# \#doc

**URL:** https://discourse.pymc.io/tag/doc/8.md

[Latest](https://discourse.pymc.io/latest.md) · [Categories](https://discourse.pymc.io/categories.md) · [Tags](https://discourse.pymc.io/tags.md)

---

## [Trouble accessing pytensor docs from Japan](https://discourse.pymc.io/t/trouble-accessing-pytensor-docs-from-japan/14293)

<div class="topic-metadata">

**Author:** [@jhandsel](https://discourse.pymc.io/u/jhandsel)\
**Replies:** 2\
**Last updated:** [April 22, 2024, 2:25am UTC](https://discourse.pymc.io/t/trouble-accessing-pytensor-docs-from-japan/14293 "2024-04-22T02:25:41Z")

</div>

I’m having trouble accessing https://pytensor.readthedocs.io/ from Japan. Every time I try to access the page, I get a “Verify you are human” checkbox to tick from cloudflare. When the page does load, it’s in plain HTML.…

---

## [Trouble with trying to build docs locally with gitpod](https://discourse.pymc.io/t/trouble-with-trying-to-build-docs-locally-with-gitpod/13941)

<div class="topic-metadata">

**Author:** [@brandonhorsley](https://discourse.pymc.io/u/brandonhorsley)\
**Replies:** 2\
**Last updated:** [March 22, 2024, 2:15pm UTC](https://discourse.pymc.io/t/trouble-with-trying-to-build-docs-locally-with-gitpod/13941 "2024-03-22T14:15:01Z")

</div>

Hi all, I’ve spent my whole day trying to figure this out but I think it is time to call in some help :sweat\_smile: So I have been working on a github issue concerning the absence of inverse trig functions from pymc, b…

---

## [Error in Defining Bayesian NN with Multivariate Gaussians](https://discourse.pymc.io/t/error-in-defining-bayesian-nn-with-multivariate-gaussians/13904)

<div class="topic-metadata">

**Author:** [@NourJ](https://discourse.pymc.io/u/NourJ)\
**Replies:** 1\
**Last updated:** [February 29, 2024, 6:06pm UTC](https://discourse.pymc.io/t/error-in-defining-bayesian-nn-with-multivariate-gaussians/13904 "2024-02-29T18:06:12Z")

</div>

Hi there and thanks for all your work, We are trying to build a Bayesian Neural Network with Multivariate Gaussians as distributions for our parameters. We are following the structure of the code presented in the tutori…

---

## [Is pymc.Gumbel the extreme maximum or minimum distribution?](https://discourse.pymc.io/t/is-pymc-gumbel-the-extreme-maximum-or-minimum-distribution/11139)

<div class="topic-metadata">

**Author:** [@Helios1014](https://discourse.pymc.io/u/Helios1014)\
**Replies:** 1\
**Last updated:** [October 6, 2023, 11:32am UTC](https://discourse.pymc.io/t/is-pymc-gumbel-the-extreme-maximum-or-minimum-distribution/11139 "2023-10-06T11:32:07Z")

</div>

I have been reading up on the Gumbel distribution and there are two versions: an extreme maximum and an extreme minimum. The way the PDF is written in the documentation leads me to think this is the maximum but that is n…

---

## [Migrating to Pymc4 with example from PYMC docs](https://discourse.pymc.io/t/migrating-to-pymc4-with-example-from-pymc-docs/10935)

<div class="topic-metadata">

**Author:** [@Nn\_Nnn](https://discourse.pymc.io/u/Nn_Nnn)\
**Replies:** 4\
**Last updated:** [December 10, 2022, 5:45pm UTC](https://discourse.pymc.io/t/migrating-to-pymc4-with-example-from-pymc-docs/10935 "2022-12-10T17:45:56Z")

</div>

Prior and Posterior Predictive Checks — PyMC 4.4.0 documentation I am a novice starting pymc4. can you help with the following what would be considered a simple example from the pymc docs for learners. Running the foll…

---

## [How can I create a class using pm.Model's class like keras.Model or torch.nn.Module option?](https://discourse.pymc.io/t/how-can-i-create-a-class-using-pm-models-class-like-keras-model-or-torch-nn-module-option/10899)

<div class="topic-metadata">

**Author:** [@karthy257](https://discourse.pymc.io/u/karthy257)\
**Replies:** 1\
**Last updated:** [November 25, 2022, 10:43am UTC](https://discourse.pymc.io/t/how-can-i-create-a-class-using-pm-models-class-like-keras-model-or-torch-nn-module-option/10899 "2022-11-25T10:43:32Z")

</div>

I was wondering how to create a class using pm.Model’s class. Since I am coming from Torch and Tensorflow based models, I like to know how to create a class inheritance based on pymc.Model’s class like the keras.Model or…

---

## [PyMC+ArviZ: how to make the most of labeled coords and dims in PyMC 4.0](https://discourse.pymc.io/t/pymc-arviz-how-to-make-the-most-of-labeled-coords-and-dims-in-pymc-4-0/9581)

<div class="topic-metadata">

**Author:** [@OriolAbril](https://discourse.pymc.io/u/OriolAbril)\
**Replies:** 9\
**Last updated:** [November 11, 2022, 8:12pm UTC](https://discourse.pymc.io/t/pymc-arviz-how-to-make-the-most-of-labeled-coords-and-dims-in-pymc-4-0/9581 "2022-11-11T20:12:31Z")

</div>

Nearly two years ago I wrote a blog post about the integration between PyMC3 and ArviZ (which I also shared here on discourse). I have now adapted and updated it to showcase all the further improvements on dims and coord…

---

## [Pm.distributions.transforms](https://discourse.pymc.io/t/pm-distributions-transforms/10541)

<div class="topic-metadata">

**Author:** [@opherdonchin](https://discourse.pymc.io/u/opherdonchin)\
**Replies:** 9\
**Last updated:** [October 16, 2022, 1:07pm UTC](https://discourse.pymc.io/t/pm-distributions-transforms/10541 "2022-10-16T13:07:33Z")

</div>

Can someone point me to a notebook or other doc that makes clear, with examples, how to use the objects defined in pm.distributions.transforms. Maybe I’m being dense, but I can’t find anything but the briefest snippets a…

---

## [Migrating to PyMC4 from PyMC3 Multidimensional GP](https://discourse.pymc.io/t/migrating-to-pymc4-from-pymc3-multidimensional-gp/10344)

<div class="topic-metadata">

**Author:** [@Ali\_Mehrabifard](https://discourse.pymc.io/u/Ali_Mehrabifard)\
**Replies:** 1\
**Last updated:** [September 9, 2022, 2:43pm UTC](https://discourse.pymc.io/t/migrating-to-pymc4-from-pymc3-multidimensional-gp/10344 "2022-09-09T14:43:56Z")

</div>

Dear all, My apologies if the question is rudimentary. I am following a notebook from @fonnesbeck presented at PyData NYC 2019, shared here on multidimensional GP, I am using the newly released PyMC4, I am not able to d…

---

## [Equvilant APIs in PyMC v4](https://discourse.pymc.io/t/equvilant-apis-in-pymc-v4/8920)

<div class="topic-metadata">

**Author:** [@dchu1991](https://discourse.pymc.io/u/dchu1991)\
**Replies:** 14\
**Last updated:** [September 7, 2022, 9:38am UTC](https://discourse.pymc.io/t/equvilant-apis-in-pymc-v4/8920 "2022-09-07T09:38:00Z")

</div>

greetings, i was going through the example notebook Variational Inference: Bayesian Neural Networks since the VI APIs are available in pymc v4. i’ve noticed that the notebook utilized neural\_network.out.distribution.p …

---

## [How to call predict function on BART?](https://discourse.pymc.io/t/how-to-call-predict-function-on-bart/6985)

<div class="topic-metadata">

**Author:** [@justindlwhite](https://discourse.pymc.io/u/justindlwhite)\
**Replies:** 9\
**Last updated:** [July 27, 2022, 4:48pm UTC](https://discourse.pymc.io/t/how-to-call-predict-function-on-bart/6985 "2022-07-27T16:48:19Z")

</div>

I’m trying to figure out how to use the predict function with BART. I know this is very new, and the only example notebook I can find does not use it or do prediction on new data. I started with the demo notebook and tr…

---

## [Keyword in sample\_smc](https://discourse.pymc.io/t/keyword-in-sample-smc/9686)

<div class="topic-metadata">

**Author:** [@jiayuand](https://discourse.pymc.io/u/jiayuand)\
**Replies:** 8\
**Last updated:** [June 22, 2022, 5:40am UTC](https://discourse.pymc.io/t/keyword-in-sample-smc/9686 "2022-06-22T05:40:09Z")

</div>

I am currently updating pymc3 to pymc, when using pm.sample\_smc(XXX, nsteps = 50), it turns out that TypeError: SMC\_KERNEL.init() got an unexpected keyword argument ‘nsteps’. May I know how to get this solved? Thanks!

---

## [Noob question: Bayesian inference in AB test vs frequentist approach (N size)](https://discourse.pymc.io/t/noob-question-bayesian-inference-in-ab-test-vs-frequentist-approach-n-size/9708)

<div class="topic-metadata">

**Author:** [@pabloazurduy](https://discourse.pymc.io/u/pabloazurduy)\
**Replies:** 6\
**Last updated:** [June 21, 2022, 10:34pm UTC](https://discourse.pymc.io/t/noob-question-bayesian-inference-in-ab-test-vs-frequentist-approach-n-size/9708 "2022-06-21T22:34:44Z")

</div>

Hi everyone! a very noob question here about bayesian inference and AB tests. I was following this tutorial with a very simplistic AB-test example, I was wondering how sensitive was the “hypothesis test of delta” with t…

---

## [Getting Theano Working](https://discourse.pymc.io/t/getting-theano-working/9620)

<div class="topic-metadata">

**Author:** [@ahc\_ahc](https://discourse.pymc.io/u/ahc_ahc)\
**Replies:** 11\
**Last updated:** [June 13, 2022, 7:59am UTC](https://discourse.pymc.io/t/getting-theano-working/9620 "2022-06-13T07:59:43Z")

</div>

Hi, I have been trying to successfully run a program that uses a theano Op. When I follow the instructions here: Installation Guide (Linux) · pymc-devs/pymc Wiki · GitHub I get the following error when I import theano: …

---

## [Proposal for website design](https://discourse.pymc.io/t/proposal-for-website-design/9483)

<div class="topic-metadata">

**Author:** [@twiecki](https://discourse.pymc.io/u/twiecki)\
**Replies:** 14\
**Last updated:** [May 30, 2022, 10:16am UTC](https://discourse.pymc.io/t/proposal-for-website-design/9483 "2022-05-30T10:16:16Z")

</div>

Talked with @OriolAbril a bunch. Here are some thoughts I have on getting the website to a state where v4 can be released (a lot of them are already on the roadmap from Oriol): There are three pages currently: pymc.i…

---

## [Online Developer Sprint](https://discourse.pymc.io/t/online-developer-sprint/9485)

<div class="topic-metadata">

**Author:** [@cluhmann](https://discourse.pymc.io/u/cluhmann)\
**Replies:** 1\
**Last updated:** [May 25, 2022, 6:56pm UTC](https://discourse.pymc.io/t/online-developer-sprint/9485 "2022-05-25T18:56:57Z")

</div>

The PyMC Team is working towards the v4 release ! Next week (May 30 - June 5), we will be holding a (virtual) developer sprint/hackathon to try and finish off the last several issues associated with the 4.0 milestone. …

---

## [Undefined term "chain"](https://discourse.pymc.io/t/undefined-term-chain/9435)

<div class="topic-metadata">

**Author:** [@mdrum](https://discourse.pymc.io/u/mdrum)\
**Replies:** 1\
**Last updated:** [May 17, 2022, 9:10am UTC](https://discourse.pymc.io/t/undefined-term-chain/9435 "2022-05-17T09:10:00Z")

</div>

(This is a very small and subtle suggestion.) In the dev documention, in the “Introductory Overview of PyMC”, https://docs.pymc.io/en/latest/learn/core\_notebooks/pymc\_overview.html the term “chain” is introduced witho…

---

## [Documentation bugs and improvements?](https://discourse.pymc.io/t/documentation-bugs-and-improvements/9415)

<div class="topic-metadata">

**Author:** [@mdrum](https://discourse.pymc.io/u/mdrum)\
**Replies:** 2\
**Last updated:** [May 17, 2022, 5:48am UTC](https://discourse.pymc.io/t/documentation-bugs-and-improvements/9415 "2022-05-17T05:48:55Z")

</div>

Suppose I want to point out an error in the documentation, or suggest an improvement to it. Is there a special mechanism for that, or should I just use discourse.pymc.io, as I am doing now? Thank you. P.S. For example,…

---

## [API question: What are the semantics of array-style indexing on a Distribution object, with another PyMC object?](https://discourse.pymc.io/t/api-question-what-are-the-semantics-of-array-style-indexing-on-a-distribution-object-with-another-pymc-object/9343)

<div class="topic-metadata">

**Author:** [@mdrum](https://discourse.pymc.io/u/mdrum)\
**Replies:** 2\
**Last updated:** [May 9, 2022, 3:16am UTC](https://discourse.pymc.io/t/api-question-what-are-the-semantics-of-array-style-indexing-on-a-distribution-object-with-another-pymc-object/9343 "2022-05-09T03:16:34Z")

</div>

I am new to PyMC and I am studying the Simpson’s Paradox tutorial. The last line in Models 2 and 3 (cells 12 and 17) is pm.Normal("y", mu=μ, sigma=sigma\[g\], observed=data.y, dims="observation") where sigma is previousl…

---

## [Standardize Explainer on Bambi in PyMC Examples](https://discourse.pymc.io/t/standardize-explainer-on-bambi-in-pymc-examples/9326)

<div class="topic-metadata">

**Author:** [@hectormz](https://discourse.pymc.io/u/hectormz)\
**Replies:** 0\
**Last updated:** [May 3, 2022, 1:45am UTC](https://discourse.pymc.io/t/standardize-explainer-on-bambi-in-pymc-examples/9326 "2022-05-03T01:45:07Z")

</div>

I’ve been reviewing some of the GLM documents for pymc v4 and saw that .glm() has been deprecated and bambi seems to be the preferred route. Some of the examples that were originally done without bambi read a little con…

---

## [GLM Logistic Example, why divide by age by 10?](https://discourse.pymc.io/t/glm-logistic-example-why-divide-by-age-by-10/9195)

<div class="topic-metadata">

**Author:** [@Oliver](https://discourse.pymc.io/u/Oliver)\
**Replies:** 4\
**Last updated:** [April 12, 2022, 5:43pm UTC](https://discourse.pymc.io/t/glm-logistic-example-why-divide-by-age-by-10/9195 "2022-04-12T17:43:05Z")

</div>

Hi all I went over this example again and in the lm full function they divide age by 10. Thank you so much for any explanations and hints and apologies! I’m sure I"m missing something obvious once more, but I don’t see…

---

## [Running the test suite is not available on the PyMC website](https://discourse.pymc.io/t/running-the-test-suite-is-not-available-on-the-pymc-website/9075)

<div class="topic-metadata">

**Author:** [@purna135](https://discourse.pymc.io/u/purna135)\
**Replies:** 1\
**Last updated:** [March 22, 2022, 12:31pm UTC](https://discourse.pymc.io/t/running-the-test-suite-is-not-available-on-the-pymc-website/9075 "2022-03-22T12:31:16Z")

</div>

The CONTRIBUTING.md file, which describes how to run the test suite is not mentioned in the PyMC documentation. Can we include this on the website as well? So far, I’ve been running tests by first creating an environme…

---

## [PyMC documentation](https://discourse.pymc.io/t/pymc-documentation/8969)

<div class="topic-metadata">

**Author:** [@purna135](https://discourse.pymc.io/u/purna135)\
**Replies:** 10\
**Last updated:** [March 22, 2022, 12:20pm UTC](https://discourse.pymc.io/t/pymc-documentation/8969 "2022-03-22T12:20:45Z")

</div>

Hi, I’m working on a documentation issue, which is mentioned in issues #5459. While reading the existing docstring, I encountered some ambiguity, such as: It is sometimes referred to as default 0, and other times as D…

---

## [Data for a Pymc3 example analysis \[Educational Outcomes For Hearing-Impaired Children\]](https://discourse.pymc.io/t/data-for-a-pymc3-example-analysis-educational-outcomes-for-hearing-impaired-children/8682)

<div class="topic-metadata">

**Author:** [@sree\_datta](https://discourse.pymc.io/u/sree_datta)\
**Replies:** 2\
**Last updated:** [February 2, 2022, 12:19am UTC](https://discourse.pymc.io/t/data-for-a-pymc3-example-analysis-educational-outcomes-for-hearing-impaired-children/8682 "2022-02-02T00:19:35Z")

</div>

Hi All I’m testing different regression models (Linear / Logistic / Poisson) with and without hierarchical structure in the data with stable pymc-3.11.2 and experimental \`\`\`PyMC3 v4.0.0b2 (directly from Git Hub). In thi…

---

## [Migration Guide](https://discourse.pymc.io/t/migration-guide/8618)

<div class="topic-metadata">

**Author:** [@almostmeenal](https://discourse.pymc.io/u/almostmeenal)\
**Replies:** 1\
**Last updated:** [January 22, 2022, 8:52am UTC](https://discourse.pymc.io/t/migration-guide/8618 "2022-01-22T08:52:36Z")

</div>

Hello! I’m creating this post to get some opinions on what would be useful things to add in a possible comprehensive migration guide? Please put in your questions about v4 under this thread so we can try our best to answ…

---

## [How to extract the variational posterior expected --matrix-- of regression weights from a categorical model?](https://discourse.pymc.io/t/how-to-extract-the-variational-posterior-expected-matrix-of-regression-weights-from-a-categorical-model/8624)

<div class="topic-metadata">

**Author:** [@ashman](https://discourse.pymc.io/u/ashman)\
**Replies:** 8\
**Last updated:** [January 21, 2022, 8:01am UTC](https://discourse.pymc.io/t/how-to-extract-the-variational-posterior-expected-matrix-of-regression-weights-from-a-categorical-model/8624 "2022-01-21T08:01:11Z")

</div>

Hi, I have a model of type bambi.models.Model with Family name categorical and link name softmax. For this model, learned regression weights can be expressed as a matrix of size MxK, where M is the number of covariat…

---

## [How is the marginalized likelihood computed?](https://discourse.pymc.io/t/how-is-the-marginalized-likelihood-computed/8358)

<div class="topic-metadata">

**Author:** [@janjeg](https://discourse.pymc.io/u/janjeg)\
**Replies:** 4\
**Last updated:** [November 26, 2021, 3:54pm UTC](https://discourse.pymc.io/t/how-is-the-marginalized-likelihood-computed/8358 "2021-11-26T15:54:02Z")

</div>

Computing the marginal likelihood (aka evidence) p(y | \\mathcal{D}) is not straight forward (see https://arxiv.org/pdf/2005.08334.pdf for a review). What is the method used by pymc3? Where could I find a pointer to a p…

---

## [How to visualize and discourse about the Switch Operator after making it a Deterministic variable](https://discourse.pymc.io/t/how-to-visualize-and-discourse-about-the-switch-operator-after-making-it-a-deterministic-variable/8306)

<div class="topic-metadata">

**Author:** [@Philipe\_Riskalla\_Lea](https://discourse.pymc.io/u/Philipe_Riskalla_Lea)\
**Replies:** 0\
**Last updated:** [November 10, 2021, 5:18pm UTC](https://discourse.pymc.io/t/how-to-visualize-and-discourse-about-the-switch-operator-after-making-it-a-deterministic-variable/8306 "2021-11-10T17:18:03Z")

</div>

Dear all, I have been struggling with interpreting the Switch Operator in PYMC. I have a given time-series in which I presume to have 2 Switch points. By taking the Radon example provided in PYMC docs., I have impleme…

---

## [Likelihood Specification and DensityDist](https://discourse.pymc.io/t/likelihood-specification-and-densitydist/8121)

<div class="topic-metadata">

**Author:** [@Juan\_Melo](https://discourse.pymc.io/u/Juan_Melo)\
**Replies:** 3\
**Last updated:** [October 5, 2021, 8:51am UTC](https://discourse.pymc.io/t/likelihood-specification-and-densitydist/8121 "2021-10-05T08:51:09Z")

</div>

Please see screenshot below for question :slight\_smile:

---

## [Building the documentation](https://discourse.pymc.io/t/building-the-documentation/7914)

<div class="topic-metadata">

**Author:** [@stst](https://discourse.pymc.io/u/stst)\
**Replies:** 3\
**Last updated:** [August 23, 2021, 10:36pm UTC](https://discourse.pymc.io/t/building-the-documentation/7914 "2021-08-23T22:36:05Z")

</div>

I am trying to set up a clean environment for contributing to PyMC3 development. In particular, I am trying to build the documentation locally. I followed the instructions in CONTRIBUTING.md and created a dedicated cond…

[Next page](https://discourse.pymc.io/tag/doc/8.md?match_all_tags=true&page=1&tags%5B%5D=doc)