SAP HANA: My Experiences with SAP Business Objects Predictive Analysis tool
I am sure many of you are aware of SAP’s latest innovation in “Analytics” space i.e SAP Business Objects Predictive Analysis tool.
Let us see how this tool works, in this document I will discuss my experiences in using this tool.
Step 1: Login to SAP Business Objects Predictive Analysis tool as shown below and you will find the “welcome” page where all the related “Tutorials” and “Demo” videos are kept.
Step 2: Create a “New Analysis” as shown below:
In this walk-through, we shall analyze the famous “IRIS” data set; I have it in “.txt” format.
Step 3: Drag “CSV Reader” from components under “Data Reader” as shown below:
Now define the properties as shown below,
We can run the analysis till here , which will give us the table output as shown below:
Now let us use “R-K means” Clustering algorithm and let us divide the data into clusters.
Step 4: Drag the R-K means under clustering algorithms as shown below:
Now define the properties like, on which column this algorithm should run and also advanced properties like which algorithm method to be used.
In this case I choose all the columns and select “Hartigan and Wong” algorithm as shown below:
Now let us run the Analysis till here and let us highlight the newly added column “ClusterNumber” with “Blue” as shown below:
Step 5: Analyze the data:
We can also analyze the “cluster graph” not only as table shown above but also as shown below:
To understand what happened we can choose “Algorithm Summary” as shown below:
We can also do Ad-hoc analysis using “Ad-hoc chart” as shown below:
And then we can write back the new file with additional column using “CSV writer” as shown below:
Step 6: Write back the data .
Regarding SAP HANA, we can use “HANA Reader”
The HANA Reader component enables you to read data from the SAP HANA database only. Using this component, you can understand the data, look for patterns, and visualize the data using various visualization techniques. Use this component if you want to use Predictive Analysis Library (PAL) algorithms provided by SAP HANA.
Note: If you choose to use HANA Reader to read the data, you are not allowed to use SAP and R specific algorithms.
So the algorithm which I was able to use before cannot be used on top of “HANA” data, I have to use PAL algorithms.
Step 1: Drag HANA Reader as shown below:
Step 2: Make a new connection as shown below, enter port number = 30015
Now you can connect to that server instance and able to access all “Tables” and “Analysis Views” as shown below:
And we can analyze the data as shown below:
Hence we completed our walk-through.
Also read my blog on
Hope you felt the power of SAP BO Predictive Analysis, Latest innovation from the SAP to enter into Analytics Market 🙂
Hope you liked this blog. Please do comment your views 🙂