Updated to "Move log transform to causica" (#99)

* Updated to "Move log transform to causica"

* Fix the usage of tempfile in test_generate_data

Replace mktemp with mkstemp

* Update the version of the release

Author: meyerscetbon

.devcontainer/devcontainer.json

@@ -25,32 +25,37 @@
 	"customizations": {
 		"vscode": {
 			"settings": {
+				// General
+				"editor.rulers": [120],
+				"terminal.integrated.profiles.linux": {
+					"zsh": {"path": "/usr/bin/zsh"}
+				},
+				"terminal.integrated.defaultProfile.linux": "zsh",
+
+				// Python
+				"[python]": {
+					"editor.defaultFormatter": "ms-python.black-formatter"
+				},
 				"python.defaultInterpreterPath": "/usr/bin/python",
-				"python.formatting.black": true,
-				"python.linting.pylint": true,
 				"python.testing.pytestEnabled": true,
 				"python.testing.pytestArgs": [
 					"--continue-on-collection-errors",
 					"test"
 				],
 				"python.testing.unittestEnabled": false,
-				"vim.textwidth": 120,
-				"editor.rulers": [
-					120
-				],
-				"terminal.integrated.profiles.linux": {
-					"zsh": {
-						"path": "/usr/bin/zsh"
-					}
-				},
-				"terminal.integrated.defaultProfile.linux": "zsh"
+
+				// Extensions
+				"isort.args": ["--resolve-all-configs"],
+				"black-formatter.args": ["--config=./pyproject.toml"],
+				"vim.textwidth": 120
 			},
 			"extensions": [
 				"bungcip.better-toml",
 				"github.copilot",
 				"github.copilot-chat",
 				"github.copilot-labs",
 				"ms-azuretools.vscode-docker",
+				"ms-python.black-formatter",
 				"ms-python.isort",
 				"ms-python.pylint",
 				"ms-python.python",

.github/workflows/ci-build.yml

@@ -32,7 +32,7 @@ jobs:
     - name: Install dependencies
       run: |
         poetry env use 3.10
-        poetry install
+        poetry install --extras seaborn
       if: steps.cache.outputs.cache-hit != 'true'
 
     - name: Verify pre-commit checks

.gitignore

@@ -1,34 +1,4 @@
-/runs/
-/runs_opt/
-/data/*
-**/mlruns/
-/.vscode
-*.code-workspace
-__pycache__/
-/api/data
-/api/models
-/saved_models/
-/tests/regression_tests/data/
-/plots/
-/evaluation_pipeline/local_logs/*
-/experiements/GNN
-/experiments/data
-!/experiments/data/*ipynb
-research_experiments/NRI/data/*.npy
-research_experiments/NRI/logs/
-research_experiments/visl/
-research_experiments/set_transformer/set_transformer_paper/data/
-research_experiments/set_transformer/set_transformer_paper/results/
-research_experiments/e2e_causal_inference/data_generation/data
-research_experiments/e2e_causal_inference/config_files
-.tmp/
-git_info.txt
-run*kwargs*.json
-*.ipynb_checkpoints
-icml/
-outputs/
-research_experiments/context_bayes/plots
-
-# Workaround for git to keep empty data/ directory around 
-!/data/.keep
-research_experiments/**/*.ipynb
+/runs/
+__pycache__/
+.ipynb_checkpoints/
+docs/build/

.pre-commit-config.yaml

@@ -11,7 +11,7 @@ repos:
   hooks:
   - id: isort
     name: isort
-    entry: poetry run isort
+    entry: poetry run isort --resolve-all-configs
     language: system
     types: [python]
 - repo: local

Dockerfile

@@ -22,7 +22,7 @@ ENV POETRY_CACHE_DIR="/root/.cache/pypoetry" \
     POETRY_NO_INTERACTION=1 \
     POETRY_VIRTUALENVS_CREATE=false \
     POETRY_VIRTUALENVS_IN_PROJECT=false \
-    POETRY_VERSION=1.6.1
+    POETRY_VERSION=1.7.1
 ENV PATH="$PATH:$POETRY_HOME/bin"
 RUN curl -sSL https://install.python-poetry.org | python3 -
 

README.md

@@ -62,6 +62,16 @@ The Spline model uses a flexible spline flow that is learnt from the data. This
 
 To use DECI to learn the functional relationships, remove the variational distribution terms from the loss and replace the sample with the known graph.
 
+**Example using the CLI**
+
+An example of how to run a training job with the noise distribution specified in the config `src/causica/config/lightning/default_gaussian.yaml` and the data configuration specified in `src/causica/config/lightning/default_data.yaml`:
+
+```
+python -m causica.lightning.main \
+    --config src/causica/config/lightning/default_gaussian.yaml --data src/causica/config/lightning/default_data.yaml
+```
+
+
 ## Further extensions
 
 For now, we have removed Rhino and DDECI from the codebase but they will be added back. You can still access the previously released versions [here](https://github.com/microsoft/causica/releases/tag/v0.0.0).

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = src
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/README.md

@@ -0,0 +1,19 @@
+# Documentation
+
+This documentation relies on `sphinx` and `autoapi` to generate the documentation from the source code.
+
+It can be built using the following command:
+
+```console
+make html
+```
+
+This generates the documentation in the `build/html` directory.
+
+# Helpful Resources
+- https://docs.readthedocs.io/en/stable/guides/jupyter.html
+- https://coderefinery.github.io/documentation/gh_workflow/
+- https://www.sphinx-doc.org/en/master/tutorial/deploying.html#publishing-sources
+- https://coderefinery.github.io/documentation/sphinx/
+- https://github.com/brechtm/rinohtype/blob/master/.github/workflows/tests.yml (for examples of a versioned documentation)
+- https://stackoverflow.com/questions/72089650/how-to-host-multiple-version-of-a-sphinx-based-documentation-on-github

docs/src/conf.py

@@ -0,0 +1,115 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+import importlib.metadata as importlib_metadata
+import time
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+distribution = importlib_metadata.distribution("causica")
+
+project = distribution.metadata["Name"]
+author = distribution.metadata["Author"] or "Microsoft Research - Causica"
+copyright = f"{time.strftime('%Y')}, {author} and contributors"  # pylint: disable=redefined-builtin
+
+# The version info for the project you"re documenting, acts as replacement for
+# |version| and |release|, also used in various other places throughout the
+# built documents.
+#
+# The short X.Y version.
+version = distribution.version
+# The full version, including alpha/beta/rc tags.
+release = version
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+# this helped:
+# https://stackoverflow.com/questions/2701998/automatically-document-all-modules-recursively-with-sphinx-autodoc
+extensions = [
+    "sphinx.ext.autodoc",
+    "sphinx.ext.coverage",
+    "sphinx.ext.githubpages",
+    "sphinx.ext.mathjax",
+    "sphinx.ext.napoleon",
+    "sphinx.ext.viewcode",
+    "autoapi.extension",
+    "myst_parser",
+    "numpydoc",
+    "sphinx_immaterial",
+]
+
+templates_path = ["templates"]
+exclude_patterns = ["Thumbs.db", ".DS_Store"]
+autoapi_dirs = ["../../src/causica/"]
+autoapi_template_dir = "templates/autoapi"
+
+# Napoleon settings
+napoleon_google_docstring = True
+napoleon_numpy_docstring = True
+napoleon_include_init_with_doc = True
+napoleon_include_private_with_doc = True
+napoleon_include_special_with_doc = True
+napoleon_use_admonition_for_examples = False
+napoleon_use_admonition_for_notes = False
+napoleon_use_admonition_for_references = False
+napoleon_use_ivar = False
+napoleon_use_param = True
+napoleon_use_rtype = True
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = "sphinx"
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+# The theme to use for HTML and HTML Help pages.  See the documentation for
+# a list of builtin themes.
+html_theme = "sphinx_immaterial"
+html_static_path = ["static"]
+
+# Theme options are theme-specific and customize the look and feel of a theme
+# further.  For a list of options available for each theme, see the
+# documentation.
+html_theme_options = {
+    "features": [
+        "navigation.sections",
+        "navigation.instant",
+        "navigation.path",
+        "navigation.prune",
+    ],
+    "globaltoc_collapse": False,
+    "repo_url": "https://github.com/microsoft/causica",
+    "repo_name": "causica",
+    "edit_uri": "edit/master/doc",
+    "palette": [
+        {
+            "media": "(prefers-color-scheme: light)",
+            "scheme": "default",
+            "primary": "red",
+            "accent": "light-blue",
+            "toggle": {
+                "icon": "material/lightbulb-outline",
+                "name": "Switch to dark mode",
+            },
+        },
+        {
+            "media": "(prefers-color-scheme: dark)",
+            "scheme": "slate",
+            "primary": "red",
+            "accent": "orange",
+            "toggle": {
+                "icon": "material/lightbulb",
+                "name": "Switch to light mode",
+            },
+        },
+    ],
+    "toc_title_is_page_title": True,
+    "version_dropdown": True,
+    "version_json": "../im_versions.json",
+}
+
+# The master toctree document.
+master_doc = "index"

docs/src/index.md

@@ -0,0 +1,18 @@
+# Causica Documentation
+
+```{eval-rst} 
+.. toctree::
+   :hidden:
+
+    Home <self>
+
+
+```
+
+```{eval-rst}
+.. toctree::
+   :hidden:
+   :maxdepth: 2
+```
+
+This is the documentation for Causica, a Python package for causal discovery and inference.