def write_json_lsh(hash_size, grid):
'''
将生成的lsh路径放入json并存储
:param hash_size: hash size列表
:param grid: 处理完的栅格数组
:return: none
'''
data_lsh = {}
for size in hash_size:
print size
print 'list'
data_lsh[size] = []
lsh = LSHash(size, 44107)
count = 0
for line in grid:
lsh.index(line, extra_data=count)
count += 1
for id in road_id:
roads = []
res = lsh.query(grid[id])
print len(res)
for r in res:
roads.append(pack_data(r[0][1]))
data_lsh[size].append({id: roads})
with open('result_lsh.json', 'w') as f:
f.write(str(data_lsh))
def knn(data_array, data, hash_size_input, data_shape):
# init LSHash
lsh = LSHash(hash_size=hash_size_input, input_dim=data_shape[0])
# index
for col_index in range(data_shape[1]):
lsh.index(data_array[:, col_index], extra_data=data.columns[col_index])
# get a random pos
vipno_pos = rd.randint(0, data_shape[1])
# calculate and output
for k in [1, 2, 3, 4, 5]:
print 'hash size: %d' % hash_size_input
print 'value k: %d' % k
print 'target vipno: %d' % data.columns[vipno_pos]
result = []
for res in lsh.query(data_array[:, vipno_pos],
num_results=k + 1,
distance_func='euclidean'):
result.append(res[0][1])
print 'results: '
print result[1:]
def create_feature(list_author, net):
global example_image_dir
list_feature = list()
image_paths = list()
## Locality Sensitive Hashing
k = 10 # hash size
L = 5 # number of tables
d = 58 # Dimension of Feature vector
lsh = LSHash(hash_size=k, input_dim=d, num_hashtables=L)
for subfolder in list_author.keys():
subfolder_path = os.path.join(example_image_dir, subfolder)
count_items = len([
name for name in os.listdir(subfolder_path)
if os.path.isfile(os.path.join(subfolder_path, name))
])
# print(subfolder)
sum_acc = 0
sum_confiden = 0
for img in os.listdir(subfolder_path):
image_path = os.path.join(subfolder_path, img)
author, confidence, feature = predict_author_single_img(
net, image_path)
image_paths.append(image_path)
list_feature.append(feature)
lsh.index(feature, extra_data=image_path)
pickle.dump(lsh, open('lsh.p', "wb"))
return lsh, image_paths, list_feature
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 traceLSHash(queryName, hashSize):
#queryName ="hamming_query_12_3"
#需要进行hashQuery的轨迹index
indexList = [14, 249, 479, 689, 899]
XYMatrix = DateTransform()
resultList = []
nearList = []
lsh = LSHash(hashSize, 44107)
tid = 1
for traceList in XYMatrix:
lsh.index(input_point=traceList, extra_data=tid)
tid += 1
resultFile = open(queryName + '.txt', 'w')
for index in indexList:
queryList = lsh.query(XYMatrix[index], distance_func="hamming")
for result in queryList:
resultStr = str(index + 1) + " : " + str(result[0][1]) + " " + str(
result[1]) + "\n"
nearList.append(result[0][1])
resultFile.write(resultStr)
resultList.append(nearList)
nearList = []
resultFile.close()
writeHTML(resultList, queryName, "hashQuerry")
print resultList
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 test_lshash_extra_val(self):
lsh = LSHash(self.hash_size,
self.input_dim,
1,
storage_config={'dict': None})
for i in range(self.nb_elements):
lsh.index(list(self.els[i]), self.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:
self.assertIn(el[0], self.els)
self.assertIn(el[1], self.el_names)
for el in self.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]
self.assertIn(el_v, self.els)
self.assertIn(el_name, self.el_names)
self.assertEqual(el_dist, 0)
del lsh
def k_nn_lsh(k, word, decade_matrix, index_dict):
index_dict = dict(map(reversed, index_dict.items()))
num_rows = decade_matrix.get_shape()[0]
lsh = LSHash(6, num_rows)
for i in range(num_rows):
print(i)
lsh.index(decade_matrix.getrow(i).todense())
return lsh.query(word)
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 Mainfunc(self, mat_addr):
np.set_printoptions(suppress=True, precision=6, threshold=8)
s = sio.loadmat(mat_addr)
svec = s['FFE']
datalen = len(svec)
n1, n2, n3 = np.shape(svec)
data = np.zeros((n1, 87212))
m = 0
for i in range(n2):
for j in range(n3):
if svec[:, i, j].all() != 0:
data[:, m] = svec[:, i, j]
m = m + 1
# print data[:,0]
dataves = np.transpose(data)
modelindex = list(set(np.random.randint(1, 87212, size=10000)))
lsh_model = LSHash(7, n1)
for jj in modelindex:
lsh_model.index(dataves[jj, :])
# if you want to test a program
starttest = 1 # start test index
endtest = 5
testindex = random.sample(modelindex,
1) # SIZE IS THE NUMBER OF TEST FUNCTIONS
test = np.zeros((len(testindex), n1))
for i in range(len(testindex)):
# print dataves[testindex[i],:]
test[i, :] = dataves[testindex[i], :]
# print len(test)
output = open('result.txt', 'w')
timee = open('time.txt', 'w')
for queryi in range(len(testindex)):
if test[queryi, :].all() != 0:
starttime = time.time()
Atemp = lsh_model.query(test[queryi, :], 5, 'cosine')
print(str(Atemp[0]).split(')')[0]).replace('(', '')
output.write((str(Atemp[0]).split(')')[0]).replace('(', '') +
'\n')
output.write((str(Atemp[1]).split(')')[0]).replace('(', '') +
'\n')
output.write((str(Atemp[2]).split(')')[0]).replace('(', '') +
'\n')
output.write((str(Atemp[3]).split(')')[0]).replace('(', '') +
'\n')
output.write((str(Atemp[4]).split(')')[0]).replace('(', '') +
'\n')
endtime = time.time()
timee.write(str(endtime - starttime) + '\n')
# output.write(A)
output.write('\n')
output.close()
timee.close()
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 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 lshSearch(dataBase2, test2, num):
lsh = LSHash(30, 216)
def CreateIndex(array):
for item in array:
lsh.index(item)
CreateIndex(dataBase2)
test2 = test2.reshape((216,))
res = lsh.query(test2, num, distance_func='true_euclidean')
return res
def dump_lsh_data_to_pickle(bits_tid_pickle, lsh_pickle):
f = file(bits_tid_pickle, "rb")
data = pickle.load(f)
f.close()
# '10' means the bit binary (github.com/kayzh/LSHash)
lsh = LSHash(13, 10, 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 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}})
def plot_similar_tats_idx(idx: int,
feature_dict: dict,
lsh_variable: LSHash,
n_items: int = 6,
distance_func: str = 'hamming') -> plt.Figure:
"""Takes an input index for the training set and plots the closest matching tattoos to that input
tattoo.
Args:
idx : index to tattoo in the training set
feature_dict : wraps both image locations and feature vectors at the output of the cnn
before the final layer.
lsh_variable : trained lsh model to query the input image
n_items : number of items to return
distance_func : The distance function. Currently it needs to be one of ("hamming",
"euclidean", "true_euclidean", "centred_euclidean", "cosine", "l1norm"). By default
"hamming" will used.
Returns:
Matplotlib grid plot of the index image first and n other similar images.
"""
response = lsh_variable.query(feature_dict[list(
feature_dict.keys())[idx]].flatten(),
num_results=n_items + 1,
distance_func=distance_func)
return plot_similar_tats_query(response,
n_items=n_items + 1,
distance_func=distance_func)
def init_lsh(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,
args.u,
args.host,
random_dims,
1,
storage_config=args.s,
matrices_filename='project_plane.npz')
np_feature_vecs = load_features(args.f, args.v, nuse, d, lsh, args.e, off,
args.i)
return (lsh, np_feature_vecs)
def get_lshash(filename):
lsh = LSHash(30, 8)
try:
with open(filename) as f:
content = f.readlines()
content = [x.strip('\n') for x in content]
except Exception as e:
print("Cannot find the file.")
for row in content:
row = row.split(",")
row = list(map(int, row))
tmp = row[:8]
lsh.index(tmp, str(row[8]))
return lsh
def get_hash2img():
if os.path.exists(redis_rdb):
lsh = LSHash(hash_len, 960, storage_config=redis_config,
matrices_filename=matrices_file)
return lsh
else:
return create_hash2img()
def knn(data_array, data, hash_size_input, data_shape, vipno_pos, k):
# init LSHash
lsh = LSHash(hash_size=hash_size_input, input_dim=data_shape[0])
# index
for col_index in range(data_shape[1]):
lsh.index(data_array[:, col_index], extra_data=data.columns[col_index])
# calculate and output
result = []
for res in lsh.query(data_array[:, vipno_pos],
num_results=k + 1,
distance_func='euclidean'):
result.append(res[0][1])
return result[1:]
def lshTOfind(path):
lsh = LSHash(50,361)
f = open('newindex.csv')
index = csv.reader(f)
features = []
count = 0
for r in index:
features = [int(float(i)) for i in r[1:]]
lsh.index(features)
count += 1
try:
f_v = getfeatures(path)
ans = lsh.query(f_v)
if ans != []:
return searchid(int(ans[0][0][360]/10000))
except:
return []
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 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
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 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 classify_nearest_neighbor_lsh(k):
lsh = LSHash(3, 12)
labels = load_labels()
for genre, song_genres_ids in labels.groupby('category'):
print('Indexing genre: {}'.format(genre))
num_values = len(song_genres_ids.values)
for i in range(int(num_values / 2)):
val = song_genres_ids.values[i]
song_id = val[0]
song = pd.read_csv('song_data/training/{}'.format(song_id),
header=None)
for val in song.values:
lsh.index(val, extra_data=genre)
total_count = 0
match_count = 0
for genre, song_genres_ids in labels.groupby('category'):
print('Expected genre: {}'.format(genre))
num_values = len(song_genres_ids.values)
for i in range(int(num_values / 2), num_values):
val = song_genres_ids.values[i]
song_id = val[0]
song = pd.read_csv('song_data/training/{}'.format(song_id),
header=None)
genre_freqs = {}
split_song = np.array_split(song, 5,
axis=0) # Split song into sections
for s in split_song:
avg_song_val = np.mean(s) # Take average of each section
neighbours = lsh.query(avg_song_val, num_results=k)
for neighbour in neighbours:
genre = neighbour[0][1]
genre_freqs[genre] = genre_freqs.get(genre, 0) + 1
actual_genre = max(genre_freqs, key=genre_freqs.get)
print('Predicted genre: {}'.format(actual_genre))
total_count += 1
if genre == actual_genre:
match_count += 1
print('Matched {} out of {} songs: {}%'.format(
match_count, total_count, (match_count / total_count) * 100))
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 create_feature(train_image_dir, classes, net):
list_feature = list()
image_paths = list()
## Locality Sensitive Hashing
k = 10 # hash size
L = 5 # number of tables
d = 58 # Dimension of Feature vector
lsh = LSHash(hash_size=k, input_dim=d, num_hashtables=L)
for each_object in classes:
each_object_path = os.path.join(train_image_dir, each_object)
list_img = next(os.walk(each_object_path))[2]
print("hashing class: ", each_object, " which has: ", len(list_img))
for img in list_img:
image_path = os.path.join(each_object_path, img)
feature = get_feature_single_img(net, image_path)
image_paths.append(image_path)
list_feature.append(feature)
lsh.index(feature, extra_data=image_path)
return lsh, image_paths, list_feature
def index_room():
'''
lsh算法索引图片特征
:return:
'''
files = glob("./data/features/*.csv")
files_ids = [
filename.split("\\")[-1].replace(".csv", "") for filename in files
]
X = np.load("data/train.npy")
X = X.reshape(X.shape[0], -1)
encoder = load_model("data/encoder.h5")
dimension = 100
lsh_hash = LSHash(hash_size=32, input_dim=dimension)
compress_feature = encoder.predict(X)
for num, ele in enumerate(compress_feature.tolist()):
lsh_hash.index(ele, extra_data=files_ids[num])
with open("data/lsh.pkl", "wb") as fh:
pickle.dump(lsh_hash, fh)
def test_lshash(self):
lsh = LSHash(self.hash_size, self.input_dim, 1)
for i in range(self.nb_elements):
lsh.index(list(self.els[i]))
lsh.index(list(self.els[i])) # multiple insertions
hasht = lsh.hash_tables[0]
itms = [hasht.get_list(k) for k in hasht.keys()]
for itm in itms:
self.assertEqual(itms.count(itm), 1)
for el in itm:
self.assertIn(el, self.els)
for el in self.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
self.assertIn(el_v, self.els)
self.assertEqual(el_dist, 0)
del 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 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
count = 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=5, distance_func="cosine")
#print result
#no similar tweets
count += 1
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 count,
#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 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 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
def lshTOfind(path):
lsh = LSHash(10, 360)
f = open('copyindex.csv')
index = csv.reader(f)
features = []
count = 0
for r in index:
features = [float(i) for i in r[1:]]
lsh.index(features[:360], features[360])
count += 1
try:
f_v = getfeatures(path)
#print f_v
ans = lsh.query(f_v[:360], 15)
if ans != []:
res = []
for i in ans:
res.append(int(i[0][1] / 10000))
return res
#searchid(int(ans[0][0][360]/10000))
except:
return []
def subEventDetection(dictionaryFile, corpusFile, outputFile):
outputVector = []
tempDict = {}
corpus = corpora.MmCorpus(corpusFile)
dictionary = corpora.Dictionary.load(dictionaryFile)
lsh = LSHash(30, dictionary.__len__())
index = 0
for index in range(len(corpus)):
denseVector = getDenseVector(corpus[index], lsh.input_dim)
result = lsh.query(denseVector, num_results = 50, distance_func = "cosine")
#no similar tweets
if(result == []):
outputVector.append([index])
continue
assigned = False
for vector in result:
if(getDistance(vector, denseVector) == True):
for ind in range(len(outputVector)):
done = False
for tweetNo in outputVector[ind]:
if (tweetNo == tempDict[vector]):
outputVector[ind].append(index)
done = True
break
if done == True:
break
assigned = True
break
if assiged == False:
outputVector.append([index])
lsh.index(denseVector)
tempDict[tuple(denseVector)] = index
with open(outputFile, 'w') as out:
for vector in outputVector:
line = ""
for index in vector:
line += ", " + str(index)
out.write(line[2:]+"\n")
print "Please check the output file:", outputFile
class Searcher:
_DIST_FUNCTIONS = ["hamming", "euclidean", "true_euclidean", "centred_euclidean", "cosine", "l1norm"]
index = None
def __init__(self, dataset):
self.create_index(dataset)
def create_index(self, items, hash_size=6):
input_dim = len(items.values()[0])
self.index = LSHash(hash_size, input_dim)
for key in items:
self.index.index(items[key], extra_data=key)
return True
def query(self, query_item, num_results=10, distance_function='cosine'):
if distance_function not in self._DIST_FUNCTIONS:
raise Exception("{0} not supported".format(distance_function))
results = self.index.query(query_item, num_results=num_results, distance_func=distance_function)
return self.parse_results(results)
def parse_results(self, results):
return {x[0][1]:x[1] for x in results}
def eventIdentification(dictionaryFile, corpusFile, outputFile):
outputVector = []
tempDict = {}
corpus = corpora.MmCorpus(corpusFile)
dictionary = corpora.Dictionary.load(dictionaryFile)
#print "Unique Tokens:", dictionary.__len__()
lsh = LSHash(20, dictionary.__len__())
index = 0
for index in range(len(corpus)):
denseVector = getDenseVector(corpus[index], lsh.input_dim)
result = lsh.query(denseVector)
#print denseVector
#no similar tweets
if(result == []):
#print "No Similar Tweets for: ", index
tempDict[tuple(denseVector)] = len(outputVector)
outputVector.append([index])
lsh.index(denseVector)
continue
assigned = False
for vector in result:
if(getDistance(vector, denseVector) == True):
ev = tempDict[tuple(vector[0])]
outputVector[ev].append(index)
tempDict[tuple(denseVector)] = ev
#for ind in range(len(outputVector)):
#done = False
#for tweetNo in outputVector[ind]:
#if (tweetNo == tempDict[tuple(vector[0])]):
#outputVector[ind].append(index)
#done = True
#break
#if done == True:
#break
assigned = True
break
if assigned == False:
tempDict[tuple(denseVector)] = len(outputVector)
outputVector.append([index])
lsh.index(denseVector)
with open(outputFile, 'w') as out:
for vector in outputVector:
line = ""
for index in vector:
line += "," + str(index)
out.write(line[1:]+"\n")
del outputVector
del tempDict
def test():
import utils
trueIds, testSet = utils.load_test_set('fc7', 'raw', 0)
lsh = LSHash(128, np.shape(testSet[0])[0], matrices_filename='lsh_planes.data.npz', overwrite=True)
for idx, input_point in enumerate(testSet):
hastValue = lsh._hash(lsh.uniform_planes[0], input_point.tolist())
print hastValue
lsh.index(input_point, idx)
print lsh.query(testSet[3], 3)
return None
def initialize_store(self, parameters): self.store = LSHash(parameters['hash_size'], parameters['input_dim'], parameters['num_of_hashtables'], parameters['storage'])
def run():
initial = True
size = 2000
tweet_ids = []
tweet_text = []
counter = 0
num_hashtables = 13 ## recompute the random vectors if this is changed
dimension = 50000 ## recompute the random vectors if this is changed
hash_size = 13 ## length of the LSHash of the tweets
bucket_size = 100 ## size of the queue for each hash in the hash tables
comparisons = 50 ## upper bound on the number of comparisons (dot product) to find the nearest neighbor
cos_threshold = .7 ## threshold for the similarity of two tweets
## initialize the tf-idf vectorizer
vectorizer = onlineTfidfVectorizer(min_df = 1, smooth_idf=True, stop_words='english', min_dict_size = dimension)
## initialize the hash tables, specify the hash size, number of hash tabeles and the queue size
lsh = LSHash(hash_size = hash_size, input_dim = dimension, num_hashtables=num_hashtables, max_queue_size= bucket_size)
clusters = {} ## maintain the clusters
num_clusters = 0
inv_index = {} ## inverse mapping from tweet_id to clusters
Y = None
Y1 = None
f_d = open("output.txt",'w')
loc = "/Users/dilpreet/Documents/mtp_documents/markedData/data/"
for root, dirs, filenames in os.walk(loc):
for f in filenames:
with open(loc+f) as infile:
for line in infile:
## load 2000 tweets at a time
tweet = json.loads(line)
tweet_ids.append(tweet['id'])
tweet_text.append(tweet['text'])
counter = counter + 1
t2 = 0
if counter%size == 0:
t1 = time.clock()
## X contains te tf-idf score of the tweets in the "sparse row matrix" format
if initial:
X = vectorizer.fit_transform(tweet_text)
else:
X = vectorizer.transform(tweet_text)
print X.get_shape()
print len(vectorizer.vocabulary_)
## if the total number of keywords exceed the pre-specified dimension, raise error
if X.get_shape()[0] > dimension:
print X.get_shape()
print "dimension exceeded"
raise
for i in range(X.get_shape()[0]):
temp_tweet = X.getrow(i)
## query for the nearest neighbor from the lshash tables
nn = lsh.arpoxNN(temp_tweet, L=comparisons)
c = 2
scase = False
## if nearesr neighbor is not null and the cosine similarity is less than the threshold, add the tweet to the respective cluster
if nn is not None:
((a, b),c) = nn
if c <= cos_threshold:
inv_index[tweet_ids[i]] = inv_index[b]
clusters.setdefault(inv_index[b],[]).append(tweet_ids[i])
#else:
# scase = True
## else, linearly search through the previous 2000 + i tweets to find the nearest neighbor
""" code to linearly search through the tweets"""
if (c > cos_threshold or nn is None or scase):
searchY = False
if (i==0 and not initial):
searchY = True
if (i==0 and initial):
inv_index[tweet_ids[i]] = num_clusters
clusters.setdefault(num_clusters, []).append(tweet_ids[i])
num_clusters = num_clusters + 1
if (i!=0):
Z = X[:i]
#print temp_tweet.shape
t2 = temp_tweet.transpose()
#print i
a1 = Z.dot(t2).toarray()
a2 = Z.multiply(Z).sum(axis = 1)
a3 = sp.csr_matrix(t2.multiply(t2).sum()).toarray()
a2 = sp.csc_matrix(a2).toarray()
b = [j for j in range(Z.shape[0])]
a = min(b, key = lambda x: 1-float(a1[x][0])/((a2[x][0] + a3[0][0])**.5))
#a = min(Z, key = lambda x: cosine_dist(x[0], temp_tweet))
#print a
t3 = tweet_ids[a]
if (1-float(a1[a][0])/((a2[a][0] + a3[0][0])**.5))> cos_threshold:
if not initial and i != size-1:
searchY = True
else:
inv_index[tweet_ids[i]] = num_clusters
clusters.setdefault(num_clusters, []).append(tweet_ids[i])
num_clusters = num_clusters + 1
else:
inv_index[tweet_ids[i]] = inv_index[t3]
clusters.setdefault(inv_index[t3], []).append(tweet_ids[i])
if searchY == True:
Z = Y[i:]
t2 = temp_tweet.transpose()
#print i
a1 = Z.dot(t2).toarray()
a2 = Z.multiply(Z).sum(axis = 1)
a3 = sp.csr_matrix(t2.multiply(t2).sum()).toarray()
a2 = sp.csc_matrix(a2).toarray()
b1 = [j for j in range(Z.shape[0])]
a = min(b1, key = lambda x: 1-float(a1[x][0])/((a2[x][0] + a3[0][0])**.5))
t3 = Y1[a + i]
if (1-float(a1[a][0])/((a2[a][0] + a3[0][0])**.5))< cos_threshold:
inv_index[tweet_ids[i]] = inv_index[t3]
else:
inv_index[tweet_ids[i]] = num_clusters
clusters.setdefault(num_clusters, []).append(tweet_ids[i])
num_clusters = num_clusters + 1
### index the tweet into the hsh tables
lsh.index(input_point = temp_tweet, extra_data = tweet_ids[i])
initial = False
Y = X
Y1 = tweet_ids[:]
tweet_ids = []
tweet_text = []
print counter
print time.clock() - t1
f2 = open('time.txt','a')
f2.write(str(time.clock()-t1) + '\n')
f2.close()
if counter%10000==0:
f2 = open('result.txt', 'a')
f2.write(json.dumps(clusters) + "\n")
f3 = open('vocab.txt', 'a')
f4 = open('vectorizer.txt', 'a')
f3.write(json.dumps(vectorizer.vocabulary_) + "\n")
f4.write(json.dumps(vectorizer.idf_) + "\n")
#print clusters
#print vectorizer.vocabulary_
f2.close()
f3.close()
f4.close()
f2 = open('result.txt', 'w')
f2.write(json.dumps(clusters) + "\n")
f3 = open('vocab.txt', 'w')
f4 = open('vectorizer.txt', 'w')
f5 = open('inv_index.txt', 'w')
f3.write(json.dumps(vectorizer.vocabulary_) + "\n")
f4.write(json.dumps(vectorizer.idf_) + "\n")
f5.write(json.dumps(inv_index))
#print clusters
#print vectorizer.vocabulary_
f2.close()
f3.close()
f4.close()
f5.close()
numberRadius = 55
usedDataset = 'CVRR_dataset_trajectory_clustering\i5sim3.mat'
runtime = str(dt.datetime.now().timetuple()[1])+str(dt.datetime.now().timetuple()[2])+str(dt.datetime.now().timetuple()[3])+str(dt.datetime.now().timetuple()[4])
fileContainer = open('Pointwise LSH Classification Experiment ('+usedDataset[35:-4]+') at '+runtime+' HFs_'+ str(numberHFs)+'_R_'+str(numberRadius), 'a')
fileContainer.write('\n')
fileContainer.write('Welcome to our experiment : ')
fileContainer.write(str( '\nSTRATING TIME : '+ time.asctime( time.localtime(time.time()) )))
print str( '\nSTRATING TIME : '+ time.asctime( time.localtime(time.time()) ))
fileContainer.write('\n')
fileContainer.write('The discription needed for each result will be provided accordingly .....')
fileContainer.write('\n')
fileContainer.write('The used Dataset is : '+usedDataset)
fileContainer.write('\n')
print '\nStarting LSH initialization ...'
fileContainer.write(str( '\nTime before LSH initialization : '+ time.asctime( time.localtime(time.time()) )))
newLsh = LSHash(numberHFs, dimensionNumber, num_hashtables = 1)
fileContainer.write(str( '\nTime after LSH initialization : '+ time.asctime( time.localtime(time.time()) )))
print '\nStarting loading the trajectory dataset ...'
fileContainer.write(str( '\nTime before loading the trajectory dataset : '+ time.asctime( time.localtime(time.time()) )))
#------------------------------------------------------------------------------
# The Trajectory dataset - I5SIM3
#------------------------------------------------------------------------------
mat = scipy.io.loadmat(usedDataset)
datasetSize = len(mat.values()[0])
trajectoriesContainer = []
for i in range(datasetSize):
trajectoriesContainer.append([(mat.values()[0][i][0][0][j], mat.values()[0][i][0][1][j]) for j in range(len(mat.values()[0][i][0][0]))])
allPoints = []
fileContainer.write(str( '\nTime after loading trajectory dataset : '+ time.asctime( time.localtime(time.time()) )))
#------------------------------------------------------------------------------
pv = pv - np.median(pv)
#filtered = del_outlier_pitches(pv.copy())
#adjusted = filtered - filtered.mean()
pv = note_segment(pv)
for x in sliding_window(pv,ws=10):
note = x
loc = np.isnan(note)
note[loc] = 0
yield note,file
if __name__ == '__main__':
from lshash import LSHash
hash_len = 10
dm = 10
lsh = LSHash(hash_len, dm)
mid1 = '00001.mid'
mid2 = '00002.mid'
mid3 = '00003.mid'
mid4 = '00004.mid'
mid5 = '00005.mid'
mid6 = '00006.mid'
mid7 = '00007.mid'
mid8 = '00008.mid'
mid9 = '00009.mid'
mid10 = '00010.mid'
mid11 = '00011.mid'
mid12 = '00012.mid'
mid13 = '00013.mid'
mid14 = '00014.mid'
from lshash import LSHash
lsh = LSHash(hash_size=6, input_dim=8, num_hashtables=1, storage_config={"lmdb": {'path': '/Users/christianburger/Downloads/testlmdb'}})
lsh.index([1,2,3,4,5,6,7,8], 'a')
lsh.index([2,3,4,5,6,7,8,9], 'b')
lsh.index([10,12,99,1,5,31,2,3], 'c')
print lsh.query([1,2,3,4,5,6,7,7])
from lshash import LSHash import numpy as np s = LSHash(10, 8) s.index([1,2,3,4,5,6,7,8]) print s.hash_tables[0].keys()[0]
from __future__ import print_function
from __future__ import division
from scipy.spatial.distance import cosine
from tqdm import tqdm
import numpy
from lshash import LSHash
import time
start = time.time()
lsh = LSHash(8, 300)
sample_word_embeds = []
for i in tqdm(xrange(20000)):
word_embed = numpy.random.rand(300)
lsh.index(word_embed)
if i % 500 == 0:
sample_word_embeds.append(word_embed)
print("Indexing takes {} seconds".format(time.time() - start))
start = time.time()
for word_embed in sample_word_embeds:
print('-' * 80)
results = lsh.query(word_embed, num_results=None, distance_func='cosine')
print("Num result: {}".format(len(results)))
print('Nearest neighbor cosine distance:')
print(" {} | {}".format(results[1][1], cosine(results[1][0], word_embed)))
print('Query takes average {} seconds'.format((time.time() - start) / len(sample_word_embeds)))
# numberHFs = 25
# numberRadius = 151
usedDataset = 'CVRR_dataset_trajectory_clustering\labomni.mat'
fileContainer = open('Pointwise LSH Clustering SegDiff'+str(segment)+'Overlap Experiment ('+usedDataset[35:-4]+')', 'a')
fileContainer.write('\n')
fileContainer.write('Welcome to our experiment : -Segmentation more segments with Overlapping-'+' HFs_'+ str(numberHFs)+'_R_'+str(numberRadius))
fileContainer.write(str( '\nSTRATING TIME : '+ time.asctime( time.localtime(time.time()) )))
print str( '\nSTRATING TIME : '+ time.asctime( time.localtime(time.time()) ))
fileContainer.write('\n')
fileContainer.write('The discription needed for each result will be provided accordingly .....')
fileContainer.write('\n')
fileContainer.write('The used Dataset is : '+usedDataset)
fileContainer.write('\n')
print '\nStarting LSH initialization ...'
fileContainer.write(str( '\nTime before LSH initialization : '+ time.asctime( time.localtime(time.time()) )))
newLsh = LSHash(numberHFs, dimensionNumber, num_hashtables = 1)
fileContainer.write(str( '\nTime after LSH initialization : '+ time.asctime( time.localtime(time.time()) )))
print '\nStarting loading the trajectory dataset ...'
fileContainer.write(str( '\nTime before loading the trajectory dataset : '+ time.asctime( time.localtime(time.time()) )))
#------------------------------------------------------------------------------
# The Trajectory dataset - LABOMNI
#------------------------------------------------------------------------------
mat = scipy.io.loadmat(usedDataset)
datasetSize = len(mat.values()[0])
trajectoriesContainer = []
for i in range(datasetSize):
trajectoriesContainer.append([(mat.values()[0][i][0][0][j], mat.values()[0][i][0][1][j]) for j in range(len(mat.values()[0][i][0][0]))])
allPoints = []
fileContainer.write(str( '\nTime after loading trajectory dataset : '+ time.asctime( time.localtime(time.time()) )))
#------------------------------------------------------------------------------
numberHFs = 25
numberRadius = 251
usedDataset = 'CVRR_dataset_trajectory_clustering/cross.mat'
fileContainer = open('Pointwise LSH Clustering Experiment -ROUND-100- ('+usedDataset[35:-4]+') HFs_'+ str(numberHFs)+'_R_'+str(numberRadius), 'a')
fileContainer.write('\n')
fileContainer.write('Welcome to our experiment : ')
fileContainer.write(str( '\nSTRATING TIME : '+ time.asctime( time.localtime(time.time()) )))
print str( '\nSTRATING TIME : '+ time.asctime( time.localtime(time.time()) ))
fileContainer.write('\n')
fileContainer.write('The discription needed for each result will be provided accordingly .....')
fileContainer.write('\n')
fileContainer.write('The used Dataset is : '+usedDataset)
fileContainer.write('\n')
print '\nStarting LSH initialization ...'
fileContainer.write(str( '\nTime before LSH initialization : '+ time.asctime( time.localtime(time.time()) )))
newLsh = LSHash(numberHFs, dimensionNumber, num_hashtables = 1)
fileContainer.write(str( '\nTime after LSH initialization : '+ time.asctime( time.localtime(time.time()) )))
print '\nStarting loading the trajectory dataset ...'
fileContainer.write(str( '\nTime before loading the trajectory dataset : '+ time.asctime( time.localtime(time.time()) )))
#------------------------------------------------------------------------------
# The Trajectory dataset - cross
#------------------------------------------------------------------------------
mat = scipy.io.loadmat(usedDataset)
datasetSize = len(mat.values()[0])
trajectoriesContainer = []
for i in range(datasetSize):
trajectoriesContainer.append([(mat.values()[0][i][0][0][j], mat.values()[0][i][0][1][j]) for j in range(len(mat.values()[0][i][0][0]))])
allPoints = []
fileContainer.write(str( '\nTime after loading trajectory dataset : '+ time.asctime( time.localtime(time.time()) )))
#------------------------------------------------------------------------------
def main():
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).')
parser.add_argument('-u', default = 'local', help = 'CUDA client type (local, net).')
parser.add_argument('-host', default = 'localhost', help = 'CUDA server address.')
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, args.u, args.host, random_dims, 1, storage_config = args.s, matrices_filename = 'project_plane.npz')
np_feature_vecs = load_features(args.f, args.v, nuse, d, lsh, args.e, off, args.i)
if args.c == 'y':
if args.e != None and args.s == 'random':
lsh.load_index(args.e)
print "compressing index..."
lsh.compress_index(args.e)
print "compressing done."
else:
print "Please specify generated indexing file."
sys.exit(0)
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."
if args.p != 'y':
retrived = lsh.query(np_feature_vecs[1], num_results = int(args.k), expand_level = int(args.b), distance_func = 'hamming')
else:
retrived = lsh.query_in_compressed_domain(np_feature_vecs[1], num_results = int(args.k), expand_level = int(args.b), distance_func = 'hamming', gpu_mode = args.g, vlq_mode = args.l)
print retrived
start_rowx=1
#First_cs = ord(u'\u4e00')
#Last_cs = ord(u'\ufaff')
jieba.initialize()
Index = dict(zip(jieba.FREQ.keys(), range(len(jieba.FREQ))))
dim = len(Index) + 1 # -1 for excluded
data = xlrd.open_workbook(fname)
sht = data.sheet_by_name(shtname)
head = sht.row_values(0)
tweets = sht.col_values(head.index(target), start_rowx)
hash_size = int(np.ceil(np.log2(len(tweets))))
print 'hash_size: %d, dim: %d' %(hash_size, dim)
lsh=LSHash(hash_size, dim)
for tweet in tweets:
x = spar.csr_matrix((1,dim) ,dtype=np.int8)
# x = np.zeros(dim, np.bool8)
ws = jieba.cut(tweet)
try:
for w in ws:
x[Index.get(w, -1)] = 1
lsh.index(x)
except Exception, e:
print e
print tweet
sent = True
while sent:
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
