GLMPredict Function Example | Teradata Vantage - GLMPredict Example: Casting Input Column to VARCHAR - Teradata® Database

Like GLMPredict Example: Logistic Distribution Prediction, this example predicts the admission status of students. In both examples, the input column masters is categorical—the value can be yes or no. In the other example, the value is 'yes' or 'no'. In this example, the value is numerical—1 for yes or 0 for no—therefore, it must be cast to VARCHAR.

Input

• Input table: admissions_test_2, which has admissions information for 20 students
• Model: glm_admissions_model, output by "GLM Example: Logistic Regression Analysis with Intercept" in Teradata Vantage™ Machine Learning Engine Analytic Function Reference, B700-4003, with the category column modified as follows:

  attribute	predictor	category
  1	masters	'1'
  2	masters	'0'

SQL Call

CREATE MULTISET TABLE glmpredict_admissions_2 AS (
  SELECT * FROM GLMPredict (
    ON (
      SELECT id, CAST(masters AS varchar(10)) AS masters,
        gpa, stats, programming, admitted
      FROM admissions_test
    ) PARTITION BY ANY
    ON glm_admissions_model AS Model DIMENSION
    USING
    Accumulate ('id','masters','gpa','stats','programming','admitted')
    Family ('LOGISTIC')
    LinkFunction ('LOGIT')
  ) AS dt
) WITH DATA;

Output

This query returns the following table:

SELECT * FROM glmpredict_admissions_2 ORDER BY 1;

Fitted values can vary in precision, because they depend on the model table output by ML Engine GLM function and fetched to Advanced SQL Engine.

Categorizing fitted_value Column

See GLMPredict Example: Logistic Distribution Prediction.

Prediction Accuracy

See GLMPredict Example: Logistic Distribution Prediction.