seems generate may be blocking? unclear

app.py

@@ -25,7 +25,9 @@ from sklearn.svm import SVC
 from sklearn.inspection import permutation_importance
 from sklearn import preprocessing
 import pandas as pd
-from apscheduler.schedulers.background import BackgroundScheduler
+#from apscheduler.schedulers.background import BackgroundScheduler
+import sched
+import threading
 
 import random
 import time
@@ -223,57 +225,58 @@ def pluck_img(user_id, user_emb):
 
 def background_next_image():
  global prevs_df
- 
- # only let it get N (maybe 3) ahead of the user
- #not_rated_rows = prevs_df[[i[1]['user:rating'] == {' ': ' '} for i in prevs_df.iterrows()]]
- rated_rows = prevs_df[[i[1]['user:rating'] != {' ': ' '} for i in prevs_df.iterrows()]]
- while len(rated_rows) < 4:
- # not_rated_rows = prevs_df[[i[1]['user:rating'] == {' ': ' '} for i in prevs_df.iterrows()]]
- rated_rows = prevs_df[[i[1]['user:rating'] != {' ': ' '} for i in prevs_df.iterrows()]]
- time.sleep(.01)
- print('all users have 4 or less rows rated')
-
- 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()]]
- 
- # we need to intersect not_rated_rows from this user's embed > 7. Just add a new column on which user_id spawned the 
- # media. 
- 
- from_user = prevs_df[[i[1]['from_user_id'] == uid for i in prevs_df.iterrows()]]
- if len(from_user) >= 10:
- oldest = from_user.iloc[-1]['paths']
- print(f'User has {len(from_user)} rows. Popping oldest: {oldest}')
- prevs_df = prevs_df[prevs_df['paths'] != oldest]
- 
- if len(rated_rows) < 4:
- print(f'latest user {uid} has < 4 rows') # or > 7 unrated rows')
- continue
- 
- print(uid)
- embs, ys = pluck_embs_ys(uid)
+ while True:
  
- 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'] = [{' ': ' '}]
- tmp_df['from_user_id'] = [uid]
- 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:]))
+ # only let it get N (maybe 3) ahead of the user
+ #not_rated_rows = prevs_df[[i[1]['user:rating'] == {' ': ' '} for i in prevs_df.iterrows()]]
+ rated_rows = prevs_df[[i[1]['user:rating'] != {' ': ' '} for i in prevs_df.iterrows()]]
+ while len(rated_rows) < 4:
+ # not_rated_rows = prevs_df[[i[1]['user:rating'] == {' ': ' '} for i in prevs_df.iterrows()]]
+ rated_rows = prevs_df[[i[1]['user:rating'] != {' ': ' '} for i in prevs_df.iterrows()]]
+ time.sleep(.01)
+ print('all users have 4 or less rows rated')
+
+ 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()]]
+ 
+ # we need to intersect not_rated_rows from this user's embed > 7. Just add a new column on which user_id spawned the 
+ # media. 
+ 
+ from_user = prevs_df[[i[1]['from_user_id'] == uid for i in prevs_df.iterrows()]]
+ if len(from_user) >= 10:
+ oldest = from_user.iloc[-1]['paths']
+ print(f'User has {len(from_user)} rows. Popping oldest: {oldest}')
+ prevs_df = prevs_df[prevs_df['paths'] != oldest]
+ 
+ if len(rated_rows) < 4:
+ 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'] = [{' ': ' '}]
+ tmp_df['from_user_id'] = [uid]
+ 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):
@@ -475,9 +478,12 @@ Explore the latent space without text prompts based on your preferences. Learn m
 log = logging.getLogger('log_here')
 log.setLevel(logging.ERROR)
 
-scheduler = BackgroundScheduler()
-scheduler.add_job(func=background_next_image, trigger="interval", seconds=.1)
-scheduler.start()
+#scheduler = BackgroundScheduler()
+#scheduler.add_job(func=background_next_image, trigger="interval", seconds=.1)
+#scheduler.start()
+
+thread = threading.Thread(target=background_next_image,)
+thread.start()
 
 def encode_space(x):
  im_emb, _ = pipe.encode_image(