About former_member186543

former_member186543

Hi Team, We have a very simple requirement around operationalizing an ML pipeline built in SAP HANA for productive usage. We used SAP PA 3.2 expert analytics to train a model chain with different models and have exported it to SAP...

former_member186543

Hello everyone, This should be exciting for all the readers ! We just wanted to share our experience with deploying a custom Deep learned neural network model trained using Tensorflow, to detect human bodies in any image along with their gender on ...

former_member186543

Dear PA Team, In SAP PA 3.2 expert analytics, non-automated( Auto Classification ) classification models like ( C4.5 , CHAID , Naive Bayes etc. ) we get the PredictedValue column in the output. Is there also an option to get the probability or th...

former_member186543

Hi All, I am writing this blog to describe some easy steps to deploy a Python based REST API( Bottle / Flask ) application on the SAP cloud foundry environment. The current python application is a knapsack optimization problem solver created on Pyt...

former_member186543

Hi All, We are trying to build a "support vector ranking" model for a ranking case in PA 3.2 connected to HANA DB. Before trying the same, we have a general question around the Hana Partition function available in PA 3.2, so that we can also get ...

former_member186543

Hi Thomas, An extension to this, I have actually been able to run SAP WebIDE LINUX version on GCP. Destinations can also be configured the same way we do it for windows version. After that you can actually build applications technically over GCP us...

former_member186543

Nice example but this appears as a multiclass classification as compared to ranking. How if there are more than 6 records in a bucket.

former_member186543

Hi Antoine, Thanks a lot my friend for your answer! Stratified sampling won't fit in this case. SVR algorithm takes as input a set of records identified by a column called as group ID. So there are multiple groups, inside which records are ranked...

former_member186543

Hey Michael, Thanks a lot for replying on our analysis with your comments. As you must have read through, PA 3.2 is not able to connect with our HANA APL module due to an error message hence we have not been able to try APL. Whereas I hope this one...

former_member186543

Solved myself ! It's no where mentioned in the documentation that the table types of outputs should match exactly as https://cp.hana.ondemand.com/dps/d/preview/5b8e06cae5be43f5af9dbe72d73bb7a9/2.5/en-US/frameset.htm?a838906e3ecc49d199aa8627a579a2de.h...

User Statistics

User Activity

SAP Predictive factory -> Model auto retrain -> Export as HANA procedure

And we deployed - Human detection API ( Deep Learning ) on SAP Cloud foundry

Probability values in SAP Predictive analytics Classification models

Deploying Flask/Bottle Python app( Rest API ) on SAP Cloud Foundry

Support vector ranking with Data Partition in PA 3.2

Re: SAP Development Using Google Cloud Shell

Re: Predict Supplier Ranking by Integrating SAP Application with Machine Learning Algorithms

Re: Support vector ranking with Data Partition in PA 3.2

Re: SAP PA 3.2 Feedback: Awesome tool but lacks on a few basics.

Re: Error in APL execution via AFM Graph