Shuffle HDF5 dataset using h5py

Question

I have a large HDF5 file (~30GB) and I need to shuffle the entries (along the 0 axis) in each dataset. Looking through the h5py docs I wasn't able to find either randomAccess or shuffle functionality, but I'm hoping that I've missed something.

Is anyone familiar enough with HDF5 to think of a fast way to random shuffle the data?

Here is pseudocode of what I would implement with my limited knowledge:

for dataset in datasets:
    unshuffled = range(dataset.dims[0])
    while unshuffled.length != 0:
        if unshuffled.length <= 100:
            dataset[:unshuffled.length/2], dataset[unshuffled.length/2:] = dataset[unshuffled.length/2:], dataset[:unshuffled.length/2]
            break
        else:
            randomIndex1 = rand(unshuffled.length - 100)
            randomIndex2 = rand(unshuffled.length - 100)

            unshuffled.removeRange(randomIndex1..<randomIndex1+100)
            unshuffled.removeRange(randomIndex2..<randomIndex2+100)

            dataset[randomIndex1:randomIndex1 + 100], dataset[randomIndex2:randomIndex2 + 100] = dataset[randomIndex2:randomIndex2 + 100], dataset[randomIndex1:randomIndex1 + 100]

Answer 1

You can use random.shuffle(dataset) . This takes a little more than 11 minutes for a 30 GB dataset on my laptop with a Core i5 processor, 8 GB of RAM, and a 256 GB SSD. See the following:

>>> import os
>>> import random
>>> import time
>>> import h5py
>>> import numpy as np
>>>
>>> h5f = h5py.File('example.h5', 'w')
>>> h5f.create_dataset('example', (40000, 256, 256, 3), dtype='float32')
>>> # set all values of each instance equal to its index
... for i, instance in enumerate(h5f['example']):
...     h5f['example'][i, ...] = \
...             np.ones(instance.shape, dtype='float32') * i
...
>>> # get file size in bytes
... file_size = os.path.getsize('example.h5')
>>> print('Size of example.h5: {:.3f} GB'.format(file_size/2.0**30))
Size of example.h5: 29.297 GB
>>> def shuffle_time():
...     t1 = time.time()
...     random.shuffle(h5f['example'])
...     t2 = time.time()
...     print('Time to shuffle: {:.3f} seconds'.format(str(t2 - t1)))
...
>>> print('Value of first 5 instances:\n{}'
...       ''.format(str(h5f['example'][:10, 0, 0, 0])))
Value of first 5 instances:
[ 0.  1.  2.  3.  4.]
>>> shuffle_time()
Time to shuffle: 673.848 seconds
>>> print('Value of first 5 instances after '
...       'shuffling:\n{}'.format(str(h5f['example'][:10, 0, 0, 0])))
Value of first 5 instances after shuffling:
[ 15733.  28530.   4234. 14869.  10267.]
>>> h5f.close()

Performance for shuffling several smaller datasets should not be worse than this.

Answer 2

this is my solution picture

input

def shuffle(*datas):
    import random
    for d in datas:
        random.seed(666)
        random.shuffle(d)
a = list(range(6))
b = list(range(6))
c = list(range(6))
shuffle(a,b,c)
a,b,c

output

([2, 0, 1, 4, 5, 3], [2, 0, 1, 4, 5, 3], [2, 0, 1, 4, 5, 3])

input

os.chdir("/usr/local/dataset/flicker25k/")
file = h5py.File("./FLICKR-25K.h5","r+")
print(os.path.getsize("./FLICKR-25K.h5"))
images = file['images']
labels = file['LAll']
tags = file['YAll']
shuffle(images,tags,labels)

output

executed in 27.9s, finished 22:49:53 2019-05-21
3320572656