Data science and AI solution accelerator suite that provides templates for prototyping, reporting, and presenting data science analytics of specific domains
Перейти к файлу
Zhang Le 2a451b14cc
Update README.md
2019-07-13 00:18:11 +08:00
CreditRiskPrediction fix some words 2018-10-13 14:35:34 +03:00
EducationAnalytics update student drop out template 2017-08-11 11:22:22 +08:00
EmployeeAttritionPrediction Update README.md 2019-07-13 00:18:11 +08:00
GalaxyClassificationWorkflow add slide deck 2017-04-20 21:13:13 +10:00
GeneralTemplate fix some words 2018-10-13 14:35:34 +03:00
MovieRecommender update READMEs 2018-04-10 16:54:26 +08:00
ProductDemandForecast delete 2017-08-10 11:04:07 +08:00
SolarPanelForecasting Use smaller number of epoch size 2017-11-07 13:00:27 +08:00
flightDelayPredictionWithDSVM Fixed password loading issue 2017-11-27 13:32:02 +08:00
.gitignore Add backup files to be ignored. 2017-03-26 20:37:26 +08:00
LICENSE Initial commit 2017-02-13 22:04:58 -08:00
Makefile Add a generic Makefile to generate all types of documents. 2017-03-26 20:36:24 +08:00
README.md Update README 2018-04-07 16:55:57 +08:00
fix_ipynb.sh Add a generic Makefile to generate all types of documents. 2017-03-26 20:36:24 +08:00

README.md

Introduction

acceleratoRs are a collection of R/Python based lightweight data science and AI solutions that offer quick start for data scientists to experiment, prototype, and present their data analytics of specific domains.

Each of accelerators shared in this repo is structured following the project template of the Microsoft Team Data Science Process, in a simplified and accelerator-friendly version. The analytics are scripted in R markdown (Jupyter notebook), and can be used to conveniently yield outputs in various formats (ipynb, PDF, html, etc.).

How-to

  • To start with a new acceleator project, use GeneralTemplate for initialization. The GeneralTemplate consists of three parts which are Code, Data, and Docs.

    • Code - Codes of analytics for the data science problem is put in the directory. R markdown is recommended for scripting as it is easy to yield pure code as well as report in various formats (e.g., PDF, html, etc.) for the convenient of presenting.
    • Data - Data used for the analytics. It is highly recommended to put sample data in the dictory while providing reference to full set of it.
    • Docs - Normally related documentations, references, and perhaps yielded reports will be put in this directory.
  • An accelerator should be able to run interactively in an IDE that supports R markdown such as R Tools for Visual Studio (RTVS), RStudio, VS Code with AI extensions.

  • Makefile is by default provided to generate documents of other formats, or alternatively rmarkdown::render can be used for the same purpose.

Contributing

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact opencode@microsoft.com with any additional questions or comments.