diff --git a/_static/custom.css b/_static/custom.css index 080fee5..09e0e2b 100644 --- a/_static/custom.css +++ b/_static/custom.css @@ -9,3 +9,80 @@ .bg-pymc-three { background-color: #e7b07b96 !important; } + +/* -------------------- HOMEPAGE -------------------- */ + +/* Hero */ +#hero { + display: flex; + flex-direction: row; + min-height: min(calc(50vh), 1000px); /* Make hero fill up most of the page on load */ +} +#hero-left { + max-width: 680px; + width: 50%; + margin: auto 0; +} + +.homepage-button-container { + margin-bottom: 1rem; + display: flex; + flex-direction: column; +} +.homepage-button-container-row { + display: flex; + flex-wrap: wrap; +} + +.homepage-button-container a { + transition: 0.1s; +} +.homepage-button { + min-width: 142px; + padding: 0.5em 2em; + border: 1px solid var(--pst-color-primary); + border-radius: 4px; + margin: 1em 0.5em 0.5em 0; +} +.primary-button { + background-color: var(--pst-color-primary); + color: var(--pst-color-background) !important; +} +.secondary-button { + background-color: var(--pst-color-background); + color: var(--pst-color-primary); +} +.homepage-button:hover { + text-decoration: none; + background-color: var(--pst-color-secondary); + color: var(--pst-color-background); + border: 1px solid var(--pst-color-secondary); +} +.homepage-button-link { + text-decoration: underline; +} + +/* Key Features */ +.key-features-icon { + font-size: 100px; + color: #6ca0b4; +} +.key-features-name { + font-size: 25px; + font-weight: bold; +} +.key-features-body { +} + + +/* Responsive */ +@media (max-width: 790px) { + #hero { + display: block; + } + #hero-left, + #hero-right { + width: 100%; + min-width: 0px; + } +} diff --git a/about/ecosystem.md b/about/ecosystem.md index dd716bc..98f13c2 100644 --- a/about/ecosystem.md +++ b/about/ecosystem.md @@ -1,14 +1,18 @@ # PyMC ecosystem ## General purpose - - [Bambi](https://github.com/bambinos/bambi): BAyesian Model-Building Interface (BAMBI) in Python. +- [PyMC-BART](https://www.pymc.io/projects/bart/en/latest/): Bayesian Additive Regression Trees for Probabilistic programming with PyMC +- [PyMC-Extras](https://github.com/pymc-devs/pymc-extras): A collection of PyMC extra features such as cutting-edge methodologies, highly specialized statistical distributions, or complex models appear. - [calibr8](https://github.com/JuBiotech/calibr8): A toolbox for constructing detailed observation models to be used as likelihoods in PyMC. - [CausalPy](https://github.com/pymc-labs/CausalPy): A package focussing on causal inference in quasi-experimental settings. - [SunODE](https://github.com/pymc-devs/sunode): Fast ODE solver, much faster than the one that comes with PyMC. - [pymc-learn](https://github.com/pymc-learn/pymc-learn): Custom PyMC models built on top of pymc3_models/scikit-learn API +- [BART-Survival](https://github.com/CDCgov/BART-Survival): BART-Survival is a Python package that supports discrete-time Survival analyses using the non-parametric machine learning algorithm, Bayesian Additive Regression Trees (BART). + ## Domain specific +- [PyMC-Marketing](https://www.pymc-marketing.io/en/stable/): Marketing analytic tools like Marketing Mix Modeling (MMM) or Customer Lifetime Value (CLV) - [Exoplanet](https://github.com/dfm/exoplanet): a toolkit for modeling of transit and/or radial velocity observations of exoplanets and other astronomical time series. - [beat](https://github.com/hvasbath/beat): Bayesian Earthquake Analysis Tool. diff --git a/about/sponsors.md b/about/sponsors.md new file mode 100644 index 0000000..900a35b --- /dev/null +++ b/about/sponsors.md @@ -0,0 +1,66 @@ +# Sponsors +:::::{container} full-width +::::{grid} 1 2 2 2 +:gutter: 2 + +:::{grid-item-card} NumFOCUS +:link: https://numfocus.org + + + +NumFOCUS is our non-profit umbrella organization. +::: + +:::{grid-item-card} PyMC Labs +:link: https://pymc-labs.io + + + +PyMC Labs offers professional consulting services for PyMC. +::: + +:::{grid-item-card} Open Wound Research +:link: https://www.openwoundresearch.com/ + + + +A novel wound-care research organization committed to advancing actionable wound care research. +::: + +:::: +::::: + +Read more about sponsoring PyMC on our [governance](https://github.com/pymc-devs/pymc/blob/main/GOVERNANCE.md#institutional-partners-and-funding) or reach out to `pymcdevs@gmail.com` if you are interested in becoming a sponsor. + +## Past Sponsors + +*Many thanks to all our former sponsors who supported PyMC development.* + +:::::{container} full-width +::::{grid} 1 2 2 3 +:gutter: 2 + +:::{grid-item-card} Mistplay (2022-2023) +:link: https://www.mistplay.com/ + + + +Mistplay is the world's leading Loyalty Program for mobile gamers. +::: +:::{grid-item-card} ODSC (2022-2023) +:link: https://odsc.com/california/?utm_source=pymc&utm_medium=referral + + + +The future of AI gathers here. +::: +:::{grid-item-card} Adia Lab (2023-2024) +:link: https://www.adialab.ae/ + + + +Dedicated to basic and applied research in data and computational sciences. +::: + +:::: +::::: diff --git a/conf.py b/conf.py index 82dd493..73a9b58 100644 --- a/conf.py +++ b/conf.py @@ -71,7 +71,7 @@ "pymc": ("https://www.pymc.io/projects/docs/en/stable/", None), "pytensor": ("https://pytensor.readthedocs.io/en/latest/", None), "nb": ("https://www.pymc.io/projects/examples/en/latest/", None), - "pmx": ("https://www.pymc.io/projects/experimental/en/latest/", None), + "pmx": ("https://www.pymc.io/projects/extras/en/latest/", None), "scipy": ("https://docs.scipy.org/doc/scipy/", None), "xarray": ("https://docs.xarray.dev/en/stable/", None), } @@ -162,6 +162,7 @@ def setup(app): html_title = "PyMC project website" html_sidebars = { + "welcome": [], "blog/tag": [ "ablog/tagcloud.html", "sidebar-nav-bs.html", diff --git a/welcome.md b/welcome.md index 343405a..b805548 100644 --- a/welcome.md +++ b/welcome.md @@ -1,23 +1,210 @@ --- +html_theme.sidebar_secondary.remove: sd_hide_title: true --- + + + # Home -
+
+
+

Probabilistic modeling at your fingertips

+ +
+
+ Get Started + See Examples +
+
+ See API Reference → +
+
+
+
+ + +
+

+PyMC is a probabilistic programming library for Python that allows users to build Bayesian models with a simple API. It features multiple inference algorithms, forward sampling, and model updates or interventions. +

+
+ + +## Built for insight + +:::::{grid} 1 2 3 3 + +::::{grid} 1 +:::{grid-item} +:class: key-features-icon + +{material-twotone}`data_exploration` +::: +:::{grid-item} +:class: key-features-name + +Modern +::: +:::{grid-item} +:class: key-features-body + +Includes state-of-the-art inference algorithms, including MCMC (NUTS) and variational inference (ADVI). +::: +:::: + +::::{grid} 1 +:::{grid-item} +:class: key-features-icon + +{material-twotone}`how_to_reg` +::: +:::{grid-item} +:class: key-features-name + +User-friendly +::: +:::{grid-item} +:class: key-features-body + +Write your models using friendly Python syntax. [Learn Bayesian modeling](https://www.pymc.io/projects/docs/en/latest/learn.html#) from the many [example notebooks](https://www.pymc.io/projects/examples/en/latest/gallery.html). +::: +:::: + +::::{grid} 1 +:::{grid-item} +:class: key-features-icon + +{material-twotone}`speed` +::: +:::{grid-item} +:class: key-features-name + +Fast +::: +:::{grid-item} +:class: key-features-body + + Uses {doc}`PyTensor ` as its computational backend to compile through C, Numba or JAX, [run your models on the GPU](https://www.pymc-labs.io/blog-posts/pymc-stan-benchmark/), and benefit from complex graph-optimizations. +::: +:::: + +::::{grid} 1 +:::{grid-item} +:class: key-features-icon + +{material-twotone}`battery_saver` +::: +:::{grid-item} +:class: key-features-name + +Batteries included +::: +:::{grid-item} +:class: key-features-body + +Includes probability distributions, Gaussian processes, ABC, SMC and much more. It integrates nicely with {doc}`ArviZ ` for visualizations and diagnostics, as well as [Bambi](https://bambinos.github.io/bambi/) for high-level mixed-effect models. +::: +:::: + +::::{grid} 1 +:::{grid-item} +:class: key-features-icon + +{material-twotone}`alt_route` +::: +:::{grid-item} +:class: key-features-name + +Hackable +::: +:::{grid-item} +:class: key-features-body + +Allows updates and interventions to both data and model; supporting predictions, forecasts, counterfactuals, or analysis of user interventions on model inputs. +::: +:::: + +::::{grid} 1 +:::{grid-item} +:class: key-features-icon + +{material-twotone}`diversity_3` +::: +:::{grid-item} +:class: key-features-name + +Community focused +::: +:::{grid-item} +:class: key-features-body + +Ask questions on [discourse](https://discourse.pymc.io), join [MeetUp events](https://meetup.com/pymc-online-meetup/), follow us on [Twitter](https://twitter.com/pymc_devs), and start [contributing](https://www.pymc.io/projects/docs/en/latest/contributing/index.html). +::: +:::: + +::::: + + +## Ecosystem + +### General purpose + +
+ +- [Bambi](https://github.com/bambinos/bambi): BAyesian Model-Building Interface (BAMBI) in Python. +- [PyMC-BART](https://www.pymc.io/projects/bart/en/latest/): Bayesian Additive Regression Trees for Probabilistic programming with PyMC +- [PyMC-Extras](https://github.com/pymc-devs/pymc-extras): A collection of PyMC extra features such as cutting-edge methodologies, highly specialized statistical distributions, or complex models appear. +- [calibr8](https://github.com/JuBiotech/calibr8): A toolbox for constructing detailed observation models to be used as likelihoods in PyMC. +- [CausalPy](https://github.com/pymc-labs/CausalPy): A package focussing on causal inference in quasi-experimental settings. +- [SunODE](https://github.com/pymc-devs/sunode): Fast ODE solver, much faster than the one that comes with PyMC. +- [pymc-learn](https://github.com/pymc-learn/pymc-learn): Custom PyMC models built on top of pymc3_models/scikit-learn API +- [BART-Survival](https://github.com/CDCgov/BART-Survival): BART-Survival is a Python package that supports discrete-time Survival analyses using the non-parametric machine learning algorithm, Bayesian Additive Regression Trees (BART). + +
+ +### Domain specific + +
-{doc}`PyMC ` is a probabilistic programming library for Python that allows users to build Bayesian models with a simple Python API and fit them using Markov chain Monte Carlo (MCMC) methods. +- [PyMC-Marketing](https://www.pymc-marketing.io/en/stable/): Marketing analytic tools like Marketing Mix Modeling (MMM) or Customer Lifetime Value (CLV) +- [Exoplanet](https://github.com/dfm/exoplanet): a toolkit for modeling of transit and/or radial velocity observations of exoplanets and other astronomical time series. +- [beat](https://github.com/hvasbath/beat): Bayesian Earthquake Analysis Tool. -## Features -PyMC strives to make Bayesian modeling as simple and painless as possible, allowing users to focus on their problem rather than the methods. +
-Here is what sets it apart: +More about the {doc}`about/ecosystem` -* **Modern**: Includes state-of-the-art inference algorithms, including MCMC (NUTS) and variational inference (ADVI). -* **User friendly**: Write your models using friendly Python syntax. [Learn Bayesian modeling](https://www.pymc.io/projects/docs/en/latest/learn.html#) from the many [example notebooks](https://www.pymc.io/projects/examples/en/latest/gallery.html). -* **Fast**: Uses {doc}`PyTensor ` as its computational backend to compile through C, Numba or JAX, [run your models on the GPU](https://www.pymc-labs.io/blog-posts/pymc-stan-benchmark/), and benefit from complex graph-optimizations. -* **Batteries included**: Includes probability distributions, Gaussian processes, ABC, SMC and much more. It integrates nicely with {doc}`ArviZ ` for visualizations and diagnostics, as well as {doc}`Bambi ` for high-level mixed-effect models. -* **Community focused**: Ask questions on [discourse](https://discourse.pymc.io), join [MeetUp events](https://meetup.com/pymc-online-meetup/), follow us on [Twitter](https://twitter.com/pymc_devs), and start [contributing](https://www.pymc.io/projects/docs/en/latest/contributing/index.html). ## Example from Linear Regression @@ -138,72 +325,6 @@ The new data, under the above scenario would look like: | plant growth[1] | 29.809 | 0.508 | 28.832 | 30.717 | | plant growth[2] | -0.131 | 0.507 | -1.121 | 0.791 | -## Get started -* [Installation instructions](https://www.pymc.io/projects/docs/en/latest/installation.html) -* [Beginner guide (if you **do not** know Bayesian modeling)](https://www.pymc.io/projects/docs/en/latest/learn/core_notebooks/pymc_overview.html) -* [API quickstart (if you **do** know Bayesian modeling)](https://www.pymc.io/projects/examples/en/latest/introductory/api_quickstart.html) -* [Example gallery](https://www.pymc.io/projects/examples/en/latest/gallery.html) -* [Discourse help forum](https://discourse.pymc.io) - -## Announcements - -:::::{container} full-width -::::{grid} 1 2 2 3 -:gutter: 3 - -:::{grid-item-card} PyMC forked Aesara to PyTensor -:link: pytensor_announcement -:link-type: ref -:class-header: bg-pymc-three - -Release announcement -^^^ -PyTensor will allow for new features such as labeled arrays, as well as speed up development and streamline the PyMC codebase and user experience. -::: - - -:::{grid-item-card} PyMC 4.0 is officially released! -:link: v4_announcement -:link-type: ref -:class-header: bg-pymc-three - -Release announcement -^^^ -PyMC 4.0 is a major rewrite of the library with many great new features while keeping the same modeling API of PyMC3. -::: - -:::{grid-item-card} PyMC - Office Hours -:link: https://discourse.pymc.io/tag/office-hours -:class-header: bg-pymc-one - -Event -^^^ -The PyMC team has recently started hosting office hours regularly. -Subscribe on Discourse to be notified of the next event! -::: - -:::{grid-item-card} Probabilistic Programming in PyMC -:link: https://austinrochford.com/posts/intro-prob-prog-pymc.html -:class-header: bg-pymc-two - -Talk -^^^ -Austin Rochford gave the coolest talk on Probabilistic Programming in PyMC 4.0 -::: - -:::{grid-item-card} Sprint testimonials -:link: sprint_testimonial -:link-type: ref -:class-header: bg-pymc-one - -Blog post -^^^ -Read about the recent PyMC-Data Umbrella sprint in this interview with -Sandra Meneses, one of the participants who submitted a PR -::: - -:::: -::::: ## Sponsors :::::{container} full-width @@ -221,7 +342,7 @@ NumFOCUS is our non-profit umbrella organization. :::{grid-item-card} PyMC Labs :link: https://pymc-labs.io - + PyMC Labs offers professional consulting services for PyMC. ::: @@ -237,55 +358,14 @@ A novel wound-care research organization committed to advancing actionable wound :::: ::::: -## Past Sponsors - -*Many thanks to all our former sponsors who supported PyMC development.* - -:::::{container} full-width -::::{grid} 1 2 2 3 -:gutter: 2 - -:::{grid-item-card} Mistplay (2022-2023) -:link: https://www.mistplay.com/ - - +More about PyMC's {doc}`about/sponsors` -Mistplay is the world's leading Loyalty Program for mobile gamers. -::: -:::{grid-item-card} ODSC (2022-2023) -:link: https://odsc.com/california/?utm_source=pymc&utm_medium=referral - - - -The future of AI gathers here. -::: -:::{grid-item-card} Adia Lab (2023-2024) -:link: https://www.adialab.ae/ - - - -Dedicated to basic and applied research in data and computational sciences. -::: - -:::: -::::: :::{toctree} :hidden: about/ecosystem about/history +about/sponsors about/testimonials ::: - -:::{toctree} -:hidden: -:caption: External links - -Discourse -Twitter -YouTube -LinkedIn -Meetup -GitHub -:::