<div dir="ltr"><div class="gmail_extra"><div class="gmail_quote">On 10 April 2018 at 12:34, Andrea Karlova <span dir="ltr"><<a href="mailto:andrea.karlova@gmail.com" target="_blank">andrea.karlova@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><div class="gmail_quote"><div><div class="gmail-h5">On 8 April 2018 at 18:05, Blair Azzopardi <span dir="ltr"><<a href="mailto:blairuk@gmail.com" target="_blank">blairuk@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><div><div class="gmail-m_3878315376916507301h5"><div>> On 8 April 2018 at 12:49, Andrea Karlova <<a href="mailto:andrea.karlova@gmail.com" target="_blank">andrea.karlova@gmail.com</a>> wrote:<br></div><div>>> On 8 April 2018 at 05:21, Blair Azzopardi <<a href="mailto:blairuk@gmail.com" target="_blank">blairuk@gmail.com</a>> wrote:</div><div>>>> On 8 April 2018 at 01:49, Andrea Karlova <<a href="mailto:andrea.karlova@gmail.com" target="_blank">andrea.karlova@gmail.com</a>> wrote:</div><div>>>>> On 28 November 2017 at 18:33, Blair Azzopardi <<a href="mailto:blairuk@gmail.com" target="_blank">blairuk@gmail.com</a>> wrote:</div><div>>>>>> On Tue, 28 Nov 2017, 16:01 Andrea Karlova, <<a href="mailto:andrea.karlova@gmail.com" target="_blank">andrea.karlova@gmail.com</a>> wrote:</div><div>>>>>>> On 28 November 2017 at 13:17, Blair Azzopardi <<a href="mailto:blairuk@gmail.com" target="_blank">blairuk@gmail.com</a>> wrote:</div><div>>>>>>>> ---------- Forwarded message ---------</div><div>>>>>>>> From: An <<a href="mailto:notifications@github.com" target="_blank">notifications@github.com</a>></div><div>>>>>>>> Date: Tue, 28 Nov 2017, 10:00</div><div>>>>>>>> Subject: Re: [scipy/scipy] ENH: Add PDF, CDF and parameter estimation for Stable Distributions (#7374)</div><div>>>>>>>> To: scipy/scipy <<a href="mailto:scipy@noreply.github.com" target="_blank">scipy@noreply.github.com</a>></div><div>>>>>>>> </div><div>>>>>>>> Blair, is there a way to have a chat via email?</div><div>>>>>>>> </div><div>>>>>>>> On 24 November 2017 at 20:38, Blair Azzopardi <<a href="mailto:notifications@github.com" target="_blank">notifications@github.com</a>></div><div>>>>>>>> wrote:</div><div>>>>>>>> </div><div>>>>>>>> Hi @an81 <<a href="https://github.com/an81" target="_blank">https://github.com/an81</a>>. Thank you for the 550+ page book.</div><div>>>>>>>> Please can you be a bit more specific? Some sample code goes a long way</div><div>>>>>>>> too. Also can you perhaps test the existing code and highlight where the</div><div>>>>>>>> Gibbs effect might be more prominent? eg low alpha etc; perhaps this can be</div><div>>>>>>>> just documented with a recommendation that users use quad in these cases</div><div>>>>>>>> (already in code). This is until better implementation is available.</div><div>>>>>>>> —</div><div>>>>>>>> You are receiving this because you were mentioned.</div><div>>>>>>>> Reply to this email directly, view it on GitHub</div><div>>>>>>>> <<a href="https://github.com/scipy/scipy/pull/7374#issuecomment-346893569" target="_blank">https://github.com/scipy/scip<wbr>y/pull/7374#issuecomment-34689<wbr>3569</a>>, or mute</div><div>>>>>>>> the thread</div><div>>>>>>>> <<a href="https://github.com/notifications/unsubscribe-auth/AIfE8VNjHdqANvYfUG8Gg6feKb5np_kLks5s5ylhgaJpZM4NQBiP" target="_blank">https://github.com/notificati<wbr>ons/unsubscribe-auth/AIfE8VNjH<wbr>dqANvYfUG8Gg6feKb5np_kLks5s5yl<wbr>hgaJpZM4NQBiP</a>></div><div>>>>>>> </div><div>>>>>>> Hi Andrea</div><div>>>>>>> </div><div>>>>>>> I hope you're well and yes no problem talking chatting via email. Actually makes sense.</div><div>>>>>>> </div><div>>>>>>> Also, I hope you don't mind me messaging you via an email address found in a previous comment.</div><div>>>>>>> </div><div>>>>>>> I took a look at that book you linked to but unfortunately I don't have enough time to process it currently. I will read it in time mind you. I've found a shorter paper that might offer similar suggestions to yours:</div><div>>>>>>> </div><div>>>>>>> <a href="http://prac.im.pwr.edu.pl/~hugo/publ/SFB2005-008_Borak_Haerdle_Weron.pdf" target="_blank">http://prac.im.pwr.edu.pl/~hug<wbr>o/publ/SFB2005-008_Borak_Haerd<wbr>le_Weron.pdf</a></div><div>>>>>>> </div><div>>>>>>> Although I'm not 100% sure as it doesn't mention mejer g functions. What are your thoughts? </div><div>>>>>>> </div><div>>>>>>> Kind regards</div><div>>>>>>> Blair</div><div>>>>>> </div><div>>>>>> Hi Blair, </div><div>>>>>> </div><div>>>>>> thats great. </div><div>>>>>> Thx for your email.</div><div>>>>>> </div><div>>>>>> I ll give you access to my Dropbox folder where I have materials relevant to stable laws.</div><div>>>>>> For working with stable laws I found really useful to understand </div><div>>>>>> and actively switch between different parametrizations of the characteristic exponent. </div><div>>>>>> Zolotarev and others would have polenty of parametrization and each of them is helpful </div><div>>>>>> for different task. </div><div>>>>>> </div><div>>>>>> I guess I can share with you my python code on the github, </div><div>>>>>> you can contribute to it if you would feel like so </div><div>>>>>> and then we can just plug it into scipy lib. </div><div>>>>>> </div><div>>>>>> Is it ok to use this gmail account for sending you invitation to Dropbox?</div><div>>>>>> </div><div>>>>>> Thx,</div><div>>>>>> Kind regards,</div><div>>>>>> </div><div>>>>>> Andrea </div><div>>>>> </div><div>>>>> Hi Andrea</div><div>>>>> </div><div>>>>> Yes, please do share with this email address.</div><div>>>>> </div><div>>>>> Is it possible you could commit your changes to the existing PR I've already set up? I believe this is possible by forking my repo (script fork) and committing to that. The PR includes parameter estimation and some general framework changes around this distribution too. Also I feel there are still use cases where it's useful keep fft method. I've added you a collaborator on my fork.</div><div>>>>> </div><div>>>>> <a href="https://github.com/bsdz/scipy" target="_blank">https://github.com/bsdz/scipy</a></div><div>>>>> </div><div>>>>> Kind regards</div><div>>>>> Blair</div><div>>>> </div><div>>>> Hi Blair,</div><div>>>> </div><div>>>> hope you are well. </div><div>>>> I was looking into your code on stable laws in scipy. </div><div>>>> I ll be running a group of 4 people at hackaton which is organized by AHL in 2 weeks time</div><div>>>> and I am planning to revise and add more code into stable laws implementation. </div><div>>>> </div><div>>>> I was wondering if you can give me some quick update on what is done so far </div><div>>>> and what are urgent issues at this point according to your opinion? </div><div>>>> I have some ideas what I would like add, also the documentation page needs to be written,</div><div>>>> but just a quick check on what methods you implemented for calculating of </div><div>>>> pdfs, cdfs, and parameters estimates and how it went?</div><div>>>> </div><div>>>> Thanks a lot. </div><div>>>> Kind regards,</div><div>>>> Andrea </div><div>>>> </div><div>>> </div><div>>> Hi Andrea</div><div>>> </div><div>>> Thanks for your email. I'm cc-ing this email along with out previous correspondence to the scipy-dev mailing list (as bottom post) . Please direct all your future messages here. </div><div>>> </div><div>>> It's good to hear you plan to improve my PR (coincidentally at my old employer Man, although at the time they weren't interested in Stable laws).</div><div>>> </div><div>>> I did implement your suggestions to use Zolotarev's formulations. All the code is under <a href="https://github.com/scipy/scipy/pull/7374" target="_blank">https://github.com/scipy/scipy<wbr>/pull/7374</a> as you are aware.</div><div>>> </div><div>>> You could perhaps look at improving documentation, adding more / improving tests and any optimisations you can think of. </div><div>>> </div><div>>> Either I can re-add you as a collaborator to my repo (I removed you when I hadn't heard back from you previously) or you can email me a patch and I'll integrate it into PR 7374.</div><div>>> </div><div>>> Thanks</div><div>>> Blair </div><div>></div></div></div><span><div>> Hi Blair,</div><div>> </div><div>> yes, if you could add me to your repository, </div><div>> so I can look into what is done and start to test your code,</div><div>> so that I can look into some patches, that would be great.</div><div><br></div></span><div>Hi Andrea</div><div><br></div><div>Actually, just to be cautious. Could you fork my scipy repo (it has all the changes there) and then create a PR into that repo? I can then merge it and it should push upstream into my main PR.</div></div></div></blockquote><div><br></div></div></div><div>Sure, no worries. </div><span class="gmail-"><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><span><div><br></div><div>> How does your code performs in neighbourhood of alpha = 1?</div><div>> How does it perform when the asymetry parameter beta gets close to its boundary values?</div><div><br></div></span><div>Please run the code and check. My testing took samples from Nolan's public domain executables and tested against those values. Although I tested against a range of parameters I might not have tested those ranges specifically. It's all in the unit tests in the PR, see test class TestLevyStable. Extending the testing here would be helpful.</div></div></div></blockquote><div><br></div></span><div>Ok.</div><span class="gmail-"><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><span><div> </div><div>> Do you have somewhere in Latex notes on your fft implementation, </div><div>> with some theoretical investigation of the performance of the method?</div><div><br></div></span><div>This is all in the code documentation along with references.</div></div></div></blockquote><div><br></div></span><div>Ok, so the answer to my question is no and there is only available info in the comments in the code, right? </div></div></div></div></blockquote><div><br></div><div>It's in the code, please look at function _pdf_from_cf_with_fft(), it has a docstring that refers to "[MS]". The full reference is then in the main docstring along with page numbers.</div><div><br></div><div><a href="https://github.com/scipy/scipy/pull/7374/files#diff-6e4287784ff3e7a5c6d89d442bea3fbbR3683-R3694">https://github.com/scipy/scipy/pull/7374/files#diff-6e4287784ff3e7a5c6d89d442bea3fbbR3683-R3694</a><br></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><div class="gmail_quote"><span class="gmail-"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><span><div><br></div><div>> I am planning to write a research paper about the implementation in the Scipy, which I ll put on my ArXiv,</div><div>> and to which I ll refer in the documentation, so that if people are interested in the performance, they can look into paper. </div><div>> So I ll be listing the co-authors of this piece of code there. </div><div>> If there are other people who worked on the stable laws implementation in Scipy, it would be nice if I can have the list of them. </div><div>> Also if you have some note on fft, I can join it into my research note and add you as a coauthor of the note,</div><div>> depends upon you.</div><div><br></div></span><div>So far, I'm the sole author of this PR. Again, all papers and references are in the PR. Please please do look at the code.</div></div></div></blockquote></span><div>Ok, done. Thanks. </div><span class="gmail-"><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><div><br></div><div>> </div><div>> Kind regards,</div><div>> Andrea </div><div><br></div><div>Just some additional points, you need to subscribe to the scipy-dev mailing list for your messages to get through. Also, the mailing list uses bottom posting for email messages; that means, all replies are bottom of original message (not the top.)</div><div><br></div></div></div></blockquote><div><br></div></span><div>Sure.</div></div></div></div></blockquote><div><br></div><div>Btw, it seems your messages aren't getting through to scip-dev mailing list. You can subscribe here:</div><div><br></div><div><a href="https://mail.python.org/mailman/listinfo/scipy-dev">https://mail.python.org/mailman/listinfo/scipy-dev</a><br></div><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><div class="gmail_quote"><span class="gmail-"><div> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><div></div><div>Look forward to your contribution - thanks!</div></div></div></blockquote><div><br></div></span><div>Me too :) </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr"><div class="gmail_extra"><span class="gmail-m_3878315376916507301HOEnZb"><font color="#888888"><div><br></div><div>Blair<br><br></div></font></span></div></div>
</blockquote></div><br></div></div>
</blockquote></div><br></div></div>