View source on GitHub |
A CategoricalColumn
with a vocabulary file. (deprecated)
tf.compat.v1.feature_column.categorical_column_with_vocabulary_file(
key,
vocabulary_file,
vocabulary_size=None,
num_oov_buckets=0,
default_value=None,
dtype=tf.dtypes.string
)
Use this when your inputs are in string or integer format, and you have a
vocabulary file that maps each value to an integer ID. By default,
out-of-vocabulary values are ignored. Use either (but not both) of
num_oov_buckets
and default_value
to specify how to include
out-of-vocabulary values.
For input dictionary features
, features[key]
is either Tensor
or
SparseTensor
. If Tensor
, missing values can be represented by -1
for int
and ''
for string, which will be dropped by this feature column.
Example with num_oov_buckets
:
File '/us/states.txt' contains 50 lines, each with a 2-character U.S. state
abbreviation. All inputs with values in that file are assigned an ID 0-49,
corresponding to its line number. All other values are hashed and assigned an
ID 50-54.
import tensorflow as tf
states = tf.feature_column.categorical_column_with_vocabulary_file(
key='states', vocabulary_file='states.txt', vocabulary_size=5,
num_oov_buckets=1)
columns = [states]
features = {'states':tf.constant([['california', 'georgia', 'michigan',
'texas', 'new york'], ['new york', 'georgia', 'california', 'michigan',
'texas']])}
linear_prediction = tf.compat.v1.feature_column.linear_model(features,
columns)
Example with default_value
:
File '/us/states.txt' contains 51 lines - the first line is 'XX', and the
other 50 each have a 2-character U.S. state abbreviation. Both a literal 'XX'
in input, and other values missing from the file, will be assigned ID 0. All
others are assigned the corresponding line number 1-50.
import tensorflow as tf
states = tf.feature_column.categorical_column_with_vocabulary_file(
key='states', vocabulary_file='states.txt', vocabulary_size=6,
default_value=0)
columns = [states]
features = {'states':tf.constant([['california', 'georgia', 'michigan',
'texas', 'new york'], ['new york', 'georgia', 'california', 'michigan',
'texas']])}
linear_prediction = tf.compat.v1.feature_column.linear_model(features,
columns)
And to make an embedding with either:
import tensorflow as tf
states = tf.feature_column.categorical_column_with_vocabulary_file(
key='states', vocabulary_file='states.txt', vocabulary_size=5,
num_oov_buckets=1)
columns = [tf.feature_column.embedding_column(states, 3)]
features = {'states':tf.constant([['california', 'georgia', 'michigan',
'texas', 'new york'], ['new york', 'georgia', 'california', 'michigan',
'texas']])}
input_layer = tf.keras.layers.DenseFeatures(columns)
dense_tensor = input_layer(features)
Returns | |
---|---|
A CategoricalColumn with a vocabulary file.
|