# Training empty data

**URL:** <https://community.drivendata.org/t/training-empty-data/495>\
**Category:** From Fog Nets to Neural Nets\
**Created:** [March 27, 2016, 3:19pm UTC](https://community.drivendata.org/t/training-empty-data/495 "2016-03-27T15:19:19Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Seiji](https://avatars.discourse-cdn.com/v4/letter/s/fbc32d/32.png) [@Seiji](https://community.drivendata.org/u/Seiji)\
**Post date:** [March 27, 2016, 3:19pm UTC](https://community.drivendata.org/t/training-empty-data/495/1 "2016-03-27T15:19:20Z")

</div>

Hi guys,

I noticed that the first few rows of the training data doesn’t have values.  
Was this done intentionally?  
Thank you

---

<div class="post-metadata">

**Author:** ![bull](https://yyz2.discourse-cdn.com/flex028/user_avatar/community.drivendata.org/bull/32/8_2.png) [@bull](https://community.drivendata.org/u/bull)\
**Post date:** [March 29, 2016, 5:05pm UTC](https://community.drivendata.org/t/training-empty-data/495/2 "2016-03-29T17:05:02Z")

</div>

It wasn’t removed intentionally, but it is missing from the dataset as indicated. The measurement devices were being initialized during this time. You could either drop those first 4 measurements for training purposes or impute the fog water data using the datasets that have measurements during that time.