def __getitem__()

in benchmarks/dlrm/ootb/dlrm_data_pytorch.py [0:0]

• 30 lines of code
• 17 McCabe index (conditional complexity)

    def __getitem__(self, index):

        if isinstance(index, slice):
            return [
                self[idx] for idx in range(
                    index.start or 0, index.stop or len(self), index.step or 1
                )
            ]

        if self.memory_map:
            if self.split == 'none' or self.split == 'train':
                # check if need to swicth to next day and load data
                if index == self.offset_per_file[self.day]:
                    # print("day_boundary switch", index)
                    self.day_boundary = self.offset_per_file[self.day]
                    fi = self.npzfile + "_{0}_reordered.npz".format(
                        self.day
                    )
                    # print('Loading file: ', fi)
                    with np.load(fi) as data:
                        self.X_int = data["X_int"]  # continuous  feature
                        self.X_cat = data["X_cat"]  # categorical feature
                        self.y = data["y"]          # target
                    self.day = (self.day + 1) % self.max_day_range

                i = index - self.day_boundary
            elif self.split == 'test' or self.split == 'val':
                # only a single day is used for testing
                i = index + (0 if self.split == 'test' else self.test_size)
            else:
                sys.exit("ERROR: dataset split is neither none, nor train or test.")
        else:
            i = index

        if self.max_ind_range > 0:
            return self.X_int[i], self.X_cat[i] % self.max_ind_range, self.y[i]
        else:
            return self.X_int[i], self.X_cat[i], self.y[i]