def read_vocab(vocab_f, minfreq=0):
vocab = []
for l in line_reader(vocab_f):
if eval(l.rstrip().split("\t")[1]) > minfreq:
vocab.append(l.rstrip().split("\t")[0])
return vocab
def prepare_cluster_map(brown_cluster_file):
"""
Build a word-to-clusterid map.
"""
mapping = {}
for l in line_reader(brown_cluster_file):
c_id, w, fq = l.strip().split("\t")
mapping[w] = c_id # keep string cluster ids
return mapping
def prepare_cluster_map(brown_cluster_file):
"""
Build a word-to-clusterid map.
"""
mapping = {}
for l in line_reader(brown_cluster_file):
c_id, w, fq = l.strip().split("\t")
mapping[w] = c_id # keep string cluster ids
return mapping
def prepare_cluster_to_word_map(brown_cluster_file):
"""
Build a clusterid-to-word map.
"""
mapping = defaultdict(set)
for l in line_reader(brown_cluster_file):
c_id, w, fq = l.strip().split("\t")
mapping[c_id].add(w) # keep string cluster ids
return mapping
def prepare_cluster_to_word_map(brown_cluster_file):
"""
Build a clusterid-to-word map.
"""
mapping = defaultdict(set)
for l in line_reader(brown_cluster_file):
c_id, w, fq = l.strip().split("\t")
mapping[c_id].add(w) # keep string cluster ids
return mapping
def read_embed(embed_f):
"""
simply read the embedding file into two structures, one for vocabulary and one for embeddings
"""
w_to_emb = {}
for c, l in enumerate(line_reader(embed_f)):
if c == 0:
m, n = map(eval, l.strip().split())
continue
w, *e = l.strip().split()
assert len(e) == n
w_to_emb[w] = e
return w_to_emb
def read_embed(embed_f):
"""
simply read the embedding file into two structures, one for vocabulary and one for embeddings
"""
w_to_emb = {}
for c, l in enumerate(line_reader(embed_f)):
if c == 0:
m, n = map(eval, l.strip().split())
continue
w, *e = l.strip().split()
assert len(e) == n
w_to_emb[w] = e
return w_to_emb
def load_embed(embed_f, vocab_f):
"""
Reads the embedding file and returns the numpy matrix, where row ids corresponds to vocab ids
"""
w_dict = LabelDictionary(read_vocab(vocab_f))
with open(embed_f) as in_f:
m, n = map(eval, in_f.readline().strip().split())
e_m = np.zeros((m - 1, n)) # embedding matrix; m-1 to leave out </s>
for l in line_reader(embed_f, skip=1):
w, *e = l.strip().split()
assert len(e) == n
if w not in w_dict:
continue
e_m[w_dict.get_label_id(w)] = e
return e_m
def load_embed(embed_f, vocab_f):
"""
Reads the embedding file and returns the numpy matrix, where row ids corresponds to vocab ids
"""
w_dict = LabelDictionary(read_vocab(vocab_f))
with open(embed_f) as in_f:
m, n = map(eval, in_f.readline().strip().split())
e_m = np.zeros((m - 1, n)) # embedding matrix; m-1 to leave out </s>
for l in line_reader(embed_f, skip=1):
w, *e = l.strip().split()
assert len(e) == n
if w not in w_dict:
continue
e_m[w_dict.get_label_id(w)] = e
return e_m
def read_vocab_freq(vocab_f):
vocab = {}
for l in line_reader(vocab_f):
vocab[l.rstrip().split("\t")[0]] = eval(l.rstrip().split("\t")[1])
return vocab
sm = True # split-merge procedure
if start_n_states is None:
# no split-merge
sm = False
start_n_states = desired_n
n_sent = 0
if args.tree or args.rel or args.lr:
reader = Conll07Reader(args.dataset)
sent = reader.getNext()
while sent:
n_sent += 1
sent = reader.getNext()
else:
for l in line_reader(args.dataset):
n_sent += 1
dirname = prepare_dirname(hmm_type=hmm_type,
append_string=append_string,
lang=args.lang,
max_iter=max_iter,
N=start_n_states,
n_sent=n_sent,
alpha=alpha,
minibatch_size=minibatch_size)
if args.tree or args.rel or args.lr:
if args.lang == "en":
dataset = ConllCorpus(args.dataset,
howbig=n_sent,
sm = True # split-merge procedure
if start_n_states is None:
# no split-merge
sm = False
start_n_states = desired_n
n_sent = 0
if args.tree or args.rel or args.lr:
reader = Conll07Reader(args.dataset)
sent = reader.getNext()
while sent:
n_sent += 1
sent = reader.getNext()
else:
for l in line_reader(args.dataset):
n_sent += 1
dirname = prepare_dirname(hmm_type=hmm_type, append_string=append_string, lang=args.lang, max_iter=max_iter,
N=start_n_states, n_sent=n_sent, alpha=alpha, minibatch_size=minibatch_size)
if args.tree or args.rel or args.lr:
if args.lang == "en":
dataset = ConllCorpus(args.dataset, howbig=n_sent, lemmas=lemmas, spec_rels=args.rel_spec_en,
dirname=dirname, lr=args.lr)
elif args.lang == "nl":
dataset = ConllCorpus(args.dataset, howbig=n_sent, lemmas=lemmas, spec_rels=args.rel_spec_nl,
dirname=dirname, lr=args.lr)
else:
dataset = ConllCorpus(args.dataset, howbig=n_sent, lemmas=lemmas, spec_rels=None,
dirname=dirname, lr=args.lr)
