def __init__(self):
# Load the initialization file.
configuration_filepath = os.path.dirname(os.path.realpath(__file__)) + \
os.sep + 'nlp_pipeline.config'
self.models = {}
self.load_configuration_file(configuration_filepath)
self.turbo_interface = tp.PTurboParser()
self.workers = {}
def __init__(self, tagger, lemmatizer, model_file):
self.tagger = tagger
self.lemmatize = lemmatizer.lemmatize if lemmatizer else lambda w, t: '_'
import turboparser
self._pturboparser = turboparser.PTurboParser()
self.interface = self._pturboparser.create_parser()
self.interface.load_parser_model(model_file)
def __init__(self):
self.turbo_interface = tp.PTurboParser()
self.workers = {}
def __init__(self,configuration_filepath):
# Load the initialization file.
self.models = {}
self.load_configuration_file(configuration_filepath)
self.turbo_interface = tp.PTurboParser()
self.workers = {}
from settings import *
from sys import stderr
def print(text):
stderr.write(text + '\n')
print('PREPARING TURBOPARSER')
import turboparser
turbo_interface = turboparser.PTurboParser()
print('TURBOPARSER PREPARED')
print('LOADING TOKENIZERS')
import nltk
sentence_tokenizer = nltk.data.load(tokenizer_model)
word_tokenizer = nltk.TreebankWordTokenizer()
print('TOKENIZERS LOADED')
if 'TAG' in implemented_methods or 'LEMMATIZE' in implemented_methods:
print('LOADING TAGGER')
tagger = turbo_interface.create_tagger()
tagger.load_tagger_model(b_tagger_model)
print('TAGGER LOADED')
if 'LEMMATIZE' in implemented_methods or 'TAG' in implemented_methods or 'PARSE' in implemented_methods:
print('LOADING LEMMATIZER')
from lemmatizer import lemmatize
print('LEMMATIZER LOADED')
if 'PARSE' in implemented_methods: