def fit(self, X):
X = X.astype(numpy.float32)
d = len(X[0])
self.m = findmean(X, d, 10)
X = isotropize(X, d, self.m)
hypercube_dim = int(numpy.log2(len(X))) - 2
self._index = Dolphinn(X, d, hypercube_dim)
def fit(self, X):
X = X.astype(numpy.float32)
d = len(X[0])
self.m = findmean(X, d, 10)
X = isotropize(X, d, self.m)
hypercube_dim = int(numpy.log2(len(X))) - 2
self._index = Dolphinn(X, d, hypercube_dim)
def fit(self, X):
if X.dtype != numpy.float32:
X = numpy.array(X, dtype=numpy.float32)
d = X.shape[1]
self.m = findmean(X, d, 10)
X = isotropize(X, d, self.m)
hypercube_dim = int(numpy.log2(len(X))) - 2
self._index = Dolphinn(X, d, hypercube_dim)
def fit(self, X):
if X.dtype != numpy.float32:
X = numpy.array(X, dtype=numpy.float32)
d = X.shape[1]
self.m = findmean(X, d, 10)
X = isotropize(X, d, self.m)
hypercube_dim = int(numpy.log2(len(X))) - 2
self._index = Dolphinn(X, d, hypercube_dim)
def query(self, v, n):
q = numpy.array([v])
q = isotropize(q, len(v), self.m)
res = self._index.queries(q, n, self.num_probes)
return res[0]
M = 1 ##########################
#READ FILES
#D1: data dimension, P: dataset
#D2: query dimension, Q: queryset
(D1, P) = fr.fvecs_read("siftsmall/siftsmall_base.fvecs")
(D2, Q) = fr.fvecs_read("siftsmall/siftsmall_query.fvecs")
if D1 != D2:
raise IOError("Data points and query points are of different dimension")
D = D1
#CHANGE OF ORIGIN
#find the mean of randomly sampled points
m = fr.findmean(P, D, 10)
#then consider this mean as the origin
P = fr.isotropize(P, D, m)
Q = fr.isotropize(Q, D, m)
K = int(np.log2(len(P))) - 2 ##########################
print "New dimension K=", K
#PREPROCESSING
tic = time.clock()
dol = Dolphinn(P, D, K)
toc = time.clock()
print "Preprocessing time: ", toc - tic
#QUERIES
tic = time.clock()
#assign keys to queries
solQ = dol.queries(Q, M, num_of_probes)
toc = time.clock()
def query(self, v, n):
q = numpy.array([v])
q = isotropize(q, len(v), self.m)
res = self._index.queries(q, n, self.num_probes)
return res[0]