TD_NaiveBayesTextClassifierPredict Syntax Elements - Teradata Vantage
Teradata® VantageCloud Lake
- Deployment
- VantageCloud
- Edition
- Lake
- Product
- Teradata Vantage
- Published
- January 2023
- ft:locale
- en-US
- ft:lastEdition
- 2024-12-11
- dita:mapPath
- phg1621910019905.ditamap
- dita:ditavalPath
- pny1626732985837.ditaval
- dita:id
- phg1621910019905
- InputTokenColumn
- Specify the name of the PredictorValues column that contains the tokens.
- ModelType
- [Optional] Specify the model type of the text classifier.
- Default: 'Multinomial'
- DocIDColumns
- Specify the names of the PredictorValues columns that contain the document identifier.
- ModelTokenColumn
- [Optional] Specify the name of the Model table column that contains the tokens.
- Default: First column of Model table
- ModelCategoryColumn
- [Optional] Specify the name of the Model table column that contains the prediction categories.
- Default: Second column of Model table
- ModelProbColumn
- [Optional] Specify the name of the Model table column that contains the probability values.
- Default: Third column of Model table
- TopK
- [Disallowed with Responses, otherwise optional.] Specify the number of most likely prediction categories to output with their log-likelihood values (for example, the top 10 most likely prediction categories). To see the probability of each class, use OutputProb ('true').
- Default: All prediction categories
- Responses
- [Disallowed with TopK, otherwise optional.] Specify the labels for which to output log-likelihood values and probabilities (with OutputProb ('true')).
- OutputProb
- Specify whether to output the calculated probability for each observation.
- Default: 'false'
- Accumulate
- Specify the names of the PredictorValues table columns to copy to the output table.
- Specify either all or none of the syntax elements ModelTokenColumn, ModelCategoryColumn, and ModelProbColumn.
- Specifying neither TopK nor Responses is equivalent to specifying TopK.