project_retrieval_app.py

import streamlit as st

st.set_page_config(page_title="Start")
st.markdown("""
# Searching Python projects with neural networks

## Authors

- Jakub Bartczuk
- Paweł Rychlikowski (promotor)

## Motivation
The following application illustrates neural network based models for searching github.

With over 500 starred repositories searching through them became cumbersome. I did a [small project for retrieval on starred repositories](https://github.com/lambdaofgod/examples-counterexamples/blob/master/notebooks/text_mining/Github_Starred_Repositories.ipynb) which looked promising, but it is hard to gauge how useful such solution would be in practice.

In the thesis I use [PapersWithCode](https://paperswithcode.com/) data for information retrieval.

PapersWithCode contains links between papers and repositories that implement them. Most repositories are tagged with at least one task like "unsupervised segmentation" or "semantic parsing".

Tasks are research topics like "object detection" or "multivariate time series imputation".

## Features
- [x] Searching using Neural Bag of Words features
- [ ] Searching using selectable model
  - [ ] add Word2Vec on READMEs

""")