<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Python on Xavier Valls Pla</title>
    <link>http://xvallspl.github.io/tags/python/</link>
    <description>Recent content in Python on Xavier Valls Pla</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en-us</language>
    <lastBuildDate>Thu, 18 Sep 2025 09:30:00 +0200</lastBuildDate>

	<atom:link href="http://xvallspl.github.io/tags/python/index.xml" rel="self" type="application/rss+xml" />


    <item>
      <title>Chasing ML for fraud detection — and ending up with rules instead</title>
      <link>http://xvallspl.github.io/blog/fraud-detection/</link>
      <pubDate>Thu, 18 Sep 2025 09:30:00 +0200</pubDate>

      <guid>http://xvallspl.github.io/blog/fraud-detection/</guid>
      <description>Earlier this year I took on a part-time project for a telecom operator: see if machine learning could replace, or at least augment, their existing fraud and abuse detection. The brief was about as open as it gets &amp;mdash; try to make this AI-first, figure out how, here&amp;#39;s the data, ask if you have questions.</description>
    </item>

    <item>
      <title>Porting SixDesk&#39;s post-processing to Python and SQL</title>
      <link>http://xvallspl.github.io/blog/cern/sixdeskdb/</link>
      <pubDate>Mon, 23 May 2016 09:45:00 +0200</pubDate>

      <guid>http://xvallspl.github.io/blog/cern/sixdeskdb/</guid>
      <description>This article is part of a short series adapted from my Bachelor&#39;s thesis on post-processing routines for long-term beam stability in particle accelerators. Some of the implementation details below reflect SixDesk/SixDeskDB as they stood in 2015-16 and may not match their current state.
 The previous article in this series walked through postpr, SixTrack&#39;s Fortran post-processing subroutine, and the pile of interdependent Bash, AWK and Fortran scripts SixDesk wraps around it to turn a full dynamic-aperture study into a handful of plots.</description>
    </item>

  </channel>
</rss>
