Update app.py

app.py

@@ -246,38 +246,40 @@ def background_next_image():
         rated_rows = prevs_df[[i[1]['user:rating'] != {' ': ' '} for i in prevs_df.iterrows()]]
         time.sleep(.01)
         print('all users have 8 or more rows left to rate')
-    
-    latest_user_id = rated_rows.iloc[-1]['latest_user_to_rate']
-    rated_rows = prevs_df[[i[1]['user:rating'].get(latest_user_id, None) is not None for i in prevs_df.iterrows()]]
-    not_rated_rows = prevs_df[[i[1]['user:rating'].get(latest_user_id, None) is None for i in prevs_df.iterrows()]]
-    while len(rated_rows) < 4 or len(not_rated_rows) > 10:
-        rated_rows = prevs_df[[i[1]['user:rating'].get(latest_user_id, None) is not None for i in prevs_df.iterrows()]]
-        not_rated_rows = prevs_df[[i[1]['user:rating'].get(latest_user_id, None) is None for i in prevs_df.iterrows()]]
-        time.sleep(.01)
-        print('latest user has < 4 rated_rows')
-    
-    print(latest_user_id)
-    embs, ys = pluck_embs_ys(latest_user_id)
-    
-    user_emb = get_user_emb(embs, ys)
-    img, embs = generate(user_emb)
-    print(img)
-    if img:
-        tmp_df = pd.DataFrame(columns=['paths', 'embeddings', 'ips', 'user:rating', 'latest_user_to_rate'])
-        tmp_df['paths'] = [img]
-        tmp_df['embeddings'] = [embs]
-        tmp_df['user:rating'] = [{' ': ' '}]
-        prevs_df = pd.concat((prevs_df, tmp_df))
-        # we can free up storage by deleting the image
-        if len(prevs_df) > 50:
-            oldest_path = prevs_df.iloc[6]['paths']
-            if os.path.isfile(oldest_path):
-                os.remove(oldest_path)
-            else:
-                # If it fails, inform the user.
-                print("Error: %s file not found" % oldest_path)
-            # only keep 50 images & embeddings & ips, then remove oldest besides calibrating
-            prevs_df = pd.concat((prevs_df.iloc[:6], prevs_df.iloc[7:]))
+
+
+    # TODO set this to run such that it's on a per-user-in-the-db basis; we only want to be ~5 ahead of every user in the db
+    user_id_list = set(rated_rows['latest_user_to_rate'].to_list())
+
+    for uid in user_id_list:
+        rated_rows = prevs_df[[i[1]['user:rating'].get(uid, None) is not None for i in prevs_df.iterrows()]]
+        not_rated_rows = prevs_df[[i[1]['user:rating'].get(uid, None) is None for i in prevs_df.iterrows()]]
+        if len(rated_rows) < 4 or len(not_rated_rows) > 7:
+            print(f'latest user {uid} has < 4 rows or > 7 unrated rows')
+            continue
+        
+        print(uid)
+        embs, ys = pluck_embs_ys(uid)
+        
+        user_emb = get_user_emb(embs, ys)
+        img, embs = generate(user_emb)
+        print(img)
+        if img:
+            tmp_df = pd.DataFrame(columns=['paths', 'embeddings', 'ips', 'user:rating', 'latest_user_to_rate'])
+            tmp_df['paths'] = [img]
+            tmp_df['embeddings'] = [embs]
+            tmp_df['user:rating'] = [{' ': ' '}]
+            prevs_df = pd.concat((prevs_df, tmp_df))
+            # we can free up storage by deleting the image
+            if len(prevs_df) > 50:
+                oldest_path = prevs_df.iloc[6]['paths']
+                if os.path.isfile(oldest_path):
+                    os.remove(oldest_path)
+                else:
+                    # If it fails, inform the user.
+                    print("Error: %s file not found" % oldest_path)
+                # only keep 50 images & embeddings & ips, then remove oldest besides calibrating
+                prevs_df = pd.concat((prevs_df.iloc[:6], prevs_df.iloc[7:]))
     
 
 def pluck_embs_ys(user_id):