TC7.2 - R Studio for Analytics, exploiting Tensor Flow

Primary tabs

Test Case Title

TC7.2 - R Studio for Analytics, exploiting Tensor Flow

Goal

Create a MicroService starting from R Studio processes for Analytics, exploiting Tensor Flow.

Prerequisites

A simple skill for using R Studio to execute Data Analytics and machine learning algorithms.

Using a PC or Mobile with a web browser.

Conquer a minimal skill on producing R programme if you need to change the program or develop a new one.

The following functionalities are available only for specific Snap4city users with specific privileges.

Expected successful result

Create a MicroService for IOT providing support for real time data analytics which is performed by using Tensor Flow via the NVIDIA Titan Xp accessible on the server.

Steps

 

 

Please note that to correctly perform this Test Case you need and access to the R Studio Virtual Machine as described below. To have access to a Virtual Machine to perform R Studio please contact snap4city@disit.org.

 

From R Studio process to MicroService using tensorflow

In this test case we see how to create a MicroService starting from R Studio processes, for data analytics, exploiting Tensor Flow.

  1. The installation of the R-package "tensorflow" is a necessary requirement.

    tensorflow package allows the R interfacing to 'TensorFlow' (https://www.tensorflow.org/), an open source software library for numerical computation using data flow graphs.

 



Fig: ‘TensorFlowRegression.R’ script.

tf$device(‘gpu:0’) allow to select the GPU device.