Xiaochang Wu comments

Results 15 comments of


Xiaochang Wu

Probably DAAL_CHECK_EX error for fullNUsers in implicit_als

@PIVOVAR3AL

Probably DAAL_CHECK_EX error for fullNUsers in implicit_als

@Alexsandruss Thanks for the fix. I will check. And I have opened several issues related to ALS. #1476 #1513 #1514 . The blocking one is #1513.

Add other stats for low-order moments

Thanks @makart19. For weight column, Could also consider a general support for weighted points as a general feature for all algorithms, such as weighted points for kmeans etc. Check Spark's...

getBlockOfRows can not return block of rows exceeding 2 gigabytes

@PIVOVAR3AL

Support RowMergedNumericTable as GPU Kmeans input dataset

#1712

ALS algorithm failed to solve a system of normal equations

> @xwu99, did [c6c5219](https://github.com/oneapi-src/oneDAL/commit/c6c5219c85e5bceb0392e54e653e00e8cc45e21f) fix your case? Thanks for the fix. I am working on another algorithm. I will validate ALS and let you know.

daal4py PCA with svdDense method error in distributed mode

Also check #758

[PCA] svdDense in distributed mode does not work for unnormailized data

Attach [Reproducer](https://github.com/intel/scikit-learn-intelex/files/6904880/pca-dal-tests.tar.gz)

[PCA] don't normalize input data before applying PCA or provide a parameter to turn off normalization

And in distributed mode, d4p will not normalize as batch mode. (maybe another bug). So need to examine all the behaviors and update them in a consistent way.

ONEAPI_DEVICE_SELECTOR not working under sub-process

@oleksandr-pavlyk I faced a similar situation, when modifying ONEAPI_DEVICE_SELECTOR after import dpctl, the recalling of get_devices doesn't respect the modified filter. ``` import dpctl import os print("First import dpctl") #...