GitLab

* change metropolis kernel for independent metropolis kernel

* fix pyupgrade

* fix float32

* clean code

* add inline comments and update docstring

* add inline comments and update docstring

* Add eight schools pickle test

* Add deterministic test

* adding test for str() explicitly

* Add end of line

* fixes #4112, promote dynamic type to full class

* removing unused import functools
Co-authored-by: Ravin Kumar <ravinsdrive@gmail.com>

* Black formatted 15 files

* Ran pyupgrade on all files

* 1. Fix  AttributeError: 'Rectangle' object has no property 'normed'
2. Upadte using the style guide
3. Other minor changes

* modifications based on updated style file

* use inference data in posterior predictive

* blacken

* 🎨

* 🎨

* 🎨

* Apply pyupgrade

* Add pyupgrade as commit hook

* Manually fix some pyupgrade changes

* adding unit tests for new __str__ functionality

* use get_var_name instead of str to get variable name

* adding semantically meaningful __str__

* correcting import syntax error

* patch type of Deterministic to ensure proper handling of str()

* adding test for tuning.starting.allinmodel

* more precise exception checks in unit test
Co-authored-by: Marco Gorelli <m.e.gorelli@gmail.com>
Co-authored-by: Marco Gorelli <m.e.gorelli@gmail.com>

* Add basic MLDA-MCMC algorithm (proposal and step method)

* Add example scripts for MLDA

* Make coarse_models kwarg into a normal argument

* Fix docstring in MLDA class

* Fix examples code style/comments

* Remove redundant code, improve comments

* Make MLDA do block sampling by default

* Add new MLDA example with FEniCS black box component

* Small change in readme

* Add run instructions in readme

* Change example parameters in sample()

* Minor changes and comments

* Add extra parameters in readme

* Number of chains change

* Make changes to mlda example parameters, go back to compound sampling for mlda by default, edit readme accordingly

* Updated the FEniCS code so it's more efficient

* Add eigenpairs projection and change input parameters

* Edit readme to reflect projection function

* Add compound step support and improve example.py

* Update readme

* Add new tests tests, most of them failing

* Fix test_types bug

* Refactoring of MLDA to allow retaining all methods information

* Add more tests

* Pass more parameters to Metropolis init

* Complete tuning continuation, add basic block/coumpound parameter

* Remove some mlda if statements and simplify other parts

* Change example parameters

* Add and fix tests

* Add some comments and remove redundant code

* Add xfail to test_models_utils test when new pandas version are used

* Add description to test_examples for multilevel normal example

* Remove xfail related to pandas in test_models_utils, remove redundant function from test_step

* Try removing failing test

* Remove redundant code

* Skip some failing tests

* Add sine wave test in test_examples

* Change true parameters index

* Fix index j in coarse models loop to avoid warning

* Remove sine test

* Remove unused library

* Improve docstrings and remove some redundant code/comments

* Revert some pointless changes to tests

* Fix style

* Add notebook example and utility code

* Remove old mlda example and update notebook

* Update notebook again

* Change the citation and add a use example to the MLDA docstring

* Change competence to be incompatible with discrete vars, remove discrete var detection code from MLDA init

* Add young warning and change default subsampling value

* Add more comments, change sys.exit to exception, change tests to reflect that, convert coarse_models to positional argument in MLDA

* Add is_mlda_flag to prevent tuning reset when Metropolis is used as the base sampler of MLDA

* Add more extensive docstrings

* Re-run and re-render notebook after changes

* Add tuning for tune and scaling and refactor some parameter names to be consistent with what they represent

* Regenerate notebook and add .py version of it

* Delete notebook with old name

* Fix pylint errors, move .py example, fix failing test

* Add computer specs to notebook

* Change class checks to using isinstance

* Add more tests for stats, competence, etc and fix bug with tune flag not being overriden in compound sub-methods

* Remove duplicate sample_except()

* Move is_mlda_base checks for reseting inside Metropolis' reset_tuning()

* Add DEMetropolis to notebook

* Add MLDA groundwater flow notebook which uses blocked samplers only

* Add comparison with DEMCMC-Z amd longer runs for convergence in example notebook

* Add separate subsampling rates

* Edit docstring

* Fix handling of one integer for subsampling rate

* Add tests and change subsampling argument name in examples/tests

* Add notebook with extra benchmarks and tuning demo

* Change subsampling rate to rates in notebook examples (including new benchmarking one)

* Do not count stuck proposals from lower chain as accepted

* Convert base_scaling stats to one stat of type object, modify tests for stats and also test for declining acceptance rate

* Fix pm.DensityDist in notebooks/scripts by replacing with pm.Potential

This is done because of the bug described in https://github.com/arviz-devs/arviz/issues/1279. The commit also changes a few parameters in the MLDA .py example to match the ones in the equivalent notebook.

* Move MLDA and RecursiveDAProposal classes to new mlda.py file, add a new MetropolisMLDA class which inherits Metropolis and just alters the reset_tuning function, modify test_step and __init__ files accordingly

* Remove MLDA notebooks and .py example script, remove code that uses fenics and delete reference to example from MLDA class docstring

* Blacken MLDA code and tests, separate MLDA type tests from other methods, fix some stylistic issues

* Add simple linear regression notebook which can serve as MLDA starting point for new users

* Modify some comments in the simple notebook and re-run

* Add typing to mlda.py

* Connect the two separate strings in mlda.py

* Modify simple linear regression notebook: coarse model uses subset of data, more comments, performance comparison with Metropolis

* Add more comments, format using PyMC3 NB style guide (blacken, watermark, arviz style, imports, etc)

* Add simple regression notebook to table of examples

* Add gravity surveying notebook

* Add MLDA line in 3.9.x release notes

* Edit notebook imports to adhere to nbqa-isort rules

* Add gravity notebook to table of contents
Co-authored-by: Mikkel Lykkegaard <mikkelbue@gmail.com>

Fix for issue #4098.
Co-authored-by: Robert P. Goldman <rpgoldman@sift.net>

* 1. Fix: AttributeError: 'Rectangle' object has no property 'normed'
2. Format the notebook according to the style guide

* Use arviz plotting functions

* black format

* Update the link to related notebook

* Added notebook and data for LGCP tutorial

* Replacing nested loop for data preprocessing

* Adjusting priors and clarifying marks model

* Minor additions to text of LGCP tutorial

* Fixing import order

* add pre-commit check to CI, check notebook imports are sorted

* update to v2

* Reorder import statements according to pep8

* Blackified continuous.py file

* Set Black vertical limit to 100

* Added reformatting with Junpeng's comments

* Reinstated outer tt.switch in logcdf of Flat distribution

* Deleted import of get_variable_name

* fix gp-maunaloa until rugby analytics

* move %env after imports

* nbqa isort

* put plt.style.use after imports

* another 10 notebooks

* 10th notebook

* put magic at bottom of cell

* separate first-party imports

* use np.where for clarity

* apply black_nbconvert to patch

* treat array of shape (1,) as scalar

* adding generic machinery for generating string representations

* double quotes for strings

* Update pymc3/distributions/distribution.py
Co-authored-by: Thomas Wiecki <thomas.wiecki@gmail.com>

* restoring return None behavior of TransformedDistribution::_repr_latex_

* extra . for import

* renaming _distr_parameters() to _distr_parameters_for_repr() to avoid confusion

* replacing old _repr_latex_ functionality with new one

* adding new repr functionality to Deterministic

* replacing old with new str repr  functionality in  PyMC3Variable

* ensure that TransformedDistribution does not mess up its str repr

* new str repr functionality in Model

* don't touch __str__ for now

* fixing _repr_latex_ for Simulator
Co-authored-by: Thomas Wiecki <thomas.wiecki@gmail.com>

* fixed error message and lightly updated

* updated according to pymc3 notebook standards

* placed arviz calls in model context

* grabbed InferenceData object for arviz plotting

* Fixed typos and reran first models in Mauna Loa 2

* Fixed typos and reran whole Mauna Loa NB

* Blackified Mauna Loa NB

* Ran last super long model

* Finished updating Mauna Loa 2 NB

* Blackified Mauna Loa 2 NB

* Cosmetic fixes to getting started notebook.

There were some problems with the version on the PyMC3 docs site.
Fixed some warnings.  Tidied up some markup (some of which didn't seem to process properly on gh pages), and added a note explaining about pm.Deterministic

* Improve date plot.

Very ugly way to keep xticklabels from crashing into each other. Not sure if this is the right thing, or if ArviZ should be fixed to automatically format date-times better.

* Add example of pm.Deterministic

Thanks to @AlexAndorra.

* 1) Fixed: FutureWarnings
2) Updated the notebook to follow the consistent style
3) Use arviz functions directly for plotting on inference data

Fromat the notebook in Black-format

Minor formatting

minor change to execute last cell

Minor text changes.

Renaming file

update the filename in the doc: PyMC3_tips_and_heuristic.ipynb to conditional-autoregressive-model.ipynb

Minos change to remove .ipynb from the name

Move conditional-autoregressive-mode.ipynb from tutorial "How-To" to examples "Gaussian Processes"

* Move the data to csv file (scotland_lips_cancer.csv) instead being hard-coded in conditional-autoregressive-model.ipynb

* Read data from csv file instead of the hardcoded version in notebook.