def __init__(self,
fasta_filename,
kabat_filename,
alphabet,
count,
is_random=False):
self.count = count
self.alphabet = alphabet
if kabat_filename is not None:
self.load_kabat(kabat_filename)
self.markup = []
else:
self.markup = None
raw_data = svm_tools.get_raw_data(fasta_filename, is_random)
i = 0
self.data = []
for record in raw_data:
if not self.is_marked() or record.id in self.regions:
i += 1
self.data.append(record)
if self.is_marked():
self.markup.append(self.regions[record.id])
if i >= count:
break
def __init__(self, filename_list, gene_type_list, alphabet, count_per_file, is_random):
self.alphabet = alphabet
self.data = []
self.markup = None if gene_type_list is None else []
for filename, gene_type in zip(filename_list, gene_type_list):
raw_data = svm_tools.get_raw_data(filename, is_random)
self.data.extend(raw_data[:count_per_file])
if self.is_marked():
self.markup.extend([self.type_to_number[gene_type]] * count_per_file)
def __init__(self, filename_list, gene_type_list, alphabet, count_per_file,
is_random):
self.alphabet = alphabet
self.data = []
self.markup = None if gene_type_list is None else []
for filename, gene_type in zip(filename_list, gene_type_list):
raw_data = svm_tools.get_raw_data(filename, is_random)
self.data.extend(raw_data[:count_per_file])
if self.is_marked():
self.markup.extend([self.type_to_number[gene_type]] *
count_per_file)
def __init__(self, fasta_filename, kabat_filename, alphabet, count, is_random=False):
self.count = count
self.alphabet = alphabet
if kabat_filename is not None:
self.load_kabat(kabat_filename)
self.markup = []
else:
self.markup = None
raw_data = svm_tools.get_raw_data(fasta_filename, is_random)
i = 0
self.data = []
for record in raw_data:
if not self.is_marked() or record.id in self.regions:
i += 1
self.data.append(record)
if self.is_marked():
self.markup.append(self.regions[record.id])
if i >= count:
break
