Skip to Content

Prepare to import SAP Predictive Analytics Datasets

Previous

Prepare to import SAP Predictive Analytics Datasets

By Abdel DADOUCHE

Prepare to import SAP Predictive Analytics Sample Dataset in your SAP HANA, express edition instance

Details

You will learn

As part of the SAP Predictive Analytics documentation, you can download sample datasets to address many Machine learning scenarios.

In this tutorial, you will learn how to import all the SAP Predictive Analytics sample dataset into your SAP HANA, express edition instance.

For each data set, you will be provided with the table creation DDL and IMPORT FROM SQL statement if you choose that route.

Prerequisite: Prepare your environment

The steps detailed in this tutorial and the related links will assume that you have completed the following tutorial:

Please log in to access this content.
Prerequisite : Create a dedicated schema

In addition, it is a good practice to separate data into different schema based on their origin.

In this tutorial, you will be using the PA_DATA schema to load the SAP Predictive Analytics sample data.

If you have already created the schema, move to the next step.

Connect to the HXE tenant using the ML_USER user credentials and execute the following SQL statement:

CREATE SCHEMA PA_DATA;
Please log in to access this content.
Info: Import methods

Importing flat data set files like CSV can be achieved in multiple ways.

The following links provide details about the most common methods:

  • Using the SAP HANA Tools for Eclipse

    If you are planning on using the Import feature from the SAP HANA Tools for Eclipse, you will need to download the dataset file on the Eclipse host.

  • Using the IMPORT FROM SQL command

    If you are planning on using the IMPORT FROM SQL command, you will either directly download or transfer the dataset file on your SAP HANA, express edition host. The tutorial will demonstrate a direct download using WGET.

    As explained in the IMPORT FROM SQL command how to guide, the import is by default only possible from the /usr/sap/HXE/HDB90 directory.

Please log in to access this content.
Info: SAP Predictive Analytics Datasets

The SAP Predictive Analytics Datasets are available as part of the online documentation.

Open the online documentation page in a browser and click on the View All for the Sample section.

This will display the list of sample dataset available.
info doc

Please log in to access this content.
Import: Association Rules Dataset

You can refer to the following tutorial to import the dataset: Import SAP Predictive Analytics Association Rules

Provide an answer to the question below then click on Validate.

What is the primary key column for the CUSTOMERS_REFERENCES table?
×
Import: Census Dataset

You can refer to the following tutorial to import the dataset: Import SAP Predictive Analytics Census Dataset

Provide an answer to the question below then click on Validate.

How many columns does the Census table contains?
×
Import: Geo localization Dataset

You can refer to the following tutorial to import the dataset: Import SAP Predictive Analytics Geo localization Dataset

Provide an answer to the question below then click on Validate.

What TIMESTAMP format was used to loaded the Gowalla data (as described in step 3)?
×
Import: Social Dataset

You can refer to the following tutorial to import the dataset: Import SAP Predictive Analytics Social Datasets

Provide an answer to the question below then click on Validate.

What is the primary key column for the LINKS_SN_NODES table?
×
Import: Text Coding Dataset

You can refer to the following tutorial to import the dataset: Import SAP Predictive Analytics Text Coding Datasets

Provide an answer to the question below then click on Validate.

What TIMESTAMP format was used to loaded the DMC2006_ENRICHED data (as described in step 3)?
×
Import: Time Series Dataset

You can refer to the following tutorial to import the dataset: Import SAP Predictive Analytics Time Series Datasets

Provide an answer to the question below then click on Validate.

How many columns does the CASHFLOW table contains?
×

Updated 03/27/2018

Time to Complete

10 Min.

Beginner
Next
Back to top