本文整理汇总了Python中spacy.symbols.ORTH属性的典型用法代码示例。如果您正苦于以下问题：Python symbols.ORTH属性的具体用法？Python symbols.ORTH怎么用？Python symbols.ORTH使用的例子？那么恭喜您, 这里精选的属性代码示例或许可以为您提供帮助。您也可以进一步了解该属性所在类spacy.symbols的用法示例。
在下文中一共展示了symbols.ORTH属性的4个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __init__
# 需要导入模块: from spacy import symbols [as 别名]
# 或者: from spacy.symbols import ORTH [as 别名]
def __init__(self,
archive_file=DEFAULT_ARCHIVE_FILE,
cuda_device=DEFAULT_CUDA_DEVICE,
model_file=None,
context_size=3):
""" Constructor for NLU class. """
self.context_size = context_size
check_for_gpu(cuda_device)
if not os.path.isfile(archive_file):
if not model_file:
raise Exception("No model for MILU is specified!")
archive_file = cached_path(model_file)
archive = load_archive(archive_file,
cuda_device=cuda_device)
self.tokenizer = SpacyWordSplitter(language="en_core_web_sm")
_special_case = [{ORTH: u"id", LEMMA: u"id"}]
self.tokenizer.spacy.tokenizer.add_special_case(u"id", _special_case)
dataset_reader_params = archive.config["dataset_reader"]
self.dataset_reader = DatasetReader.from_params(dataset_reader_params)
self.model = archive.model
self.model.eval() 示例2: add_special_cases
# 需要导入模块: from spacy import symbols [as 别名]
# 或者: from spacy.symbols import ORTH [as 别名]
def add_special_cases(self, toks: Collection[str]):
for w in toks:
self.tok.tokenizer.add_special_case(w, [{ORTH: w}]) 示例3: run
# 需要导入模块: from spacy import symbols [as 别名]
# 或者: from spacy.symbols import ORTH [as 别名]
def run():
for model in MODELS:
print("Load model ", model)
loaded_model = get_model(model)
special_cases_str = os.getenv(f"{model}_special_cases", "")
if special_cases_str:
for special_case in special_cases_str.split(','):
loaded_model.tokenizer.add_special_case(
special_case,
[{ORTH: special_case}]
)
print("Loaded all models. Starting HTTP server.")
httpd = simple_server.make_server('0.0.0.0', 8000, APP)
httpd.serve_forever() 示例4: __init__
# 需要导入模块: from spacy import symbols [as 别名]
# 或者: from spacy.symbols import ORTH [as 别名]
def __init__(self, language="en", special_cases=None, regex_cases=None):
self.nlp = spacy.load(language)
self.nlp.tokenizer.add_special_case('<eos>', [{ORTH: '<eos>'}])
self.nlp.tokenizer.add_special_case('<bos>', [{ORTH: '<bos>'}])
self.nlp.tokenizer.add_special_case('<sos>', [{ORTH: '<sos>'}])
self.nlp.tokenizer.add_special_case('<unk>', [{ORTH: '<unk>'}])
self.nlp.tokenizer.add_special_case('<pad>', [{ORTH: '<pad>'}])
special_cases = [] if special_cases is None else special_cases
for case in special_cases:
self.nlp.tokenizer.add_special_case(case, [{ORTH: case}])
self.regex_cases = [] if regex_cases is None else [re.compile(i, flags=re.IGNORECASE) for i in regex_cases]