XGBoostPredict Example: Multiple-Class Classification - Teradata Vantage

Machine Learning Engine Analytic Function Reference

Product
Teradata Vantage
Release Number
8.10
1.1
Published
October 2019
Language
English (United States)
Last Update
2019-12-31
dita:mapPath
ima1540829771750.ditamap
dita:ditavalPath
jsj1481748799576.ditaval
dita:id
B700-4003
lifecycle
previous
Product Category
Teradata Vantageā„¢

Input

SQL Call

CREATE MULTISET TABLE iris_predict AS (
  SELECT * FROM XGBoostPredict (
    ON iris_test AS InputTable PARTITION BY ANY
    ON xgboost_model_2 AS Model DIMENSION ORDER BY tree_id, iter, class_num
    USING
    IDColumn ('id')
    NumBoostedTrees (2)
    OutputProb ('t')
    Responses ('1','2','3')
    Accumulate ('species')
  ) AS dt
) WITH DATA;

Output

SELECT * FROM iris_predict ORDER BY id;
 id  species prediction prob_1  prob_2  prob_3  
 --- ------- ---------- ------- ------- ------- 
   5 1       1          0.48291 0.26014 0.25695
  10 1       1          0.51761 0.24292 0.23947
  15 1       1          0.48375 0.26095 0.25531
  20 1       1           0.4993 0.25484 0.24586
  25 1       1          0.46432 0.27109 0.26459
  30 1       1          0.46374 0.26897 0.26729
  35 1       1          0.51766 0.24334 0.23901
  40 1       1          0.48499 0.26244 0.25256
  45 1       1          0.49165 0.26029 0.24806
  50 1       1          0.51104 0.24842 0.24054
  55 2       2          0.25653 0.48713 0.25634
  60 2       2          0.27605 0.45864 0.26531
  65 2       2           0.2491 0.51434 0.23656
  70 2       2          0.25703 0.49888 0.24409
  75 2       2          0.25475 0.48738 0.25787
  80 2       2           0.2486 0.50984 0.24156
  85 2       2          0.25221 0.50593 0.24187
  90 2       2          0.25178  0.5083 0.23992
  95 2       2          0.24871 0.51341 0.23788
 100 2       2          0.25119 0.50696 0.24185
 105 3       3          0.25368   0.252 0.49432
 110 3       3           0.2631 0.25911 0.47778
 115 3       3          0.26164 0.27229 0.46607
 120 3       2          0.25457 0.48861 0.25682
 125 3       3          0.26082 0.25934 0.47984
 130 3       2          0.26659 0.38281  0.3506
 135 3       2          0.26095 0.47176  0.2673
 140 3       3          0.26547 0.26201 0.47252
 145 3       3          0.26082 0.25934 0.47984
 150 3       3          0.26762  0.3638 0.36858

Download a zip file of all examples and a SQL script file that creates their input tables from the attachment in the left sidebar.