pyterrier/nq.pisa

---
# pretty_name: "" # Example: "MS MARCO Terrier Index"
tags:
- pyterrier
- pyterrier-artifact
- pyterrier-artifact.sparse_index
- pyterrier-artifact.sparse_index.pisa
task_categories:
- text-retrieval
viewer: false
---

# nq.pisa

## Description

A PISA index for the NQ (Natural Questions) dataset

## Usage

```python
# Load the artifact
import pyterrier as pt
index = pt.Artifact.from_hf('pyterrier/nq.pisa')
index = pt.bm25() # returns a BM25 retriever
```

## Benchmarks

| name | nDCG@10 | R@1000 |
|:-------|----------:|---------:|
| bm25 | 0.3071 | 0.8977 |
| dph | 0.2988 | 0.8947 |

## Reproduction

```python
import pyterrier as pt
from tqdm import tqdm
import ir_datasets
from pyterrier_pisa import PisaIndex
index = PisaIndex("nq.pisa", threads=16)
dataset = ir_datasets.load('beir/nq')
docs = ({'docno': d.doc_id, 'text': d.default_text()} for d in tqdm(dataset.docs))
index.index(docs)
```

## Metadata

```
{
"type": "sparse_index",
"format": "pisa",
"package_hint": "pyterrier-pisa",
"stemmer": "porter2"
}
```