Apply labels to ilastik project file from training data

extensions/chaeo/examples/label_patches.py

@@ -10,6 +10,6 @@ if __name__ == '__main__':
         where_patches=(root / 'batch-output-20231012-0016/2d_patches_training').__str__(),
         object_csv=(root / 'batch-output-20231011-0003/df_objects.csv').__str__(),
         ecotaxa_tsv='c:/Users/rhodes/projects/proj0011-plankton-seg/exp0013/ecotaxa_export_10468_20231012_0930.tsv',
-        where_output=autonumber_new_directory(root, 'labeled_patches')
+        where_output=autonumber_new_directory(root, 'labeled_patches'),
     )
     print('Finished')

extensions/chaeo/examples/transfer_labels_to_ilastik_object_classifier.py

+import csv
 from pathlib import Path
 import h5py
 import ilastik.applets.objectClassification
+import numpy as np
 import pandas as pd
 
 from extensions.ilastik.models import IlastikObjectClassifierModel
@@ -8,16 +10,35 @@ from extensions.ilastik.models import IlastikObjectClassifierModel
 def transfer_labels_to_ilastik_ilp(ilp, df_stack_meta):
 
     with h5py.File(ilp, 'r+') as h5:
+        where_out = Path(ilp).parent
+
+        # export complete HDF5 tree
+        with open(where_out / 'h5tree.txt', 'w') as hf:
+            tt = []
+            h5.visititems(lambda k, v: tt.append([k, str(v)]))
+            for line in tt:
+                hf.write(f'{line[0]} --- {line[1]}\n')
+        h5.visititems(lambda k, v: print(k + ' : ' + str(v)))
+
+        # change key of label names
+        ln = ['none'] + list(df_stack_meta.sort_values('annotation_class_id').annotation_class.unique())
+        del h5['ObjectClassification/LabelNames']
+        h5.create_dataset('ObjectClassification/LabelNames', data=np.array(ln).astype('O'))
+
+        # change object labels
         ts = h5['ObjectClassification']['LabelInputs']['0000']
         for ti in ts.items():
-            idx = int(ti[0])
+            assert len(ti) == 2  # one for unlabeled area, one for labeled area
+            idx = int(ti[0])  # important because keys are strings and hence not sorted numerically
             ds = ti[1]
             la_old = ds[1]
-            ds[1] = float(df_stack_meta.loc[df_stack_meta.zi == idx, 'annotation_class_id'].iat[0])
+
+            # unit index, i.e. reserve 1 for no object
+            ds[1] = float(1 + df_stack_meta.loc[df_stack_meta.zi == idx, 'annotation_class_id'].iat[0])
             print(f'Changed label {ti} from {la_old} to {ds[1]}')
 
 if __name__ == '__main__':
-    ilp = 'c:/Users/rhodes/model-server/ilastik/test_automate_obj_labels.ilp'
+    ilp = 'c:/Users/rhodes/model-server/ilastik/test_autolabel_obj.ilp'
     df = pd.read_csv(
         'c:/Users/rhodes/projects/proj0011-plankton-seg/exp0009/output/labeled_patches-20231013-0022/training_stack.csv'
     )