HMMEvaluator Arguments - Teradata Vantage

Machine Learning Engine Analytic Function Reference

Product
Teradata Vantage
Release Number
8.00
1.0
Published
May 2019
Language
English (United States)
Last Update
2019-11-22
dita:mapPath
blj1506016597986.ditamap
dita:ditavalPath
blj1506016597986.ditaval
dita:id
B700-4003
lifecycle
previous
Product Category
Teradata Vantageā„¢
InitStateModelColumn
Specify the model_key_attribute column in the InitStateProb table.
InitStateColumn
Specify the state_key_attribute column in the InitStateProb table.
InitStateProbColumn
Specify the probability column in the InitStateProb table.
TransAttributeColumn
Specify the model_attribute column in the TransProb table.
TransFromStateColumn
Specify the from_state_key_attribute column in the TransProb table.
TransToStateColumn
Specify the to_state_key_attribute column in the TransProb table.
TransProbColumn
Specify the probability column in the TransProb table.
EmitModelColumn
Specify the model_attribute column in the EmissionProb table.
EmitStateColumn
Specify the state_key_attribute column in the EmissionProb table.
EmitObsColumn
Specify the observed_key_attribute column in the EmissionProb table.
EmitProbColumn
Specify the probability column in the EmissionProb table.
ModelColumn
Specify the name of the column that contains the model attribute. Then model_column must match a model_key in the PARTITION BY clause.
SeqColumn
Specify the name of the column that contains the sequence attribute. The sequence_column must be a sequence attribute in the PARTITION BY clause.
ObsColumn
Specify the name of the column that contains the observed symbols.
Observed symbols are case-sensitive.
Incremental
[Optional] Specify whether to compute only new sequence probabilities.
If you omit the SeqProbColumn argument, the function cannot determine whether the observed sequence is new; therefore, it treats all model sequences in the input tables as new.
Default: 'true'
ShowChangeRate
[Optional] Specify whether to show the percentage change that corresponds to the applied model with the difference from previous predicted probability.
Default: 'true'
SeqProbColumn
[Optional] Specify the name of the column that contains the values for calculating the change rate.
SkipColumn
[Optional] Specify the name of the input column whose value determines whether the function skips the row.
Accumulate
[Optional] Specify the names of the input_table columns to copy to the output table.