mappers.py 文件源码

def tfidf(x, vocab_size, smooth=True, name=None):
  """Maps the terms in x to their term frequency * inverse document frequency.

  The inverse document frequency of a term is calculated as 1+
  log((corpus size + 1) / (document frequency of term + 1)) by default.

  Example usage:
    example strings [["I", "like", "pie", "pie", "pie"], ["yum", "yum", "pie]]
    in: SparseTensor(indices=[[0, 0], [0, 1], [0, 2], [0, 3], [0, 4],
                              [1, 0], [1, 1], [1, 2]],
                     values=[1, 2, 0, 0, 0, 3, 3, 0])
    out: SparseTensor(indices=[[0, 0], [0, 1], [0, 2], [1, 0], [1, 1]],
                      values=[1, 2, 0, 3, 0])
         SparseTensor(indices=[[0, 0], [0, 1], [0, 2], [1, 0], [1, 1]],
                      values=[(1/5)*(log(3/2)+1), (1/5)*(log(3/2)+1), (1/5),
                              (1/3), (2/3)*(log(3/2)+1])
    NOTE that the first doc's duplicate "pie" strings have been combined to
    one output, as have the second doc's duplicate "yum" strings.

  Args:
    x: A `SparseTensor` representing int64 values (most likely that are the
        result of calling string_to_int on a tokenized string).
    vocab_size: An int - the count of vocab used to turn the string into int64s
        including any OOV buckets.
    smooth: A bool indicating if the inverse document frequency should be
        smoothed. If True, which is the default, then the idf is calculated as
        1 + log((corpus size + 1) / (document frequency of term + 1)).
        Otherwise, the idf is
        1 +log((corpus size) / (document frequency of term)), which could
        result in a divizion by zero error.
    name: (Optional) A name for this operation.

  Returns:
    Two `SparseTensor`s with indices [index_in_batch, index_in_bag_of_words].
    The first has values vocab_index, which is taken from input `x`.
    The second has values tfidf_weight.
  """

  def _to_vocab_range(x):
    """Enforces that the vocab_ids in x are positive."""
    return tf.SparseTensor(
        indices=x.indices,
        values=tf.mod(x.values, vocab_size),
        dense_shape=x.dense_shape)

  with tf.name_scope(name, 'tfidf'):
    cleaned_input = _to_vocab_range(x)

    term_frequencies = _to_term_frequency(cleaned_input, vocab_size)

    count_docs_with_term_column = _count_docs_with_term(term_frequencies)
    # Expand dims to get around the min_tensor_rank checks
    sizes = tf.expand_dims(tf.shape(cleaned_input)[0], 0)
    # [batch, vocab] - tfidf
    tfidfs = _to_tfidf(term_frequencies,
                       analyzers.sum(count_docs_with_term_column,
                                     reduce_instance_dims=False),
                       analyzers.sum(sizes),
                       smooth)
    return _split_tfidfs_to_outputs(tfidfs)