# Is Feature Column still relevant?

**URL:** <https://community.deeplearning.ai/t/is-feature-column-still-relevant/133284>\
**Category:** Data Pipelines with TensorFlow Data Services\
**Tags:** week-module-3\
**Created:** [May 31, 2022, 5:18pm UTC](https://community.deeplearning.ai/t/is-feature-column-still-relevant/133284 "2022-05-31T17:18:24Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Constantine\_Bardis](https://avatars.discourse-cdn.com/v4/letter/c/58956e/32.png) [@Constantine\_Bardis](https://community.deeplearning.ai/u/Constantine_Bardis)\
**Post date:** [May 31, 2022, 5:18pm UTC](https://community.deeplearning.ai/t/is-feature-column-still-relevant/133284/1 "2022-05-31T17:18:24Z")

</div>

Hi,

I’d like to ask, is the material on feature columns still relevant? I am talking about the “# Classify structured data with feature columns” notebook, since the authors themselves say that should be avoided for new code in favor of using Keras’s built-in layers for preprocessing.

---

<div class="post-metadata">

**Author:** ![reinoudbosch](https://avatars.discourse-cdn.com/v4/letter/r/22d042/32.png) [@reinoudbosch](https://community.deeplearning.ai/u/reinoudbosch)\
**Post date:** [May 19, 2023, 3:35pm UTC](https://community.deeplearning.ai/t/is-feature-column-still-relevant/133284/2 "2023-05-19T15:35:29Z")

</div>