ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more

tf.feature_column.numeric_column

Represents real valued or numerical features.

Used in the notebooks

Used in the guide Used in the tutorials

Example:

Assume we have data with two features a and b.

data = {'a': [15, 9, 17, 19, 21, 18, 25, 30],
   'b': [5.0, 6.4, 10.5, 13.6, 15.7, 19.9, 20.3 , 0.0]}

Let us represent the features a and b as numerical features.

a = tf.feature_column.numeric_column('a')
b = tf.feature_column.numeric_column('b')

Feature column describe a set of transformations to the inputs.

For example, to "bucketize" feature a, wrap the a column in a feature_column.bucketized_column. Providing 5 bucket boundaries, the bucketized_column api will bucket this feature in total of 6 buckets.

a_buckets = tf.feature_column.bucketized_column(a,
   boundaries=[10, 15, 20, 25, 30])

Create a DenseFeatures layer which will apply the transformations described by the set of tf.feature_column objects:

feature_layer = tf.keras.layers.DenseFeatures([a_buckets, b])
print(feature_layer(data))
tf.Tensor(
[[ 0.   0.   1.   0.   0.   0.   5. ]
 [ 1.   0.   0.   0.   0.   0.   6.4]
 [ 0.   0.   1.   0.   0.   0.  10.5]
 [ 0.   0.   1.   0.   0.   0.  13.6]
 [ 0.   0.   0.   1.   0.   0.  15.7]
 [ 0.   0.   1.   0.   0.   0.  19.9]
 [ 0.   0.   0.   0.   1.   0.  20.3]
 [ 0.   0.   0.   0.   0.   1.   0. ]], shape=(8, 7), dtype=float32)

key A unique string identifying the input feature. It is used as the column name and the dictionary key for feature parsing configs, feature Tensor objects, and feature columns.
shape An iterable of integers specifies the shape of the Tensor. An integer can be given which means a single dimension Tensor with given width. The Tensor representing the column will have the shape of [batch_size] + shape.
default_value A single value compatible with dtype or an iterable of values compatible with dtype which the column takes on during tf.Example parsing if data is missing. A default value of None