def sequence_categorical_column_with_identity(key, num_buckets, default_value=None): """Returns a feature column that represents sequences of integers. Pass this to `embedding_column` or `indicator_column` to convert sequence categorical data into dense representation for input to sequence NN, such as RNN. Example: ```python watches = sequence_categorical_column_with_identity( 'watches', num_buckets=1000) watches_embedding = embedding_column(watches, dimension=10) columns = [watches_embedding] features = tf.parse_example(..., features=make_parse_example_spec(columns)) sequence_feature_layer = SequenceFeatures(columns) sequence_input, sequence_length = sequence_feature_layer(features) sequence_length_mask = tf.sequence_mask(sequence_length) rnn_cell = tf.keras.layers.SimpleRNNCell(hidden_size) rnn_layer = tf.keras.layers.RNN(rnn_cell) outputs, state = rnn_layer(sequence_input, mask=sequence_length_mask) ``` Args: key: A unique string identifying the input feature. num_buckets: Range of inputs. Namely, inputs are expected to be in the range `[0, num_buckets)`. default_value: If `None`, this column's graph operations will fail for out-of-range inputs. Otherwise, this value must be in the range `[0, num_buckets)`, and will replace out-of-range inputs. Returns: A `SequenceCategoricalColumn`. Raises: ValueError: if `num_buckets` is less than one. ValueError: if `default_value` is not in range `[0, num_buckets)`. """ return fc.SequenceCategoricalColumn( fc.categorical_column_with_identity(key=key, num_buckets=num_buckets, default_value=default_value))
def sequence_categorical_column_with_hash_bucket(key, hash_bucket_size, dtype=dtypes.string): """A sequence of categorical terms where ids are set by hashing. Pass this to `embedding_column` or `indicator_column` to convert sequence categorical data into dense representation for input to sequence NN, such as RNN. Example: ```python tokens = sequence_categorical_column_with_hash_bucket( 'tokens', hash_bucket_size=1000) tokens_embedding = embedding_column(tokens, dimension=10) columns = [tokens_embedding] features = tf.parse_example(..., features=make_parse_example_spec(columns)) sequence_feature_layer = SequenceFeatures(columns) sequence_input, sequence_length = sequence_feature_layer(features) sequence_length_mask = tf.sequence_mask(sequence_length) rnn_cell = tf.keras.layers.SimpleRNNCell(hidden_size) rnn_layer = tf.keras.layers.RNN(rnn_cell) outputs, state = rnn_layer(sequence_input, mask=sequence_length_mask) ``` Args: key: A unique string identifying the input feature. hash_bucket_size: An int > 1. The number of buckets. dtype: The type of features. Only string and integer types are supported. Returns: A `SequenceCategoricalColumn`. Raises: ValueError: `hash_bucket_size` is not greater than 1. ValueError: `dtype` is neither string nor integer. """ return fc.SequenceCategoricalColumn( fc.categorical_column_with_hash_bucket( key=key, hash_bucket_size=hash_bucket_size, dtype=dtype))
def sequence_categorical_column_with_vocabulary_list(key, vocabulary_list, dtype=None, default_value=-1, num_oov_buckets=0): """A sequence of categorical terms where ids use an in-memory list. Pass this to `embedding_column` or `indicator_column` to convert sequence categorical data into dense representation for input to sequence NN, such as RNN. Example: ```python colors = sequence_categorical_column_with_vocabulary_list( key='colors', vocabulary_list=('R', 'G', 'B', 'Y'), num_oov_buckets=2) colors_embedding = embedding_column(colors, dimension=3) columns = [colors_embedding] features = tf.parse_example(..., features=make_parse_example_spec(columns)) sequence_feature_layer = SequenceFeatures(columns) sequence_input, sequence_length = sequence_feature_layer(features) sequence_length_mask = tf.sequence_mask(sequence_length) rnn_cell = tf.keras.layers.SimpleRNNCell(hidden_size) rnn_layer = tf.keras.layers.RNN(rnn_cell) outputs, state = rnn_layer(sequence_input, mask=sequence_length_mask) ``` Args: key: A unique string identifying the input feature. vocabulary_list: An ordered iterable defining the vocabulary. Each feature is mapped to the index of its value (if present) in `vocabulary_list`. Must be castable to `dtype`. dtype: The type of features. Only string and integer types are supported. If `None`, it will be inferred from `vocabulary_list`. default_value: The integer ID value to return for out-of-vocabulary feature values, defaults to `-1`. This can not be specified with a positive `num_oov_buckets`. num_oov_buckets: Non-negative integer, the number of out-of-vocabulary buckets. All out-of-vocabulary inputs will be assigned IDs in the range `[len(vocabulary_list), len(vocabulary_list)+num_oov_buckets)` based on a hash of the input value. A positive `num_oov_buckets` can not be specified with `default_value`. Returns: A `SequenceCategoricalColumn`. Raises: ValueError: if `vocabulary_list` is empty, or contains duplicate keys. ValueError: `num_oov_buckets` is a negative integer. ValueError: `num_oov_buckets` and `default_value` are both specified. ValueError: if `dtype` is not integer or string. """ return fc.SequenceCategoricalColumn( fc.categorical_column_with_vocabulary_list( key=key, vocabulary_list=vocabulary_list, dtype=dtype, default_value=default_value, num_oov_buckets=num_oov_buckets))
def sequence_categorical_column_with_vocabulary_file(key, vocabulary_file, vocabulary_size=None, num_oov_buckets=0, default_value=None, dtype=dtypes.string): """A sequence of categorical terms where ids use a vocabulary file. Pass this to `embedding_column` or `indicator_column` to convert sequence categorical data into dense representation for input to sequence NN, such as RNN. Example: ```python states = sequence_categorical_column_with_vocabulary_file( key='states', vocabulary_file='/us/states.txt', vocabulary_size=50, num_oov_buckets=5) states_embedding = embedding_column(states, dimension=10) columns = [states_embedding] features = tf.parse_example(..., features=make_parse_example_spec(columns)) sequence_feature_layer = SequenceFeatures(columns) sequence_input, sequence_length = sequence_feature_layer(features) sequence_length_mask = tf.sequence_mask(sequence_length) rnn_cell = tf.keras.layers.SimpleRNNCell(hidden_size) rnn_layer = tf.keras.layers.RNN(rnn_cell) outputs, state = rnn_layer(sequence_input, mask=sequence_length_mask) ``` Args: key: A unique string identifying the input feature. vocabulary_file: The vocabulary file name. vocabulary_size: Number of the elements in the vocabulary. This must be no greater than length of `vocabulary_file`, if less than length, later values are ignored. If None, it is set to the length of `vocabulary_file`. num_oov_buckets: Non-negative integer, the number of out-of-vocabulary buckets. All out-of-vocabulary inputs will be assigned IDs in the range `[vocabulary_size, vocabulary_size+num_oov_buckets)` based on a hash of the input value. A positive `num_oov_buckets` can not be specified with `default_value`. default_value: The integer ID value to return for out-of-vocabulary feature values, defaults to `-1`. This can not be specified with a positive `num_oov_buckets`. dtype: The type of features. Only string and integer types are supported. Returns: A `SequenceCategoricalColumn`. Raises: ValueError: `vocabulary_file` is missing or cannot be opened. ValueError: `vocabulary_size` is missing or < 1. ValueError: `num_oov_buckets` is a negative integer. ValueError: `num_oov_buckets` and `default_value` are both specified. ValueError: `dtype` is neither string nor integer. """ return fc.SequenceCategoricalColumn( fc.categorical_column_with_vocabulary_file( key=key, vocabulary_file=vocabulary_file, vocabulary_size=vocabulary_size, num_oov_buckets=num_oov_buckets, default_value=default_value, dtype=dtype))