def get()

in ludwig/data/dataset.py [0:0]

• 19 lines of code
• 6 McCabe index (conditional complexity)

    def get(self, feature_name, idx=None):
        if idx is None:
            idx = range(self.size)
        if (self.data_hdf5_fp is None or
                'preprocessing' not in self.features[feature_name] or
                'in_memory' not in self.features[feature_name]['preprocessing']):
            return self.dataset[feature_name][idx]
        if self.features[feature_name]['preprocessing']['in_memory']:
            return self.dataset[feature_name][idx]

        sub_batch = self.dataset[feature_name][idx]

        indices = np.empty((3, len(sub_batch)), dtype=np.int64)
        indices[0, :] = sub_batch
        indices[1, :] = np.arange(len(sub_batch))
        indices = indices[:, np.argsort(indices[0])]

        with h5py.File(self.data_hdf5_fp, 'r') as h5_file:
            im_data = h5_file[feature_name + '_data'][indices[0, :], :, :]
        indices[2, :] = np.arange(len(sub_batch))
        indices = indices[:, np.argsort(indices[1])]
        return im_data[indices[2, :]]