1.0 - 8.00 - NamedEntityFinder Example - Teradata Vantage

Teradata® Vantage Machine Learning Engine Analytic Function Reference

Product
Teradata Vantage
Release Number
1.0
8.00
Release Date
May 2019
Content Type
Programming Reference
Publication ID
B700-4003-098K
Language
English (United States)

Input

Input Table: assortedtext_input
id source content
1001 misc contact Alan by email at sports@espn.com for all sport info
1002 misc contact Mark at cricket@espn.com for all cricket info
1003 misc contact Roger at tennis@espn.com for all tennis info
1004 wiki The contiguous United States consists of the 48 adjoining U.S. states plus Washington, D.C., on the continent of North America
1005 wiki California's economy is centered onTechnology,Finance,real estate services, Government, and professional, Scientific and Technical business Services; together comprising 58% of the State Government economy
1006 wiki Houston is the largest city in Texas and the fourth-largest in the United States, while San Antonio is the second largest and seventh largest in the state.
1007 wiki Thomas is a photographer whose natural landscapes of the West are also a statement about the importance of the preservation of the wildness

SQL Call

SELECT * FROM NamedEntityFinder (
  ON assortedtext_input PARTITION BY ANY
  ON namefind_configure AS ConfigureTable DIMENSION
  USING
  TextColumn ('content')
  Model ('all')
  Accumulate ('id', 'source')
) AS dt;

Output

id source entity entity_type
1002 misc Mark person
1002 misc cricket@espn.com email
1004 wiki United States location
1004 wiki U.S. location
1004 wiki Washington location
1004 wiki North America location
1006 wiki Texas location
1006 wiki United States location
1006 wiki San Antonio location
1001 misc sports@espn.com email
1003 misc Roger person
1003 misc tennis@espn.com email
1005 wiki State Government organization
1005 wiki 58% percentage
1007 wiki Thomas person