stage1.py 文件源码

def _load_sets(self):
        print("Loading datasets")

        train_patients = pd.read_csv(os.path.join(self._directory, "stage1_labels.csv"))
        test_patients = pd.read_csv(os.path.join(self._directory, "stage1_sample_submission.csv"))

        for idx, row in test_patients.iterrows():
            self._test_set.append(row['id'])

        for idx, row in train_patients.iterrows():
            self._train_set.append([row['id'], row['cancer']])

        #Create permutation for random loading
        self.shuffle()

        print("Loading datasets: Done!")