def get_dataset()

in datasets/toy_binary.py [0:0]

• 11 lines of code
• 4 McCabe index (conditional complexity)

    def get_dataset(self):

        data_location = "data/"

        # parse dataframe and feature domains
        self.df = pd.read_csv(os.path.join(data_location, "toy_binary.csv"))
        self.domain = json.load(open(os.path.join(data_location, "toy_binary.json")))

        # check domain and csv header are consistent
        assert set(self.df.columns) == set(self.domain.keys())

        # return one-hot encoding of entrire dataset
        dataset = self.project_feats()

        if not self.use_subset:
            self.n, self.d = dataset.shape
            return dataset
        else:
            return dataset[: self.n, : self.d]