def __getitem__()

in dlrm_data_caffe2.py [0:0]

• 26 lines of code
• 16 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.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.")

        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]