def extract_features(self, x: CArray) -> CArray:
"""
Extract EMBER features
Parameters
----------
x : CArray
program sample
Returns
-------
CArray
EMBER features
"""
extractor = PEFeatureExtractor(2, print_feature_warning=False)
x_bytes = bytes(x.astype(np.int).tolist()[0])
features = CArray(
[np.array(extractor.feature_vector(x_bytes), dtype=np.float32)])
return features
def extract_features(self, x: CArray):
extractor = PEFeatureExtractor(2)
x_bytes = bytes(x.astype(np.int).tolist()[0])
features = CArray(
[np.array(extractor.feature_vector(x_bytes), dtype=np.float32)])
return features
def test_input_shape(self):
"""Test CArray.input_shape behavior."""
array = CArray([[[2, 3], [22, 33]], [[4, 5], [44, 55]]])
array_s = \
CArray([[[2, 3], [22, 33]], [[4, 5], [44, 55]]], tosparse=True)
ref_shape = (2, 2, 2)
# not propagate on getitem (as it returns new objects)
out = array[0:2, 0:2]
self.assertEqual(out.input_shape, out.shape)
out = array_s[0:2, 0:2]
self.assertEqual(out.input_shape, out.shape)
# not propagate on other generic methods (as they return new objects)
out = array.astype(float)
self.assertEqual(out.input_shape, out.shape)
out = array.unique()
self.assertEqual(out.input_shape, out.shape)
out = array.all(axis=0)
self.assertEqual(out.input_shape, out.shape)
# not propagate on classmethods (es. concatenate/append)
out = CArray.concatenate(array, array, axis=0)
self.assertEqual(out.input_shape, out.shape)
out = CArray.concatenate(array, array, axis=None)
self.assertEqual(out.input_shape, out.shape)
# should propagate on copy/deepcopy
from copy import copy, deepcopy
array_c = copy(array)
self.assertEqual(array_c.input_shape, ref_shape)
array_c = copy(array_s)
self.assertEqual(array_c.input_shape, ref_shape)
array_c = deepcopy(array)
self.assertEqual(array_c.input_shape, ref_shape)
array_c = deepcopy(array_s)
self.assertEqual(array_c.input_shape, ref_shape)
array_c = array.deepcopy()
self.assertEqual(array_c.input_shape, ref_shape)
array_c = array_s.deepcopy()
self.assertEqual(array_c.input_shape, ref_shape)
# should propagate on setitem
array_c = array.deepcopy()
array_c[0:2, 0:2] = 200
self.assertEqual(array_c.input_shape, ref_shape)
array_c = array.deepcopy()
array_c[0:2, 0:2] = CArray([[100, 200], [300, 400]])
self.assertEqual(array_c.input_shape, ref_shape)
array_c = array_s.deepcopy()
array_c[0:2, 0:2] = CArray([[100, 200], [300, 400]])
self.assertEqual(array_c.input_shape, ref_shape)
# should propagate on todense/tosparse
self.assertEqual(array.tosparse().input_shape, ref_shape)
self.assertEqual(array.todense().input_shape, ref_shape)
self.assertEqual(array_s.tosparse().input_shape, ref_shape)
self.assertEqual(array_s.todense().input_shape, ref_shape)
