def _test_random(self):
print 'Single Scan Random Sample algorithm'
for N in map(int, [10, 1e2, 1e3, 1e4, 1e5, 1e6]):
pr = PPReader('population.csv', 'dummy.csv', N=N)
# Read dummy files into buffer
start_time = time.time()
pr.init()
elapsed_time = time.time() - start_time
sys.stdout.write('init done: %f seconds taken.\t' % elapsed_time)
sys.stdout.flush()
# Actual test
start_time = time.time()
r = RandomSampling(dist_func, K=5)
r.sample(pr)
elapsed_time = time.time() - start_time
sampled = r.get_sampled()
sys.stdout.write('%d: %f\n' % (N, elapsed_time))
sys.stdout.flush()
def large_sample(self):
pr = PPReader('test_pp.csv', 'test_pp.csv')
return np.array([a for a in pr.itr()])