def __init__(self):
freeling.util_init_locale("default")
self.lang= "en"
self.ipath="/usr/local"
self.lpath=self.ipath + "/share/freeling/" + self.lang + "/"
self.tk=freeling.tokenizer(self.lpath+"tokenizer.dat")
self.sp=freeling.splitter(self.lpath+"splitter.dat")
# create the analyzer with the required set of maco_options
self.morfo=freeling.maco(self.my_maco_options(self.lang,self.lpath));
# then, (de)activate required modules
self.morfo.set_active_options (False, # UserMap
False, # NumbersDetection,
True, # PunctuationDetection,
False, # DatesDetection,
True, # DictionarySearch,
True, # AffixAnalysis,
False, # CompoundAnalysis,
True, # RetokContractions,
False, # MultiwordsDetection,
True, # NERecognition,
False, # QuantitiesDetection,
True); # ProbabilityAssignment
# create tagger
self.tagger = freeling.hmm_tagger(self.lpath+"tagger.dat",True,2)
# create sense annotator
self.sen = freeling.senses(self.lpath+"senses.dat");
# create sense disambiguator
self.wsd = freeling.ukb(self.lpath+"ukb.dat");
# create dependency parser
self.parser = freeling.dep_treeler(self.lpath+"dep_treeler/dependences.dat");
def process_file(essay_lst, x):
index = 1
for entry in essay_lst:
# create tagger
essay = entry[1]
id = entry[0]
tagger = freeling.hmm_tagger(lpath + "tagger.dat", True, 2)
# create sense annotator
sen = freeling.senses(lpath + "senses.dat")
# create sense disambiguator
wsd = freeling.ukb(lpath + "ukb.dat")
# create dependency parser
parser = freeling.chart_parser(lpath + "/chunker/grammar-chunk.dat")
dep = freeling.dep_txala(lpath + "/dep_txala/dependences.dat",
parser.get_start_symbol())
# tokenize input line into a list of words
lw = tk.tokenize(essay)
# split list of words in sentences, return list of sentences
ls = sp.split(lw)
# perform morphosyntactic analysis and disambiguation
ls = morfo.analyze(ls)
ls = tagger.analyze(ls)
# annotate and disambiguate senses
ls = sen.analyze(ls)
ls = wsd.analyze(ls)
# parse sentences
ls = parser.analyze(ls)
ls = dep.analyze(ls)
# do whatever is needed with processed sentences
if x == 2:
essays_vacation_tagged.append((id, ProcessSentences(ls)))
elif x == 3:
essays_famous_tagged.append((id, ProcessSentences(ls)))
print(index)
index += 1
def __init__(self):
freeling.util_init_locale("default")
self.lang = "en"
self.ipath = "/usr/local"
self.lpath = self.ipath + "/share/freeling/" + self.lang + "/"
self.tk = freeling.tokenizer(self.lpath + "tokenizer.dat")
self.sp = freeling.splitter(self.lpath + "splitter.dat")
# create the analyzer with the required set of maco_options
self.morfo = freeling.maco(self.my_maco_options(self.lang, self.lpath))
# then, (de)activate required modules
self.morfo.set_active_options(
False, # UserMap
False, # NumbersDetection,
True, # PunctuationDetection,
False, # DatesDetection,
True, # DictionarySearch,
True, # AffixAnalysis,
False, # CompoundAnalysis,
True, # RetokContractions,
False, # MultiwordsDetection,
True, # NERecognition,
False, # QuantitiesDetection,
True)
# ProbabilityAssignment
# create tagger
self.tagger = freeling.hmm_tagger(self.lpath + "tagger.dat", True, 2)
# create sense annotator
self.sen = freeling.senses(self.lpath + "senses.dat")
# create sense disambiguator
self.wsd = freeling.ukb(self.lpath + "ukb.dat")
# create dependency parser
self.parser = freeling.dep_treeler(self.lpath +
"dep_treeler/dependences.dat")
True, # AffixAnalysis,
False, # CompoundAnalysis,
True, # RetokContractions,
True, # MultiwordsDetection,
True, # NERecognition,
False, # QuantitiesDetection,
True)
# ProbabilityAssignment
# create tagger
tagger = pyfreeling.hmm_tagger(lpath + "tagger.dat", True, 2)
# create sense annotator
sen = pyfreeling.senses(lpath + "senses.dat")
# create sense disambiguator
wsd = pyfreeling.ukb(lpath + "ukb.dat")
# create dependency parser
parser = pyfreeling.dep_treeler(lpath + "treeler/dependences.dat")
# process input text
text = "".join(sys.stdin.readlines())
# tokenize input line into a list of words
lw = tk.tokenize(text)
# split list of words in sentences, return list of sentences
ls = sp.split(lw)
# perform morphosyntactic analysis and disambiguation
ls = morfo.analyze(ls)
ls = tagger.analyze(ls)
# annotate and disambiguate senses
True, # PunctuationDetection,
True, # DatesDetection,
True, # DictionarySearch,
True, # AffixAnalysis,
False, # CompoundAnalysis,
True, # RetokContractions,
True, # MultiwordsDetection,
True, # NERecognition,
True, # QuantitiesDetection,
True)
# ProbabilityAssignment
# create tagger, sense anotator, and parsers
tg = pyfreeling.hmm_tagger(DATA + LANG + "/tagger.dat", True, 2)
sen = pyfreeling.senses(DATA + LANG + "/senses.dat")
wsd = pyfreeling.ukb(DATA + LANG + "/ukb.dat")
parser = pyfreeling.dep_lstm(DATA + LANG + "/dep_lstm/params-es.dat")
for filepath in os.listdir(ruta_archivos):
file = os.path.join(ruta_archivos, filepath)
process = Popen([argOE_script, 'rel', 'es', file], stdout=PIPE)
(output, err) = process.communicate()
exit_code = process.wait()
print(output.decode('utf-8'))
content = open(file, 'r').read()
l = tk.tokenize(content)
ls = sp.split(l)
ls = mf.analyze(ls)