Python sortedcontainers.SortedList类代码示例

def test_delitem():
    random.seed(0)
    slt = SortedList(range(100), load=17)
    while len(slt) > 0:
        pos = random.randrange(len(slt))
        del slt[pos]
        slt._check()

 def score_of_a_vacated_people(self, universo, work='translations'):
     factor = math.sqrt(len(universo))
     scores = SortedList(load=round(factor))
     for (people, score) in self.__scores__().items():
         if people in universo:
             scores.add(TranslatorScore(people, score[work]))
     return scores.pop(0)

def test_delitem_slice():
    slt = SortedList(range(100))
    slt._reset(17)
    del slt[10:40:1]
    del slt[10:40:-1]
    del slt[10:40:2]
    del slt[10:40:-2]

def test_copy_copy():
    import copy
    alpha = SortedList(range(100), load=7)
    beta = copy.copy(alpha)
    alpha.add(100)
    assert len(alpha) == 101
    assert len(beta) == 100

def test_setitem_extended_slice():
    slt = SortedList(range(0, 1000, 10), load=17)
    lst = list(range(0, 1000, 10))
    lst[10:90:10] = range(105, 905, 100)
    slt[10:90:10] = range(105, 905, 100)
    assert slt == lst
    slt._check()

    def extract_collocations(self, metric_class):
        assert issubclass(metric_class, Metric)
        metric = metric_class()
        collocations = SortedList(key=lambda x: -x[0])
        
        unigram_counts = self.language_model.get_unigrams()
        bigram_counts = self.language_model.get_bigrams()

        for (first, last), freq_bigram in bigram_counts.items():

            if self.exclude_punctuation:
                if first in self.PUNCT or last in self.PUNCT:
                    continue

            if self.exclude_conj:
                if first in self.CONJ_RU or last in self.CONJ_RU:
                    continue

            if self.exclude_props:
                if first in self.PROPOSITIONS_RU or last in self.PROPOSITIONS_RU:
                    continue

            freq_first, freq_last = unigram_counts[first], unigram_counts[last]
            
            metric_val = metric.evaluate(freq_first, freq_last, freq_bigram,
                                         self.language_model.get_vocab_size())
            collocations.add((metric_val, freq_first,
                              freq_last, freq_bigram,
                              first, last))
            
        return collocations

def test_eq():
    this = SortedList(range(10), load=4)
    that = SortedList(range(20), load=4)
    assert not (this == that)
    that.clear()
    that.update(range(10))
    assert this == that

def iana_rir_gen_ip_list(user_rir_list):

    # generates a list of networks that can be blocked by RIR

    # we use a SortedList so that elements are inserted in order. This allows cidr_merge to work
    rir_slash_eight_list = SortedList()

    with open('iana') as iana_file:

        iana_csv = csv.reader(iana_file)

        for line in iana_csv:

            for rir in user_rir_list:

                # case in which the whois line from our csv contains the RIR
                if rir in line[3]:

                    network = line[0].lstrip('0')
                    rir_slash_eight_list.add(netaddr.IPNetwork(network))

                    # if we find a match, there is no reason to see if the other RIRs are on the same line
                    break

        # run cidr_merge to summarize
        rir_slash_eight_list = netaddr.cidr_merge(rir_slash_eight_list)

    return rir_slash_eight_list

    def predict(self, X):
        y = np.zeros(len(X))
        for i,x in enumerate(X): # test points
            sl = SortedList(load=self.k) # stores (distance, class) tuples
            for j,xt in enumerate(self.X): # training points
                diff = x - xt
                d = diff.dot(diff)
                if len(sl) < self.k:
                    # don't need to check, just add
                    sl.add( (d, self.y[j]) )
                else:
                    if d < sl[-1][0]:
                        del sl[-1]
                        sl.add( (d, self.y[j]) )
            # print "input:", x
            # print "sl:", sl

            # vote
            votes = {}
            for _, v in sl:
                # print "v:", v
                votes[v] = votes.get(v,0) + 1
            # print "votes:", votes, "true:", Ytest[i]
            max_votes = 0
            max_votes_class = -1
            for v,count in votes.iteritems():
                if count > max_votes:
                    max_votes = count
                    max_votes_class = v
            y[i] = max_votes_class
        return y

class DijkstraFixedPoint:
	def __init__(self, automaton, initial_set, accepted_set):
		self.automaton = automaton
		self.set_to_visit = SortedList(initial_set,key= lambda d: -len(d))
		self.accepted_set = accepted_set

	def iter_fix_point_set(self,max_size=10):
		if len(self.set_to_visit)==0:
			raise StopIteration()

		F = self.set_to_visit.pop()

		nF = {k:[v] for k,v in F.items()}
		new_size_of_fp = len(nF)
		reach_accepted_set = False
		for u,lu in F.items():
			labelled_edges = self.automaton.get_labelled_successors(u)
			succ = labelled_edges[lu]
			for s in succ:
				if s in self.accepted_set:
					reach_accepted_set = True
				if (s not in nF) and (s not in self.accepted_set):
					nF[s] = list(self.automaton.get_successor_labels(s))
					new_size_of_fp = len(nF)
					if new_size_of_fp>max_size:
						return False,F


		newF = self.expand_successor_set(nF)
		if F in newF:
			newF.remove(F)
		self.set_to_visit.update(newF)
		accept_fix_point = (len(newF)==0) and reach_accepted_set
		return accept_fix_point,F


	def expand_successor_set(self,nF):
		sF = []
		# import operator
		# size = reduce(operator.mul, [len(v) for v in nF.values()], 1)
		for conf in itertools.product(*nF.values()):
			sF.append({k:v for k,v in zip(nF.keys(),conf)})
		return sF

	def __iter__(self):
		return self

	def next(self):
		return self.iter_fix_point_set()

	def next_fixed_point(self,max_size):
		fp_found = 0
		try:
			while fp_found==False:
					fp_found,fp = self.iter_fix_point_set(max_size)
					#print "#"*len(fp)
		except StopIteration:
			return False,None
		return fp_found,fp

def test_pickle():
    import pickle
    alpha = SortedList(range(10000))
    alpha._reset(500)
    beta = pickle.loads(pickle.dumps(alpha))
    assert alpha == beta
    assert alpha._load == 500
    assert beta._load == 1000

 def find_latest(self):
     sorted = SortedList()
     for i in self.bucket.list(prefix=self.db_name):
         parts = i.name.split('/')
         if len(parts) == 3:
             d = datetime.datetime.strptime(parts[1], "%m%d%Y").date()
             sorted.add(d)
     return sorted[len(sorted)-1].strftime('%m%d%Y')

def read_rirs(country_list, permit, rir_list=RIR_NAMES):

    # list containing our file objects
    file_list = []

    # we use a SortedList so that elements are inserted in order. This allows cidr_merge to work
    rir_ips = SortedList()

    # Open the files we downloaded earlier and store the file object
    for rir in rir_list:
        file_list.append(open(rir))

    for f in file_list:

        for line in f:

            curr_line = line.split('|')

            try:

                # we want only the ipv4 lines that are for a specific country
                # also only want countries that we are going to block
                if (curr_line[2] == "ipv4" and curr_line[1] != "*") and \
                    ((permit and curr_line[1] not in country_list) or
                     (not permit and curr_line[1] in country_list)):

                    country_code = curr_line[1]
                    network_id = curr_line[3]
                    wildcard = int(curr_line[4])-1

                    try:

                        # Add network to list, if the number of IPs was not a
                        # power of 2 (wildcard is not valid).
                        # AddrFormatError is thrown
                        rir_ips.add(netaddr.IPNetwork(network_id + "/" + str(netaddr.IPAddress(wildcard))))

                    # Handle case in where our mask is invalid by rounding DOWN
                    except netaddr.AddrFormatError:

                        print "rounded network " + network_id + " with " + str(wildcard) + \
                              " hosts up to nearest power of 2"
                        wildcard = next_power_of_2(wildcard) - 1
                        print wildcard + 1
                        rir_ips.add(netaddr.IPNetwork(network_id + "/" + str(netaddr.IPAddress(wildcard))))

            # IndexErrors only occur when parsing columns we don't need
            except IndexError:

                pass

        f.close()

    # cidr_merge takes our list of IPs and summarizes subnets where possible
    # this greatly decreases the number of ACL entries
    rir_ips = netaddr.cidr_merge(rir_ips)

    return rir_ips

class InMemoryBackend(object):
    """
    The backend that keeps the results in the memory.
    """
    def __init__(self, *args, **kwargs):
        def get_timestamp(result):
            return timestamp_parser.parse(result['timestamp'])

        self._results = dict()
        self._sorted = SortedList(key=get_timestamp)

    def disconnect(self):
        return succeed(None)

    def store(self, result):
        """
        Store a single benchmarking result and return its identifier.

        :param dict result: The result in the JSON compatible format.
        :return: A Deferred that produces an identifier for the stored
            result.
        """
        id = uuid4().hex
        self._results[id] = result
        self._sorted.add(result)
        return succeed(id)

    def retrieve(self, id):
        """
        Retrive a result by the given identifier.
        """
        try:
            return succeed(self._results[id])
        except KeyError:
            return fail(ResultNotFound(id))

    def query(self, filter, limit=None):
        """
        Return matching results.
        """
        matching = []
        for result in reversed(self._sorted):
            if len(matching) == limit:
                break
            if filter.viewitems() <= result.viewitems():
                matching.append(result)
        return succeed(matching)

    def delete(self, id):
        """
        Delete a result by the given identifier.
        """
        try:
            result = self._results.pop(id)
            self._sorted.remove(result)
            return succeed(None)
        except KeyError:
            return fail(ResultNotFound(id))

 def dir(self, file_pattern):
     attrs = self.sftp.listdir_attr(self.remote_dir)
     filtered = SortedList()
     for attr in attrs:
         if hasattr(attr, "filename"):
             filename = attr.filename
             if re.match(file_pattern, filename):
                 remote_file = RemoteFile(filename, attr.st_mtime)
                 filtered.add(remote_file)
     return filtered