if __name__ == "__main__":
pt = ProgramTimer()
parser = OptionParser(version="%prog 0.8")
parser.add_option("-s","--samples_filename",help="Read samples from FILE",metavar="FILE")
parser.add_option("-m","--model_filename",help="Read rules from FILE",metavar="FILE")
parser.add_option("-t","--target_sample",help="Set the target SAMPLE for selecting",metavar="SAMPLE")
parser.add_option("-f","--target_samples_filename",help="Read target samples from filename, one per line")
parser.add_option("-o","--output_filename",help="Write selected rules to FILE",metavar="FILE")
parser.add_option("-g","--output_genomes",action="store_true",default=False,help="Output genomes that satisfy rules instead")
(options, args) = parser.parse_args()
pt.start()
fileio = FileIO()
samples = fileio.load_samples(options.samples_filename)
target_samples = []
if options.target_sample:
for sample in samples:
if (sample.id == options.target_sample):
target_samples.append(sample)
elif options.target_samples_filename:
target_sample_ids = [x.strip() for x in open(options.target_samples_filename).readlines()]
for target_sample_id in target_sample_ids:
for sample in samples:
if (sample.id == target_sample_id):
target_samples.append(sample)
else:
print "You must specify a target sample"
sys.exit(1)
errorCount += 1
if not options.input_classes_filename:
error("Please provide a phenotype class file with -c /path/to/phenotype.file")
errorCount += 1
if not options.target_class:
error("Please provide the phenotype target to be predicted with -t \"TRAITNAME\"")
errorCount += 1
if not options.output_filename:
error("Please specify a file for the output with -o /path/to/result.file")
errorCount += 1
if errorCount > 0:
error("For help on usage, try calling:\n\tpython %s -h" % os.path.basename(sys.argv[0]))
exit(1)
fileio = FileIO()
samples = fileio.load_samples(options.input_samples_filename)
if options.feature_select:
print "Selecting top %d features from %s, ordered by %s"%(options.feature_select_top_n,options.feature_select,options.feature_select_score)
from pica.AssociationRule import load_rules,AssociationRuleSet
selected_rules = AssociationRuleSet()
rules = load_rules(options.feature_select)
rules.set_target_accuracy(options.feature_select_score)
selected_rules.extend(rules[:options.feature_select_top_n])
samples = samples.feature_select(selected_rules)
classes = fileio.load_classes(options.input_classes_filename)
samples.load_class_labels(classes)
print "Sample set has %d features."%(samples.get_number_of_features())
samples.set_current_class(options.target_class)
print "Parameters from %s"%(options.parameters)
print "Compressing features...",
samples = samples.compress_features()
samples_filename = sys.argv[1]
class_labels_filename = sys.argv[2]
metadata_filename = sys.argv[3]
output_filename = sys.argv[4]
from pica.Sample import SampleSet, ClassLabelSet
from pica.io.FileIO import FileIO
from pica.IntegerMapping import IntegerMapping
from pica.trainers.cwmi.CWMILibrary import CWMILibrary
fileio = FileIO()
cwmilibrary = CWMILibrary()
metadata = fileio.load_metadata(metadata_filename)
samples = fileio.load_samples(samples_filename)
classes = fileio.load_classes(class_labels_filename)
samples.load_class_labels(classes)
confounders = metadata.get_key_list()[1:]
outlines = []
header_line = ["phenotype"]
header_line.extend(confounders)
header_line.append("total")
outlines.append("\t".join(header_line))
for class_name in classes.get_classes():
"generate phenotype map"
samples.set_current_class(class_name)
if not options.input_samples_filename:
error("Please provide a genotype sample file with -s /path/to/genotype.file")
errorCount += 1
if not options.model_filename:
error("Please provide a model file for this phenotype with -m /path/to/model.file")
errorCount += 1
if not options.target_class:
error("Please provide the phenotype target to be predicted with -t \"TRAITNAME\"")
errorCount += 1
if errorCount > 0:
error("For help on usage, try calling:\n\tpython %s -h" % os.path.basename(sys.argv[0]))
exit(1)
fileio = FileIO()
if options.algorithm == "libsvm.libSVMClassifier": # RVF: part of SVM fix (feature-index map)
samples = fileio.load_samples(options.input_samples_filename, indexToAttribute=options.model_filename)
else: #original code
samples = fileio.load_samples(options.input_samples_filename)
if options.input_classes_filename:
classes = fileio.load_classes(options.input_classes_filename)
else:
classes = fileio.init_null_classes(options.input_samples_filename, options.target_class)
#RVF
"""rules = load_rules(options.model_filename) #original code"""
if options.algorithm == "libsvm.libSVMClassifier":
m = svm_model(options.model_filename)
with open(options.model_filename+".classlabelmap", 'rb') as handle:
clm = pickle.loads(handle.read())
with open(options.model_filename+".classlabelmapindex", 'rb') as handle:
clmi= pickle.loads(handle.read())
import sys
samples_filename = sys.argv[1]
class_labels_filename = sys.argv[2]
metadata_filename = sys.argv[3]
output_filename = sys.argv[4]
from pica.Sample import SampleSet, ClassLabelSet
from pica.io.FileIO import FileIO
from pica.IntegerMapping import IntegerMapping
from pica.trainers.cwmi.CWMILibrary import CWMILibrary
fileio = FileIO()
cwmilibrary = CWMILibrary()
metadata = fileio.load_metadata(metadata_filename)
samples = fileio.load_samples(samples_filename)
classes = fileio.load_classes(class_labels_filename)
samples.load_class_labels(classes)
confounders = metadata.get_key_list()[1:]
outlines = []
header_line = ["phenotype"]
header_line.extend(confounders)
header_line.append("total")
outlines.append("\t".join(header_line))
for class_name in classes.get_classes():
"generate phenotype map"
samples.set_current_class(class_name)
"Please provide a model file for this phenotype with -m /path/to/model.file"
)
errorCount += 1
if not options.target_class:
error(
"Please provide the phenotype target to be predicted with -t \"TRAITNAME\""
)
errorCount += 1
if errorCount > 0:
error("For help on usage, try calling:\n\tpython %s -h" %
os.path.basename(sys.argv[0]))
exit(1)
fileio = FileIO()
if options.algorithm == "libsvm.libSVMClassifier": # RVF: part of SVM fix (feature-index map)
samples = fileio.load_samples(options.input_samples_filename,
indexToAttribute=options.model_filename)
else: #original code
samples = fileio.load_samples(options.input_samples_filename)
if options.input_classes_filename:
classes = fileio.load_classes(options.input_classes_filename)
else:
classes = fileio.init_null_classes(options.input_samples_filename,
options.target_class)
#RVF
"""rules = load_rules(options.model_filename) #original code"""
if options.algorithm == "libsvm.libSVMClassifier":
m = svm_model(options.model_filename)
with open(options.model_filename + ".classlabelmap", 'rb') as handle:
clm = pickle.loads(handle.read())
with open(options.model_filename + ".classlabelmapindex",