kaknikhil commented on a change in pull request #432: MADLIB-1351 : Added stopping criteria on perplexity to LDA URL: https://github.com/apache/madlib/pull/432#discussion_r320443388
########## File path: src/ports/postgres/modules/lda/test/lda.sql_in ########## @@ -288,3 +288,57 @@ CREATE OR REPLACE FUNCTION validate_lda_output() RETURNS integer AS $$ $$ LANGUAGE plpgsql; select validate_lda_output(); + + +---------- TEST CASES FOR PERPLEXITY ---------- + +drop table if exists lda_model, lda_output_data; +SELECT lda_train( Review comment: We should add few more test cases. In all these case we need to assert that we calculated the perplexity at the right iteration. 1. no_of_iterations % evaluate_every != 0. 2. both no_of_iters and evaluate_every = 1 3. no_of_iterations % evaluate_every == 0 and no_of_iterations != evaluate_every 4. Set evaluate_every to 0 and -1 5. When perplexity_tol is reached before finishing all the iterations ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
