How can I serialize a numpy array while preserving matrix dimensions?

Question

numpy.array.tostring doesn\'t seem to preserve information about matrix dimensions (see this question), requiring the user to issue a call to numpy.array.

Answer 1

I found the code in Msgpack-numpy helpful. https://github.com/lebedov/msgpack-numpy/blob/master/msgpack_numpy.py

I modified the serialised dict slightly and added base64 encoding to reduce the serialised size.

By using the same interface as json (providing load(s),dump(s)), you can provide a drop-in replacement for json serialisation.

This same logic can be extended to add any automatic non-trivial serialisation, such as datetime objects.

---

EDIT I've written a generic, modular, parser that does this and more. https://github.com/someones/jaweson

---

My code is as follows:

np_json.py

from json import *
import json
import numpy as np
import base64

def to_json(obj):
    if isinstance(obj, (np.ndarray, np.generic)):
        if isinstance(obj, np.ndarray):
            return {
                '__ndarray__': base64.b64encode(obj.tostring()),
                'dtype': obj.dtype.str,
                'shape': obj.shape,
            }
        elif isinstance(obj, (np.bool_, np.number)):
            return {
                '__npgeneric__': base64.b64encode(obj.tostring()),
                'dtype': obj.dtype.str,
            }
    if isinstance(obj, set):
        return {'__set__': list(obj)}
    if isinstance(obj, tuple):
        return {'__tuple__': list(obj)}
    if isinstance(obj, complex):
        return {'__complex__': obj.__repr__()}

    # Let the base class default method raise the TypeError
    raise TypeError('Unable to serialise object of type {}'.format(type(obj)))


def from_json(obj):
    # check for numpy
    if isinstance(obj, dict):
        if '__ndarray__' in obj:
            return np.fromstring(
                base64.b64decode(obj['__ndarray__']),
                dtype=np.dtype(obj['dtype'])
            ).reshape(obj['shape'])
        if '__npgeneric__' in obj:
            return np.fromstring(
                base64.b64decode(obj['__npgeneric__']),
                dtype=np.dtype(obj['dtype'])
            )[0]
        if '__set__' in obj:
            return set(obj['__set__'])
        if '__tuple__' in obj:
            return tuple(obj['__tuple__'])
        if '__complex__' in obj:
            return complex(obj['__complex__'])

    return obj

# over-write the load(s)/dump(s) functions
def load(*args, **kwargs):
    kwargs['object_hook'] = from_json
    return json.load(*args, **kwargs)


def loads(*args, **kwargs):
    kwargs['object_hook'] = from_json
    return json.loads(*args, **kwargs)


def dump(*args, **kwargs):
    kwargs['default'] = to_json
    return json.dump(*args, **kwargs)


def dumps(*args, **kwargs):
    kwargs['default'] = to_json
    return json.dumps(*args, **kwargs)

You should be able to then do the following:

import numpy as np
import np_json as json
np_data = np.zeros((10,10), dtype=np.float32)
new_data = json.loads(json.dumps(np_data))
assert (np_data == new_data).all()