python类DefaultDict()的实例源码

def find_parts(self) -> ty.ValuesView:
        """ Find all files generated by inputs.
        Returns:
            [ file path ]
        """
        files = collections.defaultdict(list)
        # type: ty.DefaultDict[str, ty.List[str]]
        for fname in sorted(os.listdir(self._working_dir)):
            fpath = os.path.join(self._working_dir, fname)
            if not os.path.isfile(fpath):
                continue
            oid = fname.split('.', 1)[0]
            if len(oid) == 40:
                files[oid].append(fpath)
        return files.values()

    # @tc.typecheck

def assign_data(centroids: Sequence[Centroid], data: Iterable[Point]) -> Dict[Centroid, Sequence[Point]]:
    'Assign data the closest centroid'
    d : DefaultDict[Point, List[Point]] = defaultdict(list)
    for point in data:
        centroid: Point = min(centroids, key=partial(dist, point))
        d[centroid].append(point)
    return dict(d)

def __init__(self) -> None:
        self.sentence_buffer: List[str] = []
        self.sentences: List[List[str]] = []
        self.num_total_words = 0
        # Cluster id -> List of (start_index, end_index) spans.
        self.clusters: DefaultDict[int, List[Tuple[int, int]]] = collections.defaultdict(list)
        # Cluster id -> List of start_indices which are open for this id.
        self.coref_stacks: DefaultDict[int, List[int]] = collections.defaultdict(list)

def __init__(self, name, gatewayIDs: List[ModuleID]):
        # call the thread class
        super().__init__()
        self.name = 'Dispatcher ' + name
        self._gatewayIDs = gatewayIDs
        self._routeMap = self._initRouteMap(gatewayIDs)  # type: DefaultDict[ModuleID, ModuleID]
        self._groupMap = {}  # type: DefaultDict[GroupID, List[ModuleID]]
        self._msgCount = 0

def _initRouteMap(self, gatewayIDs: List[ModuleID]) -> DefaultDict[ModuleID, ModuleID]:
        """
        Initial filling the route map with gateways
        """
        routeMap = {}
        for gatewayID in gatewayIDs:
            routeMap[gatewayID] = gatewayID
        return routeMap

def _convertToMap(sourceParts: List[SourcePart]) -> DefaultDict[ModuleID, SourcePart]:
        sourcesByID = {}
        for sourcePart in sourceParts:
            sourcesByID[sourcePart.sourceID] = sourcePart
        return sourcesByID

def _pretty_print(self, frequencies: DefaultDict[Any, DefaultDict[Any, int]]) -> str:
        lines = []
        for category in frequencies:
            line = '{}: '.format(category)
            category_frequency = frequencies[category]
            ordered = OrderedDict(sorted(category_frequency.items(), key=lambda t: t[1], reverse=True))
            for word, frequency in ordered.items():
                if frequency > 1:
                    line += '({}, {}) '.format(word, frequency)

            lines.append(line)

        lines.sort()
        return '\n'.join(lines)

def __init__(self) -> None:
        self.counters = DefaultDict[str, int](int)

def _process_coref_span_annotations_for_word(label: str,
                                                 word_index: int,
                                                 clusters: DefaultDict[int, List[Tuple[int, int]]],
                                                 coref_stacks: DefaultDict[int, List[int]]) -> None:
        """
        For a given coref label, add it to a currently open span(s), complete a span(s) or
        ignore it, if it is outside of all spans. This method mutates the clusters and coref_stacks
        dictionaries.

        Parameters
        ----------
        label : ``str``
            The coref label for this word.
        word_index : ``int``
            The word index into the sentence.
        clusters : ``DefaultDict[int, List[Tuple[int, int]]]``
            A dictionary mapping cluster ids to lists of inclusive spans into the
            sentence.
        coref_stacks: ``DefaultDict[int, List[int]]``
            Stacks for each cluster id to hold the start indices of active spans (spans
            which we are inside of when processing a given word). Spans with the same id
            can be nested, which is why we collect these opening spans on a stack, e.g:

            [Greg, the baker who referred to [himself]_ID1 as 'the bread man']_ID1
        """
        if label != "-":
            for segment in label.split("|"):
                # The conll representation of coref spans allows spans to
                # overlap. If spans end or begin at the same word, they are
                # separated by a "|".
                if segment[0] == "(":
                    # The span begins at this word.
                    if segment[-1] == ")":
                        # The span begins and ends at this word (single word span).
                        cluster_id = int(segment[1:-1])
                        clusters[cluster_id].append((word_index, word_index))
                    else:
                        # The span is starting, so we record the index of the word.
                        cluster_id = int(segment[1:])
                        coref_stacks[cluster_id].append(word_index)
                else:
                    # The span for this id is ending, but didn't start at this word.
                    # Retrieve the start index from the document state and
                    # add the span to the clusters for this id.
                    cluster_id = int(segment[:-1])
                    start = coref_stacks[cluster_id].pop()
                    clusters[cluster_id].append((start, word_index))