Python reader.concat方法代码示例

# 需要导入模块: from nltk.corpus import reader [as 别名]
# 或者: from nltk.corpus.reader import concat [as 别名]
def tagged_paras(self, fileids=None, tagset="msd", tags=""):
        """
	    :param fileids: A list specifying the fileids that should be used.
        :param tagset: The tagset that should be used in the returned object,
                       either "universal" or "msd", "msd" is the default
        :param tags: An MSD Tag that is used to filter all parts of the used corpus
                     that are not more precise or at least equal to the given tag
        :return: the given file(s) as a list of paragraphs, each encoded as a
                 list of sentences, which are in turn encoded as a list
                 of (word,tag) tuples
        :rtype: list(list(list(tuple(str, str))))
        """
        if tagset == "universal" or tagset == "msd":
            return concat([MTEFileReader(os.path.join(self._root, f)).tagged_paras(tagset, tags) for f in self.__fileids(fileids)])
        else:
            print("Unknown tagset specified.") 

# 需要导入模块: from nltk.corpus import reader [as 别名]
# 或者: from nltk.corpus.reader import concat [as 别名]
def words(self, fileids=None):
        """
	    :param fileids: A list specifying the fileids that should be used.
        :return: the given file(s) as a list of words and punctuation symbols.
        :rtype: list(str)
        """
        return  concat([MTEFileReader(os.path.join(self._root, f)).words() for f in self.__fileids(fileids)]) 

# 需要导入模块: from nltk.corpus import reader [as 别名]
# 或者: from nltk.corpus.reader import concat [as 别名]
def sents(self, fileids=None):
        """
	    :param fileids: A list specifying the fileids that should be used.
        :return: the given file(s) as a list of sentences or utterances,
                 each encoded as a list of word strings
        :rtype: list(list(str))
        """
        return  concat([MTEFileReader(os.path.join(self._root, f)).sents() for f in self.__fileids(fileids)]) 

# 需要导入模块: from nltk.corpus import reader [as 别名]
# 或者: from nltk.corpus.reader import concat [as 别名]
def paras(self, fileids=None):
        """
	    :param fileids: A list specifying the fileids that should be used.
        :return: the given file(s) as a list of paragraphs, each encoded as a list
                 of sentences, which are in turn encoded as lists of word string
        :rtype: list(list(list(str)))
        """
        return  concat([MTEFileReader(os.path.join(self._root, f)).paras() for f in self.__fileids(fileids)]) 

# 需要导入模块: from nltk.corpus import reader [as 别名]
# 或者: from nltk.corpus.reader import concat [as 别名]
def lemma_words(self, fileids=None):
        """
	    :param fileids: A list specifying the fileids that should be used.
        :return: the given file(s) as a list of words, the corresponding lemmas
                 and punctuation symbols, encoded as tuples (word, lemma)
        :rtype: list(tuple(str,str))
        """
        return  concat([MTEFileReader(os.path.join(self._root, f)).lemma_words() for f in self.__fileids(fileids)]) 

# 需要导入模块: from nltk.corpus import reader [as 别名]
# 或者: from nltk.corpus.reader import concat [as 别名]
def tagged_words(self, fileids=None, tagset="msd", tags=""):
        """
	    :param fileids: A list specifying the fileids that should be used.
        :param tagset: The tagset that should be used in the returned object,
                       either "universal" or "msd", "msd" is the default
        :param tags: An MSD Tag that is used to filter all parts of the used corpus
                     that are not more precise or at least equal to the given tag
        :return: the given file(s) as a list of tagged words and punctuation symbols
                 encoded as tuples (word, tag)
        :rtype: list(tuple(str, str))
        """
        if tagset == "universal" or tagset == "msd":
            return concat([MTEFileReader(os.path.join(self._root, f)).tagged_words(tagset, tags) for f in self.__fileids(fileids)])
        else:
            print("Unknown tagset specified.") 

# 需要导入模块: from nltk.corpus import reader [as 别名]
# 或者: from nltk.corpus.reader import concat [as 别名]
def tagged_sents(self, fileids=None, tagset="msd", tags=""):
        """
	    :param fileids: A list specifying the fileids that should be used.
        :param tagset: The tagset that should be used in the returned object,
                       either "universal" or "msd", "msd" is the default
        :param tags: An MSD Tag that is used to filter all parts of the used corpus
                     that are not more precise or at least equal to the given tag
        :return: the given file(s) as a list of sentences or utterances, each
                 each encoded as a list of (word,tag) tuples
        :rtype: list(list(tuple(str, str)))
        """
        if tagset == "universal" or tagset == "msd":
            return concat([MTEFileReader(os.path.join(self._root, f)).tagged_sents(tagset, tags) for f in self.__fileids(fileids)])
        else:
            print("Unknown tagset specified.") 

# 需要导入模块: from nltk.corpus import reader [as 别名]
# 或者: from nltk.corpus.reader import concat [as 别名]
def lemma_paras(self, fileids=None):
        """
	    :param fileids: A list specifying the fileids that should be used.
        :return: the given file(s) as a list of paragraphs, each encoded as a
                 list of sentences, which are in turn encoded as a list of
                 tuples of the word and the corresponding lemma (word, lemma)
        :rtype: list(List(List(tuple(str, str))))
        """
        return concat([MTEFileReader(os.path.join(self._root, f)).lemma_paras() for f in self.__fileids(fileids)]) 

# 需要导入模块: from nltk.corpus import reader [as 别名]
# 或者: from nltk.corpus.reader import concat [as 别名]
def raw(self, fileids=None):
        """
	    :param fileids: A list specifying the fileids that should be used.
        :return: the given file(s) as a single string.
        :rtype: str
        """
        return concat([self.open(f).read() for f in self.__fileids(fileids)])