Python lshash.LSHash类代码示例

def test_lshash_redis_extra_val():
    """
    Test external lshash module
    """
    config = {"redis": {"host": 'localhost', "port": 6379, "db": 15}}
    sr = StrictRedis(**config['redis'])
    sr.flushdb()

    lsh = LSHash(6, 8, 1, config)
    for i in xrange(num_elements):
        lsh.index(list(els[i]), el_names[i])
        lsh.index(list(els[i]), el_names[i])  # multiple insertions
    hasht = lsh.hash_tables[0]
    itms = [hasht.get_list(k) for k in hasht.keys()]
    for itm in itms:
        assert itms.count(itm) == 1
        for el in itm:
            assert el[0] in els
            assert el[1] in el_names
    for el in els:
        res = lsh.query(list(el), num_results=1, distance_func='euclidean')[0]
        # vector an name are in the first element of the tuple res[0]
        el_v, el_name = res[0]
        # the distance is in the second element of the tuple
        el_dist = res[1]
        assert el_v in els
        assert el_name in el_names
        assert el_dist == 0
    del lsh
    sr.flushdb()

def test_lshash_redis():
    """
    Test external lshash module
    """
    config = {"redis": {"host": 'localhost', "port": 6379, "db": 15}}
    sr = StrictRedis(**config['redis'])
    sr.flushdb()

    lsh = LSHash(6, 8, 1, config)
    for i in xrange(num_elements):
        lsh.index(list(els[i]))
        lsh.index(list(els[i]))  # multiple insertions should be prevented by the library
    hasht = lsh.hash_tables[0]
    itms = [hasht.get_list(k) for k in hasht.keys()]
    for itm in itms:
        for el in itm:
            assert itms.count(itm) == 1  # have multiple insertions been prevented?
            assert el in els
    for el in els:
        res = lsh.query(list(el), num_results=1, distance_func='euclidean')[0]
        el_v, el_dist = res
        assert el_v in els
        assert el_dist == 0
    del lsh
    sr.flushdb()

    def build_index(self, X):
        f = X.shape[1]
        n = X.shape[0]

        lsh = LSHash(hash_size = 32, input_dim = f, num_hashtables = 100)
        for i in range(n):
            lsh.index(X[i], i)

        return lsh

def dump_lsh_data_to_pickle(bits_tid_pickle, lsh_pickle):
	f = file(bits_tid_pickle, "rb")
	data = pickle.load(f)
	f.close()
	#这里的参数可以调整，具体见https://github.com/kayzh/LSHash
	lsh = LSHash(13, 128, num_hashtables=1)
	map(lambda x:lsh.index(np.array([int(tmp) for tmp in x])), data.keys())	
	out = file(lsh_pickle,"wb")
	pickle.dump(lsh, out, -1)
	out.close()

def generateSingleHash(X, planesFileName, n_bits=64):
    """
    Generate a n_bits long hash for each input in X
    :param X:
    :param n_bits:
    :return:
    """
    import utils

    # overwrite old matrixes an build some random new ones
    fileName = os.path.join(utils.lsh_planes_dir, planesFileName + '.npz')
    lsh = LSHash(n_bits, np.shape(X)[0], matrices_filename=fileName, overwrite=False)

    return lsh._hash(lsh.uniform_planes[0], X.tolist())

def create_hash2img():
    img2gist = get_img2gist()
    lsh = LSHash(hash_len, 960, storage_config=redis_config,
                 matrices_filename=matrices_file)
    count = 0
    total_num = len(img2gist)
    for name, gist_v in img2gist.iteritems():
        count += 1
        lsh.index(gist_v, name)
        sys.stdout.write('%d/%d\r    ' % (count, total_num))
        sys.stdout.flush()

    print 'bucket ratio: %d/%d' % (len(lsh.hash_tables[0].keys()), 2 ** hash_len)
    return lsh

def init():

    parser = argparse.ArgumentParser(description = 'Tools for hamming distance-based image retrieval by cuda')
    parser.add_argument('-f', help = 'The filename of image raw features (SIFT).')
    parser.add_argument('-v', default = 'fvecs', help = 'The format of image raw features.')
    parser.add_argument('-s', default = 'dict', help = 'The method of indexing storage.')
    parser.add_argument('-d', default = '128', help = 'Dimensions of raw image feature.')
    parser.add_argument('-o', default = '0', help = 'Offset of accessing raw image features.')
    parser.add_argument('-n', default = '1', help = 'Number of raw image features to read.')
    parser.add_argument('-i', default = 'n', help = 'Whether to perform indexing step.')
    parser.add_argument('-e', help = 'The dirname of indexing folder.')
    parser.add_argument('-k', default = '10', help = 'Number of retrieved images.')
    parser.add_argument('-r', default = '32', help = 'Number of dimensions randomly sampled.')
    parser.add_argument('-c', default = 'n', help = 'Whether to perform compressing step.')
    parser.add_argument('-q', default = 'n', help = 'Whether to sequentially sampling.')
    parser.add_argument('-p', default = 'n', help = 'Whether to perform querying in compressed domain.')
    parser.add_argument('-g', default = 'y', help = 'GPU mode. default is "yes".')
    parser.add_argument('-l', default = 'n', help = 'VLQ base64 mode. Load VLQ base64 encoding compressed dict.')
    parser.add_argument('-b', default = '1', help = 'Expanding level of search buckets.')
    parser.add_argument('-t', default = 'int32', help = 'FastDict type (int32, int8, string).')
 
    args = parser.parse_args()
 
    d = int(args.d)
    nuse = int(args.n)
    off = int(args.o)
    random_dims = int(args.r)
 
    random_sampling = True
    if args.q == 'y':
        random_sampling = False

    lsh = LSHash(64, d, random_sampling, args.t, random_dims, 1, storage_config = args.s, matrices_filename = 'project_plane.npz')
    np_feature_vecs = load_features(args.f, args.v, nuse, d, off)

    if args.c != 'y' and args.i != 'y' and args.e != None and args.s == 'random':
        if args.p == 'y':
            print "loading compressed index."
            lsh.load_compress_index(args.e, (args.l == 'y'))
            print "loading done."
        else:
            print "loading index."
            lsh.load_index(args.e)
            print "loading done."

    print "indexing done. Ready for querying."

    return (lsh, np_feature_vecs, args)

    def __init__(self):
        self.lshIndexList = []


        # create a list of lsh indexes
        self.lsh = LSHash(NUMBER_OF_BITS_PER_HASH, NUM_TOPICS, num_hashtables=NUMBER_OF_LSH_INDEXES,
                          storage_config={"redis": {"host": "localhost", "port": 6379}})

class LshIndexer(Indexer):
	PARAMETERS = {'hash_size': 6,
				  'input_dim': 128,
				  'num_of_hashtables': 1,
				  'storage': {'redis': {'host':'localhost', 'port': 6379}}}

	def initialize_store(self, parameters):
		self.store = LSHash(parameters['hash_size'],
							parameters['input_dim'],
							parameters['num_of_hashtables'],
							parameters['storage'])

	def index(self, features):
		for feature in features:
			self.store.index(feature.data, feature.file_id)

	def query(self, feature, num_results=5):
		return self.store.query(feature, num_results)

def test_lshash():
    lsh = LSHash(6, 8, 1)
    for i in xrange(num_elements):
        lsh.index(list(els[i]))
        lsh.index(list(els[i]))  # multiple insertions
    hasht = lsh.hash_tables[0]
    itms = [hasht.get_list(k) for k in hasht.keys()]
    for itm in itms:
        assert itms.count(itm) == 1
        for el in itm:
            assert el in els
    for el in els:
        res = lsh.query(list(el), num_results=1, distance_func='euclidean')[0]
        # res is a tuple containing the vector and the distance
        el_v, el_dist = res
        assert el_v in els
        assert el_dist == 0
    del lsh

def generateHashes(X, scalar, planesFileName, n_bits=64):
    """
    Generate a n_bits long hash for each input in X
    :param X:
    :param n_bits:
    :return:
    """
    import utils

    # overwrite old matrixes an build some random new ones
    fileName = os.path.join(utils.lsh_planes_dir, planesFileName + '.npz')
    lsh = LSHash(n_bits, np.shape(X[0])[0], matrices_filename=fileName, overwrite=False)
    hashValues = []
    for input_point in X:
        input_point = scalar.transform(input_point)
        hashValues.append(lsh._hash(lsh.uniform_planes[0], input_point))

    return hashValues

def learn(routes):
    global global_training_route
    global next_hop_index
    
    extra_data_len = 2    #destination, next_hop
    ndims = len(routes[0]) - extra_data_len   #Number of dimensions
    hash_length = len(routes[0]) * 2   #arbitrarily chosen hash_length
    next_hop_index = len(routes[0]) - 1   #NextHop index at the last
    
    for i in range(0, len(routes) - 1):
        if(routes[i][next_hop_index] >= routes[i+1][next_hop_index]):
            routes[i][next_hop_index] = i+1
        else:
            routes[i][next_hop_index] = -1
    global_training_route = routes
    lsh = LSHash(hash_length, ndims)
    for entry in routes:
        lsh.index(entry[:-extra_data_len], extra_data = entry[-extra_data_len:])
    return lsh

def detect_subevent(filename):
	dictionaryFile = filename + ".dict"
	corpusFile = filename + ".mm"
	outputFile = filename + ".out"
	outputVector = []
	tempDict = {}
	outputdict={}
	corpus = corpora.MmCorpus(corpusFile)
	dictionary = corpora.Dictionary.load(dictionaryFile)
	lsh = LSHash(30, dictionary.__len__())
	index = 0
	for index in range(len(corpus)):
		#print str(index)+",",
		#print corpus[index]
		denseVector = getDenseVector(corpus[index], lsh.input_dim)
		#print getSparseVector(denseVector)
		result = lsh.query(denseVector, num_results = 50, distance_func = "euclidean")
		#print result
		#no similar tweets
		
		if(result == []):
			outputdict[index]=[]
			tempDict[getSparseVector(denseVector)] = index
			lsh.index(denseVector)
			#continue
		
		else:
			for r in result:
				if(outputdict.has_key(tempDict[getSparseVector(r[0])])):
					outputdict[tempDict[getSparseVector(r[0])]].append(index)
					break
			
		
		
	#print outputdict
	with open(outputFile, 'w') as out:
		for key in outputdict.iterkeys():
			line = str(key) 
			for i in outputdict[key]:
				line += ", " + str(i)
			out.write(line+"\n")
	
	print "Please check the output file:", outputFile

def getBuckets(fromFile):
    global nameDict
    global lsh
    nameDict = {}
    lsh = LSHash(bWidth,26, num_hashtables = num_ht)
    if fromFile:
        f = open(datafile, 'r')   
        nameList = f.readlines()
    else:
        nameList = surnames.dic.keys()
    for l in nameList:
        name = l.split(" ")[0].strip()
        nameArr = getvec(name)
        arrStr = toStr(nameArr)
        if arrStr in nameDict:
            nameDict[arrStr].append(name)
        else:
            nameDict[arrStr] = [name]
    for k in nameDict.keys():
        lsh.index(toArr(k))

def test_lshash_extra_val():
    lsh = LSHash(6, 8, 1)
    for i in xrange(num_elements):
        lsh.index(list(els[i]), el_names[i])
    hasht = lsh.hash_tables[0]
    itms = [hasht.get_list(k) for k in hasht.keys()]
    for itm in itms:
        for el in itm:
            assert el[0] in els
            assert el[1] in el_names
    for el in els:
        # res is a list, so we need to select the first entry only
        res = lsh.query(list(el), num_results=1, distance_func='euclidean')[0]
        # vector an name are in the first element of the tuple res[0]
        el_v, el_name = res[0]
        # the distance is in the second element of the tuple
        el_dist = res[1]
        assert el_v in els
        assert el_name in el_names
        assert el_dist == 0
    del lsh