def _read_train_dat(self, files):
self.F, self.lookup['src'], self.look_back['src'] = read_features(
files['feat-src'])
self.G, self.lookup['end'], self.look_back['end'] = read_features(
files['feat-end'])
self.L = load_train_valid_labels(files['linkage'], self.lookup,
self.valid_prop)
def _read_train_dat(self, embed1_file, embed2_file, label_file):
self.X, self.lookup['f'], self.look_back['f'] = read_embeddings(
embed1_file)
self.Y, self.lookup['g'], self.look_back['g'] = read_embeddings(
embed2_file)
self.L = load_train_valid_labels(label_file, self.lookup,
self.valid_prop)
def _read_train_dat(self, embed1_file, embed2_file, label_file):
self.X, self.lookup['f'], self.look_back['f'] = self._read_embeddings(
embed1_file, self.lookup['f'], self.look_back['f'])
self.Y, self.lookup['g'], self.look_back['g'] = self._read_embeddings(
embed2_file, self.lookup['g'], self.look_back['g'])
# print self.look_back['f'], len(self.look_back['f']), len(self.lookup['f'].keys())
# print self.look_back['g'], len(self.look_back['g'])
# print len(self.X), len(self.Y)
self.L = load_train_valid_labels(label_file, self.lookup,
self.valid_prop)
def __init__(self, graph, anchorfile, valid_prop, neg_ratio, log_file):
if os.path.exists('log/' + log_file + '.log'):
os.remove('log/' + log_file + '.log')
self.logger = LogHandler(log_file)
if not isinstance(graph, dict):
self.logger.error('The graph must contain src and target graphs.')
return
self.L = load_train_valid_labels(anchorfile, valid_prop)
self.graph = graph
self.look_up = dict()
self.look_up['f'] = self.graph['f'].look_up_dict
self.look_up['g'] = self.graph['g'].look_up_dict
self.look_back = dict()
self.look_back['f'] = self.graph['f'].look_back_list
self.look_back['g'] = self.graph['g'].look_back_list
self.neg_ratio = neg_ratio
self.batch_size = 1024
self.clf = svm.SVC()
def _read_train_dat(self, embed1_file, embed2_file, label_file):
self.L = load_train_valid_labels(label_file, self.valid_prop)
self.X, self.lookup_f, self.look_back_f = self._read_embeddings(
embed1_file, self.lookup_f, self.look_back_f)
self.Y, self.lookup_g, self.look_back_g = self._read_embeddings(
embed2_file, self.lookup_g, self.look_back_g)