Key Feature Additions and Changes | Teradata Package for R 17.20 - Key Feature Additions and Changes - Teradata Package for R

Teradata® Package for R User Guide

Deployment
VantageCloud
VantageCore
Edition
Enterprise
IntelliFlex
VMware
Product
Teradata Package for R
Release Number
17.20
Published
March 2024
ft:locale
en-US
ft:lastEdition
2024-04-09
dita:mapPath
efv1707506846369.ditamap
dita:ditavalPath
ayr1485454803741.ditaval
dita:id
nqx1518630623256
Product Category
Teradata Vantage

The following table lists the key feature additions and changes in the Teradata Package for R, tdplyr.

Date Release Description
March 2024 17.20.00.00
  • Added support for Analytics Database Analytic Functions:
    • Model scoring functions
    • Feature engineering transform functions
    • Path and pattern analysis functions
    • Scoring with Machine Learning Engine models functions
    • Data exploration functions
    • Text analytic functions
    • Data cleaning functions
    • Hypothesis testing functions
    • Model evaluation functions
    • Model training functions
    • Feature engineering utility functions
    • Table operator functions
    • BYOM functions
  • New display_analytic_functions() API to display all available analytic functions based on Analytics Database version, and categorize the analytic functions by function type.
  • Following analytic functions that accept Machine Learning Engine models as input are renamed:
    • `td_decision_forest_predict_sqle()` --> `td_decision_forest_predict_mle_sqle()`
    • `td_decision_tree_predict_sqle()` --> `td_decision_tree_predict_mle_sqle()`
    • `td_glm_predict_sqle()` --> `td_glm_predict_mle_sqle()`
    • `td_naivebayes_textclassifier_predict_sqle()` --> `td_naivebayes_textclassifier_predict_mle_sqle()`
    • `td_naivebayes_predict_sqle()` --> `td_naivebayes_predict_mle_sqle()`
    • `td_svm_sparse_predict_sqle()` --> `td_svm_sparse_predict_mle_sqle()`
  • Following functions does not accept models generated by Machine Learning Engine, but they now accept the model generated by the Analytics Database analytic functions exposed by Analytics Database.
    The availability of these functions depends on the version of the connected Vantage Analytics Database.
    • `td_decision_tree_predict()`
    • `td_decision_forest_predict()`
    • `td_glm_predict()`
    • `td_naivebayes_predict()`
    • `td_svm_sparse_predict()`
  • Following functions overlap between Analytics Database and Machine Learning Engine. They now point to their Analytics Database equivalent based on the Vantage version they are connected to. In order to use the corresponding Machine Learning Engine function, add the "_mle" suffix.
    • `td_decision_forest()`
    • `td_glm()`
    • `td_histogram()`
    • `td_kmeans()`
    • `td_knn()`
    • `td_text_parser()`
    • `td_naivebayes_textclassifier_predict()`
    • `td_text_parser()`
    • `td_vector_distance()`
  • Deprecated Machine Learning Engine in this release and it is not guaranteed to work. It will be removed in future release versions.
  • Deprecated Sandbox Environment feature in this release and it is not guaranteed to work. It will be removed in future release versions.