# Smoke test throws error as data files missing

**URL:** <https://community.drivendata.org/t/smoke-test-throws-error-as-data-files-missing/11051>\
**Category:** Goodnight Moon, Hello Early Literacy Screening\
**Created:** [December 10, 2024, 1:27am UTC](https://community.drivendata.org/t/smoke-test-throws-error-as-data-files-missing/11051 "2024-12-10T01:27:02Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![pankd](https://avatars.discourse-cdn.com/v4/letter/p/94ad74/32.png) [@pankd](https://community.drivendata.org/u/pankd)\
**Post date:** [December 10, 2024, 1:27am UTC](https://community.drivendata.org/t/smoke-test-throws-error-as-data-files-missing/11051/1 "2024-12-10T01:27:02Z")

</div>

I submitted the submission.zip file for the smoke test execution but the runs show error as: FileNotFoundError: [Errno 2] No such file or directory: ‘data/test\_labels.csv’  
The zip file is as per the prescribed format and contains the following:

- main.py at the base
- assets folder with the model & params  
I assume the data folder has to be created and populated at runtime.  
The same zip file has passed the test locally using the container without throwing this error.  
What could be going wrong here in the submission?

Submission Id: id-276254

---

<div class="post-metadata">

**Author:** ![emily](https://avatars.discourse-cdn.com/v4/letter/e/8c91f0/32.png) [@emily](https://community.drivendata.org/u/emily)\
**Post date:** [December 10, 2024, 4:25am UTC](https://community.drivendata.org/t/smoke-test-throws-error-as-data-files-missing/11051/2 "2024-12-10T04:25:19Z")

</div>

There is no `test_labels.csv` in the runtime environment (as those are the answers!). We do include `test_labels.csv` in the smoke test data archive (which is likely what’s in your local `data` directory) since the smoke test data is a subset of the training data. This is so you can ensure the accuracy of your local predictions.

In short, your actual submission shouldn’t expect or reference test labels. You should use the `submission_format.csv` to ensure you’re outputting the correct index and column names in your submission.csv.

---

<div class="post-metadata">

**Author:** ![pankd](https://avatars.discourse-cdn.com/v4/letter/p/94ad74/32.png) [@pankd](https://community.drivendata.org/u/pankd)\
**Post date:** [December 10, 2024, 6:03am UTC](https://community.drivendata.org/t/smoke-test-throws-error-as-data-files-missing/11051/3 "2024-12-10T06:03:23Z")

</div>

Thanks. It worked for me.