here is a screen capture of what i see when i use the pokersleuth hud.

i'm a beta tester so why is it suddenly saying my trial has expired ?

First, I want to apologize for the ongoing delay in resolving bugs. After getting off the antibiotics, my infection reappeared and I had to go back on the antibiotics for another two weeks. I've got two days left now and--God willing--I'll be back up to speed after that. Illness is, unfortunately, unpredictable.

Because each beta registration key only works for 30 days.

As soon as I have a new version ready, I'll send out an email letting everyone know and providing new keys. Anyone who has provided good feedback (such as yourself) will receive a permanent key.

oh ok i thought maybe i got a corrupt copy or something.

I just sent uploaded a new beta and sent out an email to everyone participating with new registration keys that will last throughout the Beta. If the email isn't in your inbox, check your junk-mail folder, or email support@pokersleuth.com.

Cheers!

hi i just installed the latest beta and played a few hands. It says it is getting the hands directly from the ub history file. I'm still seeing the same stats for all players.

Does the completion bar for the UB history file fill up, or does it get stuck on empty?

If you let it run for a few minutes (with the Options window closed), then open the Options window and click on Errors, does it show any parse failures?

Nevermind, grumpy64, I've found the problem. I'll have a fix ready later today.

Fixed in 1.3.0.1058!

Hi hate to keep being a bother but i have had sleuth opened for the past half an hour and i'm still waiting for it to give me the option to install the latest update. I am currently on the version that ends with 48 but i want to update to version 1.3.0.1058

well speak of the devil mister 1.3.0.1058 decided to show up.

Glad to hear it. Let me know if you run into any more problems.

I'll work on making the check-for-new-versions feature snappier (though this is lower priority than fixing bugs). As a last resort, you can always download the newest beta from this link.

any plans to add positional stats ?

Yes. Eventually Poker Sleuth will include every stat you could possibly imagine.

I'm fixing some of the urgent bugs first, then I'll work on expanding the stats.

cool

I think what he means is that you're not using the right function to fit the data.

I obviously have no idea what you're actually doing, but the first thing I thought when I looked at the above graph was "oh, that looks like the CDF of a Gaussian, but shouldn't he be using a Student's t-distribution b/c of small sample size?"

This looks cool. I have a couple of questions:

- Are your ranges just 95% confidence intervals?

- What sort of Bayesian analysis are you doing? Is it things like "we don't have enough hands to say anything directly about river c/r ranges, but given his flop aggression, etc., etc., a 95% CI would be XX-YY"? I'd love to see some data about which statistics correlate with each other, which don't, etc.

You seem like you have a solid statistics background, so I'm going to use some mathematical notation in my explanation, but feel free to ask me to explain any of it if the meaning is unclear.
Poker Sleuth uses Beta distributions (which are similar enough to Gaussian distributions that you can approximate a Beta distribution with a Gaussian), but have two key advantages when estimating probabilities:

• Pr(x < 0) = Pr(x > 0) = 0%
• Variables cancel out nicely when put through Bayes' Theorem

Technically, the ranges are 95% Bayesian credible intervals, which are similar to confidence intervals but not the same thing (I wish I could find a good article that explained the difference crisply, but I can't at the moment. The Wikipedia entries are OK) In particular, confidence intervals are prohibited from incorporating any extra information beyond the observations.

(In the Poker Sleuth Options window, you can actually adjust the "95%" to be whatever you want)
For some statistic S on a player P, Poker Sleuth currently does the following:

- Create a model M for the distribution of the statistic across all players
- Apply Bayes' Theorem to create a PDF function f(x) = Pr(S=x given M and the observations on this player) and the similar CDF function F(x)
- For a 95% credible interval, give F(2.5%) to F(97.5%) as the range

If we have no observations on a player, then F(x) is the same as the distributions across all players.

I hope that makes sense at least at a very high level.

A future version of Poker Sleuth may take into account how different statistics correlate with one another. The hardest part, as you may imagine, is determining how statistics correlate. ;-)

The preflop analysis tool ("Poker SHIP") that's part of Poker Sleuth does do some more sophisticated stuff using some basic correlations. For example, it's smart enough to know that if a player raises frequently with TJs from early position, they probably also raise with QJs from late position.

I have an OK statistics background, but I'm certainly not a statistician.

Is that 1st bullet point right?

Speaking of that background, I've heard of Beta distributions, but I'm not particularly familiar with them. I read the Wikipedia page just now, though . It's funny .. my wife is an evolutionary biologist (phylogenetic trees are constructed via Bayesian analysis), so I could probably ask her if she weren't asleep.

The Wikipedia articles are surprisingly "meh" but I guess this is the sort of thing where people get the wording wrong, so it's better to be terse. Anyway, I think it's clear what's going on. "Credible intervals" are basically what every stats 101 student thinks "confidence intervals" are, right?

It does. Thanks.

. I've been pretty interested in this for a while, but other things keep getting in the way.

I poked around your webpages a bit .. is there any chance these tools are secretly more portable than you make it seem (OS X or Linux)?

Oops! No, it should have read:

• Pr(x < 0%) = Pr(x > 100%) = 0

More explicitly, a Gaussian or Student's distribution will include probability less than 0% or more than 100%, which is gibberish. The 95% interval for a Beta distribution will always be between 0% and 100%.
Yes. That's a wonderful way of putting it.
Some parts are more portable than others:

• The HUD uses many arcane Windows tricks and is strongly tied to that platform.
• The user interface is written in C# using Windows Forms, though maybe I could port it using Mono.
• Everything else (parsing, simulation, database, etc.) is written in a mix of C and Python and quite portable.

how do i manually add a directory? i have a directory on my desktop called data that i want to add. It has all my mined hands from ub.

Here are step-by-step instructions on how to add a directory:

• Right-click on the Poker Sleuth icon in the system tray.
• Select "Options", which will pop up the Options window.
• Click on the "Directories" tab.
• Click "Add", which will pop up a dialog box for selecting a directory.
• Select the directory you wish to add.
• Click "Accept" to close the dialog box.
• Click "Accept" to close the Options window.

Your desktop is usually located in "C:\Documents and Settings\your username\Desktop" on XP or "C:\Users\your username\Desktop" on Vista.

ok i added the following directory

C:\documents and settings\all users\desktop

it isn't seeing the hands. I even put the hands directly on the desk top. Is their any way to do a force in stall?

also the new directory is not listed in the file path

ok is their anyway to do a forced import ? I ask because i took a single data mined file about 300 hands and moved it to my ub file. Once it is moved to that file sleuth does indeed recognize it. I went away for almost a hour but when i came back the completion meter under the files path had not moved at all.

omaha +1