[GitHub] spark issue #22659: [SPARK-25623][TEST] Reduce test time of LogisticRegressi...

Sun, 07 Oct 2018 20:07:01 -0700 

Github user shahidki31 commented on the issue:

    https://github.com/apache/spark/pull/22659
  
    In the test "binary logistic regression with intercept with ElasticNet 
regularization", taking around 30sec to run. But we can reduce the time to 15 
sec by reducing the iteration.
    
    
![image](https://user-images.githubusercontent.com/23054875/46590813-0a54b080-cad4-11e8-8d27-9b049fc4537c.png)
    model1 converges after 100 iteration,
    
![image](https://user-images.githubusercontent.com/23054875/46590826-19d3f980-cad4-11e8-9c81-4c42ac5559b8.png)
    model2 converges after 20 iterations. 
    So, if we make maxIter of model1 and model2 as 120 and 30 respectively, we 
can reduce the time to ~15 sec.
    
    In the test "multinomial logistic regression without intercept with 
elasticnet regularization", taking around 30 sec to run. This also can be 
reduced to 15 sec by reducing number of iteration.
    
![image](https://user-images.githubusercontent.com/23054875/46590808-032da280-cad4-11e8-8b8f-9ffffe70632d.png)
    model1 converges after 50 iteration.
    
![image](https://user-images.githubusercontent.com/23054875/46590819-10e32800-cad4-11e8-9ded-b29e68dfd0ff.png)
    model2 converges after 30 iteration.
    So, if we make maxIter of model1 and model2 as 75 and 50 respectively, we 
can reduce the computation time less than 15sec
    



---

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to