Python spacy.io方法代码示例

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def ensure_proper_language_model(nlp: Optional['Language']) -> None:
        """Checks if the spacy language model is properly loaded.

        Raises an exception if the model is invalid."""

        if nlp is None:
            raise Exception("Failed to load spacy language model. "
                            "Loading the model returned 'None'.")
        if nlp.path is None:
            # Spacy sets the path to `None` if
            # it did not load the model from disk.
            # In this case `nlp` is an unusable stub.
            raise Exception("Failed to load spacy language model for "
                            "lang '{}'. Make sure you have downloaded the "
                            "correct model (https://spacy.io/docs/usage/)."
                            "".format(nlp.lang)) 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def com_annotations(data_type: str, rp: str):
    """
    This method computes all the annotations, Lemma, POS, IS_STOPWORD etc., in the form of spaCy doc container
    for all the rows (lines) in the text data and saves the object of list of the doc (container) for each line.
    # doc = spaCy container - [https://spacy.io/api/doc]

    :argument:
        :param data_type: String either `training` or `test`
        :param rp: Absolute path of the root directory of the project
    :return:
        boolean_flag: True for successful operation.
        all_annotations: List of doc (spaCy containers) of all the lines in the data.
    """
    nlp = spacy.load("en_core_web_lg")
    all_annotations = []
    read_flag, file = read_file("raw_sentence_{0}".format(data_type), rp)
    if read_flag:
        for line in file:
            doc = nlp(remove_endline_char(line))
            all_annotations.append(doc)
        file.close()
        return True, all_annotations
    else:
        return False 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def __init__(self,model='en'):
		"""
		Create a Parser object that will use Spacy for parsing. It offers all the same languages that Spacy offers. Check out: https://spacy.io/usage/models. Note that the language model needs to be downloaded first (e.g. python -m spacy download en)
		
		:param model: Name of an available Spacy language model for parsing (e.g. en/de/es/pt/fr/it/nl)
		:type model: str
		"""

		# We only load spacy if a Parser is created (to allow ReadTheDocs to build the documentation easily)
		import spacy

		self.model = model

		if not model in Parser._models:
			Parser._models[model] = spacy.load(model, disable=['ner'])

		self.nlp = Parser._models[model] 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def _prob_block(sentence, pos_tagger):
    """Calculate probability that a sentence is an email block.
    
    https://spacy.io/usage/linguistic-features

    Parameters
    ----------
    sentence : str
        Line in email block.

    Returns
    -------
    probability(signature block | line)
    """
    
    doc = pos_tagger(sentence)
    verb_count = np.sum([token.pos_ != "VERB" for token in doc])
    return float(verb_count) / len(doc) 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def ensure_proper_language_model(nlp: Optional["Language"]) -> None:
        """Checks if the spacy language model is properly loaded.

        Raises an exception if the model is invalid."""

        if nlp is None:
            raise Exception(
                "Failed to load spacy language model. "
                "Loading the model returned 'None'."
            )
        if nlp.path is None:
            # Spacy sets the path to `None` if
            # it did not load the model from disk.
            # In this case `nlp` is an unusable stub.
            raise Exception(
                "Failed to load spacy language model for "
                "lang '{}'. Make sure you have downloaded the "
                "correct model (https://spacy.io/docs/usage/)."
                "".format(nlp.lang)
            ) 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def ensure_proper_language_model(nlp):
        # type: (Optional[Language]) -> None
        """Checks if the spacy language model is properly loaded.

        Raises an exception if the model is invalid."""

        if nlp is None:
            raise Exception("Failed to load spacy language model. "
                            "Loading the model returned 'None'.")
        if nlp.path is None:
            # Spacy sets the path to `None` if
            # it did not load the model from disk.
            # In this case `nlp` is an unusable stub.
            raise Exception("Failed to load spacy language model for "
                            "lang '{}'. Make sure you have downloaded the "
                            "correct model (https://spacy.io/docs/usage/)."
                            "".format(nlp.lang)) 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def get_default_model(model_name):
    err_msg = "Language model {0} not found. Please, refer https://spacy.io/usage/models"
    nlp = None
    if model_name is not None:
        try:
            nlp = spacy.load(model_name)
        except (ImportError, OSError):
            print(err_msg.format(model_name))
            print('Using default language model')
            nlp = get_default_model(EN_MODEL_SM)
        return nlp 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def get_nlp(language, lite, lang_model=""):
    err_msg = "Language model {0} not found. Please, refer https://spacy.io/usage/models"
    nlp = None

    if not lang_model == "" and not lang_model == "en":

        try:
            nlp = spacy.load(lang_model)
        except ImportError:
            print(err_msg.format(lang_model))
            raise

    elif language == 'en':

        if lite:
            nlp = spacy.load(EN_MODEL_DEFAULT)
        else:

            try:
                nlp = spacy.load(EN_MODEL_MD)
            except (ImportError, OSError):
                print(err_msg.format(EN_MODEL_MD))
                print('Using default language model')
                nlp = get_default_model(EN_MODEL_DEFAULT)

    elif not language == 'en':
        print('Currently only English language is supported. '
              'Please contribute to https://github.com/5hirish/adam_qas to add your language.')
        sys.exit(0)

    return nlp 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def __init__(self, *args, **kwargs):
        if 'tokenize' in kwargs:
            raise TypeError('``SpacyEncoder`` does not take keyword argument ``tokenize``.')

        try:
            import spacy
        except ImportError:
            print("Please install spaCy: " "`pip install spacy`")
            raise

        # Use English as default when no language was specified
        language = kwargs.get('language', 'en')

        # All languages supported by spaCy can be found here:
        #   https://spacy.io/models/#available-models
        supported_languages = ['en', 'de', 'es', 'pt', 'fr', 'it', 'nl', 'xx']

        if language in supported_languages:
            # Load the spaCy language model if it has been installed
            try:
                self.spacy = spacy.load(language, disable=['parser', 'tagger', 'ner'])
            except OSError:
                raise ValueError(("Language '{0}' not found. Install using "
                                  "spaCy: `python -m spacy download {0}`").format(language))
        else:
            raise ValueError(
                ("No tokenizer available for language '%s'. " + "Currently supported are %s") %
                (language, supported_languages))

        super().__init__(*args, tokenize=partial(_tokenize, tokenizer=self.spacy), **kwargs) 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def spacy_tokenize(self, text, **kwargs):
        """
        Tokenize using spaCy.

        Does whatever spaCy does. See https://spacy.io/.
        """
        tokens = self.NLP.tokenizer(text)
        return [t.text for t in tokens] 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def _check_spacy():
        if spacy is None:
            raise ImportError(
                'Failed to import `spaCy`. '
                '`spaCy` is required for POS features '
                'See https://spacy.io/usage/ for installation'
                'instructions.') 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def get_empty_candidates():
    """
    The mention generators always return at least one candidate, but signal
    it with this special candidate
    """
    return {
        "candidate_spans": [[-1, -1]],
        "candidate_entities": [["@@PADDING@@"]],
        "candidate_entity_priors": [[1.0]]
    }


# from https://spacy.io/usage/linguistic-features#custom-tokenizer-example 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def _discover_text(self, source: Source):
        """
        Apply Sentence Boundary Detection, described here https://spacy.io/usage/linguistic-features#sbd
        :param source: The source value with kind=text
        """
        # this is based on SBD described here
        doc = self.nlp(source.value)
        for sent in doc.sents:
            # TODO: would be good to add ref from source
            # TODO: add filter?
            text = sent.text.strip()
            self.storage.train.add(text=text) 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def _discover_textract(self, source: Source):
        """
        Apply textract parsing, described here http://textract.readthedocs.io/en/stable/
        :param source: The source value with kind=textract
        """
        # TODO: add textract check
        import textract
        # process it
        text = textract.process(self.resolve_path(file_path=source.value), language=self.storage.config.source_language)
        # create new source and pass it to text processor
        value = text.decode('utf-8')
        new_source = Source(idx=source.idx, kind='text', value=value)
        self._discover_text(new_source) 

# 需要导入模块: import spacy [as 别名]
# 或者: from spacy import io [as 别名]
def __init__(self, model="en", disable=None, display_prompt=True):
        if disable is None:
            disable = []
        try:
            self._parser = spacy.load(model, disable=disable)
        except OSError:
            url = "https://spacy.io/models"
            if display_prompt and license_prompt("Spacy {} model".format(model), url) is False:
                sys.exit(0)
            spacy_download(model)
            self._parser = spacy.load(model, disable=disable)