NumericColumn - Maple Help

DeepLearning

 NumericColumn
 numeric feature column

 Calling Sequence NumericColumn(key,opts)

Parameters

 key - string; label for feature column opts - zero or more options as specified below

Options

 • datatype=one of integer[4],integer[8],float[4],float[8]

The value of option datatype specifies the type of data this column will hold.

 • shape=list of integers

The shape of data the feature represents. A single scalar numerical quantity corresponds to [1]. If the data to represented is a 3x3 matrix, the shape is [3,3].

Description

 • The NumericColumn(c) command creates a feature column to represent a real numerical feature (integer or floating-point).
 • This function is part of the DeepLearning package, so it can be used in the short form NumericColumn(..) only after executing the command with(DeepLearning). However, it can always be accessed through the long form of the command by using DeepLearning[NumericColumn](..).

Details

 • The implementation of NumericColumn uses the tf.feature_column.numeric_column function from the TensorFlow Python API Documentation. Consult the TensorFlow API documentation for tf.feature_column.numeric_column for more information.

Examples

Define a feature which takes a single numeric value, in this case a physical measurement from a flower.

 > $\mathrm{with}\left(\mathrm{DeepLearning}\right):$
 > $\mathrm{fc}≔\mathrm{NumericColumn}\left("SepalLength",\mathrm{shape}=\left[1\right],\mathrm{datatype}={\mathrm{float}}_{8}\right)$
 ${\mathrm{fc}}{≔}\left[\begin{array}{c}{\mathrm{Feature Column}}\\ {\mathrm{NumericColumn\left(key=\text{'}SepalLength\text{'}, shape=\left(1,\right), default_value=None, dtype=tf.float64, normalizer_fn=None\right)}}\end{array}\right]$ (1)

Compatibility

 • The DeepLearning[NumericColumn] command was introduced in Maple 2018.