length = length, base_folder = base_folder,
training_file = os.path.join(model,
data['ric_template']), output =
"test_rric_results_" + args.output, folder = "")
if algorithm == "REC":
crossed_output = functions.run_crossed(
filename = crossed_test,
model = os.path.join(model,
data['rec_crossed_model']),
output = "test_crossed_results_" + args.output,
base_folder = base_folder, folder="")
#Read scores
if algorithm == "CROSSED" or algorithm == "REC":
crossed_scores = functions.read_crossed(
filename = crossed_output, original = args.test,
length = length)
ric_scores = None
rric_scores = None
else:
crossed_scores = None
if algorithm != "CROSSED":
if algorithm != "rRIC":
ric_scores = functions.read_ric(ric_output)
else:
ric_scores = None
if algorithm != "RIC":
rric_scores = functions.read_ric(rric_output)
else:
rric_scores = None
#Train CRoSSeD model
model = functions.train_crossed(positive=crossed_positives,
negative=crossed_negatives, model="CRoSSeD_model",
unique=unique, base_folder=base_folder)
#Aply CRoSSeD to input data
crossed_positives_output = functions.run_crossed(
filename=crossed_positives, model=model,
output="test_crossed_positives", base_folder=base_folder,
folder=unique)
crossed_negatives_output = functions.run_crossed(
filename=crossed_negatives, model=model,
output="test_crossed_negatives", base_folder=base_folder,
folder=unique)
#Read scores
crossed_positive_scores = functions.read_crossed(
filename=crossed_positives_output, original=args.positive,
length=length)
crossed_negative_scores = functions.read_crossed(
filename=crossed_negatives_output, original=args.negative,
length=length)
crossed_value_fdr = functions.get_threshold_unique(
positive = crossed_positive_scores,
negative = crossed_negative_scores,
optim = "FDR")
crossed_value_sen = functions.get_threshold_unique(
positive = crossed_positive_scores,
negative = crossed_negative_scores,
optim = "SEN")
"""
#Do REC CRoSSeD
