def __init__(self,
use_lemmas=False,
entity_types_to_censor=set(),
tag_types_to_censor=set(),
strip_final_period=False,
empath_analyze_function=None,
**kwargs):
'''
Parameters
----------
empath_analyze_function: function (default=empath.Empath().analyze)
Function that produces a dictionary mapping Empath categories to
Other parameters from FeatsFromSpacyDoc.__init__
'''
if empath_analyze_function is None:
try:
import empath
except ImportError:
raise Exception(
"Please install the empath library to use FeatsFromSpacyDocAndEmpath."
)
self._empath_analyze_function = empath.Empath().analyze
else:
self._empath_analyze_function = partial(
empath_analyze_function, kwargs={'tokenizer': 'bigram'})
FeatsFromSpacyDoc.__init__(self, use_lemmas, entity_types_to_censor,
tag_types_to_censor, strip_final_period)
def __init__(self,
use_lemmas=False,
entity_types_to_censor=set(),
tag_types_to_censor=set(),
strip_final_period=False):
FeatsFromSpacyDoc.__init__(self, use_lemmas, entity_types_to_censor,
tag_types_to_censor, strip_final_period)
self._include_chunks = False
self._rank_smoothing_constant = 0
def __init__(self,
use_lemmas=False,
entity_types_to_censor=set(),
entity_types_to_use=None,
tag_types_to_censor=set(),
strip_final_period=False):
self._entity_types_to_use = entity_types_to_use
FeatsFromSpacyDoc.__init__(self, use_lemmas, entity_types_to_censor,
tag_types_to_censor, strip_final_period)
def __init__(self,
topic_model,
use_lemmas=False,
entity_types_to_censor=set(),
entity_types_to_use=None,
tag_types_to_censor=set(),
strip_final_period=False,
keyword_processor_args={'case_sensitive': False}):
self._keyword_processor = KeywordProcessor(**keyword_processor_args)
self._topic_model = topic_model
for keyphrase in reduce(lambda x, y: set(x) | set(y),
topic_model.values()):
self._keyword_processor.add_keyword(keyphrase)
FeatsFromSpacyDoc.__init__(self, use_lemmas, entity_types_to_censor,
tag_types_to_censor, strip_final_period)
FeatsFromTopicModelBase.__init__(self, topic_model)
def __init__(self, extractor=None, **args):
import pyate
self._extractor = pyate.combo_basic if extractor is None else extractor
FeatsFromSpacyDoc.__init__(self, **args)