mmcdermott · mmcdermott · Jun 13, 2024 · Jun 13, 2024 · Jun 13, 2024 · Jun 13, 2024
diff --git a/.gitignore b/.gitignore
@@ -158,3 +158,5 @@ cython_debug/
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
+
+docs/source/generated
diff --git a/README.md b/README.md
@@ -46,15 +46,15 @@ This repository consists of two key pieces:
    what is more advanced is the efficient construction, storage, and loading of tabular features for the
    candidate AutoML models, enabling a far more extensive search over different featurization strategies.
 
-### Scripts and Examples
+## Scripts and Examples
 
 See `tests/test_integration.py` for an example of the end-to-end pipeline being run on synthetic data. This
 script is a functional test that is also run with `pytest` to verify the correctness of the algorithm.
 
 For an end to end example over MIMIC-IV, see the [companion repository](https://github.com/mmcdermott/MEDS_TAB_MIMIC_IV)
 For an end to end example over Philips eICU, see the [eICU companion repository](https://github.com/mmcdermott/MEDS_TAB_EICU).
 
-### Core CLI Scripts Overview
+## Core CLI Scripts Overview
 
 1. **`meds-tab-describe`**: This command processes MEDS data shards to compute the frequencies of different code-types
 
@@ -124,7 +124,7 @@ For an end to end example over Philips eICU, see the [eICU companion repository]
 
 6. **`meds-tab-xgboost-sweep`**: Conducts an Optuna hyperparameter sweep to optimize over `window_sizes`, `aggregations`, and `min_code_inclusion_frequency`, aiming to enhance model performance and adaptability.
 
-### Additional CLI Scripts
+## Additional CLI Scripts
 
 1. **`generate-permutations`**: Generates and prints a sorted list of all permutations from a comma separated input. This is provided for the convenience of sweeping over all possible combinations of window sizes and aggregations.
 
@@ -149,7 +149,7 @@ For an end to end example over Philips eICU, see the [eICU companion repository]
 
 # How does MEDS-Tab Work?
 
-#### What do you mean "tabular pipelines"? Isn't _all_ structured EHR data already tabular?
+## What do you mean "tabular pipelines"? Isn't _all_ structured EHR data already tabular?
 
 This is a common misconception. _Tabular_ data refers to data that can be organized in a consistent, logical
 set of rows/columns such that the entirety of a "sample" or "instance" for modeling or analysis is contained

diff --git a/docs/source/conf.py b/docs/source/conf.py
@@ -1,4 +1,5 @@
 import os
+import shutil
 import sys
 
 # Configuration file for the Sphinx documentation builder.
@@ -10,15 +11,24 @@
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
 
 project = "MEDS-Tab"
-copyright = "2024, Matthew McDermott, Nassim Oufattole, Teya Bergamaschi"
-author = "Matthew McDermott, Nassim Oufattole, Teya Bergamaschi"
-release = "0.0.1"
-version = "0.0.1"
+copyright = "2024, Nassim Oufattole, Matthew McDermott, Teya Bergamaschi, Aleksia Kolo, Hyewon Jeong"
+author = "Nassim Oufattole, Matthew McDermott, Teya Bergamaschi, Aleksia Kolo, Hyewon Jeong"
+release = "0.0.2"
+version = "0.0.2"
 
 # -- General configuration ---------------------------------------------------
 # https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
 
-sys.path.insert(0, os.path.abspath("../.."))
+# -- Path setup
+from pathlib import Path
+
+__location__ = Path(os.path.dirname(__file__))
+__src__ = __location__ / "../.."
+
+# If extensions (or modules to document with autodoc) are in another directory,
+# add these directories to sys.path here. If the directory is relative to the
+# documentation root, use os.path.abspath to make it absolute, like shown here.
+sys.path.insert(0, str(__src__))
 
 extensions = [
     "sphinx.ext.duration",
@@ -38,6 +48,24 @@
     ".md": "markdown",
 }
 
+# -- Run sphinx-apidoc
+# This ensures we don't need to run apidoc manually.
+
+# TODO: use https://github.com/sphinx-extensions2/sphinx-autodoc2
+
+from sphinx.ext import apidoc
+
+output_dir = __location__ / "generated"
+module_dir = __src__ / "src/MEDS_tabular_automl"
+if output_dir.is_dir():
+    shutil.rmtree(output_dir)
+
+try:
+    cmd_line = f"--implicit-namespaces -e -f -o {output_dir} {module_dir}"
+    apidoc.main(cmd_line.split(" "))
+except Exception as e:  # pylint: disable=broad-except
+    print(f"Running `sphinx-apidoc {cmd_line}` failed!\n{e}")
-try:
-    cmd_line = f"--implicit-namespaces -e -f -o {output_dir} {module_dir}"
-    apidoc.main(cmd_line.split(" "))
-except Exception as e:  # pylint: disable=broad-except
-    print(f"Running `sphinx-apidoc {cmd_line}` failed!\n{e}")
+try:
+    cmd_line = f"--implicit-namespaces -e -f -o {output_dir} {module_dir}"
+    apidoc.main(cmd_line.split(" "))
+except (IOError, OSError) as e:
+    print(f"Running `sphinx-apidoc {cmd_line}` failed!\n{e}")
-try:
-    cmd_line = f"--implicit-namespaces -e -f -o {output_dir} {module_dir}"
-    apidoc.main(cmd_line.split(" "))
-except Exception as e:  # pylint: disable=broad-except
-    print(f"Running `sphinx-apidoc {cmd_line}` failed!\n{e}")
+try:
+    cmd_line = f"--implicit-namespaces -e -f -o {output_dir} {module_dir}"
+    apidoc.main(cmd_line.split(" "))
+except (IOError, OSError) as e:
+    print(f"Running `sphinx-apidoc {cmd_line}` failed!\n{e}")
+
 intersphinx_mapping = {
     "python": ("https://docs.python.org/3/", None),
     "sphinx": ("https://www.sphinx-doc.org/en/master/", None),

diff --git a/docs/source/generated/src.MEDS_tabular_automl.configs.rst b/docs/source/generated/src.MEDS_tabular_automl.configs.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.configs.tabularization.rst b/docs/source/generated/src.MEDS_tabular_automl.configs.tabularization.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.describe_codes.rst b/docs/source/generated/src.MEDS_tabular_automl.describe_codes.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.file_name.rst b/docs/source/generated/src.MEDS_tabular_automl.file_name.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.generate_static_features.rst b/docs/source/generated/src.MEDS_tabular_automl.generate_static_features.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.generate_summarized_reps.rst b/docs/source/generated/src.MEDS_tabular_automl.generate_summarized_reps.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.generate_ts_features.rst b/docs/source/generated/src.MEDS_tabular_automl.generate_ts_features.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.mapper.rst b/docs/source/generated/src.MEDS_tabular_automl.mapper.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.rst b/docs/source/generated/src.MEDS_tabular_automl.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.scripts.cache_task.rst b/docs/source/generated/src.MEDS_tabular_automl.scripts.cache_task.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.scripts.describe_codes.rst b/docs/source/generated/src.MEDS_tabular_automl.scripts.describe_codes.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.scripts.launch_xgboost.rst b/docs/source/generated/src.MEDS_tabular_automl.scripts.launch_xgboost.rst
diff --git a/docs/source/generated/src.MEDS_tabular_automl.scripts.rst b/docs/source/generated/src.MEDS_tabular_automl.scripts.rst