Skip to Content
Technical Articles

Getting Started with SAP HANA Cloud VI | Machine Learning

With this blog series we provide an update with the latest information on getting started with SAP HANA Cloud on the SAP Cloud Platform.

  • Blog I – About SAP HANA Cloud with some background information and references.
  • Blog II – Creating an instance, connecting clients, sample app, and working with HDI containers.
  • Blog III – Connecting SAP Analytics Cloud using the HANA Analytics Adapter.
  • Blog IV – Cloud Foundry space travel, working with multiple instances, and defining schema names.
  • Blog V – Data masking and data anonymization.
  • Blog VI – Predictive Analysis Library (PAL) and Automated Predictive Library (APL).
  • Blog VII – Remote data access (multicloud) using remote sources and virtual tables.
  • Blog VIII – Working with SAP Web IDE for HANA Development and the SAP Cloud Platform Cloud Foundry environment.
  • Blog IX – SAP HANA Cloud and Smart Data Integration.

Any good? Post a comment, share on social media, and/or give a like. Thanks!

For more information about the free trial, see

/wp-content/uploads/2016/02/sapnwabline_885687.png

Using the Machine Learning Libraries in SAP HANA Cloud

Chief partner engineer, Philip MUGGLESTONE just updated his SAP HANA Cloud playlist on the SAP HANA Academy YouTube channel with a new video covering the machine learning libraries native to SAP HANA Cloud

  • PAL  – Predictive Analysis Library
  • APL – Automated Predictive Library

In this blog, you will find the video embedded with some additional information and resources.

You can watch the video tutorial in just under 12 minutes. What you get back is

  • Understand the prerequisites
  • Getting started with PAL
  • Getting started with APL

For those less familiar with the machine learning libraries: PAL is a native (built-in) application function library (AFL) for SAP HANA. APL bundles the algorithms of SAP Predictive Analytics which goes back to KXEN InfiniteInsight, acquired by SAP in 2013. Both AFLs can be used for linear regression and other common algorithms.

To continue your machine learning journey on SAP HANA Cloud, the following blog post is highly recommended:

Prerequisites

As with the SAP HANA platform edition (on-premises), we need to enable the script server process. Currently, this currently requires a service request on component HAN-CLS-HC (as documented). In addition, we need to create an SAP HANA Cloud instance with a minimum of 3 vCPUs. Scaling an existing SAP HANA Cloud instance up from 2 to 3 vCPUs currently also requires a service request and this can be combined.

The SAP HANA Cloud trial instance is fixed a 2 vCPUs and does not support AFLs (time of writing).

YouTube Playlist

For the complete list of tutorial videos for this playlist, see,

GitHub Code Repository

For the sample code repository, go to

Documentation

/wp-content/uploads/2016/02/sapnwabline_885687.png

Machine Learning – PAL & APL

In this tutorial, we get a brief overview about how to enable the application function libraries for SAP HANA cloud with a code walkthrough for both PAL and APL with references to the documentation.

[00:00] – Introduction and documentation

[00:30] – prerequisites: configure at least 3 vCPUs and enable script server

[01:45] – sample code ML_setup.sql

[02:00] – Setup preparations using Database Explorer

grant AFL__SYS_AFL_AFLPAL_EXECUTE to MYUSER;
grant "sap.pa.apl.base.roles::APL_EXECUTE" to MYUSER;

[04:15] – sample code ML_PAL.sql

[05:00] – create view, parameter tables, call a PAL function, working with results.

[07:00] – SAP HANA Cloud Predictive Analysis Library (PAL) reference guide

[07:20] – SAP HANA Academy – Predictive Analysis Library

[07:45] – APL Developer Guide

[08:00] – sample code ML_APL.sql

/wp-content/uploads/2016/02/sapnwabline_885687.png

Share and Connect

Enjoyed the blog? Post a comment, share on social media, and/or give a like. Thanks!

If you would like to receive updates, connect with me on

Best,

Denys van Kempen

/wp-content/uploads/2016/02/sapnwabline_885687.png

 

Be the first to leave a comment
You must be Logged on to comment or reply to a post.