SVMDensePredict Example 3: Radial Basis Model (RBF) Model - 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 Vantage™

Input

The input table is iris_test (see SVMDense Examples Input).

SQL Call

SELECT * FROM SVMDensePredict (
  ON svm_iris_test AS "input" PARTITION BY ANY
  ON densesvm_iris_rbf_model AS model DIMENSION
  USING
  IDColumn ('id')
  InputColumns ('[1:4]')
  Accumulate ('id', 'species')
) AS dt ORDER BY id;

Output

id predict_value predict_confidence species
5 setosa 0.759462243280868 setosa
10 setosa 0.749956836983807 setosa
15 setosa 0.744312392653372 setosa
20 setosa 0.761685486307989 setosa
25 setosa 0.706123801835284 setosa
30 setosa 0.74546864465768 setosa
35 setosa 0.758375257643847 setosa
40 setosa 0.762861263069852 setosa
45 setosa 0.72063801834686 setosa
50 setosa 0.764070094615493 setosa
55 versicolor 0.718583789317861 versicolor
60 versicolor 0.69705275515147 versicolor
65 versicolor 0.743635327519085 versicolor
70 versicolor 0.774094441049014 versicolor
75 versicolor 0.805953546799106 versicolor
80 versicolor 0.76991045016646 versicolor
85 versicolor 0.626297282449495 versicolor
90 versicolor 0.742172821606089 versicolor
95 versicolor 0.764061283278648 versicolor
100 versicolor 0.778180754495943 versicolor
105 virginica 0.819921814514784 virginica
110 virginica 0.789239991456868 virginica
115 virginica 0.791714097446213 virginica
120 versicolor 0.543320639355163 virginica
125 virginica 0.792639816244284 virginica
130 virginica 0.652651245896941 virginica
135 virginica 0.640968578224784 virginica
140 virginica 0.741382118250009 virginica
145 virginica 0.800886347061692 virginica
150 virginica 0.658977731573751 virginica

The prediction accuracy with the RBF model is 96.67%.