SimpleJSON and NumPy array

Question

What is the most efficient way of serializing a numpy array using simplejson?

Answer 1

If you want to apply Russ's method to n-dimensional numpy arrays you can try this

class NumpyAwareJSONEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, numpy.ndarray):
            if obj.ndim == 1:
                return obj.tolist()
            else:
                return [self.default(obj[i]) for i in range(obj.shape[0])]
        return json.JSONEncoder.default(self, obj)

This will simply turn a n-dimensional array into a list of lists with depth "n". To cast such lists back into a numpy array, my_nparray = numpy.array(my_list) will work regardless of the list "depth".

Answer 2

In order to keep dtype and dimension try this:

import base64
import json
import numpy as np

class NumpyEncoder(json.JSONEncoder):

    def default(self, obj):
        """If input object is an ndarray it will be converted into a dict 
        holding dtype, shape and the data, base64 encoded.
        """
        if isinstance(obj, np.ndarray):
            if obj.flags['C_CONTIGUOUS']:
                obj_data = obj.data
            else:
                cont_obj = np.ascontiguousarray(obj)
                assert(cont_obj.flags['C_CONTIGUOUS'])
                obj_data = cont_obj.data
            data_b64 = base64.b64encode(obj_data)
            return dict(__ndarray__=data_b64,
                        dtype=str(obj.dtype),
                        shape=obj.shape)
        # Let the base class default method raise the TypeError
        super(NumpyEncoder, self).default(obj)


def json_numpy_obj_hook(dct):
    """Decodes a previously encoded numpy ndarray with proper shape and dtype.

    :param dct: (dict) json encoded ndarray
    :return: (ndarray) if input was an encoded ndarray
    """
    if isinstance(dct, dict) and '__ndarray__' in dct:
        data = base64.b64decode(dct['__ndarray__'])
        return np.frombuffer(data, dct['dtype']).reshape(dct['shape'])
    return dct

expected = np.arange(100, dtype=np.float)
dumped = json.dumps(expected, cls=NumpyEncoder)
result = json.loads(dumped, object_hook=json_numpy_obj_hook)


# None of the following assertions will be broken.
assert result.dtype == expected.dtype, "Wrong Type"
assert result.shape == expected.shape, "Wrong Shape"
assert np.allclose(expected, result), "Wrong Values"

Answer 3

Improving On Russ's answer, I would also include the np.generic scalars:

class NumpyAwareJSONEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, np.ndarray) and obj.ndim == 1:
                return obj.tolist()
        elif isinstance(obj, np.generic):
            return obj.item()
        return json.JSONEncoder.default(self, obj)