35.3 The Data Mining Sample Data

The data used by the sample data mining programs is based on these tables in the SH schema:

SH.CUSTOMERS 
SH.SALES 
SH.PRODUCTS 
SH.SUPPLEMENTARY_DEMOGRAPHICS
SH.COUNTRIES 

The dmshgrants script grants SELECT access to the tables in SH. The dmsh.sql script creates views of the SH tables in the schema of the data mining user. The views are described in the following table:

Table 35-2 The Data Mining Sample Data

View Name Description

MINING_DATA

Joins and filters data

MINING_DATA_BUILD_V

Data for building models

MINING_DATA_TEST_V

Data for testing models

MINING_DATA_APPLY_V

Data to be scored

MINING_BUILD_TEXT

Data for building models that include text

MINING_TEST_TEXT

Data for testing models that include text

MINING_APPLY_TEXT

Data, including text columns, to be scored

MINING_DATA_ONE_CLASS_V

Data for anomaly detection

The association rules program creates its own transactional data.