start_time = time.time()
d1 = 10
d2 = 80
P1 = 0.99
P2 = 0.01
p1 = (180 - d1) / 180
p2 = (180 - d2) / 180
# estimate b and r
def equations(p):
r, b = p
return (1 - P1 - (1 - p1**r)**b, 1 - P2 - (1 - p2**r)**b)
r1, b1 = fsolve(equations, (1, 1))
r1, b1 = int(r1), int(b1)
print("r = ", r1, ", b = ", b1)
lsh = LocalitySensitiveHashing(
datafile="data_for_lsh.csv",
dim=d,
r=r1,
b=b1,
)
lsh.get_data_from_csv()
lsh.initialize_hash_store()
lsh.hash_all_data()
print("--- %s seconds ---" % (time.time() - start_time))
similarity_neighborhoods = lsh.lsh_basic_for_nearest_neighbors()
