict -o file.h5 --keep_inputs. Overrides test.expect in model.yaml")
args = parser.parse_args(raw_args)
# --------------------------------------------
mh = kipoi.get_model(args.model, args.source)
if not mh._sufficient_deps(mh.dependencies):
# model requirements should be installed
logger.warning("Required package '{0}' for model type: {1} is not listed in the dependencies".
format(mh.MODEL_PACKAGE, mh.type))
# Load the test files from model source
mh.pipeline.predict_example(batch_size=args.batch_size, output_file=args.output)
if (mh.test.expect is not None or args.expect is not None) \
and not args.skip_expect and args.output is None:
if args.expect is not None:
# `expect` specified from the CLI
expect = args.expect
else:
# `expect` taken from model.yaml
if isinstance(mh.test.expect, kipoi.specs.RemoteFile):
# download the file
output_dir = kipoi.get_source(args.source).get_model_download_dir(args.model)
makedir_exist_ok(output_dir)
mh.test.expect = mh.test.expect.get_file(os.path.join(output_dir, 'test.expect.h5'))
expect = mh.test.expect
logger.info('Testing if the predictions match the expected ones in the file: {}'.format(expect))
logger.info('Desired precision (number of matching decimal places): {}'.format(mh.test.precision_decimal))
# iteratively load the expected file
expected = kipoi.readers.HDF5Reader(expect)
expected.open()
it = expected.batch_iter(batch_size=args.batch_size)
for i, batch in enumerate(tqdm(it, total=len(expected) // args.batch_size)):
if i == 0 and ('inputs' not in batch or 'preds' not in batch):
raise ValueError("test.expect file requires 'inputs' and 'preds' "
"to be specified. Available keys: {}".format(list(expected)))
pred_batch = mh.predict_on_batch(batch['inputs'])
# compare to the predictions
# import ipdb
# ipdb.set_trace()
try:
compare_numpy_dict(pred_batch, batch['preds'], exact=False, decimal=mh.test.precision_decimal)
except Exception as e:
logger.error("Model predictions don't match the expected predictions."
"expected: {}\nobserved: {}. Exception: {}".format(batch['preds'], pred_batch, e))
expected.close()
sys.exit(1)
expected.close()
logger.info('All predictions match')
logger.info('Successfully ran test_predict')
def cli_predict(command, raw_args):
"""CLI interface to predict
"""
assert command == "predict"
parser = argparse.ArgumentParser('kipoi {}'.format(command),
description='Run the model prediction.')
add_model(parser)
add_dataloader(parser, with_args=True)
parser.add_argument('--batch_size', type=int, default=32,
help='Batch size to use in prediction')
parser.add_argument("-n", "--num_workers", type=int, default=0,
help="Number of parallel workers for loading the dataset")
parser.add_argument("-k", "--keep_inputs", action='store_true',
help="Keep the inputs in the output file. ")
parser.add_argument("-l", "--layer",
help="Which output layer to use to make the predictions. If specified," +
"`model.predict_activation_on_batch` will be invoked instead of `model.predict_on_batch`")
parser.add_argument("--singularity", action='store_true',
help="Run `kipoi predict` in the appropriate singularity container. "
"Containters will get downloaded to ~/.kipoi/envs/ or to "
"$SINGULARITY_CACHEDIR if set")
parser.add_argument('-o', '--output', required=True, nargs="+",
help="Output files. File format is inferred from the file path ending. Available file formats are: " +
", ".join(["." + k for k in writers.FILE_SUFFIX_MAP]))
args = parser.parse_args(raw_args)
dataloader_kwargs = parse_json_file_str_or_arglist(args.dataloader_args, parser)
# setup the files
if not isinstance(args.output, list):
args.output = [args.output]
for o in args.output:
ending = o.split('.')[-1]
if ending not in writers.FILE_SUFFIX_MAP:
logger.error("File ending: {0} for file {1} not from {2}".
format(ending, o, writers.FILE_SUFFIX_MAP))
sys.exit(1)
dir_exists(os.path.dirname(o), logger)
# singularity_command
if args.singularity:
from kipoi.cli.singularity import singularity_command
logger.info("Running kipoi predict in the singularity container")
# Drop the singularity flag
raw_args = [x for x in raw_args if x != '--singularity']
singularity_command(['kipoi', command] + raw_args,
args.model,
dataloader_kwargs,
output_files=args.output,
source=args.source,
dry_run=False)
return None
# --------------------------------------------
# load model & dataloader
model = kipoi.get_model(args.model, args.source)
if args.dataloader is not None:
Dl = kipoi.get_dataloader_factory(args.dataloader, args.dataloader_source)
else:
Dl = model.default_dataloader
dataloader_kwargs = kipoi.pipeline.validate_kwargs(Dl, dataloader_kwargs)
dl = Dl(**dataloader_kwargs)
# setup batching
it = dl.batch_iter(batch_size=args.batch_size,
num_workers=args.num_workers)
# Setup the writers
use_writers = []
for output in args.output:
writer = writers.get_writer(output, metadata_schema=dl.get_output_schema().metadata)
if writer is None:
logger.error("Unknown file format: {0}".format(ending))
sys.exit()
else:
use_writers.append(writer)
output_writers = writers.MultipleBatchWriter(use_writers)
# Loop through the data, make predictions, save the output
for i, batch in enumerate(tqdm(it)):
# validate the data schema in the first iteration
if i == 0 and not Dl.get_output_schema().compatible_with_batch(batch):
logger.warning("First batch of data is not compatible with the dataloader schema.")
# make the prediction
if args.layer is None:
pred_batch = model.predict_on_batch(batch['inputs'])
else:
pred_batch = model.predict_activation_on_batch(batch['inputs'], layer=args.layer)
# write out the predictions, metadata (, inputs, targets)
output_batch = prepare_batch(batch, pred_batch, keep_inputs=args.keep_inputs)
output_writers.batch_write(output_batch)
output_writers.close()
logger.info('Done! Predictions stored in {0}'.format(",".join(args.output)))
def create_tf_session(visiblegpus, per_process_gpu_memory_fraction=0.45):
import os
import tensorflow as tf
import keras.backend as K
os.environ['CUDA_VISIBLE_DEVICES'] = str(visiblegpus)
session_config = tf.ConfigProto()
session_config.gpu_options.per_process_gpu_memory_fraction = per_process_gpu_memory_fraction
session = tf.Session(config=session_config)
K.set_session(session)
return session
if __name__ == '__main__':
parser = argparse.ArgumentParser(
description='Transfer-learn a Keras model from Kipoi')
add_model(parser)
add_dataloader(parser, with_args=False)
parser.add_argument('--dl_kwargs_train',
help="training data-loader kwargs")
parser.add_argument('--dl_kwargs_eval',
help="Evaluation data-loader kwargs")
parser.add_argument('-t',
'--tasks',
type=int,
help='Number of transferred tasks')
parser.add_argument('-o', '--output', help='Output file directory')
parser.add_argument('--transfer_to',
help='Layer to which to transfer the model')
parser.add_argument(
'--freeze_to',
default=None,
def cli_create_mutation_map(command, raw_args):
"""CLI interface to calculate mutation map data
"""
assert command == "create_mutation_map"
parser = argparse.ArgumentParser(
'kipoi postproc {}'.format(command),
description='Predict effect of SNVs using ISM.')
add_model(parser)
add_dataloader(parser, with_args=True)
parser.add_argument(
'-r',
'--regions_file',
help='Region definition as VCF or bed file. Not a required input.')
# TODO - rename path to fpath
parser.add_argument('--batch_size',
type=int,
default=32,
help='Batch size to use in prediction')
parser.add_argument(
"-n",
"--num_workers",
type=int,
default=0,
help="Number of parallel workers for loading the dataset")
parser.add_argument("-i",
"--install_req",
action='store_true',
help="Install required packages from requirements.txt")
parser.add_argument(
'-o',
'--output',
required=True,
help="Output HDF5 file. To be used as input for plotting.")
parser.add_argument(
'-s',
"--scores",
default="diff",
nargs="+",
help=
"Scoring method to be used. Only scoring methods selected in the model yaml file are"
"available except for `diff` which is always available. Select scoring function by the"
"`name` tag defined in the model yaml file.")
parser.add_argument(
'-k',
"--score_kwargs",
default="",
nargs="+",
help=
"JSON definition of the kwargs for the scoring functions selected in --scores. The "
"definiton can either be in JSON in the command line or the path of a .json file. The "
"individual JSONs are expected to be supplied in the same order as the labels defined in "
"--scores. If the defaults or no arguments should be used define '{}' for that respective "
"scoring method.")
parser.add_argument(
'-l',
"--seq_length",
type=int,
default=None,
help=
"Optional parameter: Model input sequence length - necessary if the model does not have a "
"pre-defined input sequence length.")
args = parser.parse_args(raw_args)
# extract args for kipoi.variant_effects.predict_snvs
dataloader_arguments = parse_json_file_str(args.dataloader_args)
if args.output is None:
raise Exception("Output file `--output` has to be set!")
# --------------------------------------------
# install args
if args.install_req:
kipoi.pipeline.install_model_requirements(args.model,
args.source,
and_dataloaders=True)
# load model & dataloader
model = kipoi.get_model(args.model, args.source)
regions_file = os.path.realpath(args.regions_file)
output = os.path.realpath(args.output)
with cd(model.source_dir):
if not os.path.exists(regions_file):
raise Exception("Regions inputs file does not exist: %s" %
args.regions_file)
# Check that all the folders exist
file_exists(regions_file, logger)
dir_exists(os.path.dirname(output), logger)
if args.dataloader is not None:
Dl = kipoi.get_dataloader_factory(args.dataloader,
args.dataloader_source)
else:
Dl = model.default_dataloader
if not isinstance(args.scores, list):
args.scores = [args.scores]
dts = get_scoring_fns(model, args.scores, args.score_kwargs)
# Load effect prediction related model info
model_info = kipoi.postprocessing.variant_effects.ModelInfoExtractor(
model, Dl)
manual_seq_len = args.seq_length
# Select the appropriate region generator and vcf or bed file input
args.file_format = regions_file.split(".")[-1]
bed_region_file = None
vcf_region_file = None
bed_to_region = None
vcf_to_region = None
if args.file_format == "vcf" or regions_file.endswith("vcf.gz"):
vcf_region_file = regions_file
if model_info.requires_region_definition:
# Select the SNV-centered region generator
vcf_to_region = kipoi.postprocessing.variant_effects.SnvCenteredRg(
model_info, seq_length=manual_seq_len)
logger.info('Using variant-centered sequence generation.')
elif args.file_format == "bed":
if model_info.requires_region_definition:
# Select the SNV-centered region generator
bed_to_region = kipoi.postprocessing.variant_effects.BedOverlappingRg(
model_info, seq_length=manual_seq_len)
logger.info('Using bed-file based sequence generation.')
bed_region_file = regions_file
else:
raise Exception("")
if model_info.use_seq_only_rc:
logger.info(
'Model SUPPORTS simple reverse complementation of input DNA sequences.'
)
else:
logger.info(
'Model DOES NOT support simple reverse complementation of input DNA sequences.'
)
from kipoi.postprocessing.variant_effects.mutation_map import _generate_mutation_map
mdmm = _generate_mutation_map(
model,
Dl,
vcf_fpath=vcf_region_file,
bed_fpath=bed_region_file,
batch_size=args.batch_size,
num_workers=args.num_workers,
dataloader_args=dataloader_arguments,
vcf_to_region=vcf_to_region,
bed_to_region=bed_to_region,
evaluation_function_kwargs={'diff_types': dts},
)
mdmm.save_to_file(output)
logger.info('Successfully generated mutation map data')
def cli_grad_to_file(command, raw_args):
""" CLI to save seq inputs of grad*input to a bigwig file
"""
assert command == "gr_inp_to_file"
parser = argparse.ArgumentParser('kipoi postproc {}'.format(command),
description='Save grad*input in a file.')
add_model(parser)
add_dataloader(parser, with_args=True)
# TODO - rename path to fpath
parser.add_argument('-f',
'--input_file',
required=False,
help="Input HDF5 file produced from `grad`")
parser.add_argument('-o',
'--output',
required=False,
help="Output bigwig for bedgraph file")
parser.add_argument(
'--sample',
required=False,
type=int,
default=None,
help=
"Input line for which the BigWig file should be generated. If not defined all"
"samples will be written.")
parser.add_argument(
'--model_input',
required=False,
default=None,
help=
"Model input name to be used for plotting. As defined in model.yaml. Can be omitted if"
"model only has one input.")
args = parser.parse_args(raw_args)
# Check that all the folders exist
dir_exists(os.path.dirname(args.output), logger)
# --------------------------------------------
# install args
import matplotlib.pyplot
matplotlib.pyplot.switch_backend('agg')
import matplotlib.pylab as plt
from kipoi.postprocessing.variant_effects.mutation_map import MutationMapPlotter
from kipoi.postprocessing.gradient_vis.vis import GradPlotter
from kipoi.writers import BedGraphWriter
logger.info('Loading gradient results file and model info...')
gp = GradPlotter.from_hdf5(args.input_file,
model=args.model,
source=args.source)
if args.sample is not None:
samples = [args.sample]
else:
samples = list(range(gp.get_num_samples(args.model_input)))
if args.output.endswith(".bed") or args.output.endswith(".bedgraph"):
of_obj = BedGraphWriter(args.output)
else:
raise Exception("Output file format not supported!")
logger.info('Writing...')
for sample in samples:
gp.write(sample, model_input=args.model_input, writer_obj=of_obj)
logger.info('Saving...')
of_obj.close()
logger.info('Successfully wrote grad*input to file.')
def cli_grad(command, raw_args):
"""CLI interface to predict
"""
from .main import prepare_batch
from kipoi.model import GradientMixin
assert command == "grad"
from tqdm import tqdm
parser = argparse.ArgumentParser(
'kipoi {}'.format(command),
description='Save gradients and inputs to a hdf5 file.')
add_model(parser)
add_dataloader(parser, with_args=True)
parser.add_argument('--batch_size',
type=int,
default=32,
help='Batch size to use in prediction')
parser.add_argument(
"-n",
"--num_workers",
type=int,
default=0,
help="Number of parallel workers for loading the dataset")
parser.add_argument("-i",
"--install_req",
action='store_true',
help="Install required packages from requirements.txt")
parser.add_argument(
"-l",
"--layer",
default=None,
help="Which output layer to use to make the predictions. If specified,"
+
"`model.predict_activation_on_batch` will be invoked instead of `model.predict_on_batch`",
required=False)
parser.add_argument(
"--final_layer",
help=
"Alternatively to `--layer` this flag can be used to indicate that the last layer should "
"be used.",
action='store_true')
parser.add_argument(
"--pre_nonlinearity",
help=
"Flag indicating that it should checked whether the selected output is post activation "
"function. If a non-linear activation function is used attempt to use its input. This "
"feature is not available for all models.",
action='store_true')
parser.add_argument(
"-f",
"--filter_idx",
help=
"Filter index that should be inspected with gradients. If not set all filters will "
+ "be used.",
default=None)
parser.add_argument(
"-a",
"--avg_func",
help=
"Averaging function to be applied across selected filters (`--filter_idx`) in "
+ "layer `--layer`.",
choices=GradientMixin.allowed_functions,
default="sum")
parser.add_argument(
'--selected_fwd_node',
help="If the selected layer has multiple inbound connections in "
"the graph then those can be selected here with an integer "
"index. Not necessarily supported by all models.",
default=None,
type=int)
parser.add_argument(
'-o',
'--output',
required=True,
nargs="+",
help=
"Output files. File format is inferred from the file path ending. Available file formats are: "
+ ", ".join(["." + k for k in writers.FILE_SUFFIX_MAP]))
args = parser.parse_args(raw_args)
dataloader_kwargs = parse_json_file_str(args.dataloader_args)
# setup the files
if not isinstance(args.output, list):
args.output = [args.output]
for o in args.output:
ending = o.split('.')[-1]
if ending not in writers.FILE_SUFFIX_MAP:
logger.error("File ending: {0} for file {1} not from {2}".format(
ending, o, writers.FILE_SUFFIX_MAP))
sys.exit(1)
dir_exists(os.path.dirname(o), logger)
# --------------------------------------------
# install args
if args.install_req:
kipoi.pipeline.install_model_requirements(args.model,
args.source,
and_dataloaders=True)
layer = args.layer
if layer is None and not args.final_layer:
raise Exception(
"A layer has to be selected explicitely using `--layer` or implicitely by using the"
"`--final_layer` flag.")
# Not a good idea
# if layer is not None and isint(layer):
# logger.warn("Interpreting `--layer` value as integer layer index!")
# layer = int(args.layer)
# load model & dataloader
model = kipoi.get_model(args.model, args.source)
if not isinstance(model, GradientMixin):
raise Exception("Model does not support gradient calculation.")
if args.dataloader is not None:
Dl = kipoi.get_dataloader_factory(args.dataloader,
args.dataloader_source)
else:
Dl = model.default_dataloader
dataloader_kwargs = kipoi.pipeline.validate_kwargs(Dl, dataloader_kwargs)
dl = Dl(**dataloader_kwargs)
filter_idx_parsed = None
if args.filter_idx is not None:
filter_idx_parsed = parse_filter_slice(args.filter_idx)
# setup batching
it = dl.batch_iter(batch_size=args.batch_size,
num_workers=args.num_workers)
# Setup the writers
use_writers = []
for output in args.output:
ending = output.split('.')[-1]
W = writers.FILE_SUFFIX_MAP[ending]
logger.info("Using {0} for file {1}".format(W.__name__, output))
if ending == "tsv":
assert W == writers.TsvBatchWriter
use_writers.append(
writers.TsvBatchWriter(file_path=output, nested_sep="/"))
elif ending == "bed":
raise Exception("Please use tsv or hdf5 output format.")
elif ending in ["hdf5", "h5"]:
assert W == writers.HDF5BatchWriter
use_writers.append(writers.HDF5BatchWriter(file_path=output))
else:
logger.error("Unknown file format: {0}".format(ending))
sys.exit(1)
# Loop through the data, make predictions, save the output
for i, batch in enumerate(tqdm(it)):
# validate the data schema in the first iteration
if i == 0 and not Dl.output_schema.compatible_with_batch(batch):
logger.warn(
"First batch of data is not compatible with the dataloader schema."
)
# make the prediction
pred_batch = model.input_grad(batch['inputs'],
filter_idx=filter_idx_parsed,
avg_func=args.avg_func,
layer=layer,
final_layer=args.final_layer,
selected_fwd_node=args.selected_fwd_node,
pre_nonlinearity=args.pre_nonlinearity)
# write out the predictions, metadata (, inputs, targets)
# always keep the inputs so that input*grad can be generated!
# output_batch = prepare_batch(batch, pred_batch, keep_inputs=True)
output_batch = batch
output_batch["grads"] = pred_batch
for writer in use_writers:
writer.batch_write(output_batch)
for writer in use_writers:
writer.close()
logger.info('Done! Gradients stored in {0}'.format(",".join(args.output)))
def cli_ism(command, raw_args):
# TODO: find a way to define the model output selection
"""CLI interface to predict
"""
# from .main import prepare_batch
assert command == "ism"
from tqdm import tqdm
from .ism import Mutation
parser = argparse.ArgumentParser('kipoi interpret {}'.format(command),
description='Calculate DeepLIFT scores.')
add_model(parser)
add_dataloader(parser, with_args=True)
parser.add_argument('--batch_size',
type=int,
default=32,
help='Batch size to use in prediction')
parser.add_argument(
"-n",
"--num_workers",
type=int,
default=0,
help="Number of parallel workers for loading the dataset")
parser.add_argument("--model_input",
help="Name of the model input that should be scored.",
required=True)
parser.add_argument(
'-s',
"--scores",
default="diff",
nargs="+",
help=
"Scoring method to be used. Only scoring methods selected in the model yaml file are"
"available except for `diff` which is always available. Select scoring function by the"
"`name` tag defined in the model yaml file.")
parser.add_argument(
'-k',
"--score_kwargs",
default=None,
nargs="+",
help=
"JSON definition of the kwargs for the scoring functions selected in --scores. The "
"definiton can either be in JSON in the command line or the path of a .json file. The "
"individual JSONs are expected to be supplied in the same order as the labels defined in "
"--scores. If the defaults or no arguments should be used define '{}' for that respective "
"scoring method.")
parser.add_argument(
"-c",
"--category_axis",
help="Using the selected model input with `--model_input`: Which "
"dimension of that array contains the one-hot encoded categories?"
" e.g. for a one-hot encoded DNA-sequence"
"array with input shape (1000, 4) for a single sample, "
"`category_dim` is 1, for (4, 1000) `category_dim`"
"is 0.",
default=1,
type=int,
required=False)
parser.add_argument(
"-f",
"--output_sel_fn",
help="Define an output selection function in order to return effects"
"on the output of the function. example definitoin: "
"`--output_sel_fn my_file.py::my_sel_fn`",
default=None,
required=False)
parser.add_argument(
'-o',
'--output',
required=True,
nargs="+",
help="Output files. File format is inferred from the file path ending. "
"Available file formats are: " +
", ".join(["." + k for k in writers.FILE_SUFFIX_MAP]))
args = parser.parse_args(raw_args)
dataloader_kwargs = parse_json_file_str(args.dataloader_args)
# setup the files
if not isinstance(args.output, list):
args.output = [args.output]
for o in args.output:
ending = o.split('.')[-1]
if ending not in writers.FILE_SUFFIX_MAP:
logger.error("File ending: {0} for file {1} not from {2}".format(
ending, o, writers.FILE_SUFFIX_MAP))
sys.exit(1)
dir_exists(os.path.dirname(o), logger)
# --------------------------------------------
if not isinstance(args.scores, list):
args.scores = [args.scores]
# load model & dataloader
model = kipoi.get_model(args.model, args.source)
if args.dataloader is not None:
Dl = kipoi.get_dataloader_factory(args.dataloader,
args.dataloader_source)
else:
Dl = model.default_dataloader
dataloader_kwargs = kipoi.pipeline.validate_kwargs(Dl, dataloader_kwargs)
dl = Dl(**dataloader_kwargs)
# setup batching
it = dl.batch_iter(batch_size=args.batch_size,
num_workers=args.num_workers)
# Setup the writers
use_writers = []
for output in args.output:
ending = output.split('.')[-1]
W = writers.FILE_SUFFIX_MAP[ending]
logger.info("Using {0} for file {1}".format(W.__name__, output))
if ending == "tsv":
assert W == writers.TsvBatchWriter
use_writers.append(
writers.TsvBatchWriter(file_path=output, nested_sep="/"))
elif ending == "bed":
raise Exception("Please use tsv or hdf5 output format.")
elif ending in ["hdf5", "h5"]:
assert W == writers.HDF5BatchWriter
use_writers.append(writers.HDF5BatchWriter(file_path=output))
else:
logger.error("Unknown file format: {0}".format(ending))
sys.exit(1)
output_sel_fn = None
if args.output_sel_fn is not None:
file_path, obj_name = tuple(args.output_sel_fn.split("::"))
output_sel_fn = getattr(load_module(file_path), obj_name)
m = Mutation(model,
args.model_input,
scores=args.scores,
score_kwargs=args.score_kwargs,
batch_size=args.batch_size,
output_sel_fn=output_sel_fn,
category_axis=args.category_axis,
test_ref_ref=True)
out_batches = {}
# Loop through the data, make predictions, save the output..
# TODO: batch writer fails because it tries to concatenate on highest dimension rather than the lowest!
for i, batch in enumerate(tqdm(it)):
# validate the data schema in the first iteration
if i == 0 and not Dl.output_schema.compatible_with_batch(batch):
logger.warn(
"First batch of data is not compatible with the dataloader schema."
)
# calculate scores without reference for the moment.
pred_batch = m.score(batch['inputs'])
# with the current writers it's not possible to store the scores and the model inputs in the same file
output_batch = {}
output_batch["scores"] = pred_batch
for k in output_batch:
if k not in out_batches:
out_batches[k] = []
out_batches[k].append(output_batch[k])
# concatenate batches:
full_output = {
k: np.concatenate([np.array(el) for el in v])
for k, v in out_batches.items()
}
logger.info('Full output shape: {0}'.format(
str(full_output["scores"].shape)))
for writer in use_writers:
writer.batch_write(full_output)
for writer in use_writers:
writer.close()
logger.info('Done! ISM stored in {0}'.format(",".join(args.output)))
def cli_feature_importance(command, raw_args):
"""CLI interface to predict
"""
# from .main import prepare_batch
assert command == "feature_importance"
parser = argparse.ArgumentParser(
'kipoi {}'.format(command),
description='Save gradients and inputs to a hdf5 file.')
add_model(parser)
add_dataloader(parser, with_args=True)
parser.add_argument("--imp_score",
help="Importance score name",
choices=available_importance_scores())
parser.add_argument("--imp_score_kwargs", help="Importance score kwargs")
parser.add_argument('--batch_size',
type=int,
default=32,
help='Batch size to use in prediction')
parser.add_argument(
"-n",
"--num_workers",
type=int,
default=0,
help="Number of parallel workers for loading the dataset")
# TODO - handle the reference-based importance scores...
# io
parser.add_argument(
'-o',
'--output',
required=True,
nargs="+",
help=
"Output files. File format is inferred from the file path ending. Available file formats are: "
+ ", ".join(["." + k for k in writers.FILE_SUFFIX_MAP]))
args = parser.parse_args(raw_args)
dataloader_kwargs = parse_json_file_str(args.dataloader_args)
imp_score_kwargs = parse_json_file_str(args.imp_score_kwargs)
# setup the files
if not isinstance(args.output, list):
args.output = [args.output]
for o in args.output:
ending = o.split('.')[-1]
if ending not in writers.FILE_SUFFIX_MAP:
logger.error("File ending: {0} for file {1} not from {2}".format(
ending, o, writers.FILE_SUFFIX_MAP))
sys.exit(1)
dir_exists(os.path.dirname(o), logger)
# --------------------------------------------
# install args
if args.install_req:
kipoi.pipeline.install_model_requirements(args.model,
args.source,
and_dataloaders=True)
# load model & dataloader
model = kipoi.get_model(args.model,
args.source,
with_dataloader=args.dataloader is None)
if args.dataloader is not None:
Dl = kipoi.get_dataloader_factory(args.dataloader,
args.dataloader_source)
else:
Dl = model.default_dataloader
dataloader_kwargs = kipoi.pipeline.validate_kwargs(Dl, dataloader_kwargs)
dl = Dl(**dataloader_kwargs)
# get_importance_score
ImpScore = get_importance_score(args.imp_score)
if not ImpScore.is_compatible(model):
raise ValueError("model not compatible with score: {0}".format(
args.imp_score))
impscore = ImpScore(model, **imp_score_kwargs)
# setup batching
it = dl.batch_iter(batch_size=args.batch_size,
num_workers=args.num_workers)
# Setup the writers
use_writers = []
for output in args.output:
ending = output.split('.')[-1]
W = writers.FILE_SUFFIX_MAP[ending]
logger.info("Using {0} for file {1}".format(W.__name__, output))
if ending == "tsv":
assert W == writers.TsvBatchWriter
use_writers.append(
writers.TsvBatchWriter(file_path=output, nested_sep="/"))
elif ending == "bed":
raise Exception("Please use tsv or hdf5 output format.")
elif ending in ["hdf5", "h5"]:
assert W == writers.HDF5BatchWriter
use_writers.append(writers.HDF5BatchWriter(file_path=output))
else:
logger.error("Unknown file format: {0}".format(ending))
sys.exit(1)
# Loop through the data, make predictions, save the output
for i, batch in enumerate(tqdm(it)):
# validate the data schema in the first iteration
if i == 0 and not Dl.output_schema.compatible_with_batch(batch):
logger.warn(
"First batch of data is not compatible with the dataloader schema."
)
# make the prediction
# TODO - handle the reference-based importance scores...
importance_scores = impscore.score(batch['inputs'])
# write out the predictions, metadata (, inputs, targets)
# always keep the inputs so that input*grad can be generated!
# output_batch = prepare_batch(batch, pred_batch, keep_inputs=True)
output_batch = batch
output_batch["importance_scores"] = importance_scores
for writer in use_writers:
writer.batch_write(output_batch)
for writer in use_writers:
writer.close()
logger.info('Done! Importance scores stored in {0}'.format(",".join(
args.output)))
def cli_deeplift(command, raw_args):
"""CLI interface to predict
"""
# TODO: find a way to define the "reference" for a scored sequence.
# from .main import prepare_batch
assert command == "deeplift"
from tqdm import tqdm
from .referencebased import DeepLift
from .referencebased import get_mxts_modes
parser = argparse.ArgumentParser('kipoi interpret {}'.format(command),
description='Calculate DeepLIFT scores.')
add_model(parser)
add_dataloader(parser, with_args=True)
parser.add_argument('--batch_size',
type=int,
default=32,
help='Batch size to use in prediction')
parser.add_argument(
"-n",
"--num_workers",
type=int,
default=0,
help="Number of parallel workers for loading the dataset")
parser.add_argument(
"-l",
"--layer",
type=int,
default=None,
help="With respect to which layer the scores should be calculated.",
required=True)
parser.add_argument(
"--pre_nonlinearity",
help=
"Flag indicating that it should checked whether the selected output is post activation "
"function. If a non-linear activation function is used attempt to use its input. This "
"feature is not available for all models.",
action='store_true')
parser.add_argument(
"-f",
"--filter_idx",
help="Filter index that should be inspected with gradients",
default=None,
required=True,
type=int)
parser.add_argument("-m",
"--mxts_mode",
help="Deeplift score, allowed values are: %s" %
str(list(get_mxts_modes().keys())),
default='rescale_conv_revealcancel_fc')
parser.add_argument(
'-o',
'--output',
required=True,
nargs="+",
help=
"Output files. File format is inferred from the file path ending. Available file formats are: "
+ ", ".join(["." + k for k in writers.FILE_SUFFIX_MAP]))
args = parser.parse_args(raw_args)
dataloader_kwargs = parse_json_file_str(args.dataloader_args)
# setup the files
if not isinstance(args.output, list):
args.output = [args.output]
for o in args.output:
ending = o.split('.')[-1]
if ending not in writers.FILE_SUFFIX_MAP:
logger.error("File ending: {0} for file {1} not from {2}".format(
ending, o, writers.FILE_SUFFIX_MAP))
sys.exit(1)
dir_exists(os.path.dirname(o), logger)
# --------------------------------------------
layer = args.layer
if layer is None and not args.final_layer:
raise Exception(
"A layer has to be selected explicitely using `--layer` or implicitely by using the"
"`--final_layer` flag.")
# Not a good idea
# if layer is not None and isint(layer):
# logger.warn("Interpreting `--layer` value as integer layer index!")
# layer = int(args.layer)
# load model & dataloader
model = kipoi.get_model(args.model, args.source)
if args.dataloader is not None:
Dl = kipoi.get_dataloader_factory(args.dataloader,
args.dataloader_source)
else:
Dl = model.default_dataloader
dataloader_kwargs = kipoi.pipeline.validate_kwargs(Dl, dataloader_kwargs)
dl = Dl(**dataloader_kwargs)
# setup batching
it = dl.batch_iter(batch_size=args.batch_size,
num_workers=args.num_workers)
# Setup the writers
use_writers = []
for output in args.output:
ending = output.split('.')[-1]
W = writers.FILE_SUFFIX_MAP[ending]
logger.info("Using {0} for file {1}".format(W.__name__, output))
if ending == "tsv":
assert W == writers.TsvBatchWriter
use_writers.append(
writers.TsvBatchWriter(file_path=output, nested_sep="/"))
elif ending == "bed":
raise Exception("Please use tsv or hdf5 output format.")
elif ending in ["hdf5", "h5"]:
assert W == writers.HDF5BatchWriter
use_writers.append(writers.HDF5BatchWriter(file_path=output))
else:
logger.error("Unknown file format: {0}".format(ending))
sys.exit(1)
d = DeepLift(model,
output_layer=args.layer,
task_idx=args.filter_idx,
preact=args.pre_nonlinearity,
mxts_mode=args.mxts_mode,
batch_size=args.batch_size)
# Loop through the data, make predictions, save the output
for i, batch in enumerate(tqdm(it)):
# validate the data schema in the first iteration
if i == 0 and not Dl.output_schema.compatible_with_batch(batch):
logger.warn(
"First batch of data is not compatible with the dataloader schema."
)
# calculate scores without reference for the moment.
pred_batch = d.score(batch['inputs'], None)
# write out the predictions, metadata (, inputs, targets)
# always keep the inputs so that input*grad can be generated!
# output_batch = prepare_batch(batch, pred_batch, keep_inputs=True)
output_batch = batch
output_batch["scores"] = pred_batch
for writer in use_writers:
writer.batch_write(output_batch)
for writer in use_writers:
writer.close()
logger.info('Done! Gradients stored in {0}'.format(",".join(args.output)))
