Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import timeit
- def main():
- import h5py, cyrandom
- allchr = "".join((chr(i) for i in range(33,127)))
- pspool = [[cyrandom.choice(allchr) for _ in range(cyrandom.randint(10, 100))] for x in range(100000)]
- chunkl = []
- for _ in range(5000000):
- b1 = cyrandom.choice(pspool)
- cyrandom.shuffle(b1)
- chunkl.append(''.join(b1).encode('utf-8'))
- f = h5py.File('h5.h5','w')
- for k in range(50000000//5000000):
- l = [str(k).encode('utf-8')]
- # cyrandom.shuffle(chunkl)
- print(k)
- f.create_dataset(str(k), data=chunkl+l,)
- del chunkl
- f.close()
- def query():
- import h5py
- f = h5py.File('h5.h5','a')
- wbw = set(f['0'].value)
- count = []
- for k in f.keys():
- print(k)
- for x in f[k].value:
- if x not in wbw:
- count.append(x)
- print(count)
- f.close()
- print(timeit.timeit(main, number=1))
- print(timeit.timeit(query, number=1))
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement