def read_sequence_list_conll(self, train_file, max_sent_len=100000, max_nr_sent=100000):
""" Read a conll2002 or conll2003 file into a sequence list."""
instance_list = self.read_conll_instances(train_file, max_sent_len, max_nr_sent)
seq_list = SequenceList(self.word_dict) # for indices
for sent_x in instance_list:
seq_list.add_sequence(sent_x)
return seq_list
def prepare_chains(self):
# training sequences
self.train = SequenceList(self.x_dict)
print("Creating training from corpus.")
with open(self.corpus_file) as IN:
for c, l in enumerate(IN, 1):
if c > self.howbig:
break
self.train.add_sequence([w for w in l.strip().split(" ")])
def read_sequence_list_conll(self,
train_file,
max_sent_len=100000,
max_nr_sent=100000):
""" Read a conll2002 or conll2003 file into a sequence list."""
instance_list = self.read_conll_instances(train_file, max_sent_len,
max_nr_sent)
seq_list = SequenceList(self.word_dict) # for indices
for sent_x in instance_list:
seq_list.add_sequence(sent_x)
return seq_list
def __init__(self):
#observation vocabulary
self.x_dict = LabelDictionary(["walk", "shop", "clean", "tennis"])
#training sequences
train_seqs = SequenceList(self.x_dict)
train_seqs.add_sequence(["walk", "walk", "shop", "clean"])
train_seqs.add_sequence(["walk", "walk", "shop", "clean"])
train_seqs.add_sequence(["walk", "shop", "shop", "clean"])
self.train = train_seqs
def load_seq(s):
from sequences.sequence_list import SequenceList
seq_list = SequenceList(word_dict, tag_dict)
words = []
tags = []
line = s.rstrip()
pairs = line.split(' ')
for pair in pairs:
fields = pair.split('_')
words.append(fields[0])
tags.append(fields[1])
seq_list.add_sequence(words, tags)
return seq_list[0]
class TextCorpus:
def __init__(self, corpus_file, minfreq=0, howbig=10000):
"""
:param minfreq: minimum frequency of a word in order to be taken into account
:param howbig: number of sentences to take into account
"""
self.corpus_file = corpus_file
self.vocab_file = "{}.vocab".format(
self.corpus_file) # file of form: w\tf\n
self.minfreq = minfreq
self.howbig = howbig
try:
self.x_dict = LabelDictionary(
read_vocab(self.vocab_file, self.minfreq))
except IOError:
self.prepare_vocab_dict()
self.x_dict = LabelDictionary(
read_vocab(self.vocab_file, self.minfreq))
print("LabelDictionary created.")
def prepare_chains(self):
# training sequences
self.train = SequenceList(self.x_dict)
print("Creating training from corpus.")
with open(self.corpus_file) as IN:
for c, l in enumerate(IN, 1):
if c > self.howbig:
break
self.train.add_sequence([w for w in l.strip().split(" ")])
def prepare_vocab_dict(self):
from collections import defaultdict
vocab_dict = defaultdict(int)
with open(self.corpus_file) as IN, open(self.vocab_file, "w") as OUT:
for c, l in enumerate(IN, 1):
if c > self.howbig:
break
for w in l.strip().split(" "):
vocab_dict[w] += 1
for w, f in vocab_dict.items():
OUT.write("{}\t{}\n".format(w, f))
print("Vocabulary file prepared.")
class TextCorpus:
def __init__(self, corpus_file, minfreq=0, howbig=10000):
"""
:param minfreq: minimum frequency of a word in order to be taken into account
:param howbig: number of sentences to take into account
"""
self.corpus_file = corpus_file
self.vocab_file = "{}.vocab".format(self.corpus_file) # file of form: w\tf\n
self.minfreq = minfreq
self.howbig = howbig
try:
self.x_dict = LabelDictionary(read_vocab(self.vocab_file, self.minfreq))
except IOError:
self.prepare_vocab_dict()
self.x_dict = LabelDictionary(read_vocab(self.vocab_file, self.minfreq))
print("LabelDictionary created.")
def prepare_chains(self):
# training sequences
self.train = SequenceList(self.x_dict)
print("Creating training from corpus.")
with open(self.corpus_file) as IN:
for c, l in enumerate(IN, 1):
if c > self.howbig:
break
self.train.add_sequence([w for w in l.strip().split(" ")])
def prepare_vocab_dict(self):
from collections import defaultdict
vocab_dict = defaultdict(int)
with open(self.corpus_file) as IN, open(self.vocab_file, "w") as OUT:
for c, l in enumerate(IN, 1):
if c > self.howbig:
break
for w in l.strip().split(" "):
vocab_dict[w] += 1
for w, f in vocab_dict.items():
OUT.write("{}\t{}\n".format(w, f))
print("Vocabulary file prepared.")
def prepare_chains(self):
# training sequences
self.train = SequenceList(self.x_dict)
print("Creating training from corpus.")
with open(self.corpus_file) as IN:
for c, l in enumerate(IN, 1):
if c > self.howbig:
break
self.train.add_sequence([w for w in l.strip().split(" ")])
def load_seq(s):
from sequences.sequence_list import SequenceList
seq_list = SequenceList(word_dict, tag_dict)
ex_x = []
ex_y = []
contents = s.decode('string-escape').split('\n')
for line in contents:
toks = line.split()
if len(toks) < 2:
continue
pos = toks[4]
word = toks[1]
pos = pos.lower()
assert pos in mapping
assert word in word_dict
pos = mapping[pos]
assert pos in tag_dict
ex_x.append(word)
ex_y.append(pos)
seq_list.add_sequence(ex_x, ex_y)
return seq_list[0]
def load_seq(s):
from sequences.sequence_list import SequenceList
seq_list = SequenceList(word_dict, tag_dict)
ex_x = []
ex_y = []
contents = s.decode('string-escape').split('\n')
for line in contents:
toks = line.split()
if len(toks) < 2:
continue
pos = toks[4]
word = toks[1]
pos = pos.lower()
assert pos in mapping
assert word in word_dict
pos = mapping[pos]
assert pos in tag_dict
ex_x.append(word)
ex_y.append(pos)
seq_list.add_sequence(ex_x, ex_y)
return seq_list[0]
def __init__(self):
#observation vocabulary
self.x_dict = LabelDictionary(["walk", "shop", "clean", "tennis"])
#training sequences
train_seqs = SequenceList(self.x_dict)
train_seqs.add_sequence(["walk", "walk", "shop", "clean"])
train_seqs.add_sequence(["walk", "walk", "shop", "clean"])
train_seqs.add_sequence(["walk", "shop", "shop", "clean"])
self.train = train_seqs
def __init__(self):
self.word_dict = LabelDictionary()
self.sequence_list = SequenceList(self.word_dict)
