Help protect the Great Barrier Reef with TensorFlow on Kaggle Join Challenge


Represents real valued or numerical features.

Used in the notebooks

Used in the guide Used in the tutorials


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])
[[ 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 will cause to fail if an example does not contain this column. If a single value is provided, the same value will be applied as the default value for every item. If an iterable of values is provided, the shape of the default_value should be equal to the given shape.
dtype defines the type of values. Default value is tf.float32. Must be a non-quantized, real integer or floating point type.
normalizer_fn If not None, a function that can be used to normalize the value of the tensor after default_value is applied for parsing. Normalizer function takes the input Tensor as its argument, and returns the output Tensor. (e.g. lambda x: (x - 3.0) / 4.2). Please note that even though the most common use case of this function is normalization, it can be used for any kind of Tensorflow transformations.

A NumericColumn.

TypeError if any dimension in shape is not an int
ValueError if any dimension in shape is not a positive integer
TypeError if default_value is an iterable but not compatible with shape
TypeError if default_value is not compatible with dtype.
ValueError if dtype is not convertible to