scalar_vectorize.py 文件源码

def accumulate_user_vectors(users, max_prods, product_lookup, max_users, testmode):
  BUFFER_SIZE = float('inf') # XXX: see what mem usage looks like before over-engineering
  vec_accumulator = []
  nusers = 0
  for user in users:
    vecs = get_user_vectors(user, max_prods, product_lookup, testmode)
    vec_accumulator.append(vecs)
    nusers += 1
    if max_users and nusers >= max_users:
      break
    if nusers % 10000 == 0:
      print "{}... ".format(nusers)

  print "Accumulated vectors for {} users".format(len(vec_accumulator))
  concatted = np.concatenate(vec_accumulator)
  final_arr = concatted.view(np.recarray)
  return final_arr