def test_get_classes_by_partial_name(self):
classes = ReflectionHandler.get_classes_by_partial_name(
"Implanting", "simulation/signal_implanting_strategy/")
self.assertSetEqual(
{
HealthySequenceImplanting, ReceptorImplanting,
FullSequenceImplanting
}, set(classes))
def parse_commandline_arguments(args):
ReflectionHandler.get_classes_by_partial_name("", "ml_methods/")
ml_method_names = [
cl.__name__
for cl in ReflectionHandler.all_nonabstract_subclasses(MLMethod)
] + ["SimpleLogisticRegression"]
parser = argparse.ArgumentParser(
description="tool for building immuneML Galaxy YAML from arguments")
parser.add_argument(
"-o",
"--output_path",
required=True,
help="Output location for the generated yaml file (directiory).")
parser.add_argument(
"-f",
"--file_name",
default="specs.yaml",
help=
"Output file name for the yaml file. Default name is 'specs.yaml' if not specified."
)
parser.add_argument(
"-l",
"--labels",
required=True,
help=
"Which metadata labels should be predicted for the dataset (separated by comma)."
)
parser.add_argument(
"-m",
"--ml_methods",
nargs="+",
choices=ml_method_names,
required=True,
help="Which machine learning methods should be applied.")
parser.add_argument("-t",
"--training_percentage",
type=float,
required=True,
help="The percentage of data used for training.")
parser.add_argument(
"-c",
"--split_count",
type=int,
required=True,
help=
"The number of times to repeat the training process with a different random split of the data."
)
parser.add_argument(
"-s",
"--sequence_type",
choices=["complete", "subsequence"],
default=["subsequence"],
nargs="+",
help="Whether complete CDR3 sequences are used, or k-mer subsequences."
)
parser.add_argument(
"-p",
"--position_type",
choices=["invariant", "positional"],
nargs="+",
help=
"Whether IMGT-positional information is used for k-mers, or the k-mer positions are position-invariant."
)
parser.add_argument("-g",
"--gap_type",
choices=["gapped", "ungapped"],
nargs="+",
help="Whether the k-mers contain gaps.")
parser.add_argument("-k", "--k", type=int, nargs="+", help="K-mer size.")
parser.add_argument("-kl",
"--k_left",
type=int,
nargs="+",
help="Length before gap when k-mers are used.")
parser.add_argument("-kr",
"--k_right",
type=int,
nargs="+",
help="Length after gap when k-mers are used.")
parser.add_argument("-gi",
"--min_gap",
type=int,
nargs="+",
help="Minimal gap length when gapped k-mers are used.")
parser.add_argument("-ga",
"--max_gap",
type=int,
nargs="+",
help="Maximal gap length when gapped k-mers are used.")
parser.add_argument(
"-r",
"--reads",
choices=[ReadsType.UNIQUE.value, ReadsType.ALL.value],
nargs="+",
default=[ReadsType.UNIQUE.value],
help=
"Whether k-mer counts should be scaled by unique clonotypes or all observed receptor sequences"
)
return parser.parse_args(args)
