sample.py 文件源码

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

        train_patients = pd.read_csv("data/stage1/" + "stage1_labels.csv")

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

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

        #Create permutation for random loading
        self.shuffle()

        print("Loading datasets: Done!")