# Problem in Kaggle with section 3.1 of baseline code

**URL:** <https://community.drivendata.org/t/problem-in-kaggle-with-section-3-1-of-baseline-code/10291>\
**Category:** SNOMED CT Entity Linking\
**Created:** [February 12, 2024, 8:19am UTC](https://community.drivendata.org/t/problem-in-kaggle-with-section-3-1-of-baseline-code/10291 "2024-02-12T08:19:35Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![Augustine](https://avatars.discourse-cdn.com/v4/letter/a/c68b51/32.png) [@Augustine](https://community.drivendata.org/u/Augustine)\
**Post date:** [February 12, 2024, 8:19am UTC](https://community.drivendata.org/t/problem-in-kaggle-with-section-3-1-of-baseline-code/10291/1 "2024-02-12T08:19:35Z")

</div>

Hi all, I hit a bump in the road.

I went through the process of registering and certification to get to the data. Great experience and learning about latest research protocols.

I used Kaggle due to limited access to technical resources. So, the code work fine as I switch to a lower model version and also decreased the batch sizes. The model performed not too bad with an accuracy of 87%.

The section **‘3.1. Load the Knowledge Base’** , in particular with this line of code:**“SG = SnomedGraph.from\_serialized(”…/snomed\_graph/full\_concept\_graph.gml")"**,

I kept on receiving an error that the file don’t exist. Also note, I checked the script, i.e., snomed\_graph.py, and there is no class or function or output called 'full\_concept\_graph.gml.

Also note that i created the script for snomed\_graph.py and import it as a library, as required. Can anyone please direct me to the correct way to solve this. As I am eager to complete the baseline sub and continue.

Thank you

A

---

<div class="post-metadata">

**Author:** ![will\_hardman](https://avatars.discourse-cdn.com/v4/letter/w/b5e925/32.png) [@will\_hardman](https://community.drivendata.org/u/will_hardman)\
**Post date:** [February 12, 2024, 10:12am UTC](https://community.drivendata.org/t/problem-in-kaggle-with-section-3-1-of-baseline-code/10291/2 "2024-02-12T10:12:58Z")

</div>

Hi @Augustine,

The `snomed_graph` utility was created to help participants load the SNOMED Clinical Terminology into a graph data stucture and then to query it.

In section 3.1 of the notebook, the commentary shows you how to create a graph from the raw SNOMED RF2 files (which are structured as tab-delimited, tabular data files) if you haven’t got a prebuilt GML file already.

The line:

```auto
SG = SnomedGraph.from_rf2("SnomedCT_InternationalRF2_PRODUCTION_20230531T120000Z_Challenge_Edition")

```

… will build you a graph. It’ll take a few minutes to complete. You can then save the graph and reload it locally using the notebook code.

For more details on how to use the `snomed_graph` package, see the “usage” notebook in the project’s homepage: [snomed\_graph/usage.ipynb at main · VerataiLtd/snomed\_graph · GitHub](https://github.com/VerataiLtd/snomed_graph/blob/main/usage.ipynb)

Wishing you the best of luck.

Will

---

<div class="post-metadata">

**Author:** ![Augustine](https://avatars.discourse-cdn.com/v4/letter/a/c68b51/32.png) [@Augustine](https://community.drivendata.org/u/Augustine)\
**Post date:** [February 12, 2024, 10:15am UTC](https://community.drivendata.org/t/problem-in-kaggle-with-section-3-1-of-baseline-code/10291/3 "2024-02-12T10:15:53Z")

</div>

@Will,

Thank you for the speedy feedback, much appreciated.

A

---

<div class="post-metadata">

**Author:** ![jmitura](https://avatars.discourse-cdn.com/v4/letter/j/90ced4/32.png) [@jmitura](https://community.drivendata.org/u/jmitura)\
**Post date:** [April 13, 2024, 1:10pm UTC](https://community.drivendata.org/t/problem-in-kaggle-with-section-3-1-of-baseline-code/10291/4 "2024-04-13T13:10:38Z")

</div>

Hello @will_hardman@Augustine and where one can find SnomedCT\_InternationalRF2\_PRODUCTION\_20230531T120000Z folder?  
in [SNOMED CT Entity Linking Challenge v1.0.0](https://physionet.org/content/snomed-ct-entity-challenge/1.0.0/) i can only find what is on image

 ![image](https://canada1.discourse-cdn.com/flex028/uploads/drivendata1/original/2X/a/af717eed465fca2bd2f02eabf61abda2b021df7f.png)