Python collections.defaultdict() Examples

def __init__(self):
        self.args = None
        self.alignDistance = 0
        self.samples = collections.OrderedDict()
        self.genome = None
        self.sources = {}
        self.annotationSets = collections.OrderedDict()

        # for storing axes, annotations, etc, by allele
        self.alleleTracks = collections.defaultdict(collections.OrderedDict)
        self.trackCompositor = None

        self.dotplots = {}
        self.info = {}

        self.reset() 

def _add_sparse_vector_labes(self, graph, vertex_v, node_feature_list):
        # add the vector with a feature resulting from hashing
        # the discrete labeled graph sparse encoding with the sparse vector
        # feature, the val is then multiplied.
        svec = graph.nodes[vertex_v].get(self.key_svec, None)
        if svec:
            vec_feature_list = defaultdict(lambda: defaultdict(float))
            for radius_dist_key in node_feature_list:
                for feature in node_feature_list[radius_dist_key]:
                    val = node_feature_list[radius_dist_key][feature]
                    for i in svec:
                        vec_val = svec[i]
                        key = fast_hash_2(feature, i, self.bitmask)
                        vec_feature_list[radius_dist_key][key] += val * vec_val
            node_feature_list = vec_feature_list
        return node_feature_list 

def extract_sequence_and_score(graph=None):
    # make dict with positions as keys and lists of ids as values
    pos_to_ids = defaultdict(list)
    for u in graph.nodes():
        if 'position' not in graph.node[u]:  # no position attributes in graph, use the vertex id instead
            raise Exception('Missing "position" attribute in node:%s %s' % (u, graph.node[u]))
        else:
            pos = graph.node[u]['position']
        # accumulate all node ids
        pos_to_ids[pos] += [u]

    # extract sequence of labels and importances
    seq = [None] * len(pos_to_ids)
    score = [0] * len(pos_to_ids)
    for pos in sorted(pos_to_ids):
        ids = pos_to_ids[pos]
        labels = [graph.node[u].get('label', 'N/A') for u in ids]
        # check that all labels for the same position are identical
        assert(sum([1 for label in labels if label == labels[0]]) == len(labels)
               ), 'ERROR: non identical labels referring to same position: %s  %s' % (pos, labels)
        seq[pos] = labels[0]
        # average all importance score for the same position
        importances = [graph.node[u].get('importance', 0) for u in ids]
        score[pos] = np.mean(importances)
    return seq, score 

def compute_matching_neighborhoods_fraction(GA, GB, pairings):
    count = 0
    matches = dict([(i, j) for i, j in enumerate(pairings)])
    matching_edges = defaultdict(list)
    for i, j in GA.edges():
        ii = matches[i]
        jj = matches[j]
        if (ii, jj) in GB.edges():
            matching_edges[i].append(j)
            matching_edges[j].append(i)
    for u in GA.nodes():
        if matching_edges.get(u, False):
            neighbors = nx.neighbors(GA, u)
            matches_neighborhood = True
            for v in neighbors:
                if v not in matching_edges[u]:
                    matches_neighborhood = False
                    break
            if matches_neighborhood:
                count += 1
    return float(count) / len(GA.nodes()) 

def lifecycle(args):
    if args.delete:
        return resources.s3.BucketLifecycle(args.bucket_name).delete()
    rule = defaultdict(list, Prefix=args.prefix, Status="Enabled")
    if args.transition_to_infrequent_access is not None:
        rule["Transitions"].append(dict(StorageClass="STANDARD_IA", Days=args.transition_to_infrequent_access))
    if args.transition_to_glacier is not None:
        rule["Transitions"].append(dict(StorageClass="GLACIER", Days=args.transition_to_glacier))
    if args.expire is not None:
        rule["Expiration"] = dict(Days=args.expire)
    if args.abort_incomplete_multipart_upload is not None:
        rule["AbortIncompleteMultipartUpload"] = dict(DaysAfterInitiation=args.abort_incomplete_multipart_upload)
    if len(rule) > 2:
        clients.s3.put_bucket_lifecycle_configuration(Bucket=args.bucket_name,
                                                      LifecycleConfiguration=dict(Rules=[rule]))
    try:
        for rule in resources.s3.BucketLifecycle(args.bucket_name).rules:
            print(json.dumps(rule))
    except ClientError as e:
        expect_error_codes(e, "NoSuchLifecycleConfiguration")
        logger.error("No lifecycle configuration for bucket %s", args.bucket_name) 

def sample_latent(self, input, input_latent_mu, input_latent_sigma, pred_latent_mu,
                    pred_latent_sigma, initial_pose_mu, initial_pose_sigma, sample=True):
    '''
    Return latent variables: dictionary containing pose and content.
    Then, crop objects from the images and encode into z.
    '''
    latent = defaultdict(lambda: None)

    beta = self.get_transitions(input_latent_mu, input_latent_sigma,
                                pred_latent_mu, pred_latent_sigma, sample)
    pose = self.accumulate_pose(beta)
    # Sample initial pose
    initial_pose = self.pyro_sample('initial_pose', dist.Normal, initial_pose_mu,
                                    initial_pose_sigma, sample)
    pose += initial_pose.view(-1, 1, self.n_components, self.pose_latent_size)
    pose = self.constrain_pose(pose)

    # Get input objects
    input_pose = pose[:, :self.n_frames_input, :, :]
    input_obj = self.get_objects(input, input_pose)
    # Encode the sampled objects
    z = self.object_encoder(input_obj)
    z = self.sample_content(z, sample)
    latent.update({'pose': pose, 'content': z})
    return latent 

def __init__(self, config, flows_dir, ports_dir, num_timesteps, debug=False):
        self.logger = logging.getLogger("LogHistory")
        if debug:
            self.logger.setLevel(logging.DEBUG)

        self.log_entry = namedtuple("LogEntry", "source destination type")
        self.ports = defaultdict(list)
        self.flows = defaultdict(list)

        self.data = defaultdict(lambda: defaultdict(lambda: defaultdict(int)))
        self.current_timestep = 0
        self.total_timesteps = num_timesteps

        self.parse_config(config)
        self.parse_logs(num_timesteps, flows_dir, ports_dir)
        self.info()

        pretty(self.data) 

def loadEmbedding(filename):
    """
    加载词向量文件

    :param filename: 文件名
    :return: embeddings列表和它对应的索引
    """
    embeddings = []
    word2idx = defaultdict(list)
    with open(filename, mode="r", encoding="utf-8") as rf:
        for line in rf:
            arr = line.split(" ")
            embedding = [float(val) for val in arr[1: -1]]
            word2idx[arr[0]] = len(word2idx)
            embeddings.append(embedding)
    return embeddings, word2idx 

def load_json_logs(json_logs):
    # load and convert json_logs to log_dict, key is epoch, value is a sub dict
    # keys of sub dict is different metrics, e.g. memory, bbox_mAP
    # value of sub dict is a list of corresponding values of all iterations
    log_dicts = [dict() for _ in json_logs]
    for json_log, log_dict in zip(json_logs, log_dicts):
        with open(json_log, 'r') as log_file:
            for line in log_file:
                log = json.loads(line.strip())
                # skip lines without `epoch` field
                if 'epoch' not in log:
                    continue
                epoch = log.pop('epoch')
                if epoch not in log_dict:
                    log_dict[epoch] = defaultdict(list)
                for k, v in log.items():
                    log_dict[epoch][k].append(v)
    return log_dicts 

def __init__(self, tau=0, name="", ds_name=""):
        self.name = name
        self.ds_name = ds_name
        self.tau = tau

        self.ids = set()
        self.ids_correct = set()
        self.ids_correct_fp = set()
        self.ids_agree = set()

        # Legal = there is a fingerprint match below threshold tau
        self.ids_legal = set()

        self.counts = defaultdict(lambda: 0)
        self.counts_legal = defaultdict(lambda: 0)
        self.counts_correct = defaultdict(lambda: 0)

        # Total number of examples
        self.i = 0 

def _save_sorted_results(self, run_stats, scores, image_count, filename):
    """Saves sorted (by score) results of the evaluation.

    Args:
      run_stats: dictionary with runtime statistics for submissions,
        can be generated by WorkPiecesBase.compute_work_statistics
      scores: dictionary mapping submission ids to scores
      image_count: dictionary with number of images processed by submission
      filename: output filename
    """
    with open(filename, 'w') as f:
      writer = csv.writer(f)
      writer.writerow(['SubmissionID', 'ExternalTeamId', 'Score',
                       'MedianTime', 'ImageCount'])
      get_second = lambda x: x[1]
      for s_id, score in sorted(iteritems(scores),
                                key=get_second, reverse=True):
        external_id = self.submissions.get_external_id(s_id)
        stat = run_stats.get(
            s_id, collections.defaultdict(lambda: float('NaN')))
        writer.writerow([s_id, external_id, score,
                         stat['median_eval_time'],
                         image_count[s_id]]) 

def metric_values(metric, by_labels=()):
    """Return values for the metric."""
    if metric._type == "gauge":
        suffix = ""
    elif metric._type == "counter":
        suffix = "_total"

    values = defaultdict(list)
    for sample_suffix, labels, value in metric._samples():
        if sample_suffix == suffix:
            if by_labels:
                label_values = tuple(labels[label] for label in by_labels)
                values[label_values] = value
            else:
                values[sample_suffix].append(value)

    return values if by_labels else values[suffix] 

def __init__(self,corpus_dir,datastore_type='file',db_name='corpus.db'):
        '''
        Read links and associated categories for specified articles 
        in text file seperated by a space

        Args:
            corpus_dir (str): The directory to save the generated corpus
            datastore_type (Optional[str]): Format to save generated corpus.
                                            Specify either 'file' or 'sqlite'.
            db_name (Optional[str]): Name of database if 'sqlite' is selected.
        '''

        self.g = Goose({'browser_user_agent': 'Mozilla','parser_class':'soup'})
        #self.g = Goose({'browser_user_agent': 'Mozilla'})
        self.corpus_dir = corpus_dir
        self.datastore_type = datastore_type
        self.db_name = db_name
        self.stats = defaultdict(int)

        self._create_corpus_dir(self.corpus_dir)

        self.db = None
        if self.datastore_type == 'sqlite':
            self.db = self.corpus_dir + '/' + self.db_name
            self._set_up_db(self.db) 

def _create_unique_fields_cache(cells):
    primary_key_column_numbers = []
    cache = {}

    # Unique
    for _, cell in enumerate(cells, start=1):
        field = cell.get('field')
        column_number = cell.get('column-number')
        if field is not None:
            if field.descriptor.get('primaryKey'):
                primary_key_column_numbers.append(column_number)
            if field.constraints.get('unique'):
                cache[tuple([column_number])] = defaultdict(list)

    # Primary key
    if primary_key_column_numbers:
        cache[tuple(primary_key_column_numbers)] = defaultdict(list)

    return cache 

def __init__(self, annotation_file=None):
        """
        Constructor of Microsoft COCO helper class for reading and visualizing annotations.
        :param annotation_file (str): location of annotation file
        :param image_folder (str): location to the folder that hosts images.
        :return:
        """
        # load dataset
        self.dataset,self.anns,self.cats,self.imgs = dict(),dict(),dict(),dict()
        self.imgToAnns, self.catToImgs = defaultdict(list), defaultdict(list)
        if not annotation_file == None:
            print('loading annotations into memory...')
            tic = time.time()
            dataset = json.load(open(annotation_file, 'r'))
            assert type(dataset)==dict, 'annotation file format {} not supported'.format(type(dataset))
            print('Done (t={:0.2f}s)'.format(time.time()- tic))
            self.dataset = dataset
            self.createIndex() 

def precook(s, n=4, out=False):
    """
    Takes a string as input and returns an object that can be given to
    either cook_refs or cook_test. This is optional: cook_refs and cook_test
    can take string arguments as well.

    :param s:
    :param n:
    :param out:
    :return:
    """
    words = s.split()
    counts = defaultdict(int)
    for k in xrange(1,n+1):
        for i in xrange(len(words)-k+1):
            ngram = tuple(words[i:i+k])
            counts[ngram] += 1
    return (len(words), counts) 

def addVariantResults(self, dataHub):
        variant = str(dataHub.variant)
        for sampleName, sample in dataHub.samples.items():
            counts = collections.Counter()
            reasons = {}
            alnScores = collections.defaultdict(list)
            insertSizes = collections.defaultdict(list)

            # collect stats
            for alnCollection in sample.alnCollections:
                allele = alnCollection.choice
                counts[allele] += 1

                if not allele in reasons:
                    reasons[allele] = collections.Counter()

                reasons[allele][alnCollection.why] += 1
                alnScores[allele].append(sum(aln.score for aln in alnCollection.chosenSet().getAlignments()))
                insertSizes[allele].append(len(alnCollection.chosenSet()))



            # record stats
            for allele, count in counts.items():
                self.stats.append([variant, sampleName, allele, "count", count])

            for allele in reasons:
                for reason in reasons[allele]:
                    self.stats.append([variant, sampleName, allele, "reason_{}".format(reason), reasons[allele][reason]])

            for allele in alnScores:
                self.stats.append([variant, sampleName, allele, "alnScore_mean", numpy.mean(alnScores[allele])])
                self.stats.append([variant, sampleName, allele, "alnScore_std", numpy.std(alnScores[allele])])

            for allele in insertSizes:
                self.stats.append([variant, sampleName, allele, "insertSize_mean", numpy.mean(insertSizes[allele])])
                self.stats.append([variant, sampleName, allele, "insertSize_std", numpy.std(insertSizes[allele])]) 

def getToMatch(self):
        tomatch = set()
        readsByID = collections.defaultdict(ReadSet)

        for region in self.regions:
            for read in self.loadRegion(region.chr(), region.start(), region.end()):
                tomatch.add(read)
                readsByID[read.qname].add(read)

                if self.sampleReads is not None and len(readsByID) > self.sampleReads:
                    return None, None
                if self.maxReads and len(tomatch) > self.maxReads:
                    raise TooManyReadsException

        return tomatch, readsByID 

def getAnnotations(self, chrom, start, end, clip=False, extension=1000000):
        chrom = self.fixChromFormat(chrom)
        
        lines = self.tabix.fetch(chrom, max(0, start-extension), end+extension)

        transcriptsToLines = collections.defaultdict(list)

        for i, line in enumerate(lines):
            if len(line) < 2:
                continue    

            try:            
                tx = re.match(RE_TRANSCRIPT, line).group(1)
            except AttributeError:
                tx = "anno{}".format(i)


            transcriptsToLines[tx].append(line)

        genes = []
        for transcript, lines in transcriptsToLines.items():
            genes.append(GTFGene(lines))

        if extension > 0:
            genes = [gene for gene in genes if not (end<gene.start or start>gene.end)]#start<=gene.start<=end or start<=gene.end<=end)]

        if clip:
            for gene in genes:
                gene.clip(start, end)

        return genes 

def create_storyboard(uri,date,title,text,expanded_search,top_results):

    clientips  = defaultdict(int)
    reqmethods = defaultdict(int)
    rescontype = defaultdict(int)
    referers   = defaultdict(int)
    refered    = defaultdict(int)
    requests   = []


    for row in expanded_search:
        clientips[row['clientIp']]+=1
        reqmethods[row['requestMethod']]+=1
        rescontype[row['responseContentType']]+=1
        if row['uri'] == uri:
           #Source URI's that refered the user to the threat
           referers[row['referer']]+=1
           requests += [{'clientip':row['clientIp'], 'referer':row['referer'],'reqmethod':row['requestMethod'], 'resconttype':row['responseContentType']}]

        else:
            #Destination URI's refered by the threat
            refered[row['uri']]+=1

    create_incident_progression(uri,requests,refered,date)
    create_timeline(uri,clientips,date,top_results)
    save_comments(uri,title,text,date)

    return True 

def _transform(self, original_graph):
        graph = self._graph_preprocessing(original_graph)
        # collect all features for all vertices for each label_index
        feature_list = defaultdict(lambda: defaultdict(float))
        for v in graph.nodes():
            # only for vertices of type 'node', i.e. not for the 'edge' type
            if graph.nodes[v].get('node', False):
                self._transform_vertex(graph, v, feature_list)
        _clean_graph(graph)
        return self._normalization(feature_list) 

def _add_vector_labes(self, graph, vertex_v, node_feature_list):
        # add the vector with an offset given by the feature, multiplied by val
        vec = graph.nodes[vertex_v].get(self.key_vec, None)
        if vec:
            vec_feature_list = defaultdict(lambda: defaultdict(float))
            for radius_dist_key in node_feature_list:
                for feature in node_feature_list[radius_dist_key]:
                    val = node_feature_list[radius_dist_key][feature]
                    for i, vec_val in enumerate(vec):
                        key = (feature + i) % self.bitmask
                        vec_feature_list[radius_dist_key][key] += val * vec_val
            node_feature_list = vec_feature_list
        return node_feature_list 

def _compute_vertex_based_features(self, graph):
        feature_rows = []
        for v in graph.nodes():
            # only for vertices of type 'node', i.e. not for the 'edge' type
            if graph.nodes[v].get('node', False):
                feature_list = defaultdict(lambda: defaultdict(float))
                self._transform_vertex(graph, v, feature_list)
                feature_rows.append(self._normalization(feature_list))
        data_matrix = self._convert_dict_to_sparse_matrix(feature_rows)
        return data_matrix


# ------------------------------------------------------------------- 

def cost(args):
    if not (args.group_by or args.group_by_tag):
        args.group_by = ["SERVICE"]
    get_cost_and_usage_args = dict(get_common_method_args(args), Metrics=args.metrics)
    get_cost_and_usage_args["GroupBy"] = [dict(Type="DIMENSION", Key=k) for k in args.group_by]
    get_cost_and_usage_args["GroupBy"] += [dict(Type="TAG", Key=k) for k in args.group_by_tag]
    rows = collections.defaultdict(dict)
    try:
        account_name = clients.iam.list_account_aliases()["AccountAliases"][0]
    except Exception:
        account_name = boto3.session.Session().profile_name
    title = "{} ({})".format(args.group_by[0] if args.group_by else "Tag:" + args.group_by_tag[0], account_name)
    args.columns, cell_transforms = [title], {"TOTAL": format_float}
    for page in clients.ce.get_cost_and_usage(**get_cost_and_usage_args)["ResultsByTime"]:
        args.columns.append(page["TimePeriod"]["Start"])
        cell_transforms[page["TimePeriod"]["Start"]] = format_float
        for i, group in enumerate(page["Groups"]):
            value = group["Metrics"][args.metrics[0]]
            if isinstance(value, dict) and "Amount" in value:
                value = float(value["Amount"])
            rows[group["Keys"][0]].setdefault(title, group["Keys"][0])
            rows[group["Keys"][0]].setdefault("TOTAL", 0)
            rows[group["Keys"][0]]["TOTAL"] += value
            rows[group["Keys"][0]][page["TimePeriod"]["Start"]] = value
    args.columns.append("TOTAL")
    rows = [row for row in rows.values() if row["TOTAL"] > args.min_total]
    rows = sorted(rows, key=lambda row: -row["TOTAL"])
    page_output(tabulate(rows, args, cell_transforms=cell_transforms)) 

def scrawl_kernel(arch):
    re_href = re.compile('href="?({arch}[^ <>"]*)"?'.format(arch=arch))
    url = "https://toolchains.bootlin.com/downloads/releases/toolchains/{arch}/test-system/".format(arch=arch)
    response = requests.get(url + "?C=M;O=D")
    text = response.text
    links = re_href.findall(text)
    links_dict = defaultdict(lambda: defaultdict(dict))
    for link in links:
        version = get_link_version(link)
        libc = get_link_libc(link)
        filetype = get_link_filetype(link)

        # TODO: make sure they have been compiled at the same time
        if filetype not in links_dict[version][libc]:
            if filetype is None:
                return None, None, None
            links_dict[version][libc][filetype] = url + link

    state = "bleeding-edge"
    if "stable" in links_dict:
        state = "stable"

    for libc in ["glibc", "uclibc", "musl"]:
        if libc in links_dict[state]:
            break
    else:
        libc = None

    target = links_dict[state][libc]

    dtb = target.get("dtb", None)
    rootfs = target.get("rootfs", None)
    kernel = target.get("kernel", None)

    return kernel, dtb, rootfs 

def __init__(self, data):
        self.data = data
        self.callees = defaultdict(set)
        for func in self.data["functions"]:
            for call in func["called_from"]:
                self.callees[call].add(func["entry_point"]) 

def __init__(self, data):
        self.data = data
        self.callees = defaultdict(set)
        for func in self.data["functions"]:
            for call in func["called_from"]:
                self.callees[call].add(func["entry_point"]) 

def reset_uids():
    global _UID_PREFIXES
    _UID_PREFIXES = defaultdict(int) 

def get_classroom(url_rid, url_semester):
    """教室查询"""
    # decrypt identifier in URL
    try:
        _, room_id = decrypt(url_rid, resource_type='room')
    except ValueError:
        return render_template("common/error.html", message=MSG_INVALID_IDENTIFIER)
    # todo 支持没有学期的room
    # RPC to get classroom timetable
    try:
        room = entity_service.get_classroom_timetable(url_semester, room_id)
    except Exception as e:
        return handle_exception_with_error_page(e)

    with tracer.trace('process_rpc_result'):
        cards = defaultdict(list)
        for card in room.cards:
            day, time = lesson_string_to_tuple(card.lesson)
            cards[(day, time)].append(card)

    empty_5, empty_6, empty_sat, empty_sun = _empty_column_check(cards)

    available_semesters = semester_calculate(url_semester, room.semesters)

    return render_template('entity/room.html',
                           room=room,
                           cards=cards,
                           empty_sat=empty_sat,
                           empty_sun=empty_sun,
                           empty_6=empty_6,
                           empty_5=empty_5,
                           available_semesters=available_semesters,
                           current_semester=url_semester) 

def generate_ics_file(type_: str, identifier: str, semester: str) -> str:
    """生成ics文件并返回文件名"""
    from everyclass.server import statsd  # 需要在这里导入，否则导入的结果是None

    cal_filename = f"{type_}_{identifier}_{semester}.ics"
    cal_full_path = os.path.join(calendar_dir(), cal_filename)
    # 有缓存、且缓存时间小于一天，且不用强刷缓存
    if os.path.exists(cal_full_path) \
            and use_cache(cal_filename):
        logger.info("ics cache hit")
        statsd.increment("calendar.ics.cache.hit")
        return cal_filename
    statsd.increment("calendar.ics.cache.miss")

    # 无缓存、或需要强刷缓存
    with tracer.trace('rpc'):
        # 获得原始学号或教工号
        if type_ == 'student':
            rpc_result = entity_service.get_student_timetable(identifier, semester)
        else:
            # teacher
            rpc_result = entity_service.get_teacher_timetable(identifier, semester)

        semester = Semester(semester)

        cards: Dict[Tuple[int, int], List[Dict]] = defaultdict(list)
        for card in rpc_result.cards:
            cards[lesson_string_to_tuple(card.lesson)].append(dict(name=card.name,
                                                                   teacher=teacher_list_to_name_str(card.teachers),
                                                                   week=card.weeks,
                                                                   week_string=card.week_string,
                                                                   classroom=card.room,
                                                                   cid=card.card_id_encoded))

    ics_generator.generate(name=rpc_result.name,
                           cards=cards,
                           semester=semester,
                           filename=cal_filename)

    return cal_filename