def check_correctness():
N = 10**4
thirds = [ak.cast(ak.arange(i, N*3, 3), 'str') for i in range(3)]
thickrange = thirds[0].stick(thirds[1], delimiter='_').stick(thirds[2], delimiter='_')
answer = ak.cast(ak.arange(N*3), 'str')
assert (thickrange.flatten('_') == answer).all()
assert (thickrange.flatten('_', regex=True) == answer).all()
assert (thickrange.flatten('_+', regex=True) == answer).all()
def time_flatten(N, trials):
print(">>> arkouda flatten")
cfg = ak.get_config()
print("numLocales = {}, N = {:,}".format(cfg["numLocales"], N))
thirds = [ak.cast(ak.arange(i, N*3, 3), 'str') for i in range(3)]
thickrange = thirds[0].stick(thirds[1], delimiter='_').stick(thirds[2], delimiter='_')
nbytes = thickrange.nbytes * thickrange.entry.itemsize
non_regex_times = []
regex_literal_times = []
regex_pattern_times = []
for i in range(trials):
start = time.time()
non_regex = thickrange.flatten('_')
end = time.time()
non_regex_times.append(end - start)
start = time.time()
regex_literal = thickrange.flatten('_', regex=True)
end = time.time()
regex_literal_times.append(end - start)
start = time.time()
regex_pattern = thickrange.flatten('_+', regex=True)
end = time.time()
regex_pattern_times.append(end - start)
avg_non_regex = sum(non_regex_times) / trials
avg_regex_literal = sum(regex_literal_times) / trials
avg_regex_pattern = sum(regex_pattern_times) / trials
answer = ak.cast(ak.arange(N*3), 'str')
assert (non_regex == answer).all()
assert (regex_literal == answer).all()
assert (regex_pattern == answer).all()
print("non-regex flatten with literal delimiter Average time = {:.4f} sec".format(avg_non_regex))
print("regex flatten with literal delimiter Average time = {:.4f} sec".format(avg_regex_literal))
print("regex flatten with pattern delimiter Average time = {:.4f} sec".format(avg_regex_pattern))
print("non-regex flatten with literal delimiter Average rate = {:.4f} GiB/sec".format(nbytes/2**30/avg_non_regex))
print("regex flatten with literal delimiter Average rate = {:.4f} GiB/sec".format(nbytes/2**30/avg_regex_literal))
print("regex flatten with pattern delimiter Average rate = {:.4f} GiB/sec".format(nbytes/2**30/avg_regex_pattern))
def power_law(N):
'''
Power law distributed (alpha = 2.5) reals and integers in (1, 2**32)
'''
y = ak.uniform(N)
a = -2.5 # power law exponent, between -2 and -3
ub = 2**32 # upper bound
data = ((ub**(a + 1) - 1) * y + 1)**(1 / (a + 1))
yield 'power-law float64', data
datai = ak.cast(data, ak.int64)
yield 'power-law int64', datai
def check_correctness(dtype, seed):
N = 10**4
if dtype == 'int64':
a = ak.randint(0, 2**32, N, seed=seed)
z = ak.zeros(N, dtype=dtype)
elif dtype == 'float64':
a = ak.randint(0, 1, N, dtype=ak.float64, seed=seed)
z = ak.zeros(N, dtype=dtype)
elif dtype == 'str':
a = ak.random_strings_uniform(1, 16, N, seed=seed)
z = ak.cast(ak.zeros(N), 'str')
perm = ak.coargsort([a, z])
if dtype in ('int64', 'float64'):
assert ak.is_sorted(a[perm])
perm = ak.coargsort([z, a])
if dtype in ('int64', 'float64'):
assert ak.is_sorted(a[perm])
def time_ak_gather(isize, vsize, trials, dtype, random, seed):
print(">>> arkouda {} gather".format(dtype))
cfg = ak.get_config()
Ni = isize * cfg["numLocales"]
Nv = vsize * cfg["numLocales"]
print("numLocales = {}, num_indices = {:,} ; num_values = {:,}".format(cfg["numLocales"], Ni, Nv))
# Index vector is always random
i = ak.randint(0, Nv, Ni, seed=seed)
if seed is not None:
seed += 1
if random or seed is not None:
if dtype == 'int64':
v = ak.randint(0, 2**32, Nv, seed=seed)
elif dtype == 'float64':
v = ak.randint(0, 1, Nv, dtype=ak.float64, seed=seed)
elif dtype == 'bool':
v = ak.randint(0, 1, Nv, dtype=ak.bool, seed=seed)
elif dtype == 'str':
v = ak.random_strings_uniform(1, 16, Nv, seed=seed)
else:
if dtype == 'str':
v = ak.cast(ak.arange(Nv), 'str')
else:
v = ak.ones(Nv, dtype=dtype)
timings = []
for _ in range(trials):
start = time.time()
c = v[i]
end = time.time()
timings.append(end - start)
tavg = sum(timings) / trials
print("Average time = {:.4f} sec".format(tavg))
if dtype == 'str':
offsets_transferred = 3 * c.offsets.size * c.offsets.itemsize
bytes_transferred = (c.offsets.size * c.offsets.itemsize) + (2 * c.bytes.size)
bytes_per_sec = (offsets_transferred + bytes_transferred) / tavg
else:
bytes_per_sec = (c.size * c.itemsize * 3) / tavg
print("Average rate = {:.2f} GiB/sec".format(bytes_per_sec/2**30))
