added purity and diversity scores

app.py

@@ -1,5 +1,6 @@
 import streamlit as st
 from datasets import load_dataset
+import numpy as np
 
 st.set_page_config(page_title="High-Level dataset")
 
@@ -11,10 +12,15 @@ QS = {
 }
 SPLITS = ["test", "train"]
 
+AVG_PURITY = 1.10
+
+AVG_DIVERSITY = 0.872819
+MIN_DIVERSITY = 0
+MAX_DIVERSITY = 100
+
 @st.cache
 def load_data(split):
 
-    #with st.spinner('Loading the data...'):
     dataset = load_dataset("michelecafagna26/hl")
 
     coco2id = {int(dataset[split][i]['file_name'].replace("COCO_train2014_", "").replace(".jpg", "")): i for i in
@@ -25,20 +31,27 @@ def load_data(split):
 
 def write_obj(dataset, img_id, options, split, list_type="num", show_questions=False,
               show_conf=False):
+
     st.image(dataset[split][img_id]['image'])
 
-    # col1, col2 = st.columns(2)
-    #
-    # col1.metric(label="Diversity score",
-    #             value=round(self_bleu[f"COCO_train2014_{img_id}.jpg"], 2),
-    #             delta=round(self_bleu[f"COCO_train2014_{img_id}.jpg"] - AVG_DIVERSITY, 2),
-    #             help="Normalized complementary 3-way Self-BLEU score. The delta is the difference with the average")
-    #
-    # col2.metric(label="Purity score",
-    #             value=round(bleurt[f"COCO_train2014_{img_id}.jpg"], 2),
-    #             delta=round(bleurt[f"COCO_train2014_{img_id}.jpg"] - AVG_PURITY, 2),
-    #             help="Normalized 3-way Bleurt score. The delta is the difference with the average")
-    #
+    item_purity = np.mean([np.mean(dataset[split][img_id]['purity'][k]) for k in dataset[split][img_id]['purity']])
+    item_diversity = np.mean(list(dataset[split][img_id]['diversity'].values()))
+
+    # normalize
+    item_diversity = 1-(item_diversity-MIN_DIVERSITY)/(MAX_DIVERSITY-MIN_DIVERSITY)
+
+    col1, col2 = st.columns(2)
+
+    col1.metric(label="Diversity score",
+                value=round(item_diversity, 2),
+                delta=round(item_diversity - AVG_DIVERSITY, 2),
+                help="Item's internal lexical diversity.\n Positive delta means higher then the average")
+
+    col2.metric(label="Purity score",
+                value=round(item_purity, 2),
+                delta=round(item_purity - AVG_PURITY, 2),
+                help="Item's internal semantic similarity.\n Positive delta means higher then the average")
+
     for field in options:
 
         st.markdown(f"## {field.capitalize()}")
@@ -61,7 +74,6 @@ def write_obj(dataset, img_id, options, split, list_type="num", show_questions=F
 
 
 def main():
-
     st.title('High-Level Dataset')
 
     show_questions = st.sidebar.checkbox('Questions')
@@ -75,19 +87,18 @@ def main():
         'Split',
         SPLITS)
 
-
     dataset, coco2id = load_data(split)
 
     # sidebar
     choosen_image = st.selectbox(
         'Select an image',
         list(coco2id.keys()),
-        help="write a key like: 532"
+        help="write a key like: 7603"
     )
 
-    write_obj(dataset, coco2id[choosen_image], options=options, split=split,
-              list_type="num", show_questions=show_questions, show_conf=show_conf)
+    write_obj(dataset, coco2id[choosen_image], options=options, split=split, list_type="num",
+              show_questions=show_questions, show_conf=show_conf)
 
 
-if __name__=="__main__":
-    main()
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -1,2 +1,3 @@
 datasets==2.9.0
-streamlit==1.17.0
+streamlit==1.17.0
+numpy==1.21.1