baseURL = "http://blog.pymc-learn.org/"

title = "pymc-learn Blog"

enableEmoji = true

footnotereturnlinkcontents = "^{^}"

disqusShortname = "emaasit"

defaultContentLanguage = "en"

defaultContentLanguageInSubdir = false

[permalinks]

post = "/post/:year/:month/:day/:slug/"

[blackfriday]

hrefTargetBlank = true

# Examples: "Mon, Jan 2, 2006" or "2006-01-02"

date_format = "Mon, Jan 2, 2006"

# Enable global LaTeX math rendering?

# If false, you can enable it locally on a per page basis.

math = true

# For more info on the highlighting options, see:

# https://gcushen.github.io/hugo-academic-demo/post/writing-markdown-latex/#highlighting-options

highlight = true

highlight_languages = []

# highlight_style = "github"

# highlight_version = "9.9.0"

# Enable native social sharing buttons?

sharing = true

# Link custom CSS and JS assets

# (relative to /static/css and /static/js respectively)

custom_css = ["cc-fonts.css"]

custom_js = []

# Publication types.

# Used to categorize publications.

# The index of the publication type in the list is used as its unique numerical identifier.

# The numeric ID is used in a publication's frontmatter to categorize it.

# The language can be edited below.

# For multi-lingual sites, copy this block to each language section at the end of this file.

publication_types = [

'Uncategorized', # 0

'Conference proceedings', # 1

'Journal', # 2

'Work in progress', # 3

'Technical report', # 4

'Book', # 5

'Book chapter' # 6

]

#

# Icon pack "fa" includes the following social network icons:

#

# twitter, weibo, linkedin, github, facebook, pinterest, google-plus,

# youtube, instagram, soundcloud

#

# For email icon, use "fa" icon pack, "envelope" icon, and

# "mailto:your@email.com" as the link.

#

# Full list: https://fortawesome.github.io/Font-Awesome/icons/

#

# Icon pack "ai" includes the following academic network icons:

#

# google-scholar, arxiv, orcid, researchgate, mendeley

#

# Full list: https://jpswalsh.github.io/academicons/

[[params.social]]

icon = "envelope"

icon_pack = "fa"

link = "mailto:devs@pymc-learn.org"

[[params.social]]

icon = "twitter"

icon_pack = "fa"

link = "//twitter.com/pymc_learn"

[[params.social]]

icon = "github"

icon_pack = "fa"

link = "//github.com/pymc-learn"

[[menu.main]]

name = "Home"

url = "/"

weight = 1

[[menu.main]]

name = "pymc-learn"

url = "http://pymc-learn.org"

weight = 2

[taxonomies]

tag = "tags"

category = "categories"

publication_type = "publication_types"

title: 'pymc-learn: Practical Probabilistic Machine Learning in Python'

author: Daniel Emaasit

date: '2018-10-15'

slug: pymc-learn-practical-probabilistic-machine-learning-in-python

categories:

- Announcement

tags:

- bayesian

- pymc3

- scikit-learn

- machine-learning

PyMC3 is a Python package for probabilistic machine learning that enables users

to build bespoke models for their specific problems using a probabilistic

modeling framework. However, PyMC3 lacks the steps between creating a model and

reusing it with new data in production. The missing steps include: scoring a

model, saving a model for later use, and loading the model in production

systems. In contrast, *scikit-learn* which has become the standard

library for machine learning provides a simple API that makes it very easy for

users to train, score, save and load models in production. However,

*scikit-learn* may not have the model for a user's specific problem.

These limitations have led to the development of the open

source *pymc3-models* library which provides a template to build bespoke

PyMC3 models on top of the *scikit-learn* API and reuse them in

production. This enables users to easily and quickly train, score, save and

load their bespoke models just like in *scikit-learn*.

The ``pymc-learn`` project leverages the template in *pymc3-models* to

develop custom Bayesian models. This provides users with probabilistic models

in a simple workflow that mimics the scikit-learn API.

1. Ghahramani, Z. (2015). Probabilistic machine learning and artificial intelligence. Nature, 521(7553), 452.

2. Bishop, C. M. (2013). Model-based machine learning. Phil. Trans. R. Soc. A, 371(1984), 20120222.

3. Murphy, K. P. (2012). Machine learning: a probabilistic perspective. MIT Press.

4. Barber, D. (2012). Bayesian reasoning and machine learning. Cambridge University Press.

5. Salvatier, J., Wiecki, T. V., & Fonnesbeck, C. (2016). Probabilistic programming in Python using PyMC3. PeerJ Computer Science, 2, e55.

<html lang="en-us">

<meta http-equiv="content-type" content="text/html; charset=utf-8">

<meta name="viewport" content="width=device-width, initial-scale=1.0, maximum-scale=1">

<title> Announcement &middot; pymc-learn Blog </title>

<link rel="stylesheet" href="/css/slim.css">

<link rel="stylesheet" href="/css/highlight.min.css">

<link href='https://fonts.googleapis.com/css?family=Source+Sans+Pro:400,700|Source+Code+Pro' rel='stylesheet' type='text/css'>

<link rel="apple-touch-icon-precomposed" sizes="144x144" href="/apple-touch-icon-144-precomposed.png">

<link rel="shortcut icon" href="/favicon.ico">

<link href="/categories/announcement/index.xml" rel="alternate" type="application/rss+xml" title="pymc-learn Blog" />

<div class="container">

<div class="header">

<h1 class="site-title"><a href="/">pymc-learn Blog</a></h1>

<p class="site-tagline"></p>

<div class="nav">

<a class="nav-btn" href="#">

<span class="ci ci-burger"></span>

</a>

<ul class="nav-list">

<li><a href="/">Home</a></li>

<li><a href="http://pymc-learn.org">pymc-learn</a></li>

<li class="spacer">&ac;</li>

</ul>

</div>

<div class="content">

<div class="posts">

<div class="post">

<h2 class="post-title"><a href="/post/2018/10/15/pymc-learn-practical-probabilistic-machine-learning-in-python/">pymc-learn: Practical Probabilistic Machine Learning in Python</a></h2>

<span class="post-date">Oct 15, 2018</span>

<span class="post-tags">

#<a href="/tags/bayesian">bayesian</a>&nbsp;

#<a href="/tags/pymc3">pymc3</a>&nbsp;

#<a href="/tags/scikit-learn">scikit-learn</a>&nbsp;

#<a href="/tags/machine-learning">machine-learning</a>&nbsp;

</span>

</div>

</div>

<div class="pagination">

</div>

<div class="footer">

<p>Powered by <a href="http://gohugo.io">Hugo</a>. This theme—Slim—is open sourced on <a href="https://github.com/zhe/hugo-theme-slim">Github</a>.</p>

</div>

<script src="/js/slim.js"></script>

<?xml version="1.0" encoding="utf-8" standalone="yes" ?>

<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">

<channel>

<title>Announcement on pymc-learn Blog</title>

<link>/categories/announcement/</link>

<description>Recent content in Announcement on pymc-learn Blog</description>

<generator>Hugo -- gohugo.io</generator>

<language>en-us</language>

<lastBuildDate>Mon, 15 Oct 2018 00:00:00 +0000</lastBuildDate>

<atom:link href="/categories/announcement/index.xml" rel="self" type="application/rss+xml" />

<item>

<title>pymc-learn: Practical Probabilistic Machine Learning in Python</title>

<link>/post/2018/10/15/pymc-learn-practical-probabilistic-machine-learning-in-python/</link>

<pubDate>Mon, 15 Oct 2018 00:00:00 +0000</pubDate>

<guid>/post/2018/10/15/pymc-learn-practical-probabilistic-machine-learning-in-python/</guid>

<description>PyMC3 is a Python package for probabilistic machine learning that enables users to build bespoke models for their specific problems using a probabilistic modeling framework. However, PyMC3 lacks the steps between creating a model and reusing it with new data in production. The missing steps include: scoring a model, saving a model for later use, and loading the model in production systems. In contrast, scikit-learn which has become the standard library for machine learning provides a simple API that makes it very easy for users to train, score, save and load models in production.</description>

</item>

</channel>

</rss>

<!DOCTYPE html><html><head><title>/categories/announcement/</title><link rel="canonical" href="/categories/announcement/"/><meta name="robots" content="noindex"><meta charset="utf-8" /><meta http-equiv="refresh" content="0; url=/categories/announcement/" /></head></html>