> For the complete documentation index, see [llms.txt](https://docs.everesteer.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.everesteer.ai/for-developers/offline-scoring-toolkit.md).

# Offline scoring toolkit

The `scoring` extra ships a faithful, dependency-light re-implementation of the platform's CORR20, AIMC and NCORR transforms, so you can score your predictions offline before you ever spend a live round or a capped submission.

```bash
pip install "everestapi[scoring]"
```

{% tabs %}
{% tab title="Tournament" %}
Validate before you spend a round.

```python
from everestapi import scoring

val = pd.read_parquet(client.download_dataset(split="validation"))
feature_cols = [c for c in val.columns if c.startswith("feature_")]
preds = my_model.predict(val[feature_cols])

# score per exped (cross-section), then average
corrs = [
    scoring.corr20(preds[val.exped_id == e], val.loc[val.exped_id == e, "target"])
    for e in val.exped_id.unique()
]
```

{% endtab %}

{% tab title="Hackathon" %}
Score a holdout you carve from the labeled `train` split, before you spend a run on the currently open round.

```python
from everestapi import scoring

# holdout: a slice of train, after your fit window, matching the primary target's horizon
preds = my_model.predict(holdout[feature_cols])

corrs = [
    scoring.corr20(preds[holdout.exped_id == e], holdout.loc[holdout.exped_id == e, "target_everest_20"])
    for e in holdout.exped_id.unique()
]
```

{% endtab %}
{% endtabs %}

{% hint style="warning" %}
This scores your own labels against your own holdout, for tuning only. The official round score is server-side, against an answer key you never receive.

Read the current payout weights from `explain_scoring` rather than hardcoding them. `scoring.payout()` requires them as explicit keyword arguments by design, so a stale weight cannot silently drift from platform config.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.everesteer.ai/for-developers/offline-scoring-toolkit.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.