def __init__(self, cfg):
self.cfg = cfg
self.lang = self.cfg.get("deps", "lang")
self.out_fn = self.cfg.get("machine", "definitions_binary_out")
ensure_dir(os.path.dirname(self.out_fn))
self.dependency_processor = DependencyProcessor(self.cfg)
dep_map_fn = cfg.get("deps", "dep_map")
self.read_dep_map(dep_map_fn)
self.undefined = set()
self.lemmatizer = Lemmatizer(cfg)
self.lexicon_fn = self.cfg.get("machine", "definitions_binary")
self.lexicon = Lexicon.load_from_binary(self.lexicon_fn)
self.word2lemma = {}
def __init__(self, cfg):
self.cfg = cfg
self.lang = self.cfg.get("deps", "lang")
self.out_fn = self.cfg.get("machine", "definitions_binary_out")
ensure_dir(os.path.dirname(self.out_fn))
self.dependency_processor = DependencyProcessor(self.cfg)
dep_map_fn = cfg.get("deps", "dep_map")
self.read_dep_map(dep_map_fn)
self.undefined = set()
self.lemmatizer = Lemmatizer(cfg)
self.lexicon_fn = self.cfg.get("machine", "definitions_binary")
self.lexicon = Lexicon.load_from_binary(self.lexicon_fn)
self.word2lemma = {}
def __init__(self, cfg, direct_parse=False):
self.cfg = cfg
self.lang = self.cfg.get("deps", "lang")
if (not direct_parse):
self.out_fn = self.cfg.get("machine", "definitions_binary_out")
ensure_dir(os.path.dirname(self.out_fn))
self.dependency_processor = DependencyProcessor(self.cfg)
dep_map_fn = cfg.get("deps", "dep_map")
self.undefined = set()
self.lemmatizer = Lemmatizer(cfg)
self.lexicon_fn = self.cfg.get("machine", "definitions_binary")
self.lexicon = Lexicon.load_from_binary(self.lexicon_fn)
self.read_dep_map(dep_map_fn)
self.word2lemma = {}
self.first_only = cfg.getboolean('filter', 'first_only')
def __init__(self, cfg, direct_parse=False):
self.cfg = cfg
self.lang = self.cfg.get("deps", "lang")
if(not direct_parse):
self.out_fn = self.cfg.get("machine", "definitions_binary_out")
ensure_dir(os.path.dirname(self.out_fn))
self.dependency_processor = DependencyProcessor(self.cfg)
dep_map_fn = cfg.get("deps", "dep_map")
self.undefined = set()
self.lemmatizer = Lemmatizer(cfg)
self.lexicon_fn = self.cfg.get("machine", "definitions_binary")
self.lexicon = Lexicon.load_from_binary(self.lexicon_fn)
self.read_dep_map(dep_map_fn)
self.word2lemma = {}
self.first_n = cfg.getint('filter', 'first_n')
self.graph_dir = self.cfg.get('machine', 'graph_dir')
ensure_dir(self.graph_dir)
def __init__(self, cfg, cfg_section="word_sim"):
try:
self.batch = cfg.getboolean(cfg_section, "batch")
except NoSectionError:
self.batch = False
self.cfg = cfg
self.graph_dir = cfg.get(cfg_section, "graph_dir")
ensure_dir(self.graph_dir)
self.lemmatizer = Lemmatizer(cfg)
self.lexicon_fn = self.cfg.get(cfg_section, "definitions_binary")
self.lexicon = Lexicon.load_from_binary(self.lexicon_fn)
self.defined_words = self.lexicon.get_words()
self.word_sim_cache = {}
self.lemma_sim_cache = {}
self.links_nodes_cache = {}
self.stopwords = set(nltk_stopwords.words("english"))
self.expand = cfg.getboolean(cfg_section, "expand")
logging.info("expand is {0}".format(self.expand))
def __init__(self, cfg, cfg_section='word_sim'):
self.batch = cfg.getboolean(cfg_section, 'batch')
logging.warning("fourlangpath is {0}".format(
cfg.get(cfg_section, 'fourlangpath')))
self.cfg = cfg
self.graph_dir = cfg.get(cfg_section, "graph_dir")
ensure_dir(self.graph_dir)
self.lemmatizer = Lemmatizer(cfg)
self.lexicon_fn = self.cfg.get(cfg_section, "definitions_binary")
self.lexicon = Lexicon.load_from_binary(self.lexicon_fn)
self.defined_words = self.lexicon.get_words()
self.word_sim_cache = {}
self.lemma_sim_cache = {}
self.links_nodes_cache = {}
self.stopwords = set(nltk_stopwords.words('english'))
self.sim_feats = SimFeatures(cfg, cfg_section)
self.expand = cfg.getboolean(cfg_section, "expand")
logging.info("expand is {0}".format(self.expand))
def __init__(self, cfg, cfg_section='word_sim'):
self.batch = cfg.getboolean(cfg_section, 'batch')
logging.warning("fourlangpath is {0}".format(
cfg.get(cfg_section, 'fourlangpath')))
self.cfg = cfg
self.graph_dir = cfg.get(cfg_section, "graph_dir")
ensure_dir(self.graph_dir)
self.lemmatizer = Lemmatizer(cfg)
self.lexicon_fn = self.cfg.get(cfg_section, "definitions_binary")
self.lexicon = Lexicon.load_from_binary(self.lexicon_fn)
self.defined_words = self.lexicon.get_words()
self.word_sim_cache = {}
self.lemma_sim_cache = {}
self.links_nodes_cache = {}
self.stopwords = set(nltk_stopwords.words('english'))
self.sim_feats = SimFeatures(cfg, cfg_section, self.lexicon)
self.expand = cfg.getboolean(cfg_section, "expand")
compositional = cfg.getboolean('similarity', 'compositional')
if compositional is True:
self.text_to_4lang = TextTo4lang(cfg, direct_parse=True)
logging.info("expand is {0}".format(self.expand))
self.allow_4lang = cfg.getboolean('machine', 'allow_4lang')
