using csv now

backend/disentangle_concepts.py

@@ -4,8 +4,8 @@ from sklearn.model_selection import train_test_split
 import torch
 import PIL
 
-def get_separation_space(type_bin, annotations):
-    abstracts = np.array([ann[type_bin] for ann in annotations['annotations']])
+def get_separation_space(type_bin, annotations, df):
+    abstracts = np.array([float(ann) for ann in df[type_bin]])
     abstract_idxs = list(np.argsort(abstracts))[:200]
     repr_idxs = list(np.argsort(abstracts))[-200:]
     X = np.array([annotations['z_vectors'][i] for i in abstract_idxs+repr_idxs])

data/annotated_files/sim_seeds0000-10000.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e82d206b3aa231c00176a24c8de33a6299e92e65b23013a40538146b8d24ff8
+size 5645518

pages/1_Disentanglement.py

@@ -37,7 +37,8 @@ with st.expander("See more instruction", expanded=False):
 annotations_file = './data/annotated_files/annotations_parallel_seeds0000-10000.pkl'
 with open(annotations_file, 'rb') as f:
     annotations = pickle.load(f)
-    
+
+ann_df = pd.read_csv('./data/annotated_files/sim_seeds0000-10000.csv')
 concepts = './data/concepts.txt'
 with open(concepts) as f:
     labels = [line.strip() for line in f.readlines()]
@@ -94,7 +95,7 @@ smoothgrad_col_1, smoothgrad_col_2, smoothgrad_col_3, smoothgrad_col_4, smoothgr
 
 # ---------------------------- DISPLAY COL 1 ROW 1 ------------------------------
 with output_col_1:
-    separation_vector, number_important_features = get_separation_space(concept_id, annotations)
+    separation_vector, number_important_features = get_separation_space(concept_id, annotations, ann_df)
     # st.write(f'Class ID {input_id} - {input_label}: {pred_prob*100:.3f}% confidence')
     st.write('Separation vector', separation_vector)
     header_col_1.write(f'Concept {concept_id} - Number of relevant nodes: {number_important_features}')