Saving numpy array in mongodb

user_82159 0
Viewed 23713

I have a couple of MongoDB documents wherein one my the fields is best represented as a matrix (numpy array). I would like to save this document to MongoDB, how do I do this?

{
'name' : 'subject1',
'image_name' : 'blah/foo.png',
'feature1' : np.array(...)
}
mongodb nosql numpy python
6 Answers

I know this is an old question but here is an elegant solution which works in new versions of pymongo:

import pickle
from bson.binary import Binary, USER_DEFINED_SUBTYPE
from bson.codec_options import TypeCodec, TypeRegistry, CodecOptions
import numpy as np

class NumpyCodec(TypeCodec):
    python_type = np.ndarray
    bson_type = Binary

    def transform_python(self, value):
        return Binary(pickle.loads(value), USER_DEFINED_SUBTYPE)

    def transform_bson(self, value):
        if value.subtype == USER_DEFINED_SUBTYPE:
            return pickle.dumps(value, protocol=2)
        return value

def get_codec_options():
    numpy_codec = NumpyCodec()
    type_registry = TypeRegistry([numpy_codec])
    codec_options = CodecOptions(type_registry=type_registry)
    return codec_options

def get_collection(name, db):
    codec_options = get_codec_options()
    return db.get_collection(name, codec_options=codec_options)

Then you can get you collection this way:

from pymongo import MongoClient
client = MongoClient()
db = client['my_db']
my_collection = get_collection('my_collection', db)

Afterwards, you just insert and find with Numpy arrays in your database transparently.

user_21171970
Related