def global_src_features(X, D, sparse_coder, n_class_atoms, n_jobs=1):
"""
return the features for each datapoint which
are the approximation errors of the datapoint encoded
over each sub-dictionary in D
"""
E = global_error(X, D, sparse_coder, n_class_atoms, n_jobs=n_jobs)
Z_final = norm_cols(E)
return Z_final
def local_src_features(X, D, sparse_coder, n_class_atoms, n_jobs=1):
n_samples = X.shape[1]
n_classes = len(n_class_atoms)
data = [X]
args = [D, n_class_atoms, sparse_coder]
Z_final = run_parallel(func=local_error, data=data, args=args, batched_args=None,
result_shape=(n_classes, n_samples), n_batches=100, mmap=False,
msg="building global SRC features", n_jobs=n_jobs)
Z_final = norm_cols(Z_final)
return Z_final