Metadata-Version: 2.1
Name: efficient-first-stage-retrieval
Version: 0.0.30
Summary: Master Thesis with the L3S at Lebniz University Hannover
Home-page: https://github.com/real-tesco/efficient_first_stage_retrieval/tree/master/
Author: Jesco Brandt
Author-email: luca-brandt@web.de
License: Apache Software License 2.0
Keywords: efficient first stage retrieval information
Platform: UNKNOWN
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Natural Language :: English
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Requires-Python: >=3.6
Description-Content-Type: text/markdown

# Efficient First Stage Retrieval using Dense Representations and KNN
> Summary description here.


This file will become your README and also the index of your documentation.
> test

## Install

`pip install efficient_first_stage_retrieval`

## How to use

Use calculate_score to calculate MAP and MRR from actual qrels in fn_qrels and from predictions in prediction

```python
calculate_score(fn_qrels='data/robust/qrels.robust2004.txt', prediction="score.txt")
```

Use do_run to calculate predictions from 'searcher' and queries 'topic' and used time and store it in file and 'time-' + file

```python
do_run(file, topics, searcher)
```


