from cuckoovec import CuckooVector import numpy as np import string from ngrams import * vocab = [c for c in string.ascii_uppercase + string.ascii_lowercase] # letters n = 5 t = 2 # form random sparse vectors from <= t random words and weights def randsparse(t): return dict(zip(np.random.choice(vocab, t), np.random.randn(t))) s1 = [randsparse(t) for i in range(n)] s2 = [randsparse(t) for i in range(n)] t1 = ngrams(s1) print(t1) t2 = ngrams(s2) v1 = CuckooVector(t1) v2 = CuckooVector(t2) # these should be close to orthogonal. print(v1.dot(v2))
d = 10000000 # high dimension
t = 500000 # number of actual features
m1 = randsparse(d, t)
m2 = randsparse(d, t)
v1 = densify(m1, d)
v2 = densify(m2, d)
cv1 = CuckooVector(m1)
cv2 = CuckooVector(m2)
print("2-norms: ")
print(np.linalg.norm(v1))
print(cv1.norm(2))
print(np.linalg.norm(v2))
print(cv2.norm(2))
print("dots: ")
print(np.dot(v1,v2))
print(cv1.dot(cv2))
v1 = v1 + v2
cv1.add(cv2)
print("2-norm of sums: ")
print(np.linalg.norm(v1))
print(cv1.norm(2))
dist = 0
for k in set().union(m1, m2):
dist = dist + (abs(v1[int(k)] - cv1[k]))
print("1-distance between sums: ")
print(dist)
