https://github.com/sol-eng/tensorflow-w-r

TensorFlow with R
https://github.com/sol-eng/tensorflow-w-r

keras modeling r rstudio-server shiny tensorflow tensorflow-tutorials tidyverse

Last synced: 2 months ago
JSON representation

TensorFlow with R

• Host: GitHub
• URL: https://github.com/sol-eng/tensorflow-w-r
• Owner: sol-eng
• License: apache-2.0
• Created: 2018-10-09T22:46:58.000Z (about 6 years ago)
• Default Branch: main
• Last Pushed: 2021-11-12T13:13:53.000Z (about 3 years ago)
• Last Synced: 2024-07-31T19:18:06.994Z (5 months ago)
• Topics: keras, modeling, r, rstudio-server, shiny, tensorflow, tensorflow-tutorials, tidyverse
• Language: HTML
• Homepage:
• Size: 13.3 MB
• Stars: 46
• Watchers: 7
• Forks: 11
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
Tensorflow with R

======================================================

![](images/tfwr.png)

## Contents

### R Notebook

R document that details the process of creating and deploying the model.  

- Copy published to RStudio Connect: http://colorado.rstudio.com/rsc/content/1553/tensorflow-w-r.nb.html

### Exported Keras/Tensorflow model

A folder that contains a Keras Neural Network model developed, and created in the R Notebook.  The resulting files are Tensorflow, not R.  The main file is a [Protocol Buffer](https://developers.google.com/protocol-buffers/?hl=en)

The model was also deployed to RStudio Connect and can be found here: http://colorado.rstudio.com/rsc/connect/#/apps/2230/access

### Shiny app

Source code for the Shiny application that uses the deployed Keras model in RStudio Connect as its source.  It uses `shinymaterial` to make it more mobile-friendly.

- Deployed app on RStudio Connect: http://colorado.rstudio.com/rsc/churn/overtime/

- Short link to the same app: http://rstd.io/churn





### Presentation 

Companion presentation deck in PDF format: https://github.com/sol-eng/tensorflow-w-r/blob/master/presentation/tensorflow-w-R.pdf







### Automated workflow

An example of how to automate the workflow using the `drake` package is in the **workflow** folder. 

- Published R Notebook: http://colorado.rstudio.com/rsc/content/2159/tensorflow-drake.nb.html