def setup(test=False, order=1, learn_options=None, data_file=None):
if 'num_proc' not in learn_options.keys():
learn_options['num_proc'] = None
if 'num_thread_per_proc' not in learn_options.keys():
learn_options['num_thread_per_proc'] = None
num_proc = local_multiprocessing.configure(TEST=test, num_proc=learn_options["num_proc"],
num_thread_per_proc=learn_options["num_thread_per_proc"])
learn_options["num_proc"] = num_proc
learn_options["order"] = order # gets used many places in code, not just here
if "cv" not in learn_options.keys():
# if no CV preference is specified, use leave-one-gene-out
learn_options["cv"] = "gene"
if "normalize_features" not in learn_options.keys():
# if no CV preference is specified, use leave-one-gene-out
learn_options["normalize_features"] = True
if "weighted" not in learn_options.keys():
learn_options['weighted'] = None
if "all pairs" not in learn_options.keys():
learn_options["all pairs"] = False
if "include_known_pairs" not in learn_options.keys():
learn_options["include_known_pairs"] = False
if "include_gene_guide_feature" not in learn_options.keys():
learn_options["include_gene_guide_feature"] = 0 #used as window size, so 0 is none
#these should default to true to match experiments before they were options:
if "gc_features" not in learn_options.keys():
learn_options["gc_features"] = True
if "nuc_features" not in learn_options.keys():
learn_options["nuc_features"] = True
if 'train_genes' not in learn_options.keys():
learn_options["train_genes"] = None
if 'test_genes' not in learn_options.keys():
learn_options["test_genes"] = None
if "num_proc" not in learn_options:
learn_options["num_proc"] = None
if "num_thread_per_proc" not in learn_options:
learn_options["num_thread_per_proc"] = None
if 'seed' not in learn_options:
learn_options['seed'] = 1
if "flipV1target" not in learn_options:
learn_options["flipV1target"] = False
if 'num_genes_remove_train' not in learn_options:
learn_options['num_genes_remove_train'] = None
if "include_microhomology" not in learn_options:
learn_options["include_microhomology"] = False
assert "testing_non_binary_target_name" in learn_options.keys(), "need this in order to get metrics, though used to be not needed, so you may newly see this error"
if learn_options["testing_non_binary_target_name"] not in ['ranks', 'raw', 'thrs']:
raise Exception('learn_otions["testing_non_binary_target_name"] must be in ["ranks", "raw", "thrs"]')
Xdf, Y, gene_position, target_genes = load_data.from_file(data_file, learn_options)
learn_options['all_genes'] = target_genes
if test:
learn_options["order"] = 1
feature_sets = feat.featurize_data(Xdf, learn_options, Y, gene_position)
np.random.seed(learn_options['seed'])
return Y, feature_sets, target_genes, learn_options, num_proc
def setup(test=False, order=1, learn_options=None, data_file=None):
if 'num_proc' not in learn_options.keys():
learn_options['num_proc'] = None
if 'num_thread_per_proc' not in learn_options.keys():
learn_options['num_thread_per_proc'] = None
num_proc = local_multiprocessing.configure(
TEST=test,
num_proc=learn_options["num_proc"],
num_thread_per_proc=learn_options["num_thread_per_proc"])
learn_options["num_proc"] = num_proc
learn_options[
"order"] = order # gets used many places in code, not just here
if "cv" not in learn_options.keys():
# if no CV preference is specified, use leave-one-gene-out
learn_options["cv"] = "gene"
if "normalize_features" not in learn_options.keys():
# if no CV preference is specified, use leave-one-gene-out
learn_options["normalize_features"] = True
if "weighted" not in learn_options.keys():
learn_options['weighted'] = None
if "all pairs" not in learn_options.keys():
learn_options["all pairs"] = False
if "include_known_pairs" not in learn_options.keys():
learn_options["include_known_pairs"] = False
if "include_gene_guide_feature" not in learn_options.keys():
learn_options[
"include_gene_guide_feature"] = 0 #used as window size, so 0 is none
#these should default to true to match experiments before they were options:
if "gc_features" not in learn_options.keys():
learn_options["gc_features"] = True
if "nuc_features" not in learn_options.keys():
learn_options["nuc_features"] = True
if 'train_genes' not in learn_options.keys():
learn_options["train_genes"] = None
if 'test_genes' not in learn_options.keys():
learn_options["test_genes"] = None
if "num_proc" not in learn_options:
learn_options["num_proc"] = None
if "num_thread_per_proc" not in learn_options:
learn_options["num_thread_per_proc"] = None
if 'seed' not in learn_options:
learn_options['seed'] = 1
if "flipV1target" not in learn_options:
learn_options["flipV1target"] = False
if 'num_genes_remove_train' not in learn_options:
learn_options['num_genes_remove_train'] = None
if "include_microhomology" not in learn_options:
learn_options["include_microhomology"] = False
assert "testing_non_binary_target_name" in learn_options.keys(
), "need this in order to get metrics, though used to be not needed, so you may newly see this error"
if learn_options["testing_non_binary_target_name"] not in [
'ranks', 'raw', 'thrs'
]:
raise Exception(
'learn_otions["testing_non_binary_target_name"] must be in ["ranks", "raw", "thrs"]'
)
Xdf, Y, gene_position, target_genes = load_data.from_file(
data_file, learn_options)
learn_options['all_genes'] = target_genes
if test:
learn_options["order"] = 1
feature_sets = feat.featurize_data(Xdf, learn_options, Y, gene_position)
np.random.seed(learn_options['seed'])
return Y, feature_sets, target_genes, learn_options, num_proc
def shared_setup(learn_options, order, test):
if 'num_proc' not in learn_options.keys():
learn_options['num_proc'] = None
if 'num_thread_per_proc' not in learn_options.keys():
learn_options['num_thread_per_proc'] = None
num_proc = local_multiprocessing.configure(TEST=test, num_proc=learn_options["num_proc"],
num_thread_per_proc=learn_options["num_thread_per_proc"])
learn_options["num_proc"] = num_proc
learn_options["order"] = order # gets used many places in code, not just here
if "cv" not in learn_options.keys():
# if no CV preference is specified, use leave-one-gene-out
learn_options["cv"] = "gene"
if "normalize_features" not in learn_options.keys():
# if no CV preference is specified, use leave-one-gene-out
learn_options["normalize_features"] = True
if "weighted" not in learn_options.keys():
learn_options['weighted'] = None
if "all pairs" not in learn_options.keys():
learn_options["all pairs"] = False
if "include_known_pairs" not in learn_options.keys():
learn_options["include_known_pairs"] = False
if "include_gene_guide_feature" not in learn_options.keys():
learn_options["include_gene_guide_feature"] = 0 #used as window size, so 0 is none
#these should default to true to match experiments before they were options:
if "gc_features" not in learn_options.keys():
learn_options["gc_features"] = True
if "nuc_features" not in learn_options.keys():
learn_options["nuc_features"] = True
if 'train_genes' not in learn_options.keys():
learn_options["train_genes"] = None
if 'test_genes' not in learn_options.keys():
learn_options["test_genes"] = None
if "num_proc" not in learn_options:
learn_options["num_proc"] = None
if "num_thread_per_proc" not in learn_options:
learn_options["num_thread_per_proc"] = None
if 'seed' not in learn_options:
learn_options['seed'] = 1
if "flipV1target" not in learn_options:
learn_options["flipV1target"] = False
if 'num_genes_remove_train' not in learn_options:
learn_options['num_genes_remove_train'] = None
if "include_microhomology" not in learn_options:
learn_options["include_microhomology"] = False
if "algorithm_hyperparam_search" not in learn_options:
learn_options["algorithm_hyperparam_search"] = "grid" # other options is bo for bayesian optimization
return num_proc