def test_generator(self):
dim = 1000
active = 666
gen = ri.Generator(dim=dim, num_active=active)
ri1 = gen.generate()
self.assertEqual(len(ri1.negative), len(ri1.negative))
self.assertEqual(len(ri1.positive), gen.num_active // 2)
v1 = ri1.to_vector()
self.assertEqual(len(v1), dim)
self.assertEqual(v1.max(), 1)
self.assertEqual(v1.min(), -1)
self.assertEqual(v1.sum(), 0)
vectors = [gen.generate().to_vector() for x in range(0, 18)]
t0 = time.time()
for i in range(999):
v = gen.generate()
t1 = time.time()
print("time to generate: ", t1 - t0)
def test_to_dist_vector(self):
dim = 10
active = 4
gen = ri.Generator(dim=dim, num_active=active)
ri1 = gen.generate()
print(ri1)
dist_v1 = ri1.to_dist_vector()
print(dist_v1)
def test_rescale(self):
dim = 10
active = 4
gen = ri.Generator(dim=dim, num_active=active)
ri1 = gen.generate().to_vector()
ri2 = gen.generate().to_vector()
s = ri1 + ri1 + ri2
print(s)
print(s / np.max(s, axis=0))
def test_to_sparse(self):
dim = 100
active = 4
gen = ri.Generator(dim=dim, num_active=active)
index1 = gen.generate()
ri_v1 = index1.to_vector()
sparse_array = ri_to_sparse(index1)
self.assertEqual(len(sparse_array.active), active)
index2 = ri.ri_from_indexes(dim, sparse_array.active)
ri_v2 = index2.to_vector()
npt.assert_array_equal(ri_v1, ri_v2)
def test_svd(self):
dim = 500
active = 5
gen = ri.Generator(dim=dim, num_active=active)
num_samples = 100
c_matrix = np.matrix([gen.generate().to_vector() for i in range(num_samples)])
# c_matrix = np.matrix([ri_v / np.max(ri_v, axis=0) for ri_v in c_matrix])
print("Original: ", c_matrix.shape)
# perform svd
u, s, vt = np.linalg.svd(c_matrix, full_matrices=False)
print("Decomposition: ", (u.shape, np.diag(s).shape, vt.shape))
# reconstruct
r_matrix = np.dot(u, np.dot(np.diag(s), vt))
print("Re-Construction: ", r_matrix.shape)
self.assertTrue(np.allclose(c_matrix, r_matrix))
# low-rank approximation
k = 2
ru = u[:,:k]
rs = np.diag(s[:k])
rvt = vt[:k]
print("Low-Rank Decomposition: ", (ru.shape, rs.shape, rvt.shape))
lr_matrix = np.dot(ru, np.dot(rs, rvt))
print("Low-Rank Approximation Shape: ", lr_matrix.shape)
self.assertEqual(lr_matrix.shape, c_matrix.shape)
# dimensional reduction (just take u and s, since vocab_size is used to convert back to the original matrix)
ld_matrix = np.dot(ru,rs)
print("Lower-Dimensional Matrix: ", ld_matrix.shape)
import os.path
import h5py
import numpy as np
from deepsign.rp import ri
home = os.getenv("HOME")
result_path = home + "/data/results/"
ri_dim = 500
ri_active = 5
num_samples = 100
gen = ri.Generator(dim=ri_dim, num_active=ri_active)
c_matrix = np.matrix([gen.generate().to_vector() for i in range(num_samples)])
# write the matrix to hdf5 dataset
sample_word = "test".encode("utf8")
vocab = [sample_word] * num_samples
vocab = np.array(vocab)
counts = [1] * num_samples
counts = np.array(counts)
filename = "random_indexing_test.hdf5"
dataset_path = result_path + filename
print("writing to ", dataset_path)
dataset_name = "ri_d{0}_a{1}".format(ri_dim, ri_active)
print("dataset: " + dataset_name)