Retrievalrecall

---
name: retrievalrecall
description: Compute the RetrievalRecall metric — provided by torchmetrics. Use when the user has predictions and ground-truth and needs to compute RetrievalRecall, or asks how to score with RetrievalRecall.
metadata:
  skill_kind: metric
  source_lib: torchmetrics
  import_path: torchmetrics.RetrievalRecall
  source: library_introspection
---

# retrievalrecall

> Metric `RetrievalRecall` from `torchmetrics` (torchmetrics.RetrievalRecall)

## When to invoke this skill

The user has predictions + ground truth and asks to evaluate with RetrievalRecall, or
mentions `torchmetrics.RetrievalRecall` directly, or wants the standard torchmetrics implementation.

## Reference signature

```python
from torchmetrics import RetrievalRecall

# _RetrievalRecall(empty_target_action: str = 'neg', ignore_index: Optional[int] = None, top_k: Optional[int] = None, **kwargs: Any) -> None
```

## Library docstring

```
Wrapper for deprecated import.

>>> from torch import tensor
>>> indexes = tensor([0, 0, 0, 1, 1, 1, 1])
>>> preds = tensor([0.2, 0.3, 0.5, 0.1, 0.3, 0.5, 0.2])
>>> target = tensor([False, False, True, False, True, False, True])
>>> r2 = _RetrievalRecall(top_k=2)
>>> r2(preds, target, indexes=indexes)
tensor(0.7500)
```

## Quick recipe

```python
import torchmetrics as _m
score = _m.RetrievalRecall(y_true, y_pred)
```

## Don'ts

- Don't reimplement when the library version handles edge cases (NaN, ties, empty inputs) better than a hand-rolled formula.
- Always check the library version's argument order — sklearn is `(y_true, y_pred)` while torchmetrics is `(preds, target)`.