Merge pull request #370 from elfi-dev/dev

Release v.0.8.0
elfi-dev · Mar 29, 2021 · e735abb · e735abb
2 parents 5ce82ed + 147206c
commit e735abb
Show file tree

Hide file tree

Showing 42 changed files with 6,007 additions and 1,556 deletions.
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
@@ -9,10 +9,11 @@ Please provide a short summary here
 
 If your contribution adds, removes or somehow changes the functional behavior of the package, please check that
 
-- [ ] You have included or updated all the relevant documentation
-- [ ] The proposed changes pass all unit tests (check step 6 of CONTRIBUTING.rst for details)
+- [ ] You have included or updated all the relevant documentation 
 - [ ] You have added appropriate unit tests to ensure the new features behave as expected
 
+and the proposed changes pass all unit tests (check step 6 of CONTRIBUTING.rst for details)
+
 #### Copyright and Licensing
 
 Please list the copyright holder for the work you are submitting (this will be you or your assignee, such as a university or company):

diff --git a/.travis.yml b/.travis.yml
@@ -23,6 +23,7 @@ install:
   - pip install numpy
   - pip install -r requirements-dev.txt
   - pip install -e .
+  - pip install "dask[distributed]" --upgrade
 
 script:
   - if [[ "$TRAVIS_OS_NAME" == "linux" ]]; then ipcluster start -n 2 --daemonize ; fi

diff --git a/CHANGELOG.rst b/CHANGELOG.rst
@@ -1,6 +1,20 @@
 Changelog
 =========
 
+0.8.0 (2021-03-29)
+------------------
+- Merge adaptive distance ABC-SMC and ABC-SMC functionalities
+- Split `DensityRatioEstimation` from utils.py into separate file
+- Refactor parameter_inferency.py into methodtype-wise individual files  
+- Rename `elfi.methods.mcmc.gelman_rubin` as `elfi.methods.mcmc.gelman_rubin_statistic`
+- Refactor `class ModelPrior` from `methods.utils` to `model.extensions`.
+- Add adaptive threshold selection method for ABC-SMC
+- Modify ProgressBar-functionality
+- Add constrains to ExpIntVar-acquisition so that no queries will be outside prior support
+- Add ABC-SMC with adaptive distance
+- Add Robust optimisation Monte Carlo method
+- Fix small issues in ABC-SMC which did not work in 1-dimensional problems or with output names
+- Update README.md
 
 0.7.7 (2020-10-12)
 ------------------

diff --git a/Makefile b/Makefile
@@ -72,23 +72,29 @@ docs: ## generate Sphinx HTML documentation, including API docs
 	$(MAKE) -C docs html
 	# $(BROWSER) docs/_build/html/index.html
 
-CONTENT_URL := http://research.cs.aalto.fi/pml/software/elfi/docs/0.6.2/
+CONTENT_URL := https://raw.githubusercontent.com/elfi-dev/notebooks/dev/figures/
 
 notebook-docs: ## Conver notebooks to rst docs. Assumes you have them in `notebooks` directory.
 	jupyter nbconvert --to rst ../notebooks/quickstart.ipynb --output-dir docs
 	sed -i '' 's|\(quickstart_files/quickstart.*\.\)|'${CONTENT_URL}'\1|g' docs/quickstart.rst
 
 	jupyter nbconvert --to rst ../notebooks/tutorial.ipynb --output-dir docs/usage
-	sed -i '' 's|\(tutorial_files/tutorial.*\.\)|'${CONTENT_URL}usage/'\1|g' docs/usage/tutorial.rst
+	sed -i '' 's|\(tutorial_files/tutorial.*\.\)|'${CONTENT_URL}'\1|g' docs/usage/tutorial.rst
+
+	jupyter nbconvert --to rst ../notebooks/adaptive_distance.ipynb --output-dir docs/usage
+	sed -i '' 's|\(adaptive_distance_files/adaptive_distance.*\.\)|'${CONTENT_URL}'\1|g' docs/usage/adaptive_distance.rst	
+
+	jupyter nbconvert --to rst ../notebooks/adaptive_threshold_selection.ipynb --output-dir docs/usage
+	sed -i '' 's|\(adaptive_threshold_selection_files/adaptive_threshold_selection.*\.\)|'${CONTENT_URL}'\1|g' docs/usage/adaptive_threshold_selection.rst		
 
 	jupyter nbconvert --to rst ../notebooks/BOLFI.ipynb --output-dir docs/usage
-	sed -i '' 's|\(BOLFI_files/BOLFI.*\.\)|'${CONTENT_URL}usage/'\1|g' docs/usage/BOLFI.rst
+	sed -i '' 's|\(BOLFI_files/BOLFI.*\.\)|'${CONTENT_URL}'\1|g' docs/usage/BOLFI.rst
 
 	jupyter nbconvert --to rst ../notebooks/parallelization.ipynb --output-dir docs/usage
-	sed -i '' 's|\(parallelization_files/parallelization.*\.\)|'${CONTENT_URL}usage/'\1|g' docs/usage/parallelization.rst
+	sed -i '' 's|\(parallelization_files/parallelization.*\.\)|'${CONTENT_URL}'\1|g' docs/usage/parallelization.rst
 
 	jupyter nbconvert --to rst ../notebooks/non_python_operations.ipynb --output-dir docs/usage --output=external
-	sed -i '' 's|\(external_files/external.*\.\)|'${CONTENT_URL}usage/'\1|g' docs/usage/external.rst
+	sed -i '' 's|\(external_files/external.*\.\)|'${CONTENT_URL}'\1|g' docs/usage/external.rst
 
 # release: clean ## package and upload a release
 # 	python setup.py sdist upload

diff --git a/README.md b/README.md
@@ -1,6 +1,4 @@
-**Version 0.7.7 released!** See the [CHANGELOG](CHANGELOG.rst) and [notebooks](https://github.com/elfi-dev/notebooks).
-
-**NOTE:** For the time being NetworkX 2 is incompatible with ELFI.
+**Version 0.8.0 released!** See the [CHANGELOG](CHANGELOG.rst) and [notebooks](https://github.com/elfi-dev/notebooks).
 
 ELFI - Engine for Likelihood-Free Inference
 ===========================================
@@ -22,7 +20,10 @@ inference out of the box.
 Currently implemented LFI methods:
 - ABC Rejection sampler
 - Sequential Monte Carlo ABC sampler
+- SMC-ABC sampler with [adaptive threshold selection](https://projecteuclid.org/journals/bayesian-analysis/advance-publication/Adaptive-Approximate-Bayesian-Computation-Tolerance-Selection/10.1214/20-BA1211.full)
+- SMC-ABC sampler with [adaptive distance](https://projecteuclid.org/euclid.ba/1460641065)
 - [Bayesian Optimization for Likelihood-Free Inference (BOLFI)](http://jmlr.csail.mit.edu/papers/v17/15-017.html)
+- [Robust Optimisation Monte Carlo](https://arxiv.org/abs/1904.00670)
 
 Other notable included algorithms and methods:
 - Bayesian Optimization
@@ -37,8 +38,8 @@ asked from elfi-support.at.hiit.fi, but the
 is preferable.
 
 
-Installation
-------------
+Installation with pip
+---------------------
 
 ELFI requires Python 3.6 or greater. You can install ELFI by typing in your terminal:
 
@@ -53,6 +54,27 @@ pip3 install elfi
 Note that in some environments you may need to first install `numpy` with
 `pip install numpy`. This is due to our dependency to `GPy` that uses `numpy` in its installation.
 
+Installation from conda-forge
+-----------------------------
+
+Installing `elfi` from the `conda-forge` channel can be achieved by adding `conda-forge` to your channels with:
+
+```
+conda config --add channels conda-forge
+```
+
+Once the `conda-forge` channel has been enabled, `elfi` can be installed with:
+
+```
+conda install elfi
+```
+
+It is possible to list all of the versions of `elfi` available on your platform with:
+
+```
+conda search elfi --channel conda-forge
+```
+
 ### Optional dependencies
 
 - `graphviz` for drawing graphical models (needs [Graphviz](http://www.graphviz.org)), highly recommended
@@ -100,7 +122,7 @@ Resolving these may sometimes go wrong:
 - If you receive an error about `yaml.load`, install `pyyaml`.
 - On OS X with Anaconda virtual environment say `conda install python.app` and then use
 `pythonw` instead of `python`.
-- Note that ELFI requires Python 3.5 or greater so try `pip3 install elfi`.
+- Note that ELFI requires Python 3.6 or greater so try `pip3 install elfi`.
 - Make sure your Python installation meets the versions listed in `requirements.txt`.
 
 

diff --git a/docs/api.rst b/docs/api.rst
@@ -27,6 +27,7 @@ Below is the API for creating generative models.
    elfi.Summary
    elfi.Discrepancy
    elfi.Distance
+   elfi.AdaptiveDistance
 
 **Other**
 
@@ -48,8 +49,11 @@ Below is a list of inference methods included in ELFI.
 .. autosummary::
    elfi.Rejection
    elfi.SMC
+   elfi.AdaptiveDistanceSMC
+   elfi.AdaptiveThresholdSMC
    elfi.BayesianOptimization
    elfi.BOLFI
+   elfi.ROMC
 
 
 **Result objects**
@@ -165,6 +169,10 @@ Modelling API classes
    :members:
    :inherited-members:
 
+.. autoclass:: elfi.AdaptiveDistance
+   :members:
+   :inherited-members:
+
 
 **Other**
 
@@ -194,6 +202,14 @@ Inference API classes
    :members:
    :inherited-members:
 
+.. autoclass:: elfi.AdaptiveDistanceSMC
+   :members:
+   :inherited-members:
+
+.. autoclass:: elfi.AdaptiveThresholdSMC
+   :members:
+   :inherited-members:
+
 .. autoclass:: elfi.BayesianOptimization
    :members:
    :inherited-members:
@@ -202,6 +218,10 @@ Inference API classes
    :members:
    :inherited-members:
 
+.. autoclass:: elfi.ROMC
+   :members:
+   :inherited-members:
+
 
 **Result objects**
 
@@ -223,6 +243,9 @@ Inference API classes
    :members:
    :inherited-members:
 
+.. autoclass:: RomcSample
+   :members:
+   :inherited-members:
 
 **Post-processing**
 

diff --git a/docs/conf.py b/docs/conf.py
@@ -32,7 +32,8 @@ def __getattr__(cls, name):
         'distributed', 'distributed.client', 'graphviz', 'matplotlib', 'sobol_seq', 'GPy',
         'dask.delayed', 'scipy.linalg', 'scipy.optimize', 'scipy.stats', 'scipy.spatial',
         'scipy.sparse', 'scipy.special', 'matplotlib.pyplot', 'numpy.random', 'networkx',
-        'ipyparallel', 'numpy.lib', 'numpy.lib.format', 'sklearn.linear_model'
+        'ipyparallel', 'numpy.lib', 'numpy.lib.format', 'sklearn.linear_model',
+        'sklearn.pipeline', 'sklearn.preprocessing'
     ]
     sys.modules.update((mod_name, Mock()) for mod_name in MOCK_MODULES)
 

diff --git a/docs/index.rst b/docs/index.rst
@@ -23,9 +23,15 @@ Currently implemented LFI methods:
 
 - ABC rejection sampler
 - Sequential Monte Carlo ABC sampler
+- ABC-SMC sampler with `adaptive distance`_
+- ABC-SMC sampler with `adaptive threshold selection`_
 - Bayesian Optimization for Likelihood-Free Inference (BOLFI_) framework
+- Robust Optimization Monte Carlo (ROMC_) framework
 
+.. _adaptive distance: https://projecteuclid.org/euclid.ba/1460641065
+.. _adaptive threshold selection: https://projecteuclid.org/journals/bayesian-analysis/advance-publication/Adaptive-Approximate-Bayesian-Computation-Tolerance-Selection/10.1214/20-BA1211.full
 .. _BOLFI: http://jmlr.org/papers/v17/15-017.html
+.. _ROMC:  http://proceedings.mlr.press/v108/ikonomov20a.html
 
 ELFI also has the following non LFI methods:
 
@@ -52,6 +58,8 @@ Additionally, ELFI integrates tools for visualization, model comparison, diagnos
     :caption: Usage
 
     usage/tutorial
+    usage/adaptive_distance
+    usage/adaptive_threshold_selection
     usage/parallelization
     usage/BOLFI
     usage/external

diff --git a/docs/quickstart.rst b/docs/quickstart.rst
@@ -96,7 +96,7 @@ visualize the model:
 
 
 
-.. image:: http://research.cs.aalto.fi/pml/software/elfi/docs/0.6.2/quickstart_files/quickstart_11_0.svg
+.. image:: https://raw.githubusercontent.com/elfi-dev/notebooks/dev/figures/quickstart_files/quickstart_11_0.svg
 
 
 
@@ -134,5 +134,5 @@ Let’s plot also the marginal distributions for the parameters:
 
 
 
-.. image:: http://research.cs.aalto.fi/pml/software/elfi/docs/0.6.2/quickstart_files/quickstart_16_0.png
+.. image:: https://raw.githubusercontent.com/elfi-dev/notebooks/dev/figures/quickstart_files/quickstart_16_0.png
 
diff --git a/docs/usage/BOLFI.rst b/docs/usage/BOLFI.rst
@@ -51,7 +51,7 @@ the basic tutorial, and load it from ready-made examples:
 
 
 
-.. image:: http://research.cs.aalto.fi/pml/software/elfi/docs/0.6.2/usage/BOLFI_files/BOLFI_5_0.svg
+.. image:: https://raw.githubusercontent.com/elfi-dev/notebooks/dev/figures/BOLFI_files/BOLFI_5_0.svg
 
 
 
@@ -166,7 +166,7 @@ investigated further:
 
 
 
-.. image:: http://research.cs.aalto.fi/pml/software/elfi/docs/0.6.2/usage/BOLFI_files/BOLFI_15_1.png
+.. image:: https://raw.githubusercontent.com/elfi-dev/notebooks/dev/figures/BOLFI_files/BOLFI_15_1.png
 
 
 It may be useful to see the acquired parameter values and the resulting
@@ -178,7 +178,7 @@ discrepancies:
 
 
 
-.. image:: http://research.cs.aalto.fi/pml/software/elfi/docs/0.6.2/usage/BOLFI_files/BOLFI_17_0.png
+.. image:: https://raw.githubusercontent.com/elfi-dev/notebooks/dev/figures/BOLFI_files/BOLFI_17_0.png
 
 
 There could be an unnecessarily high number of points at parameter
@@ -212,7 +212,7 @@ triangle):
 
 
 
-.. image:: http://research.cs.aalto.fi/pml/software/elfi/docs/0.6.2/usage/BOLFI_files/BOLFI_23_0.png
+.. image:: https://raw.githubusercontent.com/elfi-dev/notebooks/dev/figures/BOLFI_files/BOLFI_23_0.png
 
 
 Sampling
@@ -300,7 +300,7 @@ convenience methods:
 
 
 
-.. image:: http://research.cs.aalto.fi/pml/software/elfi/docs/0.6.2/usage/BOLFI_files/BOLFI_29_0.png
+.. image:: https://raw.githubusercontent.com/elfi-dev/notebooks/dev/figures/BOLFI_files/BOLFI_29_0.png
 
 
 The black vertical lines indicate the end of warmup, which by default is
@@ -312,5 +312,5 @@ half of the number of iterations.
 
 
 
-.. image:: http://research.cs.aalto.fi/pml/software/elfi/docs/0.6.2/usage/BOLFI_files/BOLFI_31_0.png
+.. image:: https://raw.githubusercontent.com/elfi-dev/notebooks/dev/figures/BOLFI_files/BOLFI_31_0.png