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, # DatesDetection,
True, # DictionarySearch,
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)
False,
True,
True,
True, # select which among created
True,
True,
True,
True, # submodules are to be used.
False,
False,
True,
True) # default: all created submodules are used
# create tagger, sense anotator, and parsers
tg = pyfreeling.hmm_tagger(DATA + LANG + "/tagger.dat", True, 2)
sen = pyfreeling.senses(DATA + LANG + "/senses.dat")
parser = pyfreeling.chart_parser(DATA + LANG + "/chunker/grammar-chunk.dat")
dep = pyfreeling.dep_txala(DATA + LANG + "/dep_txala/dependences.dat",
parser.get_start_symbol())
def distribution(hospital_files_names):
dist_hospitals = {}
for name, files in hospital_file_names.items():
if name != 'all':
dist_hospitals[name] = len(files)
return dist_hospitals
def file_size(hospitals_files_name, dir_annotated_corpora):
DATA + LANG + "/probabilitats.dat");
# create analyzers
tk=pyfreeling.tokenizer(DATA+LANG+"/tokenizer.dat");
sp=pyfreeling.splitter(DATA+LANG+"/splitter.dat");
sid=sp.open_session();
mf=pyfreeling.maco(op);
# activate mmorpho odules to be used in next call
mf.set_active_options(False, True, True, True, # select which among created
True, True, False, True, # submodules are to be used.
True, True, True, True ); # default: all created submodules are used
# create tagger, sense anotator, and parsers
tg=pyfreeling.hmm_tagger(DATA+LANG+"/tagger.dat",True,2);
sen=pyfreeling.senses(DATA+LANG+"/senses.dat");
parser= pyfreeling.chart_parser(DATA+LANG+"/chunker/grammar-chunk.dat");
dep=pyfreeling.dep_txala(DATA+LANG+"/dep_txala/dependences.dat", parser.get_start_symbol());
# process input text
lin=sys.stdin.readline();
print ("Text language is: "+la.identify_language(lin)+"\n");
while (lin) :
l = tk.tokenize(lin);
ls = sp.split(sid,l,False);
ls = mf.analyze(ls);
ls = tg.analyze(ls);
def set_up_analyzer():
## Check whether we know where to find FreeLing data files
if "FREELINGDIR" not in os.environ:
if sys.platform == "win32" or sys.platform == "win64":
os.environ["FREELINGDIR"] = "C:\\Program Files"
else:
os.environ["FREELINGDIR"] = "/usr/local"
#print("FREELINGDIR environment variable not defined, trying ", os.environ["FREELINGDIR"], file=sys.stderr)
if not os.path.exists(os.environ["FREELINGDIR"] + "/share/freeling"):
#print("Folder",os.environ["FREELINGDIR"]+"/share/freeling", "not found.\nPlease set FREELINGDIR environment variable to FreeLing installation directory", file=sys.stderr)
sys.exit(1)
# Location of FreeLing configuration files.
DATA = os.environ["FREELINGDIR"] + "/share/freeling/"
# Init locales
pyfreeling.util_init_locale("default")
#create language detector. Used just to show it. Results are printed
# but ignored (after, it is assumed language is LANG)
la = pyfreeling.lang_ident(DATA + "common/lang_ident/ident-few.dat")
# create options set for maco analyzer. Default values are Ok, except for data files.
LANG = "ru"
op = pyfreeling.maco_options(LANG)
op.set_data_files("", DATA + "common/punct.dat", DATA + LANG + "/dicc.src",
DATA + LANG + "/afixos.dat", "",
DATA + LANG + "/locucions.dat", DATA + LANG + "/np.dat",
DATA + LANG + "/quantities.dat",
DATA + LANG + "/probabilitats.dat")
# create analyzers
tk = pyfreeling.tokenizer(DATA + LANG + "/tokenizer.dat")
sp = pyfreeling.splitter(DATA + LANG + "/splitter.dat")
sid = sp.open_session()
mf = pyfreeling.maco(op)
# activate mmorpho odules to be used in next call
mf.set_active_options(
False,
True,
True,
True, # select which among created
True,
True,
False,
True, # submodules are to be used.
True,
True,
True,
True)
# default: all created submodules are used
# create tagger, sense anotator, and parsers
tg = pyfreeling.hmm_tagger(DATA + LANG + "/tagger.dat", True, 2)
sen = pyfreeling.senses(DATA + LANG + "/senses.dat")
#parser= pyfreeling.chart_parser(DATA+LANG+"/chunker/grammar-chunk.dat");
#dep=pyfreeling.dep_txala(DATA+LANG+"/dep_txala/dependences.dat", parser.get_start_symbol());
return (tk, sp, sid, mf, tg, sen)
