Good testsets for tablebases testing

Discussion of chess software programming and technical issues.

Moderators: hgm, Rebel, chrisw

Sergei S. Markoff
Posts: 227
Joined: Mon Sep 12, 2011 11:27 pm
Location: Moscow, Russia

Good testsets for tablebases testing

Post by Sergei S. Markoff »

Have you seen any of them?
It would be great to have some testsets with 100-200 positions for checking a corectness of TBs probe implementation.
The Force Be With You!
Vinvin
Posts: 5228
Joined: Thu Mar 09, 2006 9:40 am
Full name: Vincent Lejeune

Re: Good testsets for tablebases testing

Post by Vinvin »

Sergei S. Markoff wrote:Have you seen any of them?
It would be great to have some testsets with 100-200 positions for checking a corectness of TBs probe implementation.
May be this thread can help : http://www.talkchess.com/forum/viewtopic.php?t=57331
User avatar
Fabio Gobbato
Posts: 217
Joined: Fri Apr 11, 2014 10:45 am
Full name: Fabio Gobbato

Re: Good testsets for tablebases testing

Post by Fabio Gobbato »

For which tablebase are you looking a testsets?

I have made a big one for syzygy. It's a csv file with these fields:
fen,dtz,wdl,

Here is the link: https://drive.google.com/file/d/0B_0jof ... sp=sharing
Sergei S. Markoff
Posts: 227
Joined: Mon Sep 12, 2011 11:27 pm
Location: Moscow, Russia

Re: Good testsets for tablebases testing

Post by Sergei S. Markoff »

Thak you.
I'm testing Syzygy implementation just now and I'm trying to find a good way to test my probe code adaptation for SmarThink. The ideal way is to use some epd testset with multiple FEN + best move lines.
The Force Be With You!