SSA Sociobehavioral characteristics and HIV incidence: Unsupervised machine learning techniques

Introduction

This is a Renku project for the longitudinal study on sociobehavioral characteristics and HIV incidence in select SSA countries using unsupervised machine learning techniques.

code directory contains Aziza's original code along with the results obtained as run in the original paper.

data directory contains both the data used in the original paper and new data obtained for this longitudinal study.

notebooks directory containes notebook to play with the original code on the new data and simplify the process.

Working with the project

The simplest way to start your project is right from the Renku platform - just click on the Environments tab and start a new session. This will start an interactive environment right in your browser.

To work with the project anywhere outside the Renku platform, click the Settings tab where you will find the git repo URLs - use git to clone the project on whichever machine you want.

Changing interactive environment dependencies

Using R for the project, the packages used in the original code have been added to install.R and the environment was built upon it. However, you can add python and conda packages in requirements.txt and environment.yml if needed.

## Open a terminal, and run:
dw configure
## Use the following key: 

## eyJhbGciOiJIUzUxMiJ9.eyJzdWIiOiJwcm9kLXVzZXItY2xpZW50Om1yamVmZnBvc3QiLCJpc3MiOiJhZ2VudDptcmplZmZwb3N0Ojo0MWJlYTNkZC1hNTk3LTQxMDctYmU4Zi1kNmYyYTYxYzI2ZTQiLCJpYXQiOjE1NzY0MDU4NDQsInJvbGUiOlsidXNlcl9hcGlfcmVhZCIsInVzZXJfYXBpX3dyaXRlIl0sImdlbmVyYWwtcHVycG9zZSI6dHJ1ZSwic2FtbCI6e319.Oo0y2mt7X2LmNhKDygU2f15V2ULTWyDhQWtMMJfdYaJ2l-XDaJkf4py0htqVIMVY2-BmPKpuqoQuUJGvIRycIw

pip install jupyterlab "ipywidgets>=7.5"

# JupyterLab renderer support
jupyter labextension install jupyterlab-plotly@4.14.1

# OPTIONAL: Jupyter widgets extension
jupyter labextension install @jupyter-widgets/jupyterlab-manager plotlywidget@4.14.1

# Installing better nord theme for jupyterlab
jupyter labextension install @kenshohara/theme-nord-extension

Nomenclature of issues

Any issues concerning this research project can be found under the Collaboration tab "issues":

• PROJECT: used to track main steps required to complete project (do this, do that, etc)
• DATA: concerns any questions pertaining to raw data or data wrangling
• CODE: pertains to questions on code, optimizations, alternative methods, etc..
• METHODS: pertains to methods for the actual research