Re: Python and Hidden Markov Model

Path	csiph.com!usenet.pasdenom.info!gegeweb.org!de-l.enfer-du-nord.net!feeder2.enfer-du-nord.net!cs.uu.nl!news.stack.nl!newsfeed.xs4all.nl!newsfeed2.news.xs4all.nl!xs4all!newsgate.cistron.nl!newsgate.news.xs4all.nl!post.news.xs4all.nl!not-for-mail
Return-Path	<oscar.j.benjamin@gmail.com>
X-Original-To	python-list@python.org
Delivered-To	python-list@mail.python.org
X-Spam-Status	OK 0.020
X-Spam-Evidence	'H': 0.96; 'S': 0.00; 'python.': 0.02; 'subject:Python': 0.05; 'things.': 0.05; 'python': 0.09; 'friday,': 0.09; 'cc:addr:python-list': 0.10; 'language': 0.14; 'backward': 0.16; 'cc:name:python list': 0.16; 'code?': 0.16; 'list):': 0.16; 'scratch': 0.16; 'wrote:': 0.17; 'trying': 0.21; 'cc:2**0': 0.23; 'example': 0.23; 'programming': 0.23; 'specifically': 0.24; 'tried': 0.25; 'cc:addr:python.org': 0.25; 'header:In-Reply-To:1': 0.25; 'fit': 0.26; 'url:wiki': 0.26; 'coding': 0.27; 'message-id:@mail.gmail.com': 0.27; 'run': 0.28; 'url:wikipedia': 0.29; 'url:mailman': 0.29; "i'm": 0.29; 'basic': 0.30; 'room': 0.32; 'url:listinfo': 0.32; 'doubt': 0.33; 'much.': 0.33; 'problem': 0.33; 'received:google.com': 0.34; 'done': 0.34; 'list': 0.35; 'otherwise.': 0.35; 'similar': 0.35; 'received:209.85': 0.35; 'there': 0.35; 'but': 0.36; 'wanted': 0.36; 'url:org': 0.36; 'scientific': 0.36; 'anything': 0.36; 'two': 0.37; 'why': 0.37; 'received:209': 0.37; 'data': 0.37; 'subject:: ': 0.38; 'some': 0.38; 'things': 0.38; 'sure': 0.38; 'url:en': 0.38; 'system.': 0.39; 'help': 0.40; 'url:mail': 0.40; 'is.': 0.62; 'different': 0.63; 'email addr:gmail.com': 0.63; 'continuous': 0.65; 'url:%1': 0.68; '2013': 0.84; 'computation.': 0.84; 'forward,': 0.84; 'kits': 0.84; 'oscar': 0.84; 'subject:Model': 0.84; 'wrong!': 0.84
DKIM-Signature	v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=x-received:mime-version:in-reply-to:references:from:date:message-id :subject:to:cc:content-type; bh=AWp07VDmgufUJEfqs6s330qI9hlIEEKQ3GViPQAg4vQ=; b=vLwt8vIjkO5OIQowV9R4IYjYShNz0zrUBHHlOOOG3jswExjQOjI8WnMjppzHHSIygx Db0SJP7Dc1/KD946uDR9GkIsh0wwMIVuBHqUGyRHElQ0/hx+ChN1tBEC2lJPJjAd5foH d3ygFgZRcln+6J68cDjN1L7eyQ3UjdpNDmfBV7bDc5dyU65NWjzAXe+MwCEAXk2NNfbg ehF5bN1K6afX9WKZZkCZV4PBnH62qaMle2Iv72z1nnz+JF5gwYDjSKcsoLExFUa0CyVK 6QMo1yKBfe8+97REtcVjnKaR39d45so9es3ZhBkVe8gDjhPGV3J2L/wfJ6j04LQKx4yx 87Gw==
X-Received	by 10.49.118.162 with SMTP id kn2mr3667776qeb.65.1362752999723; Fri, 08 Mar 2013 06:29:59 -0800 (PST)
MIME-Version	1.0
In-Reply-To	<e8bb6ad1-85b3-47bb-9377-d20e86b91bb6@googlegroups.com>
References	<1c2a4627-4000-456a-9a5a-c61c3069b98f@googlegroups.com> <e8bb6ad1-85b3-47bb-9377-d20e86b91bb6@googlegroups.com>
From	Oscar Benjamin <oscar.j.benjamin@gmail.com>
Date	Fri, 8 Mar 2013 14:29:39 +0000
Subject	Re: Python and Hidden Markov Model
To	Subhabrata Banerjee <subhabangalore@gmail.com>
Content-Type	text/plain; charset=ISO-8859-1
Cc	Python List <python-list@python.org>
X-BeenThere	python-list@python.org
X-Mailman-Version	2.1.15
Precedence	list
List-Id	General discussion list for the Python programming language <python-list.python.org>
List-Unsubscribe	<http://mail.python.org/mailman/options/python-list>, <mailto:python-list-request@python.org?subject=unsubscribe>
List-Archive	<http://mail.python.org/pipermail/python-list/>
List-Post	<mailto:python-list@python.org>
List-Help	<mailto:python-list-request@python.org?subject=help>
List-Subscribe	<http://mail.python.org/mailman/listinfo/python-list>, <mailto:python-list-request@python.org?subject=subscribe>
Newsgroups	comp.lang.python
Message-ID	<mailman.3083.1362753003.2939.python-list@python.org> (permalink)
Lines	36
NNTP-Posting-Host	2001:888:2000:d::a6
X-Trace	1362753003 news.xs4all.nl 6951 [2001:888:2000:d::a6]:40028
X-Complaints-To	abuse@xs4all.nl
Xref	csiph.com comp.lang.python:40862

Show key headers only | View raw

On 8 March 2013 05:26,  <subhabangalore@gmail.com> wrote:
> On Friday, March 8, 2013 2:18:06 AM UTC+5:30, subhaba...@gmail.com wrote:
>>
>> I was trying to learn Hidden Markov Model. In Python there are various packages, but I was willing to do some basic calculation starting from the scratch so that I can learn the model very aptly. Do you know of any thing such?
>
> My problem is over model validation on continuous time Markov system.
> Generally, I understand the theory and can run the kits like HMM.py or Scikit-learn.
> The problem is if I can not fit the data in run time I would be at the mercy of the kit.
> So I wanted to know the coding of the computation.

If those projects can do what you want then why not just look at their code?

> I am specifically looking at the small python example of Forward, Backward and Viterbi
> calculation. I tried to surf the web but did not help much.

How about these two (both in Python):
http://en.wikipedia.org/wiki/Viterbi_algorithm#Example
http://en.wikipedia.org/wiki/Forward%E2%80%93backward_algorithm#Python_example

> I do not know much of Scientific forum.
Try scipy-user as a start (someone there may know of a better mailing list):
http://mail.scipy.org/mailman/listinfo/scipy-user

> I thought as HMM.py, NLTK, Scikit-learn are Python implementations so there would be lot
> of people in the room who would know it.
> And I got people like you, so I can not say I am wrong!

Python as a programming language is used for many different things. I
doubt that many people on this list will know what a Hidden Markov
Model is. While I do know what they are, I have never done anything
with them in Python or otherwise. However, if you ask in the right
place, I'm sure that you will find people who have done similar things
in Python.


Oscar

Thread

Python and Hidden Markov Model subhabangalore@gmail.com - 2013-03-07 12:48 -0800
  Re: Python and Hidden Markov Model Dave Angel <davea@davea.name> - 2013-03-07 19:12 -0500
  Re: Python and Hidden Markov Model Oscar Benjamin <oscar.j.benjamin@gmail.com> - 2013-03-08 00:55 +0000
  Re: Python and Hidden Markov Model subhabangalore@gmail.com - 2013-03-07 21:26 -0800
    Re: Python and Hidden Markov Model Oscar Benjamin <oscar.j.benjamin@gmail.com> - 2013-03-08 14:29 +0000
      Re: Python and Hidden Markov Model Subhabrata <subhabangalore@gmail.com> - 2013-03-08 09:53 -0800

csiph-web