corpus.py 文件源码

def describe(self, fileids=None, categories=None):
        """
        Performs a single pass of the corpus and returns a dictionary with a
        variety of metrics concerning the state of the corpus.
        """
        # Structures to perform counting.
        counts  = nltk.FreqDist()
        tokens  = nltk.FreqDist()
        started = time.time()

        # Perform single pass over paragraphs, tokenize and count
        for para in self.paras(fileids, categories):
            counts['paras'] += 1

            for sent in self._sent_tokenizer.tokenize(para):
                counts['sents'] += 1

                for word in self._word_tokenizer.tokenize(sent):
                    counts['words'] += 1
                    tokens[word] += 1

        # Compute the number of files and categories in the corpus
        n_fileids = len(self._resolve(fileids, categories) or self.fileids())
        n_topics  = len(self.categories(self._resolve(fileids, categories)))

        # Return data structure with information
        return {
            'files':  n_fileids,
            'topics': n_topics,
            'paras':  counts['paras'],
            'sents':  counts['sents'],
            'words':  counts['words'],
            'vocab':  len(tokens),
            'lexdiv': float(counts['words']) / float(len(tokens)),
            'ppdoc':  float(counts['paras']) / float(n_fileids),
            'sppar':  float(counts['sents']) / float(counts['paras']),
            'secs':   time.time() - started,
        }