Python official.recommendation.data_preprocessing.DATASET_TO_NUM_USERS_AND_ITEMS Examples

The following are 5 code examples of official.recommendation.data_preprocessing.DATASET_TO_NUM_USERS_AND_ITEMS(). You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may also want to check out all available functions/classes of the module official.recommendation.data_preprocessing , or try the search function .
Example #1
Source File: ncf_common.py    From models with Apache License 2.0 6 votes vote down vote up 
def get_inputs(params):
  """Returns some parameters used by the model."""
  if FLAGS.download_if_missing and not FLAGS.use_synthetic_data:
    movielens.download(FLAGS.dataset, FLAGS.data_dir)

  if FLAGS.seed is not None:
    np.random.seed(FLAGS.seed)

  if FLAGS.use_synthetic_data:
    producer = data_pipeline.DummyConstructor()
    num_users, num_items = data_preprocessing.DATASET_TO_NUM_USERS_AND_ITEMS[
        FLAGS.dataset]
    num_train_steps = rconst.SYNTHETIC_BATCHES_PER_EPOCH
    num_eval_steps = rconst.SYNTHETIC_BATCHES_PER_EPOCH
  else:
    num_users, num_items, producer = data_preprocessing.instantiate_pipeline(
        dataset=FLAGS.dataset, data_dir=FLAGS.data_dir, params=params,
        constructor_type=FLAGS.constructor_type,
        deterministic=FLAGS.seed is not None)
    num_train_steps = producer.train_batches_per_epoch
    num_eval_steps = producer.eval_batches_per_epoch

  return num_users, num_items, num_train_steps, num_eval_steps, producer
Example #2
Source File: ncf_common.py    From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 6 votes vote down vote up 
def get_inputs(params):
  """Returns some parameters used by the model."""
  if FLAGS.download_if_missing and not FLAGS.use_synthetic_data:
    movielens.download(FLAGS.dataset, FLAGS.data_dir)

  if FLAGS.seed is not None:
    np.random.seed(FLAGS.seed)

  if FLAGS.use_synthetic_data:
    producer = data_pipeline.DummyConstructor()
    num_users, num_items = data_preprocessing.DATASET_TO_NUM_USERS_AND_ITEMS[
        FLAGS.dataset]
    num_train_steps = rconst.SYNTHETIC_BATCHES_PER_EPOCH
    num_eval_steps = rconst.SYNTHETIC_BATCHES_PER_EPOCH
  else:
    num_users, num_items, producer = data_preprocessing.instantiate_pipeline(
        dataset=FLAGS.dataset, data_dir=FLAGS.data_dir, params=params,
        constructor_type=FLAGS.constructor_type,
        deterministic=FLAGS.seed is not None)
    num_train_steps = producer.train_batches_per_epoch
    num_eval_steps = producer.eval_batches_per_epoch

  return num_users, num_items, num_train_steps, num_eval_steps, producer
Example #3
Source File: data_test.py    From Live-feed-object-device-identification-using-Tensorflow-and-OpenCV with Apache License 2.0 5 votes vote down vote up 
def setUp(self):
    if keras_utils.is_v2_0:
      tf.compat.v1.disable_eager_execution()
    self.temp_data_dir = self.get_temp_dir()
    ratings_folder = os.path.join(self.temp_data_dir, DATASET)
    tf.io.gfile.makedirs(ratings_folder)
    np.random.seed(0)
    raw_user_ids = np.arange(NUM_USERS * 3)
    np.random.shuffle(raw_user_ids)
    raw_user_ids = raw_user_ids[:NUM_USERS]

    raw_item_ids = np.arange(NUM_ITEMS * 3)
    np.random.shuffle(raw_item_ids)
    raw_item_ids = raw_item_ids[:NUM_ITEMS]

    users = np.random.choice(raw_user_ids, NUM_PTS)
    items = np.random.choice(raw_item_ids, NUM_PTS)
    scores = np.random.randint(low=0, high=5, size=NUM_PTS)
    times = np.random.randint(low=1000000000, high=1200000000, size=NUM_PTS)

    self.rating_file = os.path.join(ratings_folder, movielens.RATINGS_FILE)
    self.seen_pairs = set()
    self.holdout = {}
    with tf.io.gfile.GFile(self.rating_file, "w") as f:
      f.write("user_id,item_id,rating,timestamp\n")
      for usr, itm, scr, ts in zip(users, items, scores, times):
        pair = (usr, itm)
        if pair in self.seen_pairs:
          continue
        self.seen_pairs.add(pair)
        if usr not in self.holdout or (ts, itm) > self.holdout[usr]:
          self.holdout[usr] = (ts, itm)

        f.write("{},{},{},{}\n".format(usr, itm, scr, ts))

    movielens.download = mock_download
    movielens.NUM_RATINGS[DATASET] = NUM_PTS
    data_preprocessing.DATASET_TO_NUM_USERS_AND_ITEMS[DATASET] = (NUM_USERS,
                                                                  NUM_ITEMS)
Example #4
Source File: data_test.py    From g-tensorflow-models with Apache License 2.0 5 votes vote down vote up 
def setUp(self):
    self.temp_data_dir = self.get_temp_dir()
    ratings_folder = os.path.join(self.temp_data_dir, DATASET)
    tf.gfile.MakeDirs(ratings_folder)
    np.random.seed(0)
    raw_user_ids = np.arange(NUM_USERS * 3)
    np.random.shuffle(raw_user_ids)
    raw_user_ids = raw_user_ids[:NUM_USERS]

    raw_item_ids = np.arange(NUM_ITEMS * 3)
    np.random.shuffle(raw_item_ids)
    raw_item_ids = raw_item_ids[:NUM_ITEMS]

    users = np.random.choice(raw_user_ids, NUM_PTS)
    items = np.random.choice(raw_item_ids, NUM_PTS)
    scores = np.random.randint(low=0, high=5, size=NUM_PTS)
    times = np.random.randint(low=1000000000, high=1200000000, size=NUM_PTS)

    self.rating_file = os.path.join(ratings_folder, movielens.RATINGS_FILE)
    self.seen_pairs = set()
    self.holdout = {}
    with tf.gfile.Open(self.rating_file, "w") as f:
      f.write("user_id,item_id,rating,timestamp\n")
      for usr, itm, scr, ts in zip(users, items, scores, times):
        pair = (usr, itm)
        if pair in self.seen_pairs:
          continue
        self.seen_pairs.add(pair)
        if usr not in self.holdout or (ts, itm) > self.holdout[usr]:
          self.holdout[usr] = (ts, itm)

        f.write("{},{},{},{}\n".format(usr, itm, scr, ts))

    movielens.download = mock_download
    movielens.NUM_RATINGS[DATASET] = NUM_PTS
    data_preprocessing.DATASET_TO_NUM_USERS_AND_ITEMS[DATASET] = (NUM_USERS,
                                                                  NUM_ITEMS)
Example #5
Source File: data_test.py    From multilabel-image-classification-tensorflow with MIT License 5 votes vote down vote up 
def setUp(self):
    self.temp_data_dir = self.get_temp_dir()
    ratings_folder = os.path.join(self.temp_data_dir, DATASET)
    tf.gfile.MakeDirs(ratings_folder)
    np.random.seed(0)
    raw_user_ids = np.arange(NUM_USERS * 3)
    np.random.shuffle(raw_user_ids)
    raw_user_ids = raw_user_ids[:NUM_USERS]

    raw_item_ids = np.arange(NUM_ITEMS * 3)
    np.random.shuffle(raw_item_ids)
    raw_item_ids = raw_item_ids[:NUM_ITEMS]

    users = np.random.choice(raw_user_ids, NUM_PTS)
    items = np.random.choice(raw_item_ids, NUM_PTS)
    scores = np.random.randint(low=0, high=5, size=NUM_PTS)
    times = np.random.randint(low=1000000000, high=1200000000, size=NUM_PTS)

    rating_file = os.path.join(ratings_folder, movielens.RATINGS_FILE)
    self.seen_pairs = set()
    self.holdout = {}
    with tf.gfile.Open(rating_file, "w") as f:
      f.write("user_id,item_id,rating,timestamp\n")
      for usr, itm, scr, ts in zip(users, items, scores, times):
        pair = (usr, itm)
        if pair in self.seen_pairs:
          continue
        self.seen_pairs.add(pair)
        if usr not in self.holdout or (ts, itm) > self.holdout[usr]:
          self.holdout[usr] = (ts, itm)

        f.write("{},{},{},{}\n".format(usr, itm, scr, ts))

    movielens.download = mock_download
    movielens.NUM_RATINGS[DATASET] = NUM_PTS
    data_preprocessing.DATASET_TO_NUM_USERS_AND_ITEMS[DATASET] = (NUM_USERS,
                                                                  NUM_ITEMS)