# Dataset confusion

**URL:** <https://community.drivendata.org/t/dataset-confusion/2421>\
**Category:** DengAI Competition\
**Created:** [June 4, 2018, 10:21am UTC](https://community.drivendata.org/t/dataset-confusion/2421 "2018-06-04T10:21:53Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Paritosh](https://avatars.discourse-cdn.com/v4/letter/p/45deac/32.png) [@Paritosh](https://community.drivendata.org/u/Paritosh)\
**Post date:** [June 4, 2018, 10:21am UTC](https://community.drivendata.org/t/dataset-confusion/2421/1 "2018-06-04T10:21:53Z")

</div>

Hi,  
I have one confusion regarding dataset as train data and test contain two diff excel file one is dengue\_label\_train and other is dengur\_feature\_train. My confusion is do i have to merge these two excel file for train data

---

<div class="post-metadata">

**Author:** ![mostain](https://avatars.discourse-cdn.com/v4/letter/m/ecae2f/32.png) [@mostain](https://community.drivendata.org/u/mostain)\
**Post date:** [August 27, 2018, 11:20am UTC](https://community.drivendata.org/t/dataset-confusion/2421/3 "2018-08-27T11:20:18Z")

</div>

If you look at the submission\_format.csv then you may get your answer.

use dengue\_features\_train.csv data for your classifier then predict label using those features data  
so your ultimate target is to output/predict total\_cases number.