def __init__(self,
corpus_file,
minfreq=0,
howbig=1000,
lemmas=True,
spec_rels=None,
dirname=None,
eval_spec_rels=False,
lr=False):
"""
:param howbig: number of sentences to take into account
"""
self.corpus_file = corpus_file
self.vocab_file = "{}.vocab{}".format(self.corpus_file, howbig)
self.rel_file = "{}.rels.vocab{}".format(self.corpus_file,
howbig) # dependency labels
self.minfreq = minfreq
self.howbig = howbig
self.lemmas = lemmas
self.lr = lr
#read built vocab
try:
self.x_dict = LabelDictionary(
read_vocab(self.vocab_file, self.minfreq))
#except FileNotFoundError:
except IOError:
self.prepare_vocab_dict()
self.x_dict = LabelDictionary(
read_vocab(self.vocab_file, self.minfreq))
print("LabelDictionary created.")
if eval_spec_rels: # in evaluation
try:
import pickle
self.r_dict = pickle.load(
open("{}/r_dict.pickle".format(dirname), "rb"))
except IOError:
sys.exit("r_dict does not exist.")
else:
if self.lr:
self.r_dict = RelationDictionary(["left", "right"])
self.r_dict.write("{}/r_dict.pickle".format(dirname))
else:
try:
r_dict = LabelDictionary(
[l.strip() for l in open(self.rel_file)])
except IOError:
self.prepare_rel_vocab_dict()
r_dict = LabelDictionary(
[l.strip() for l in open(self.rel_file)])
if spec_rels:
self.r_dict = RelationDictionary(spec_rels)
self.r_dict.add("OTHER")
self.r_dict.add_fixed_id(
(set(r_dict.names) - set(spec_rels)),
self.r_dict.get_label_id("OTHER"))
self.r_dict.write("{}/r_dict.pickle".format(dirname))
else:
self.r_dict = r_dict
print("Relation/LabelDictionary created.")
