def process_dataset(self, name):
data = FileIO.read_list_file(name)
new_data = []
for d in data:
d_list = d.split("\t")
new_data.append("\t".join([d_list[0], d_list[1], d_list[2]]))
FileIO.save_list_file("eval-datasets/lexical/7.txt", new_data)
def __init__(self):
self.dataset = FileIO.read_json_file("sematch/benchmark-data/data.txt")
self.results = FileIO.read_list_file("sematch/benchmark-data/result.txt")
self.queries = [(d['query'],d['entity']) for d in self.dataset]
self.relevants = [d['result'] for d in self.dataset]
self.synsetExpansion = SynsetExpansion()
self.engine = Engine()
self.sims = ['wup', 'lch', 'res','jcn', 'lin']
self.thresholds = [0.9,1]
self.gpcs = ['gpc1', 'gpc2', 'gpc3', 'gpc4', 'gpc5', 'gpc6']
def load_dataset(self, dataset_id):
data = FileIO.read_list_file("eval-datasets/lexical/%s.txt" % dataset_id)
word_pairs = map(lambda x: (x.split()[0], x.split()[1]), data)
human = [d.split()[2] for d in data]
return word_pairs, human
def __init__(self):
self.links = FileIO.read_json_file("db/type-linkings.txt")
self.links = {data['offset']:data for data in self.links}
self.query_processor = Query()
self.expander = SynsetExpansion(0.95, 'wup')
