I have also been playing around with python - chatgpt acts as a helpful programming buddy. So far I have got to the point where I can supply a collated pgn file of all my games (e.g. lichess, chess.com, chessbase) and get it analysed by opening (but applies to any pgn file).
I can get a break down of my win / draw / loss / score based on ECO, opening name / variation name or alternatively based on a specified number of moves currently.
There are quite a few useful python chess packages hanging around - e.g. pgnhelper will recategorise openings based on a file you supply - double checking opening / variation names and ECO codes (esp useful if missing). My thoughts were to get an automated report based on my openings to focus down on which openings have best results for me, which openings need more focus or are maybe not suited to me) and need changing.
You can do this by stepping through moves in lichess, chess.com but i wanted to have all my games analysed in one place.
I have a basic prototype working and thinking on where to go with it. My thoughts for next steps are to build out an eco / opening classification file that is geared to my repertoire and then analyse the games on that basis. pgnhelper provides a default opening classification but from what I can see you could substitute something geared more towards your own.
Uhh! Sounds interesting too. I also plan to add chatgpt at some point to make a summary of some sorts.. Will definitely check out pgnhelper. Has had some problems with adding opening names to each line
Out of curiosity, when learning how to code together with GPT-4, what materials proved most useful to understand this? Any articles or videos that you really liked?
Idea looks interesting. It is could be useful to know if my move (in the opening) was already played (especially by strong player), if it is most played move in position, or rather rarely played. And this is not that hard to implement (to code). You just get game you like to analyze this way and compare game moves against some kind of Opening Explorer (like https://lichess.org/analysis#explorer or https://www.openingtree.com/). How valuable is this information depends on quality of database from which opening explorer data are generated. So most work with such service goes to keeping that database current and remain high quality. btw, lichess has for some time also Personal Opening Explorer (https://lichess.org/blog/YXMPxxMAACEAy3g4/announcing-the-personal-opening-explorer).
I had similar idea once - to develop a service (like web service, API) which in real-time (when rapid or classical game is played/streamed) inject to game notation game references to games of strong players who reaches given current position in streamed game (as help to viewers and or commentators). That would be somewhat interesting how given position is handled by human players (as addition to computer analysis) especially when game is deep in the middlegame or in the complex endgame. But I never find enough time to implement it.
I do not know if I qualify as coding expert. I do this (computer programming) for a living, and have 25+ years of experience in the field, so if I can help somewhat (within my limited free time) then let me know. ;)
Thank you, Slavo! Your idea is definitely also interesting.
I have plans to add references a master game explore, which will add a lot of value. I was wondering if I will overuse the richness api by also using it for checking the moves for that. Alternatively I was thinking I could download the lichess master database and make my own mini explorer database in SQL, so I have the information myself.
Hope do not dissapoint you. I guess this work is done by chessbase anytime you open thr operning book. Let me know if I am wrong. Maybe the idea is a good one if you think you dont need the chessbase software (or you dont have it). In fact, the software Jose and Scid can do similar opening % charts
Hi Manual, it is very basic right now and I have a lot of ideas to make it better, but I need to start somewhere :) And I think getting it by mail will make you remember to quickly go through the games you played
Hello Martin
I have also been playing around with python - chatgpt acts as a helpful programming buddy. So far I have got to the point where I can supply a collated pgn file of all my games (e.g. lichess, chess.com, chessbase) and get it analysed by opening (but applies to any pgn file).
I can get a break down of my win / draw / loss / score based on ECO, opening name / variation name or alternatively based on a specified number of moves currently.
There are quite a few useful python chess packages hanging around - e.g. pgnhelper will recategorise openings based on a file you supply - double checking opening / variation names and ECO codes (esp useful if missing). My thoughts were to get an automated report based on my openings to focus down on which openings have best results for me, which openings need more focus or are maybe not suited to me) and need changing.
You can do this by stepping through moves in lichess, chess.com but i wanted to have all my games analysed in one place.
I have a basic prototype working and thinking on where to go with it. My thoughts for next steps are to build out an eco / opening classification file that is geared to my repertoire and then analyse the games on that basis. pgnhelper provides a default opening classification but from what I can see you could substitute something geared more towards your own.
Regards
Nigel
Uhh! Sounds interesting too. I also plan to add chatgpt at some point to make a summary of some sorts.. Will definitely check out pgnhelper. Has had some problems with adding opening names to each line
thats really cool. are you coding it in python?
Yes, that was what I could understand was best learning :)
Ingenious
Out of curiosity, when learning how to code together with GPT-4, what materials proved most useful to understand this? Any articles or videos that you really liked?
Actually I just started asking questions. I have used Replit.com as a platform, which is quite user friendly
Looks interesting. As a software tester by trade I'd be more than happy to give you a hand and try to break it a little before you unleash it!
Thanks! Obviously I want to add a lot more, but better start with something that works and build. And I will remember that, thanks!
Looks great.
Hello Martin!
Idea looks interesting. It is could be useful to know if my move (in the opening) was already played (especially by strong player), if it is most played move in position, or rather rarely played. And this is not that hard to implement (to code). You just get game you like to analyze this way and compare game moves against some kind of Opening Explorer (like https://lichess.org/analysis#explorer or https://www.openingtree.com/). How valuable is this information depends on quality of database from which opening explorer data are generated. So most work with such service goes to keeping that database current and remain high quality. btw, lichess has for some time also Personal Opening Explorer (https://lichess.org/blog/YXMPxxMAACEAy3g4/announcing-the-personal-opening-explorer).
I had similar idea once - to develop a service (like web service, API) which in real-time (when rapid or classical game is played/streamed) inject to game notation game references to games of strong players who reaches given current position in streamed game (as help to viewers and or commentators). That would be somewhat interesting how given position is handled by human players (as addition to computer analysis) especially when game is deep in the middlegame or in the complex endgame. But I never find enough time to implement it.
I do not know if I qualify as coding expert. I do this (computer programming) for a living, and have 25+ years of experience in the field, so if I can help somewhat (within my limited free time) then let me know. ;)
Thank you, Slavo! Your idea is definitely also interesting.
I have plans to add references a master game explore, which will add a lot of value. I was wondering if I will overuse the richness api by also using it for checking the moves for that. Alternatively I was thinking I could download the lichess master database and make my own mini explorer database in SQL, so I have the information myself.
Hope do not dissapoint you. I guess this work is done by chessbase anytime you open thr operning book. Let me know if I am wrong. Maybe the idea is a good one if you think you dont need the chessbase software (or you dont have it). In fact, the software Jose and Scid can do similar opening % charts
Hi Manual, it is very basic right now and I have a lot of ideas to make it better, but I need to start somewhere :) And I think getting it by mail will make you remember to quickly go through the games you played
I see. Well, I am a programmer. Actually I use Delphi. If I can help you in anyway, I ll be glad. Best wishes.
Thanks 😊 I plan to write about the progress. Feel free to give advice