Statistics package in Pharo?

Hi everyone,

Does anyone know if there is a package that contains implementation of
statistics tests like Kolmogorov-Smirnov test, Khi-2 test, etc?

I did fast research in Smalltalkhub but didn't found anything.

Thanks in advance,

Julien

Wow lots of classes, I'll browse the package and tell you if that's what
I need :)

Thanks.

On 03/03/15 11:46, Sebastian Tleye wrote:

Hi Julien,

Indeed, having a nice statistical package is missing in Pharo. The numerical methods is a nice start.
If things are missing, we should implement them.

Cheers,
Alexandre

--
_,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:
Alexandre Bergel  http://www.bergel.eu
^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;._,.;:~^~:;.

Wow lots of classes, I'll browse the package and tell you if that's what
I need :)

Thanks.

On 03/03/15 11:46, Sebastian Tleye wrote:

The only package that I know that has statistical tools is

NumericalMethods, you can install it by going to tools->Configuraiton

Browser->NumericalMethods.

Check if it has what you need

2015-03-03 11:40 GMT+01:00 Julien Delplanque <[hidden email]>:

Hi everyone,

Does anyone know if there is a package that contains implementation of

statistics tests like Kolmogorov-Smirnov test, Khi-2 test, etc?

I did fast research in Smalltalkhub but didn't found anything.

Thanks in advance,

Julien

Doesn't look like there is what I'm looking for.

Maybe I'll implement things I need if I have time but probably not a
complete package for statistics. :)

On 03/03/15 12:46, Alexandre Bergel wrote:

On 03/03/15 12:54, Serge Stinckwich wrote:
> Hi Julien, there is no KS-tests in this package. This is also something I'm looking for :-)
> NumericalMethods package is now part of SciSmalltalk distribution:
> https://github.com/SergeStinckwich/SciSmalltalk
Hi!
Nice I'll look at that.
> Join us if you want to help build statistical tools in Pharo:
> http://groups.google.com/group/scismalltalk
I'm interested since I have to implement things for a project, if it's
possible to integrate them in your package it would be nice.

Regards,

Julien

This is not really difficult to implement a khi2 or ks-test. I'm doing that with my 1st year university student in Python. I will try if I found sone time in Pharo.


Sent from my iPhone

On 03/03/15 13:11, Serge Stinckwich wrote:
> This is not really difficult to implement a khi2 or ks-test. I'm doing that with my 1st year university student in Python. I will try if I found sone time in Pharo.
I know it's not complicated, I had to implement KS test in python for
another project (but I don't think you are one of my professor :p).

I will do it soon but I'm still noob in smalltalk so I don't know where
to implement this and how: class messages or object messages for example?

Julien

Start to write tests !


Sent from my iPhone

It does not really matter. Start to write your stat test and we will go over it.
This is --highly-- important to have such tests.

Alexandre

Hi Julien,

If you are doing some statistics, I am pretty sure that you use R.
There is a connector to R software implemented in Pharo. You can use it if some methods are not implemented or too complex to do it by yourself.
The link is here: http://www.smalltalkhub.com/#!/~VincentBlondeau/RProjectConnector/

Don't hesitate to ask if you need some help on it.

Vincent

-----Message d'origine-----
De : Pharo-users [mailto:[hidden email]] De la part de Julien Delplanque
Envoyé : mardi 3 mars 2015 12:59
À : [hidden email]
Objet : Re: [Pharo-users] Statistics package in Pharo?

Doesn't look like there is what I'm looking for.

Maybe I'll implement things I need if I have time but probably not a complete package for statistics. :)

On 03/03/15 12:46, Alexandre Bergel wrote:



Ce message et les pièces jointes sont confidentiels et réservés à l'usage exclusif de ses destinataires. Il peut également être protégé par le secret professionnel. Si vous recevez ce message par erreur, merci d'en avertir immédiatement l'expéditeur et de le détruire. L'intégrité du message ne pouvant être assurée sur Internet, la responsabilité de Worldline ne pourra être recherchée quant au contenu de ce message. Bien que les meilleurs efforts soient faits pour maintenir cette transmission exempte de tout virus, l'expéditeur ne donne aucune garantie à cet égard et sa responsabilité ne saurait être recherchée pour tout dommage résultant d'un virus transmis.

This e-mail and the documents attached are confidential and intended solely for the addressee; it may also be privileged. If you receive this e-mail in error, please notify the sender immediately and destroy it. As its integrity cannot be secured on the Internet, the Worldline liability cannot be triggered for the message content. Although the sender endeavours to maintain a computer virus-free network, the sender does not warrant that this transmission is virus-free and will not be liable for any damages resulting from any virus transmitted.

hi Julien,
you can find chisquare-test, f-test, t-test in numericalmethods
werner

and you can find the doku here:
https://github.com/SquareBracketAssociates/NumericalMethods/releases
werner

On 03/03/2015 06:03 PM, Werner Kassens wrote:
> hi Julien,
> you can find chisquare-test, f-test, t-test in numericalmethods
> werner
>
>
>

On 03/03/15 18:03, Werner Kassens wrote:
> hi Julien,
Hi!
> you can find chisquare-test, f-test, t-test in numericalmethods
> werner
Oh, thanks I'll check this out!
> and you can find the doku here:
> https://github.com/SquareBracketAssociates/NumericalMethods/releases
> werner
>