# Temperature on the train file

**URL:** <https://community.drivendata.org/t/temperature-on-the-train-file/2656>\
**Category:** Cold Start Energy Forecasting\
**Created:** [September 12, 2018, 3:13am UTC](https://community.drivendata.org/t/temperature-on-the-train-file/2656 "2018-09-12T03:13:38Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![rosgori](https://avatars.discourse-cdn.com/v4/letter/r/7ab992/32.png) [@rosgori](https://community.drivendata.org/u/rosgori)\
**Post date:** [September 12, 2018, 3:13am UTC](https://community.drivendata.org/t/temperature-on-the-train-file/2656/1 "2018-09-12T03:13:38Z")

</div>

I want to read reasons to drop (or not) the column `temperature` in `consumption_train.csv`.

---

<div class="post-metadata">

**Author:** ![iandzindo](https://yyz2.discourse-cdn.com/flex028/user_avatar/community.drivendata.org/iandzindo/32/749_2.png) [@iandzindo](https://community.drivendata.org/u/iandzindo)\
**Post date:** [September 29, 2018, 8:08am UTC](https://community.drivendata.org/t/temperature-on-the-train-file/2656/2 "2018-09-29T08:08:59Z")

</div>

About 44% of temperature values are missing in the consumption\_train file. It’s really up to you whether you want to drop this column completely, or maybe try and fill in these missing values.