Python util.chunks函数代码示例

def generate(config, dnat=False, test=True):
    public_ip = config["public_ip"]
    current_ip = config["base_ip"]
    dnsmasq_content = ""
    for group in config["groups"].values():
        if not dnat:
            c = chunks([proxy["domain"] for proxy in group["proxies"]], 5)
        else:
            c = chunks([proxy["domain"] for proxy in group["proxies"] if proxy["dnat"]], 5)

        for chunk in c:
            if not dnat:
                dnsmasq_content += generate_dns(chunk, public_ip)
            else:
                dnsmasq_content += generate_dns(chunk, current_ip)

    if test:
        if not dnat:
            dnsmasq_content += generate_dns('ptest.verdandi.is', public_ip)
            dnsmasq_content += generate_dns('ptest2.verdandi.is', public_ip)
        else:
            dnsmasq_content += generate_dns('ptest.verdandi.is', current_ip)
            dnsmasq_content += generate_dns('ptest2.verdandi.is', current_ip)

    if dnat:
        for group in config["groups"].values():
            for proxy in group["proxies"]:
                if not proxy["dnat"]:
                    current_ip = long2ip(ip2long(current_ip) + 1)
                    dnsmasq_content += generate_dns(proxy["domain"], current_ip)

    return dnsmasq_content

    def train(self, X_train, X_val):

        train_true = filter(lambda x: x[2]==1, X_train)
        train_false = filter(lambda x: x[2]==0, X_train)

        val_true = filter(lambda x: x[2]==1, X_val)
        val_false = filter(lambda x: x[2]==0, X_val)

        n_train_true = len(train_true)
        n_val_true = len(val_true)

        make_epoch_helper = functools.partial(make_epoch, train_true=train_true, train_false=train_false, val_true=val_true, val_false=val_false)

        logging.info("Starting training...")
        epoch_iterator = ParallelBatchIterator(make_epoch_helper, range(P.N_EPOCHS), ordered=False, batch_size=1, multiprocess=False, n_producers=1)

        for epoch_values in epoch_iterator:
            self.pre_epoch()
            train_epoch_data, val_epoch_data = epoch_values

            train_epoch_data = util.chunks(train_epoch_data, P.BATCH_SIZE_TRAIN)
            val_epoch_data = util.chunks(val_epoch_data, P.BATCH_SIZE_VALIDATION)

            self.do_batches(self.train_fn, train_epoch_data, self.train_metrics)
            self.do_batches(self.val_fn, val_epoch_data, self.val_metrics)

            self.post_epoch()
            logging.info("Setting learning rate to {}".format(P.LEARNING_RATE  * ((0.985)**self.epoch)))
            self.l_r.set_value(P.LEARNING_RATE  * ((0.985)**self.epoch))

def collect_tweets_by_ids(tweet_ids_config_filepath, output_folder, config):

    apikeys = list(config['apikeys'].values()).pop()

    tweet_ids_config = {}
    with open(os.path.abspath(tweet_ids_config_filepath), 'r') as tweet_ids_config_rf:
        tweet_ids_config = json.load(tweet_ids_config_rf)

    max_range = 100
    
    current_ix = tweet_ids_config['current_ix'] if ('current_ix' in tweet_ids_config) else 0
    total = len(tweet_ids_config['tweet_ids'][current_ix:])
    tweet_id_chuncks = util.chunks(tweet_ids_config['tweet_ids'][current_ix:], max_range)

    for tweet_ids in tweet_id_chuncks:
        try:
            twitterCralwer = TwitterCrawler(apikeys=apikeys, client_args=CLIENT_ARGS, output_folder = output_folder)
            twitterCralwer.lookup_tweets_by_ids(tweet_ids)
            current_ix += len(tweet_ids)

        except Exception as exc:
            logger.error(exc)
            logger.error(util.full_stack()) #don't care, if Ctrl+c is hit, does not handle it.  When you restart, it restarts from the last chunk (too much trouble to handle Ctrl + c).
            # you will get duplicate tweets, so what...
            pass

        tweet_ids_config['current_ix'] = current_ix
        
        flash_cmd_config(tweet_ids_config, tweet_ids_config_filepath, output_folder)

        logger.info('COMPLETED -> (current_ix: [%d/%d])'%(current_ix, total))
        logger.info('PAUSE %ds to CONTINUE...'%WAIT_TIME)
        time.sleep(WAIT_TIME)
    else:
        logger.info('[tweets_by_ids] ALL COMPLETED')

	def decode(self, server, block_header, target, job_id = None, extranonce2 = None):
		if block_header:
			job = Object()
	
			binary_data = block_header.decode('hex')
			data0 = np.zeros(64, np.uint32)
			data0 = np.insert(data0, [0] * 16, unpack('IIIIIIIIIIIIIIII', binary_data[:64]))
	
			job.target	  = np.array(unpack('IIIIIIII', target.decode('hex')), dtype=np.uint32)
			job.header	  = binary_data[:68]
			job.merkle_end  = np.uint32(unpack('I', binary_data[64:68])[0])
			job.time		= np.uint32(unpack('I', binary_data[68:72])[0])
			job.difficulty  = np.uint32(unpack('I', binary_data[72:76])[0])
			job.state	   = sha256(STATE, data0)
			job.f		   = np.zeros(8, np.uint32)
			job.state2	  = partial(job.state, job.merkle_end, job.time, job.difficulty, job.f)
			job.targetQ	 = 2**256 / int(''.join(list(chunks(target, 2))[::-1]), 16)
			job.job_id	  = job_id
			job.extranonce2 = extranonce2
			job.server	  = server
	
			calculateF(job.state, job.merkle_end, job.time, job.difficulty, job.f, job.state2)

			if job.difficulty != self.difficulty:
				self.set_difficulty(job.difficulty)
	
			return job

    def decode(self, server, block_header, target, job_id = None, extranonce2 = None):
        if block_header:
            job = Object()

            binary_data = block_header.decode('hex')

            #data0 = list(unpack('<16I', binary_data[:64])) + ([0] * 48)

            job.headerX = binary_data[:76]
            job.dataX = unpack('<19I', job.headerX)
            job.target		= unpack('<8I', target.decode('hex'))
            job.header		= binary_data[:68]
            job.merkle_end	= uint32(unpack('<I', binary_data[64:68])[0])
            job.time		= uint32(unpack('<I', binary_data[68:72])[0])
            job.difficulty	= uint32(unpack('<I', binary_data[72:76])[0])
            # job.state		= sha256(STATE, data0)
            job.targetQ		= 2**256 / int(''.join(list(chunks(target, 2))[::-1]), 16)
            job.job_id		= job_id
            job.extranonce2	= extranonce2
            job.server		= server

            if job.difficulty != self.difficulty:
                self.set_difficulty(job.difficulty)

            return job

 def getstatusforfids(self, fids):
     status = {}
     
     for chunk in chunks(fids, 50):
         for f in arlalow.fetchbulkstatus(self.fsconn, chunk):
             status[f["fid"]] = f["status"]
     return status

def extract_all_labels(filenames, out_filepath=DATA_FOLDER+'labels.p', chunk_size=2000):
    print "EXTRACTING ALL LABELS INTO {0}".format(out_filepath)
    all_labels = []
    label_dict = {}

    filenames_chunks = util.chunks(filenames, chunk_size)

    for i, chunk in enumerate(filenames_chunks):
        pool = Pool(processes=util.CPU_COUNT)
        chunk_labels = pool.map(extract_labels, chunk)
        pool.close()

        for filepath, labels in zip(chunk, chunk_labels):
            if labels is not None:
                file_id = util.filename_without_extension(filepath)
                label_dict[file_id] = labels
                all_labels += labels

        print i+1, '/', len(filenames_chunks)

    #Write labels to file
    with open(out_filepath,'w') as f:
        pickle.dump(label_dict, f)

    print '\nLabels:'
    print len(set(all_labels))
    print Counter(all_labels)

 def __call__(self, message, state=None, *, pad=True):
     state = state or self.initial_state
     prepared_message = message + (self.padding(len(message)) if pad else b"")
     assert len(prepared_message) % self.block_size == 0
     for block in chunks(prepared_message, self.block_size):
         state = self.compress(state, block)
     return state

    def predict(self, data, modes):
        """predict whether a list of position follows atrain route by detecting
        the nearest train stops. Input is the pandas data frame of
        measurements and an array of current mode predictions.  Returns
        an array of predicted modes of the same size as the input data
        frame has rows.

        """
        # extract lat/lon from data frame
        lat = data['WLATITUDE'].values
        lon = data['WLONGITUDE'].values

        # chunk is a tuple (start_idx, end_idx, mode)
        for start_idx, end_idx, _ in ifilter(lambda chunk: chunk[2] in [MODE_CAR, MODE_BUS, MODE_TRAIN],
                                             chunks(modes, include_values=True)):
            # test for distance first
            lat_seg = lat[start_idx:end_idx]
            lon_seg = lon[start_idx:end_idx]
            valid_lat_seg = lat_seg[np.where(np.invert(np.isnan(lat_seg)))[0]]
            valid_lon_seg = lon_seg[np.where(np.invert(np.isnan(lon_seg)))[0]]

            if len(valid_lon_seg) == 0:
                continue
            # TODO: parameters have to be tuned carefully
            is_train = predict_mode_by_location(valid_lat_seg,
                                                valid_lon_seg,
                                                self.train_location_tree,
                                                self.train_location_dict,
                                                self.train_route_dict,
                                                dist_thre = 400,
                                                dist_pass_thres = 7, 
                                                num_stops_thre = 3,
                                                dist_pass_thres_perc = 0.7)

            #check entry point distance
            entry_pt_near = -1
            exit_pt_near = -1

            if start_idx-1>=0:
                if not np.isnan(lat[start_idx-1]):
                    nearest_station = find_nearest_station(lat[start_idx-1], lon[start_idx-1], self.train_location_tree, self.dist_thres_entry_exit)
                    if len(nearest_station)!=0:
                        entry_pt_near = 1
                    else:
                        entry_pt_near = 0

            if end_idx < len(modes):
                if not np.isnan(lat[end_idx]):
                    nearest_station = find_nearest_station(lat[end_idx],lon[end_idx],
                                                           self.train_location_tree,
                                                           self.dist_thres_entry_exit)
                    if len(nearest_station)!=0:
                        exit_pt_near = 1
                    else:
                        exit_pt_near = 0
            if is_train or entry_pt_near + exit_pt_near == 2:
                modes[start_idx:end_idx] = MODE_TRAIN
            else:
                modes[start_idx:end_idx] = MODE_CAR
        return modes

def crack_ecb_oracle(oracle_fn, prefix_length=0):
    block_size = guess_block_size(oracle_fn)
    if not looks_like_ecb(oracle_fn(b"A" * 100), block_size):
        raise ValueError("oracle_fn does not appear to produce ECB mode output")
    result = bytearray()
    while True:
        short_block_length = (block_size - len(result) - 1 - prefix_length) % block_size
        short_input_block = b"A" * short_block_length
        block_index = (len(result) + prefix_length) // block_size
        block_to_look_for = chunks(oracle_fn(short_input_block))[block_index]
        for guess in all_bytes_by_frequency:
            test_input = short_input_block + result + bytes([guess])
            if chunks(oracle_fn(test_input))[block_index] == block_to_look_for:
                result.append(guess)
                break
        else:  # if no byte matches
            return pkcs7_unpad(result)

def cluster_to_kml(user, cluster, cluster_id):
    """
    Creates a single, or possibly multiple KML files a given cluster.
    A KML file is limited by MyMaps to having only 10 layers, so only 
    10 sections will be in a given KML file.

    Responsibilty of caller to check existence and formatting of cluster 
    """ 
    Sections = get_section_db()
    for i,chunk in enumerate(chunks(cluster,10)):    
        sections = map(lambda section_id: Sections.find_one({'_id':section_id}), chunk)
        sections_to_kml("%s_cluster_data_kml/CLUSTER_%s_%i" % (user, str(cluster_id), i), sections)

 def add_text(self, text):
     if len(text) + len(self._lines[self.point[0]]) > self.draw_width:
         self.point_to_next_line()
     if len(text) > self.draw_width:
         lines_to_add = chunks(text, self.draw_width)
         lines_to_advance = len(lines_to_add)
         for line in lines_to_add:
             self._lines.append(line)
         self.adjust_point_by_lines(lines_to_advance)
     else:
         self._lines[self.point[0]] += text
     self.point_to_end_of_line()

 def cross_validation(self, fold, epoch):
     print 'doing cross validation...'
     splited_data = list(chunks(self.data, fold))
     hyper_test = defaultdict(int)
     for idx, (train, test) in enumerate(splited_data):
         for c in self.C:
             for rho_0 in self.RHO_0:
                 weight = self.train(train, rho_0, c, epoch=epoch)
                 precision = self.test(test, weight)
                 print 'done fold %i' % idx, ' on [rho_0: %s, c: %s]' \
                       % (rho_0, c)
                 hyper_test[(rho_0, c)] += precision
     return map(lambda (x, y): (x, y/fold), hyper_test.iteritems())

	def start_producers(self, result_queue):
		jobs = Queue()
		n_workers = params.N_PRODUCERS
		batch_count = 0

		#Flag used for keeping values in queue in order
		last_queued_job = Value('i', -1)

		for job_index, batch in enumerate(util.chunks(self.X,self.batch_size)):
			batch_count += 1
			jobs.put( (job_index,batch) )

		# Define producer (putting items into queue)
		def produce(id):
			while True:
				job_index, task = jobs.get()

				if task is None:
					#print id, " fully done!"
					break

				result = self.gen(task)

				while(True):
					#My turn to add job done
					if last_queued_job.value == job_index-1:

						with last_queued_job.get_lock():
							result_queue.put(result)
							last_queued_job.value += 1
							#print id, " worker PUT", job_index
							break

		#Start workers
		for i in xrange(n_workers):

			if params.MULTIPROCESS:
				p = Process(target=produce, args=(i,))
			else:
				p = Thread(target=produce, args=(i,))

			p.daemon = True
			p.start()

		#Add poison pills to queue (to signal workers to stop)
		for i in xrange(n_workers):
			jobs.put((-1,None))


		return batch_count, jobs

def threshold_optimization(p, y):
    print "Optimizing threshold"
    y_images = util.chunks(y, 384*512)

    def dice_objective(threshold):
        p_binary = np.where(p > threshold, 1,0)
        p_images_binary = util.chunks(p_binary, 384*512)

        mean, std, dices = dice(p_images_binary, y_images)
        return -mean

    x, v, message = scipy.optimize.fmin_l_bfgs_b(dice_objective, 0.5, approx_grad=True, bounds=[(0, 1)], epsilon=1e-03)
    print "Optimized, threshold {0}, ? {1}, termination because {2}".format(x,v,message)
    return x[0]