Change dtype of labels to int

01_preprocessing/prepare_clinical.py

@@ -15,7 +15,7 @@ from utils import remove_na, remove_constant_cols
 
 # os.chdir('..')
 # %%
-DATASET_NAME = 'HN_BZ'
+DATASET_NAME = 'HN_val'
 PROJECT_DATA_PATH = Path('data') / DATASET_NAME
 RAW_DATA_PATH = PROJECT_DATA_PATH / 'raw'
 PROCESSED_DATA_PATH = PROJECT_DATA_PATH / 'processed'
@@ -35,22 +35,22 @@ os.makedirs(PROCESSED_DATA_PATH, exist_ok=True)
 
 # Tx T-stages cluster with low T-stages in the UMAP projection
 grading_dict_binary = {
-    'T1': '0',
-    'T2': '0',
-    'T3': '1',
-    'T4': '1',
-    'T4a': '1',
-    'T4b': '1',
-    'Tx': '0',
+    'T1': 0,
+    'T2': 0,
+    'T3': 1,
+    'T4': 1,
+    'T4a': 1,
+    'T4b': 1,
+    'Tx': 0,
 }
 grading_dict_grouped = {
-    'T1': '0',
-    'T2': '1',
-    'T3': '2',
-    'T4': '3',
-    'T4a': '3',
-    'T4b': '3',
-    'Tx': '0',
+    'T1': 0,
+    'T2': 1,
+    'T3': 2,
+    'T4': 3,
+    'T4a': 3,
+    'T4b': 3,
+    'Tx': 0,
 }
 
 if DATASET_NAME == 'HN_val':
@@ -369,6 +369,13 @@ if DATASET_NAME == 'HN_val':
         clinical
     ), f'Clinical file and metadata file differ in patients.'
 
+    for label in [
+        LABEL_COL_LOCOREGIONAL,
+        LABEL_COL_T_STAGE_BINARY,
+        LABEL_COL_T_STAGE_GROUPED,
+    ]:
+        clinical[label] = clinical[label].astype(np.uint8)
+
     clinical.to_csv(PROCESSED_DATA_PATH / CLINICAL_DATA_FILENAME_CLEAN, index=False)
 
 elif DATASET_NAME == 'HN_BZ':