def _filter_index_sort()

in example_zoo/tensorflow/models/ncf_main/official/recommendation/data_preprocessing.py [0:0]


def _filter_index_sort(raw_rating_path, cache_path):
  # type: (str, str, bool) -> (dict, bool)
  """Read in data CSV, and output structured data.

  This function reads in the raw CSV of positive items, and performs three
  preprocessing transformations:

  1)  Filter out all users who have not rated at least a certain number
      of items. (Typically 20 items)

  2)  Zero index the users and items such that the largest user_id is
      `num_users - 1` and the largest item_id is `num_items - 1`

  3)  Sort the dataframe by user_id, with timestamp as a secondary sort key.
      This allows the dataframe to be sliced by user in-place, and for the last
      item to be selected simply by calling the `-1` index of a user's slice.

  While all of these transformations are performed by Pandas (and are therefore
  single-threaded), they only take ~2 minutes, and the overhead to apply a
  MapReduce pattern to parallel process the dataset adds significant complexity
  for no computational gain. For a larger dataset parallelizing this
  preprocessing could yield speedups. (Also, this preprocessing step is only
  performed once for an entire run.

  Args:
    raw_rating_path: The path to the CSV which contains the raw dataset.
    cache_path: The path to the file where results of this function are saved.

  Returns:
    A filtered, zero-index remapped, sorted dataframe, a dict mapping raw user
    IDs to regularized user IDs, and a dict mapping raw item IDs to regularized
    item IDs.
  """
  valid_cache = tf.gfile.Exists(cache_path)
  if valid_cache:
    with tf.gfile.Open(cache_path, "rb") as f:
      cached_data = pickle.load(f)

    cache_age = time.time() - cached_data.get("create_time", 0)
    if cache_age > rconst.CACHE_INVALIDATION_SEC:
      valid_cache = False

    for key in _EXPECTED_CACHE_KEYS:
      if key not in cached_data:
        valid_cache = False

    if not valid_cache:
      tf.logging.info("Removing stale raw data cache file.")
      tf.gfile.Remove(cache_path)

  if valid_cache:
    data = cached_data
  else:
    with tf.gfile.Open(raw_rating_path) as f:
      df = pd.read_csv(f)

    # Get the info of users who have more than 20 ratings on items
    grouped = df.groupby(movielens.USER_COLUMN)
    df = grouped.filter(
        lambda x: len(x) >= rconst.MIN_NUM_RATINGS) # type: pd.DataFrame

    original_users = df[movielens.USER_COLUMN].unique()
    original_items = df[movielens.ITEM_COLUMN].unique()

    # Map the ids of user and item to 0 based index for following processing
    tf.logging.info("Generating user_map and item_map...")
    user_map = {user: index for index, user in enumerate(original_users)}
    item_map = {item: index for index, item in enumerate(original_items)}

    df[movielens.USER_COLUMN] = df[movielens.USER_COLUMN].apply(
        lambda user: user_map[user])
    df[movielens.ITEM_COLUMN] = df[movielens.ITEM_COLUMN].apply(
        lambda item: item_map[item])

    num_users = len(original_users)
    num_items = len(original_items)

    mlperf_helper.ncf_print(key=mlperf_helper.TAGS.PREPROC_HP_NUM_EVAL,
                            value=rconst.NUM_EVAL_NEGATIVES)

    assert num_users <= np.iinfo(rconst.USER_DTYPE).max
    assert num_items <= np.iinfo(rconst.ITEM_DTYPE).max
    assert df[movielens.USER_COLUMN].max() == num_users - 1
    assert df[movielens.ITEM_COLUMN].max() == num_items - 1

    # This sort is used to shard the dataframe by user, and later to select
    # the last item for a user to be used in validation.
    tf.logging.info("Sorting by user, timestamp...")

    # This sort is equivalent to
    #   df.sort_values([movielens.USER_COLUMN, movielens.TIMESTAMP_COLUMN],
    #   inplace=True)
    # except that the order of items with the same user and timestamp are
    # sometimes different. For some reason, this sort results in a better
    # hit-rate during evaluation, matching the performance of the MLPerf
    # reference implementation.
    df.sort_values(by=movielens.TIMESTAMP_COLUMN, inplace=True)
    df.sort_values([movielens.USER_COLUMN, movielens.TIMESTAMP_COLUMN],
                   inplace=True, kind="mergesort")

    df = df.reset_index()  # The dataframe does not reconstruct indices in the
                           # sort or filter steps.

    grouped = df.groupby(movielens.USER_COLUMN, group_keys=False)
    eval_df, train_df = grouped.tail(1), grouped.apply(lambda x: x.iloc[:-1])

    data = {
        rconst.TRAIN_USER_KEY: train_df[movielens.USER_COLUMN]
                               .values.astype(rconst.USER_DTYPE),
        rconst.TRAIN_ITEM_KEY: train_df[movielens.ITEM_COLUMN]
                               .values.astype(rconst.ITEM_DTYPE),
        rconst.EVAL_USER_KEY: eval_df[movielens.USER_COLUMN]
                              .values.astype(rconst.USER_DTYPE),
        rconst.EVAL_ITEM_KEY: eval_df[movielens.ITEM_COLUMN]
                              .values.astype(rconst.ITEM_DTYPE),
        rconst.USER_MAP: user_map,
        rconst.ITEM_MAP: item_map,
        "create_time": time.time(),
    }

    tf.logging.info("Writing raw data cache.")
    with tf.gfile.Open(cache_path, "wb") as f:
      pickle.dump(data, f, protocol=pickle.HIGHEST_PROTOCOL)

  # TODO(robieta): MLPerf cache clear.
  return data, valid_cache