Additional Notes - Aster Analytics

Teradata Aster Analytics Foundation User Guide

Product
Aster Analytics
Release Number
6.21
Published
November 2016
Language
English (United States)
Last Update
2018-04-14
dita:mapPath
kiu1466024880662.ditamap
dita:ditavalPath
AA-notempfilter_pdf_output.ditaval
dita:id
B700-1021
lifecycle
previous
Product Category
Software

Specify the supporting files (dictionary model or file, classification model) with the ModelTable argument in AMLGenerator.

The following examples show variations in usage of the dictionary and classification model.

Example 1: Use Default Model

The Language argument determines the default model.

ModelTable ('default_sentiment_lexicon.txt')
ModelTag ('DICT')
InstalledFile ('true')

For Chinese language text, the default model is default_sentiment_lexicon_zh_cn.txt (for Simplified Chinese) and default_sentiment_lexicon_zh_tw.txt (for traditional Chinese).

Example 2: Use Dictionary Table as Model

ModelTable ('dict_table')
ModelTag ('DICT')
InstalledFile ('false')

Example 3: Use Both Dictionary Table and Dictionary File

The dictionary file is different from the default. The sentiment words from the dictionary table have a higher priority than those in the dictionary file.

ModelTable ('sentiment_lexicon.txt', 'dict_table')
InstalledFile ('true', 'false')
ModelTag ('DICT', 'DICT')
RequestArgName1 ('Model')
RequestArgVal1 ('dictionary:sentiment_lexicon.txt')

Example 4: Use Classification File

ModelTable ('sentiment_classification_model.bin')
InstalledFile ('true')
ModelTag ('CLASS')
RequestArgName1 ('Model')
RequestArgVal1 ('classification:sentiment_classification_model.bin')