python类flatten()的实例源码

def issue_to_changelog(issue):
    return dict(
        [
            ('key', issue.key),
            (
                'changelog',
                [
                    (u'Created', parse_date(issue.fields.created))
                ] + flatten([
                    [
                        (i.toString, parse_date(h.created))
                        for i in h.items if i.field == 'status'
                    ] for h in issue.changelog.histories
                ])
            )
        ]
    )

def __init__(self, past, future, features = None):
        """Create a training pattern.

        Parameters:
        past -- past feature vectors as a tensor of shape [P, V]
            where P is past days and V is the vectors/day
        future -- future feature vectors as a tensor of [F, V]
            where F is future days and V is the vectors/day
        features -- a sequence of feature names to use
            where None means use all features
        """

        # calculate training input from past features
        past_subfeatures = [[self._subfeatures(vector, features)
            for vector in vectors]
                for vectors in past]
        self._input = numpy.array(
            [list(util.flatten(vectors)) for vectors in past_subfeatures])

        # calculate training output from future volatility
        future_returns = numpy.log1p(
            [[vector.ret for vector in vectors] for vectors in future])
        self._output = numpy.std(future_returns, axis = 0, ddof = 1)\
            * numpy.sqrt(252)

        # calculate past returns for forecasts
        self._past_returns = numpy.log1p(
            [[vector.ret for vector in vectors] for vectors in past])

def intFloor(*args):
    return [int(math.floor(x)) for x in flatten(args)]

def finalize(self):
    merged_clusters = []
    for c1 in self.clusters.values():
      existing = None
      for m in c1:
        for c2 in merged_clusters:
          if m in c2:
            existing = c2
            break
        if existing is not None:
          break
      if existing is not None:
        print("Merging clusters (shouldn't happen very often.)")
        existing.update(c1)
      else:
        merged_clusters.append(set(c1))
    merged_clusters = [list(c) for c in merged_clusters]
    all_mentions = util.flatten(merged_clusters)
    assert len(all_mentions) == len(set(all_mentions))

    return {
      "doc_key": self.doc_key,
      "sentences": self.sentences,
      "speakers": self.speakers,
      "clusters": merged_clusters
    }

def print_predictions(example):
  words = util.flatten(example["sentences"])
  for cluster in example["predicted_clusters"]:
    print(u"Predicted cluster: {}".format([" ".join(words[m[0]:m[1]+1]) for m in cluster]))

def generate_respondents_summary(self):
        all_uids_by_option = [option.people.keys() for option in self.options]
        all_uids = util.flatten(all_uids_by_option)
        num_respondents = len(set(all_uids))
        if num_respondents == 0:
            output = 'Nobody responded'
        elif num_respondents == 1:
            output = '1 person responded'
        else:
            output = '{} people responded'.format(num_respondents)
        return output

def tensorize_example(self, example, is_training, oov_counts=None):
    clusters = example["clusters"]

    gold_mentions = sorted(tuple(m) for m in util.flatten(clusters))
    gold_mention_map = {m:i for i,m in enumerate(gold_mentions)}
    cluster_ids = np.zeros(len(gold_mentions))
    for cluster_id, cluster in enumerate(clusters):
      for mention in cluster:
        cluster_ids[gold_mention_map[tuple(mention)]] = cluster_id

    sentences = example["sentences"]
    num_words = sum(len(s) for s in sentences)
    speakers = util.flatten(example["speakers"])

    assert num_words == len(speakers)

    max_sentence_length = max(len(s) for s in sentences)
    max_word_length = max(max(max(len(w) for w in s) for s in sentences), max(self.config["filter_widths"]))
    word_emb = np.zeros([len(sentences), max_sentence_length, self.embedding_size])
    char_index = np.zeros([len(sentences), max_sentence_length, max_word_length])
    text_len = np.array([len(s) for s in sentences])
    for i, sentence in enumerate(sentences):
      for j, word in enumerate(sentence):
        current_dim = 0
        for k, (d, (s,l)) in enumerate(zip(self.embedding_dicts, self.embedding_info)):
          if l:
            current_word = word.lower()
          else:
            current_word = word
          if oov_counts is not None and current_word not in d:
            oov_counts[k] += 1
          word_emb[i, j, current_dim:current_dim + s] = util.normalize(d[current_word])
          current_dim += s
        char_index[i, j, :len(word)] = [self.char_dict[c] for c in word]

    speaker_dict = { s:i for i,s in enumerate(set(speakers)) }
    speaker_ids = np.array([speaker_dict[s] for s in speakers])

    doc_key = example["doc_key"]
    genre = self.genres[doc_key[:2]]

    gold_starts, gold_ends = self.tensorize_mentions(gold_mentions)

    if is_training and len(sentences) > self.config["max_training_sentences"]:
      return self.truncate_example(word_emb, char_index, text_len, speaker_ids, genre, is_training, gold_starts, gold_ends, cluster_ids)
    else:
      return word_emb, char_index, text_len, speaker_ids, genre, is_training, gold_starts, gold_ends, cluster_ids