Pass this to embedding_column or indicator_column to convert sequence
categorical data into dense representation for input to sequence NN, such as
RNN.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2024-04-26 UTC."],[],[],null,["# tf.feature_column.sequence_categorical_column_with_hash_bucket\n\n\u003cbr /\u003e\n\n|------------------------------------------------------------------------------------------------------------------------------------------------------|\n| [View source on GitHub](https://github.com/tensorflow/tensorflow/blob/v2.16.1/tensorflow/python/feature_column/sequence_feature_column.py#L152-L196) |\n\nA sequence of categorical terms where ids are set by hashing. (deprecated)\n| **Warning:** tf.feature_column is not recommended for new code. Instead, feature preprocessing can be done directly using either [Keras preprocessing\n| layers](https://www.tensorflow.org/guide/migrate/migrating_feature_columns) or through the one-stop utility [`tf.keras.utils.FeatureSpace`](https://www.tensorflow.org/api_docs/python/tf/keras/utils/FeatureSpace) built on top of them. See the [migration guide](https://tensorflow.org/guide/migrate) for details.\n\n#### View aliases\n\n\n**Compat aliases for migration**\n\nSee\n[Migration guide](https://www.tensorflow.org/guide/migrate) for\nmore details.\n\n[`tf.compat.v1.feature_column.sequence_categorical_column_with_hash_bucket`](https://www.tensorflow.org/api_docs/python/tf/feature_column/sequence_categorical_column_with_hash_bucket)\n\n\u003cbr /\u003e\n\n tf.feature_column.sequence_categorical_column_with_hash_bucket(\n key,\n hash_bucket_size,\n dtype=../../tf/dtypes#string\n )\n\n| **Deprecated:** THIS FUNCTION IS DEPRECATED. It will be removed in a future version. Instructions for updating: Use Keras preprocessing layers instead, either directly or via the [`tf.keras.utils.FeatureSpace`](../../tf/keras/utils/FeatureSpace) utility. Each of `tf.feature_column.*` has a functional equivalent in `tf.keras.layers` for feature preprocessing when training a Keras model.\n\nPass this to `embedding_column` or `indicator_column` to convert sequence\ncategorical data into dense representation for input to sequence NN, such as\nRNN.\n\n#### Example:\n\n tokens = sequence_categorical_column_with_hash_bucket(\n 'tokens', hash_bucket_size=1000)\n tokens_embedding = embedding_column(tokens, dimension=10)\n columns = [tokens_embedding]\n\n features = tf.io.parse_example(..., features=make_parse_example_spec(columns))\n sequence_feature_layer = SequenceFeatures(columns)\n sequence_input, sequence_length = sequence_feature_layer(features)\n sequence_length_mask = tf.sequence_mask(sequence_length)\n\n rnn_cell = tf.keras.layers.SimpleRNNCell(hidden_size)\n rnn_layer = tf.keras.layers.RNN(rnn_cell)\n outputs, state = rnn_layer(sequence_input, mask=sequence_length_mask)\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Args ---- ||\n|--------------------|--------------------------------------------------------------------|\n| `key` | A unique string identifying the input feature. |\n| `hash_bucket_size` | An int \\\u003e 1. The number of buckets. |\n| `dtype` | The type of features. Only string and integer types are supported. |\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Returns ------- ||\n|---|---|\n| A `SequenceCategoricalColumn`. ||\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n\u003cbr /\u003e\n\n| Raises ------ ||\n|--------------|-------------------------------------------|\n| `ValueError` | `hash_bucket_size` is not greater than 1. |\n| `ValueError` | `dtype` is neither string nor integer. |\n\n\u003cbr /\u003e"]]
View source on GitHub