def get_grammar(cls, train_trees, starting_symb='SENT'):
"""
This method returns a the grammar coputed from the training set.
Inputs:
-------
train_trees (list): List of trees to perform training
startting_symbol (str): The root symbol
"""
productions = []
# Chmosky Normal Form
for tree in train_trees:
# Remove unary rules
treetransforms.collapse_unary(tree)
# Transform to CNF
treetransforms.chomsky_normal_form(tree, horzMarkov=2)
# Copute production and store is
productions += tree.productions()
# Define the root symbol
SENT = Nonterminal(starting_symb)
# Compute the grammar using PCFG
grammar = induce_pcfg(SENT, productions)
grammar.chomsky_normal_form()
return grammar
def _induce_pcfg(self, corpus):
"""
Induce PCFG del corpus considerando lexicalización en primer nivel y grupos verbales.
"""
prods = sum((lexicalize(t, grup="grup.verb").productions() for t in lemmatized_sents(corpus.corpus)), [])
S = nltk.Nonterminal('sentence')
return nltk.induce_pcfg(S, prods)
def get_bigram_and_deep_syntax_feature(review, speller, stop_words, ps, preprocess):
res = ""
productions = []
parser = CoreNLPParser(url='http://localhost:9500')
for sentence in re.split(r"[.!?]", review):
try:
tree = next(parser.raw_parse(sentence))
# Optimize by creating Chomsky normal form
tree.collapse_unary(collapsePOS=False)
tree.chomsky_normal_form(horzMarkov=2)
productions += tree.productions()
except StopIteration:
# End of review reached
break
S = Nonterminal('S')
grammar = induce_pcfg(S, productions)
count = 0
for line in str(grammar).split("\n"):
if count == 0:
count += 1
continue
elif "'" in line:
res += re.sub(r"[(->) `\'\"\[\d\]]", "", line) + " "
res += bipos.get_bigrams_and_unigrams_of_sentence(
bow.sanitize_sentence(review, speller, stop_words, ps, preprocess))
return res
def create_pcfg_from_treebank(pickle_it=False, log_it=False, filename="treebank", full=False):
"""
Creates a PCFG from the Penn Treebank dataset using induce_pcfg
Optional pickling of this PCFG in pickled-vars/
"""
if full:
tb = ptb
else:
tb = treebank
productions = []
flat_trees = 0
for item in tb.fileids(): # Goes through all trees
for tree in tb.parsed_sents(item):
if tree.height() == 2: # Gets rid of flat trees
# print("####Tree not collected#####")
flat_trees += 1
continue
# print(" ".join(tree.leaves())) # This should print the sentences
# perform optional tree transformations, e.g.:
# tree.collapse_unary(collapsePOS = False)# Remove branches A-B-C into A-B+C
# tree.chomsky_normal_form(horzMarkov = 2)# Remove A->(B,C,D) into A->B,C+D->D
productions += tree.productions()
print("%s Flat trees purged" % flat_trees)
S = Nonterminal('S')
grammar = induce_pcfg(S, productions)
if pickle_it:
pickle.dump(grammar, open("%s%s-grammar.p" % (var_dir, filename), "wb"))
if log_it:
save_grammar_cleartext(grammar, filename)
save_lexicon_cleartext(grammar, filename)
return grammar
def pcfg_reverse(word):
s = build_tree(word, 0)
tree = nltk.Tree.fromstring(s)
productions = tree.productions()
for p in productions:
##################################################
# !!! THIS IS WHERE THE MAGIC HAPPENS !!! #
if len(p._rhs) > 1: #
p._rhs = (p._rhs[1], p._rhs[0]) #
##############################################
grammar = nltk.induce_pcfg(nltk.Nonterminal("N0"), productions)
# print(grammar) # UNCOMMENT FOR A FUN TIME!
parser = nltk.pchart.InsideChartParser(grammar)
# Shuffle to generate 1000 possible words; only the correct
# solution will be parseable with our grammar!
for i in range(1000):
cand = random.sample(word, len(word))
# print(cand) # UNCOMMENT FOR A FUN TIME!
parser.parse(cand)
for parse in parser.parse(cand):
if parse._ProbabilisticMixIn__prob > 0:
# print("number of tries: {}".format(i)) # UNCOMMENT!
return "".join(cand)
return "no reverse found, try again"
def pcfg_demo():
"""
A demonstration showing how C{WeightedGrammar}s can be created and used.
"""
from nltk.corpus import treebank
from nltk import treetransforms
from nltk import induce_pcfg
from nltk.parse import pchart
pcfg_prods = toy_pcfg1.productions()
pcfg_prod = pcfg_prods[2]
print('A PCFG production:', repr(pcfg_prod))
print(' pcfg_prod.lhs() =>', repr(pcfg_prod.lhs()))
print(' pcfg_prod.rhs() =>', repr(pcfg_prod.rhs()))
print(' pcfg_prod.prob() =>', repr(pcfg_prod.prob()))
print()
grammar = toy_pcfg2
print('A PCFG grammar:', repr(grammar))
print(' grammar.start() =>', repr(grammar.start()))
print(' grammar.productions() =>', end=' ')
# Use string.replace(...) is to line-wrap the output.
print(repr(grammar.productions()).replace(',', ',\n' + ' ' * 26))
print()
print('Coverage of input words by a grammar:')
print(grammar.covers(['a', 'boy']))
print(grammar.covers(['a', 'girl']))
# extract productions from three trees and induce the PCFG
print("Induce PCFG grammar from treebank data:")
productions = []
for item in treebank.items[:2]:
for tree in treebank.parsed_sents(item):
# perform optional tree transformations, e.g.:
tree.collapse_unary(collapsePOS=False)
tree.chomsky_normal_form(horzMarkov=2)
productions += tree.productions()
S = Nonterminal('S')
grammar = induce_pcfg(S, productions)
print(grammar)
print()
print("Parse sentence using induced grammar:")
parser = pchart.InsideChartParser(grammar)
parser.trace(3)
# doesn't work as tokens are different:
#sent = treebank.tokenized('wsj_0001.mrg')[0]
sent = treebank.parsed_sents('wsj_0001.mrg')[0].leaves()
print(sent)
for parse in parser.nbest_parse(sent):
print(parse)
def _induce_pcfg(self, corpus):
"""
Induce PCFG del corpus considerando lexicalización en primer nivel.
"""
#stemmer = SpanishStemmer()
S = nltk.Nonterminal('sentence')
arboles = []
for tree in corpus.corpus.parsed_sents():
# Trasnformamos los arboles para obtener las reglas en Forma Normal de Chomsky.
#tree.collapse_unary(collapsePOS = True, collapseRoot = True)
#tree.chomsky_normal_form(horzMarkov = 2)
arboles.append(tree.copy())
# Hago parent annotation del nivel superior a las hojas utilizando el lema de la hoja.
productions = []
for arbol in arboles:
for t in arbol.treepositions('leaves'):
arbol[t] = arbol[t].lower()
t_p = tuple(x[1] for x in enumerate(t) if x[0] != len(t)-1)
arbol[t_p].set_label(arbol[t_p].label() + "#" + corpus.obtener_lema(arbol[t]))
productions.extend(arbol.productions())
return nltk.induce_pcfg(S, productions)
def create_grammar() -> PCFG:
# 21,763 productions with word terminals
# 8,028 productions with pos terminals
# 6,275 productions with nonterminals without digits
# 5,402 productions with nonterminals without punctuation
# 2,972 productions with nonterminals without suffixes
# 707 nonterminals
# 190 nonterminals without digit labels
# 180 nonterminals without punctuation
# 63 nonterminals without suffixes
productions = []
start_symbol = Nonterminal('S')
for tree in nltk.corpus.treebank.parsed_sents():
for production in tree.productions():
if not valid_nonterminal(production.lhs()):
continue
if isinstance(production.rhs()[0], Nonterminal):
lhs = simplify_nonterminal(production.lhs())
rhs = tuple(
simplify_nonterminal(t) for t in production.rhs()
if valid_nonterminal(t))
productions.append(Production(lhs, rhs))
else:
simplified = simplify_nonterminal(production.lhs())
productions.append(
Production(simplified, (simplified.symbol(), )))
grammar = nltk.induce_pcfg(start_symbol, productions)
#print(grammar.productions())
print(len(grammar.productions()))
nonterminals = set(prod.lhs() for prod in grammar.productions())
print(sorted(nonterminals))
print(len(nonterminals))
return grammar
def induce_weights(self, sentences):
if self.grammar is None:
raise Exception("Need to call induce_structure first")
sentences = [[c for c in s] for s in sentences]
log_prob_last = 0
log_prob_curr = float('inf')
while abs(log_prob_last - log_prob_curr) > 0.0001:
log_prob_last = log_prob_curr
parser = ViterbiParser(self.grammar)
productions = []
log_prob_curr = 0
for i, sent in enumerate(sentences):
print("parsing sentence %i of %i" % (i, len(sentences)))
found = False
for tree in parser.parse(sent):
found = True
log_prob_curr += tree.logprob()
productions += tree.productions()
if not found:
print(sent)
raise Exception("Unable to parse sentence")
# print("last log prog", log_prob_last)
print("curr log prob", log_prob_curr)
self.grammar = nltk.induce_pcfg(self.start, productions)
def learn_PCFG(text_set, start_token):
s = Nonterminal(start_token)
production_list = []
for sent in text_set:
production_list += sent.productions()
return induce_pcfg(s, production_list)
def pcfg_demo():
"""
A demonstration showing how C{WeightedGrammar}s can be created and used.
"""
from nltk.corpus import treebank
from nltk import treetransforms
from nltk import induce_pcfg
from nltk.parse import pchart
pcfg_prods = toy_pcfg1.productions()
pcfg_prod = pcfg_prods[2]
print 'A PCFG production:', ` pcfg_prod `
print ' pcfg_prod.lhs() =>', ` pcfg_prod.lhs() `
print ' pcfg_prod.rhs() =>', ` pcfg_prod.rhs() `
print ' pcfg_prod.prob() =>', ` pcfg_prod.prob() `
print
grammar = toy_pcfg2
print 'A PCFG grammar:', ` grammar `
print ' grammar.start() =>', ` grammar.start() `
print ' grammar.productions() =>',
# Use string.replace(...) is to line-wrap the output.
print ` grammar.productions() `.replace(',', ',\n' + ' ' * 26)
print
print 'Coverage of input words by a grammar:'
print grammar.covers(['a', 'boy'])
print grammar.covers(['a', 'girl'])
# extract productions from three trees and induce the PCFG
print "Induce PCFG grammar from treebank data:"
productions = []
for item in treebank.items[:2]:
for tree in treebank.parsed_sents(item):
# perform optional tree transformations, e.g.:
tree.collapse_unary(collapsePOS=False)
tree.chomsky_normal_form(horzMarkov=2)
productions += tree.productions()
S = Nonterminal('S')
grammar = induce_pcfg(S, productions)
print grammar
print
print "Parse sentence using induced grammar:"
parser = pchart.InsideChartParser(grammar)
parser.trace(3)
# doesn't work as tokens are different:
#sent = treebank.tokenized('wsj_0001.mrg')[0]
sent = treebank.parsed_sents('wsj_0001.mrg')[0].leaves()
print sent
for parse in parser.nbest_parse(sent):
print parse
def generate_pcfg_productions(self, questionbank):
productions = []
with io.open(questionbank, 'r', encoding='utf8') as f:
for line in f:
line = line.strip()
sent_text = nltk.sent_tokenize(line)
for sentence in sent_text:
#print sentence
ss = self.parser.raw_parse_sents((sentence, ))
for k in ss:
for s in k:
buf = "%s" % s
buf = six.text_type(buf)
s1 = Tree.fromstring(buf)
#get rid of the ROOT
for node in s1:
if node.label() == 'ROOT':
continue
else:
s1 = node
break
s1.chomsky_normal_form(horzMarkov=2)
pdc = []
for p in s1.productions():
#remove the lexical production
if not p.is_lexical():
pdc.append(p)
productions += pdc
S = Nonterminal('S')
self.grammar = induce_pcfg(S, productions)
def _induce_pcfg(self, corpus):
"""
Induce PCFG grammar del corpus (treebank) considerando palabras UNK.
"""
unk_words = {k for k,v in self.wordfrecs.iteritems() if v == 1}
productions = []
for tree in corpus.corpus.parsed_sents():
# Trasnformamos los arboles para obtener las reglas en Forma Normal de Chomsky.
#tree.collapse_unary(collapsePOS = True, collapseRoot = True)
#tree.chomsky_normal_form(horzMarkov = 2)
# Transformo todas las hojas a minusculas.
for t in tree.treepositions('leaves'):
tree[t] = tree[t].lower()
productions += tree.productions()
new_productions = []
for pr in productions:
if len(pr.rhs()) == 1 and pr.rhs()[0] in unk_words:
new_pr = nltk.grammar.Production(pr.lhs(), ['UNK'])
new_productions.append(new_pr)
else:
new_productions.append(pr)
S = nltk.Nonterminal('sentence')
return nltk.induce_pcfg(S, new_productions)
def fit_pcfg(self, X):
if self.fitted_pcfg:
raise ValueError("PCFG.pcfg already fitted")
productions = []
for sentence in X:
# nltk format
t = nltk.tree.Tree.fromstring(sentence,
remove_empty_top_bracketing=True)
# chomky normal form
self.chomkysation(t)
#rules exraction
rules = self.extract_rules(t, lexical=False)
productions.extend(rules)
start = nltk.Nonterminal('SENT')
self.pcfg_ = nltk.induce_pcfg(start, productions)
self.pcfg_.chomsky_normal_form(flexible=False)
#get tokens
for prod in self.pcfg_._productions:
for token in prod._rhs:
if not token == 'SENT':
self.non_terminals.append(token)
self.non_terminals.insert(0, start)
#get tokens2index
self.pos2index = {}
for i, token in enumerate(self.non_terminals):
self.pos2index[token] = i
self.fitted_pcfg = True
def train_grammar(unknown_words=[], nb_reduced_production=6000):
productions = []
for item in train:
for tree in treebank.parsed_sents(item):
# perform optional tree transformations, e.g.:
tree.collapse_unary(collapsePOS=False) # Remove branches A-B-C into A-B+C
tree.chomsky_normal_form(horzMarkov=2) # Remove A->(B,C,D) into A->B,C+D->D
#tree_prods = tree.productions()
productions += tree.productions()
counter = collections.Counter(productions)
n_comms = [item for item, count in counter.most_common(nb_reduced_production) for i in range(count)]
#Adding unkwown words and terminal rules back into the reduced productions set
unknown_words_prods = []
for p in productions:
if isinstance(p._rhs[0], str):
unknown_words_prods.append(p)
for u in unknown_words:
rhs = [u]
lhs = p._lhs
new_prod = Production(lhs, rhs)
unknown_words_prods.append(new_prod)
n_comms += unknown_words_prods
S = Nonterminal('S')
grammar = induce_pcfg(S, n_comms)
return grammar
def to_pcfg(sequences, sections):
sequences = [s[s >= 0] for s in sequences]
trees = [Tree.fromstring(to_tree(s, sections)) for s in sequences]
# [t.collapse_unary(collapsePOS = False) for t in trees]
# [t.chomsky_normal_form(horzMarkov = 2) for t in trees]
prods = [p for t in trees for p in t.productions()]
print(induce_pcfg(Nonterminal('S'), prods))
def generate_grammar(f, s):
productions = []
for line in f:
tree = Tree.fromstring(line)
for prodution in tree.productions():
productions += [prodution]
return nltk.induce_pcfg(s, productions)
def get_parser(training_trees):
training_prods = sum([list(tree_to_productions(t)) for t in training_trees], list())
pos_rules = [Production(Nonterminal(lhs), ["$" + rhs]) for lhs, rhs in GRAMMAR_TO_POS.iteritems()]
training_prods += pos_rules
training_pcfg = induce_pcfg(Nonterminal("S"), training_prods)
parser = ViterbiParser(training_pcfg)
return parser, training_pcfg
def _induce_pcfg(self, corpus):
"""
Induce PCFG del corpus.
"""
prods = sum((t.productions() for t in corpus.corpus.parsed_sents()),[])
S = nltk.Nonterminal('sentence')
grammar = nltk.induce_pcfg(S, prods)
return grammar
def _train_rules_grammar(self):
print("training grammar")
self._grammar = nltk.induce_pcfg(
nltk.Nonterminal('TOP'),
reduce(lambda a, b: a + b,
map(lambda t: t.productions(), self._treebank)))
if RUN_MODE == PURE_CKY_M and UNKOWN_MODE:
add_unknowns(self._grammar)
print("finished grammar training")
def build_context_free_grammar(self, data):
productions = []
for tree in [Tree.fromstring(tree) for tree in data]:
tree.collapse_unary(collapsePOS=False)
tree.chomsky_normal_form(horzMarkov=2)
productions += tree.productions()
starting_state = Nonterminal('SENT')
grammar = induce_pcfg(starting_state, productions)
return grammar
def create_pcfg(self, trees):
productions = []
for tree in trees:
tree.collapse_unary(collapsePOS=True)
tree.chomsky_normal_form(horzMarkov=2)
productions += tree.productions()
S = Nonterminal('SENT')
grammar = induce_pcfg(S, productions)
return grammar
def induce(trees: Iterable) -> FancyPCFG:
productions = []
for tree in trees:
# tree.pretty_print()
# perform optional tree transformations, e.g.:
# tree.collapse_unary(collapsePOS = False)# Remove branches A-B-C into A-B+C
# tree.chomsky_normal_form(horzMarkov = 2)# Remove A->(B,C,D) into A->B,C+D->D
productions += tree.productions()
S = Nonterminal('S')
grammar = induce_pcfg(S, productions)
return FancyPCFG.fromCFG(grammar)
def gen_sample_data_grammars(data, root, grammar_format):
''' Generate cfg/pcfg (grammar_format) from nltk.Tree datalist '''
grammars = []
for _data in data:
for production in _data.productions():
grammars.append(production)
if grammar_format == constants.APP_DEFAULT_PCFG_FORMAT:
grammars = nltk.induce_pcfg(root, grammars)
return grammars
def induce_structure(self, sentences):
sentences = [[c for c in s] for s in sentences]
start_symbols = set()
productions = []
prod_table = {}
# group all digits together
digit_terminals = set([str(i) for i in range(10)])
# unary rules
terminals = set()
for s in sentences:
terminals.update(s)
for t in terminals:
if t in digit_terminals:
nt = nltk.Nonterminal("Digit")
else:
nt = nltk.Nonterminal("Unary%s" % self.gen_nt())
p = Production(nt, [t])
productions.append(p)
prod_table[tuple(p.rhs())] = p.lhs()
sentences = self.apply_unary_prod(sentences, prod_table)
while len(sentences) > 0:
if self.has_recursion(sentences):
p = self.generate_recursive_prod(sentences)
else:
p = self.generate_most_frequent_prod(sentences)
productions.append(p)
prod_table[tuple(p.rhs())] = p.lhs()
sentences = self.update_with_prod(sentences, prod_table)
new_sentences = []
for s in sentences:
if len(s) == 1:
start_symbols.add(s[0])
else:
new_sentences.append(s)
sentences = new_sentences
# generate the start productions
for symbol in start_symbols:
for p in productions:
if p.lhs() == symbol:
productions.append(Production(self.start, p.rhs()))
self.grammar = nltk.induce_pcfg(self.start, productions)
def _induce_pcfg(self, corpus):
"""
Induce PCFG grammar del corpus (treebank) considerando palabras UNK.
"""
def induce_unk(tree):
for prod in tree.productions():
if prod.is_lexical() and self.wordfrecs[prod.rhs()[0]] == 1:
yield nltk.Production(prod.lhs(),["UNK"])
else: yield prod
prods = sum((list(induce_unk(t)) for t in corpus.corpus.parsed_sents()), [])
S = nltk.Nonterminal('sentence')
return nltk.induce_pcfg(S, prods)
def getGrammar():
fileid = treebank.fileids()
trainfiles = fileid[:160]
#testfiles=fileid[0.8*len(fileid):]
productions = []
for item in trainfiles:
for tree in treebank.parsed_sents(item):
# perform optional tree transformations, e.g.:
tree.collapse_unary(
collapsePOS=False) # Remove branches A-B-C into A-B+C
tree.chomsky_normal_form(
horzMarkov=2) # Remove A->(B,C,D) into A->B,C+D->D
productions += tree.productions()
lhs_prod = [p.lhs() for p in productions]
rhs_prod = [p.rhs() for p in productions]
set_prod = set(productions)
list_prod = list(set_prod)
token_rule = []
for ele in list_prod:
if ele.is_lexical():
token_rule.append(ele)
set_token_rule = set(p.lhs() for p in token_rule)
list_token_rule = list(set_token_rule)
corr_list_token_rule = []
for word in list_token_rule:
if str(word).isalpha():
corr_list_token_rule.append(word)
continue
#print(corr_list_token_rule)
import nltk
a = []
for tok in corr_list_token_rule:
#lhs = nltk.grammar.Nonterminal('UNK')
lhs = 'UNK'
rhs = [u'UNK']
UNK_production = nltk.grammar.Production(lhs, rhs)
lhs2 = nltk.grammar.Nonterminal(str(tok))
a.append(nltk.grammar.Production(lhs2, [lhs]))
token_rule.extend(a)
list_prod.extend(a)
S = Nonterminal('S')
grammar = induce_pcfg(S, list_prod)
return grammar
def update_grammar(productions, unknown):
lis = pos_tagger.tag(unknown)
for i in range(len(lis)):
pos = nonterminals(lis[i][1])[0]
production_ = Production(pos, [unknown[i]])
productions.append(production_)
print production_, "added to productions"
S = Nonterminal('SENT')
grammar = induce_pcfg(S, productions)
return grammar
def build(self, examples=tuple()):
"""
:param examples: tuple or list of nltk Trees
:return:
"""
allproductions = []
for example in examples:
q = example
t = self.grammarify(q)
t = Tree("S", [t])
productions = t.productions()
allproductions += productions
pcfg = nltk.induce_pcfg(Nonterminal("S"), allproductions)
return pcfg
def createGrammar(self, userMessages, ctx):
parser = CoreNLPParser(url='http://localhost:9000')
parse_trees = []
for message in userMessages:
tokenized = nltk.sent_tokenize(message)
for sentence in tokenized:
parse_trees.append(list(parser.raw_parse(sentence))[0])
grammar_rules = set()
for tree in parse_trees:
for production in tree.productions():
grammar_rules.add(production)
start = nltk.Nonterminal('S')
grammar = nltk.induce_pcfg(start, grammar_rules)
return (' '.join((self.generate_sentence(grammar))))
def main():
# print(nltk.corpus.treebank.parsed_sents('wsj_0001.mrg')[0])
# nltk.corpus.treebank.parsed_sents('wsj_0001.mrg')[0].draw()
# print("Induce PCFG grammar from treebank data:")
#
productions = []
print(len(treebank.fileids()))
for item in treebank.fileids(): # Goes through all trees
for tree in treebank.parsed_sents(item):
# perform optional tree transformations, e.g.:
tree.collapse_unary(collapsePOS = False)# Remove branches A-B-C into A-B+C
tree.chomsky_normal_form(horzMarkov = 2)# Remove A->(B,C,D) into A->B,C+D->D
productions += tree.productions()
# #
# # print(type(productions[0]))
# #
S = Nonterminal('S')
grammar = induce_pcfg(S, productions)
# # # print(grammar) # This is a PCFG
# pickle.dump(grammar, open("tbank-grammar.p", "wb"))
# t = time.time()
# grammar = pickle.load(open("tbank-grammar.p", "rb"))
# textf = open("lexicon.txt", "w")
# n = textf.write(str(reduce(lambda a, b: a + "\n" + b, list(filter(lambda x: "'" in x, str(grammar).split("\n"))))))
# textf.close()
# print(time.time()-t)
parser = ViterbiParser(grammar)
# pickle.dump(parser, open("cky-parser.p", "wb"))
# parser = pickle.load(open("cky-parser.p", "rb"))
parser.trace(0)
sent = "John will join the board"
tokens = sent.split()
try:
grammar.check_coverage(tokens)
print("All words covered")
parses = parser.parse_all(tokens)
if parses:
lp = len(parses)
print(lp)
print(parses[0].label())
# parses[0].draw()
p = reduce(lambda a,b:a+b.prob(), list(filter(lambda x: x.label() == 'S', parses)), 0.0)
else:
p = 0
print("Probability:", p)
except:
print("Some words not covered")
def test_pcfg():
#trees = ['(S (0 1 2) (0 2 3))', '(S (0 1 2) (0 4 5))', '(S (1 1 2) (1 2 3))']
#trees = ['(S (0 1 2) (3 4 5 6))', '(S (0 1 2) (7 8) (3 4 5 6))', '(S (0 1 2) (9 4) (10 6))']
trees = [
'(S (0 1 2) (3 4 5 6))', '(S (0 1 2) (7 8) (3 4 5 6))',
'(S (0 1 2) (3 4 6))'
]
trees = [Tree.fromstring(t) for t in trees]
print(trees)
prods = [p for t in trees for p in t.productions()]
print(prods)
grammar = induce_pcfg(Nonterminal('S'), prods)
print(grammar)
sequences = [t.leaves() for t in trees]
description_length(grammar, sequences)
def __init__(self, training_set, vocabulary):
""" Initializer for the OmissionDetector
Trains a PCFG and a HMM to aid in omission detection
Args:
training_set -- list of parsed sentences
vocabulary -- set of known words
"""
prods = flatten([tree.productions() for tree in training_set])
pcfg = induce_pcfg(Nonterminal("S"), prods)
self._grammar = InvertedGrammar(pcfg)
tagged_training_set = [tagged_sent(s) for s in training_set]
self._hmm = NgramHMM(TEST_N, vocabulary)
self._hmm.train(tagged_training_set)
def pcfg_train(trees, vocab):
# Write a function pcfg_train() that takes as its input a collection
# of nltk.tree.Tree objects. For example, it might be passed some
# portion of nltk.corpus.treebank.parsed_sents(). This function
# should return a nltk.PCFG object.
all_productions = []
for t in trees:
for p in t.productions():
all_productions.append(nltk.Production(p.lhs(), p.rhs()))
pcfg = nltk.induce_pcfg(nltk.Nonterminal('S'), all_productions)
return (pcfg)
def ex7():
"""
Using NLTK's own library to generate the probabilities.
"""
productions = [
p for tree in treebank.parsed_sents() for p in tree.productions()
]
pcfg = induce_pcfg(Nonterminal("S"), productions)
# print(pcfg.productions())
parser = pchart.InsideChartParser(pcfg, beam_size=800)
for sent in sentences1:
parsed = list(parser.parse(sent.split()))
print("Parsing sent: {}".format(sent))
print(parsed[0])
def parse(sentence: str,
save: bool = True,
index: str = str(uuid.uuid4())) -> dict:
results = dict()
sentence = preprocess(sentence)
print(f'Sentence: {sentence}')
results['speech_text'] = sentence
tokenized = list(pos_parser.tokenize(sentence))
print(f'Tokenized: {tokenized}')
print(f'Total words: {len(tokenized)}\n')
tagged = list(pos_parser.tag(tokenized))
print(f'Tagged: {tagged}\n')
results['pos_tagged'] = tagged
ne_tags = ne_chunk(tagged)
entities = [(tag.label(), ' '.join(t[0] for t in tag)) for tag in ne_tags
if hasattr(tag, 'label')]
entities.extend(tag_entities(tagged))
print(f'Entities: {entities}\n')
results['named_entities'] = entities
parsed = next(pos_parser.raw_parse(sentence))
print('Grammar')
parsed.pretty_print()
root = Nonterminal('S')
grammar = induce_pcfg(root, parsed.productions())
print(grammar, '\n')
productions = [(str(prod._lhs), [str(t) for t in prod._rhs], prod.prob())
for prod in grammar._productions]
results['productions'] = productions
probabilities = [prod.prob() for prod in grammar._productions]
pcfg = reduce(mul, probabilities)
print(pcfg, '\n')
results['pcfg'] = pcfg
if save:
results['tree_bin'] = save_image(parsed, index)
return results
def pcfgParse(sentence):
productions = list()
root = nltk.Nonterminal('S')
for tree in nltk.corpus.treebank.parsed_sents():
productions += tree.productions()
grammar = nltk.induce_pcfg(root, productions)
PCFGParser = nltk.ViterbiParser(grammar)
s_sent = sentence.split()
parsed_sent = PCFGParser.parse(s_sent)
for p in parsed_sent:
print p
def getParser():
"""
:return: A Viterbi Parser
"""
productions = []
S = nltk.Nonterminal('S')
for tree in train_corpus:
productions += tree.productions()
grammar = nltk.induce_pcfg(S, productions)
for p in islice(grammar.productions(), 50):
print p
return nltk.ViterbiParser(grammar)
def construct_grammar(f, S):
productions = []
for line in f:
tree = Tree.fromstring(line)
# 把树chomsky_normal_form
# tree.collapse_unary(collapsePOS = True, collapseRoot = True)
# tree.chomsky_normal_form(horzMarkov = 2)
# tree.set_label('TOP')
for prodution in tree.productions():
if len(prodution.rhs()) == 1 and isinstance(
prodution.rhs()[0], nltk.Nonterminal):
print(prodution.rhs())
productions += [prodution]
with open('productions.txt', 'w') as f:
f.write(str(productions))
return nltk.induce_pcfg(S, productions)
def PCFG_Section():
toy_pcfg1 = PCFG.fromstring("""
S -> NP VP [1.0]
NP -> Det N [0.5] | NP PP [0.25] | 'John' [0.1] | 'I' [0.15]
Det -> 'the' [0.8] | 'my' [0.2]
N -> 'man' [0.5] | 'telescope' [0.5]
VP -> VP PP [0.1] | V NP [0.7] | V [0.2]
V -> 'ate' [0.35] | 'saw' [0.65]
PP -> P NP [1.0]
P -> 'with' [0.61] | 'under' [0.39]
""")
pcfg_prods = toy_pcfg1.productions()
pcfg_prod = pcfg_prods[2]
print('A PCFG production:', pcfg_prod)
print('pcfg_prod.lhs() =>', pcfg_prod.lhs())
print('pcfg_prod.rhs() =>', pcfg_prod.rhs())
print('pcfg_prod.prob() =>', pcfg_prod.prob())
# extract productions from three trees and induce the PCFG
print("Induce PCFG grammar from treebank data:")
productions = []
for item in treebank.fileids()[:2]:
for tree in treebank.parsed_sents(item):
# print(" ".join(tree.leaves()))
# perform optional tree transformations, e.g.:
# tree.collapse_unary(collapsePOS = False)# Remove branches A-B-C into A-B+C
# tree.chomsky_normal_form(horzMarkov = 2)# Remove A->(B,C,D) into A->B,C+D->D
prods = tree.productions()
# print(prods[0].prob())
productions += prods
S = Nonterminal('S')
grammar = induce_pcfg(S, productions)
# print(grammar) # This is a PCFG
### Parsing section below ###
print("\nParse sentence using induced grammar:")
parser = pchart.InsideChartParser(grammar)
parser.trace(1)
sent = treebank.parsed_sents('wsj_0001.mrg')[0]
print(sent.prob())
def _induce_pcfg(self, corpus):
"""
Induce PCFG del corpus.
"""
productions = []
S = nltk.Nonterminal('sentence')
for tree in corpus.corpus.parsed_sents():
# Trasnformamos los arboles para obtener las reglas en Forma Normal de Chomsky.
#tree.collapse_unary(collapsePOS = True, collapseRoot = True)
#tree.chomsky_normal_form(horzMarkov = 2)
# Transformo todas las hojas del arbol a minuscula
for t in tree.treepositions('leaves'):
tree[t] = tree[t].lower()
productions += tree.productions()
return nltk.induce_pcfg(S, productions)
def _induce_pcfg(self, corpus):
"""
Induce PCFG del corpus considerando lexicalización en primer nivel y grupos verbales.
"""
S = nltk.Nonterminal('sentence')
# Hago parent annotation del nivel superior a las hojas utilizando el lema de la hoja.
productions = []
for arbol in corpus.corpus.parsed_sents():
for t in arbol.treepositions('leaves'):
arbol[t] = arbol[t].lower()
t_p = tuple(x[1] for x in enumerate(t) if x[0] != len(t)-1)
arbol[t_p].set_label(arbol[t_p].label() + "#" + corpus.obtener_lema(arbol[t]))
verbo = corpus.obtener_lema(arbol[t])
if verbo.endswith(("ar", "er", "ir",)) and "_" not in verbo:
t_p2 = tuple(x[1] for x in enumerate(t_p) if x[0] != len(t_p)-1)
if arbol[t_p2].label() == "grup.verb":
arbol[t_p2].set_label(arbol[t_p2].label() + "#" + verbo)
productions.extend(arbol.productions())
return nltk.induce_pcfg(S, productions)
def train_pcfg():
print 'training grammar'
productions = []
# print len(treebank.fileids())
trees = []
# up to 199 less for shorter grammar for quicker training
for fileid in treebank.fileids()[0:20]:
for tree in treebank.parsed_sents(fileid):
# perform optional tree transformations, e.g.:
# Remove branches A->B->C into A->B+C so we can avoid infinite
# productions
tree.collapse_unary(collapsePOS=False)
# Remove A->(B,C,D) into A->B,C+D->D (binarization req'd by CKY parser)
# horizontal and vertical Markovization: remember parents and siblings in tree
# This gives a performance boost, but makes the grammar HUGE
# If we use these we would need to implement a tag forgetting method
#tree.chomsky_normal_form(horzMarkov = 0, vertMarkov=0)
tree.chomsky_normal_form()
productions += tree.productions()
S = nltk.Nonterminal('S')
grammar = nltk.induce_pcfg(S, productions)
print "grammar trained!"
return grammar
path = 'ancora/ancora-3.0.1es/'
corpus = ancora.AncoraCorpusReader(path)
t = corpus.parsed_sents()[0]
t.draw()
t.productions()
prods = []
for t in corpus.parsed_sents():
prods += t.productions()
#print (prods)
S = nltk.Nonterminal('sentence')
grammar = nltk.induce_pcfg(S, prods)
#prods2 = grammar.productions(lhs=nltk.Nonterminal('ncms000'))
#print (prods2)
print ("===============================================================")
print ("===============================================================")
parser = nltk.ViterbiParser(grammar)
for tree in parser.parse("El gato come pescado crudo .".split()):
print (tree)
tree.draw()
tree.prob()
print('done!')
#merge productions
Production += Production_singleCharWord
#
# inducing PCFG from the productions
#
print('\n\nInducing PCFG from the producitons occurre the treebank...')
W=nltk.Nonterminal('W')
baseline_grammar=nltk.induce_pcfg(W, Production)
print('done!')
path_grammar='../working_data/baseline.grammar.pickle'
print('\nSaving the induced grammar to',path_grammar,' ...')
f=open(path_grammar, 'wb')
pickle.dump(baseline_grammar, f)
f.close()
def PCFGlearning(dataset, start):
production_list = []
S = Nonterminal(start)
for sent in dataset:
production_list += sent.productions()
return induce_pcfg(S, production_list)
# normalize the c structures
for t in grammar_used:
t.chomsky_normal_form()
tbank_productions2 = list(treebank.sents())
test_part = tbank_productions2[int(len(tbank_productions) * 0.8):]
# prodcutions
productions = []
for t in grammar_used:
productions += Tree.productions(t)
# induce PCFG
S = nltk.Nonterminal("S")
grammar = nltk.induce_pcfg(S, productions)
prod = grammar.productions()
#helping function to get the probability of a production
def findProb(lhsa, rhsa, prod):
for p in prod:
if p.lhs() == lhsa and p.rhs() == rhsa:
return (p.prob())
def CKY(words, grammar):
nonterms = set()
for g in grammar.productions():
nonterms.add(g.lhs())
triples =[]
lenwords = len(words)
from nltk import induce_pcfg
from nltk import treetransforms
from nltk.corpus import treebank
from nltk.grammar import Nonterminal
from nltk.parse import pchart
productions = []
for tree in treebank.parsed_sents():
# perform optional tree transformations, e.g.:
tree.collapse_unary(collapsePOS=False) # Remove branches A-B-C into A-B+C
tree.chomsky_normal_form(horzMarkov=2) # Remove A->(B,C,D) into A->B,C+D->D
productions += tree.productions()
# Print the grammar
S = Nonterminal('S')
grammar = induce_pcfg(S, productions)
print grammar
from nltk.treetransforms import chomsky_normal_form
'''
tbank_productions = set(production for sent in treebank.parsed_sents()
for production in sent.productions())
'''
treebank_prods = []
for i in range(199): # for all found sets of fileids
tbstuff = treebank._fileids[i] # get a bunch of 'em
for tree in treebank.parsed_sents(tbstuff):
tree.chomsky_normal_form()
treebank_prods += tree.productions()
tTCpcfg = nltk.induce_pcfg(Nonterminal('S'), list(treebank_prods))
# induce pcfg
# PTCpcfg = nltk.induce_pcfg(tbank_grammar)
# treetransforms: chomsky_normal_form
print("done! You have your WeightedGrammar")
#tree.chomsky_normal_form(horzMarkov = 2)
# srules is the set of non-lexical rules with duplicates removed
srules = list(set(drules))
print len(srules)
# slex is the set of lexical rules with duplicates removed
slex = list(set(plex))
print len(slex)
# create a nonprobabilistic parser
grammar = ContextFreeGrammar(Nonterminal('S'),srules+slex)
parser = nltk.parse.chart.ChartParser(grammar)
# create a probabilistic parser
wgrammar = nltk.induce_pcfg(Nonterminal('S'),plex+drules)
wparser = nltk.parse.viterbi.ViterbiParser(wgrammar)
# try out the probabilistic parser on a few sentences
t = "that is very interesting .".split(' ')
trees = wparser.nbest_parse(t,n=10)
print trees
u = "from the beginning to the end , it was an entertaining game .".split(' ')
trees = wparser.nbest_parse(u,n=10)
print trees
v = "the workers dumped sacks into a bin .".split(' ')
trees = wparser.nbest_parse(v,n=10)
print trees
print trees[0].productions()
