Merge pull request #42 from VIDA-NYU/docs

README.md

@@ -1,5 +1,9 @@
 [![PyPI version](https://badge.fury.io/py/bdi-kit.svg)](https://pypi.org/project/bdi-kit)
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Documentation Status](https://readthedocs.org/projects/bdi-kit/badge/?version=latest)](https://bdi-kit.readthedocs.io/en/latest/?badge=latest)
+[![Tests](https://github.com/VIDA-NYU/bdi-kit/actions/workflows/build.yml/badge.svg)](https://github.com/VIDA-NYU/bdi-kit/actions/workflows/build.yml)
+[![Lint](https://github.com/VIDA-NYU/bdi-kit/actions/workflows/lint.yml/badge.svg)](https://github.com/VIDA-NYU/bdi-kit/actions/workflows/lint.yml)
+
 
 # bdi-kit 
 This project aims to assist users in performing data integration on biomedical data. It provides tools to streamline the process of integrating disparate biomedical datasets.
@@ -21,7 +25,7 @@ pip install git+https://github.com/VIDA-NYU/bdi-kit@devel
 
 
 ## Documentation
-See our examples [here](https://github.com/VIDA-NYU/bdi-kit/tree/devel/examples).
+Documentation is available [here](https://bdi-kit.readthedocs.io/).
 
 ## Contributing
 We format code using the [black](https://black.readthedocs.io/en/stable/) code formatter.

bdikit/api.py

@@ -20,6 +20,9 @@ class APIManager:
     def __init__(
         self,
     ):
+        """
+        Create/instantiate an APIManager object.
+        """
         # TODO: move into database object (in data_ingestion folder)
         self.dataset = None
         # TODO: move into database object (in data_ingestion folder)
@@ -32,25 +35,45 @@ def __init__(
         self.value_mappings = None  # TODO move this to a property in value_manager
 
     def load_global_table(self, global_table_path=None):
+        """
+        Load a global/target table.
+
+        :param global_table_path: Path to the CSV dataset.
+        """
         if global_table_path is None:
             self.global_table = load_dataframe(GDC_DATA_PATH)
         else:
             self.global_table = load_dataframe(global_table_path)
         return self.global_table
 
     def load_dataset(self, dataset_path):
+        """
+        Load the dataset.
+
+        :param dataset_path: Path to the CSV dataset.
+        """
         if self.global_table is None:
             self.load_global_table()
         self.dataset = load_dataframe(dataset_path)
 
         return self.dataset
 
     def reduce_scope(self):
+        """
+        Reduce the scope of the target domain. Supports only GDC format.
+        """
         self.scope_manager = ScopeReducingManager(self.dataset, self.global_table)
         self.reduced_scope = self.scope_manager.reduce()
         plot_reduce_scope(self.reduced_scope, self.dataset)
 
     def map_columns(self, algorithm="SimFloodAlgorithm"):
+        """
+        Map columns.
+
+        :param algorithm: The algorithm to perform the colum mappings. Supports: `SimFloodAlgorithm`,
+            `ComaAlgorithm`, `CupidAlgorithm`, `DistributionBasedAlgorithm`, `JaccardDistanceAlgorithm`,
+            and `GPTAlgorithm`.
+        """
         self.column_manager = ColumnMappingManager(
             self.dataset, self.global_table, algorithm
         )
@@ -61,6 +84,13 @@ def map_columns(self, algorithm="SimFloodAlgorithm"):
         return self.column_mappings
 
     def map_values(self, algorithm="EditAlgorithm"):
+        """
+        Map column values.
+
+        :param algorithm: The algorithm to perform the value mappings. Supports: `EditAlgorithm`,
+            `TFIDFAlgorithm`, `EmbeddingAlgorithm` and `LLMAlgorithm`.
+
+        """
         self.global_table_all = get_gdc_data(self.column_mappings.values())
         self.value_manager = ValueMappingManager(
             self.dataset, self.column_mappings, self.global_table_all, algorithm
@@ -73,6 +103,13 @@ def map_values(self, algorithm="EditAlgorithm"):
     def update_reduced_scope(
         self, original_column, new_candidate_name, new_candidate_sim=1.0
     ):
+        """
+        Update the values returned by the scope reducer algorithm.
+
+        :param original_column: Name of the original column.
+        :param new_candidate_name: New name of the candidate column.
+        :param new_candidate_sim: New similarity of the candidate column.
+        """
         for index in range(len(self.reduced_scope)):
             if self.reduced_scope[index]["Candidate column"] == original_column:
                 self.reduced_scope[index]["Top k columns"].append(
@@ -83,6 +120,11 @@ def update_reduced_scope(
                 break
 
     def update_column_mappings(self, new_mappings):
+        """
+        Update the column mappings.
+
+        :param new_mappings: List of tuples (original_column, correct_target_column).
+        """
         for original_column, new_target_column in new_mappings:
             self.column_mappings[original_column] = new_target_column
 
@@ -92,6 +134,14 @@ def update_column_mappings(self, new_mappings):
     def update_value_mappings(
         self, original_column, original_value, new_target_value, new_similarity=1.0
     ):
+        """
+        Update the column value mappings.
+
+        :param original_column: Name of the original column.
+        :param original_value: Name of the original column value.
+        :param new_target_value: New name of the target column value.
+        :param new_similarity: New similarity of the original and target column values.
+        """
         for index in range(len(self.value_mappings[original_column]["matches"])):
             if (
                 self.value_mappings[original_column]["matches"][index][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     = source
+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/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.http://sphinx-doc.org/
+	exit /b 1
+)
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/source/api.rst

@@ -0,0 +1,7 @@
+API
+=========
+
+.. module:: bdikit.api
+
+.. autoclass:: APIManager
+   :members:

docs/source/conf.py

@@ -0,0 +1,91 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# This file only contains a selection of the most common options. For a full
+# list see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Path setup --------------------------------------------------------------
+
+# 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.
+#
+import os
+import sys
+
+sys.path.insert(0, os.path.abspath("../../"))
+
+
+# -- Project information -----------------------------------------------------
+
+project = "bdi-kit"
+copyright = "2024, NYU"
+author = "NYU"
+
+# The full version, including alpha/beta/rc tags
+release = ""
+master_doc = "index"
+
+# -- General configuration ---------------------------------------------------
+
+# Add any Sphinx extension module names here, as strings. They can be
+# extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
+# ones.
+extensions = [
+    "sphinx.ext.autodoc",
+    "nbsphinx",
+    "nbsphinx_link",
+    "sphinxemoji.sphinxemoji",
+]
+
+# Add any paths that contain templates here, relative to this directory.
+templates_path = ["_templates"]
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This pattern also affects html_static_path and html_extra_path.
+exclude_patterns = []
+
+
+# -- 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_rtd_theme"
+
+# Add any paths that contain custom static files (such as style sheets) here,
+# relative to this directory. They are copied after the builtin static files,
+# so a file named "default.css" will overwrite the builtin "default.css".
+# html_static_path = ['_static']
+
+# html_logo = 'images/logo.png'
+
+# html_theme_options = {
+#    'logo_only': True,
+#    'display_version': False,
+# }
+
+autodoc_member_order = "bysource"
+
+autoclass_content = "both"
+
+add_module_names = False
+
+autodoc_mock_imports = [
+    "sklearn",
+    "pandas",
+    "numpy",
+    "IPython",
+    "torch",
+    "transformers",
+    "matplotlib",
+    "openai",
+    "polyfuzz",
+    "flair",
+    "autofj",
+    "Levenshtein",
+    "valentine",
+    "altair",
+    "panel",
+]

docs/source/examples.rst

@@ -0,0 +1,7 @@
+Examples
+==========
+
+Here can find different Jupyter notebook examples about how to use `bdi-kit`:
+
+- `Column and Value Mappings <https://github.com/VIDA-NYU/bdi-kit/blob/devel/examples/column_and_value_mapping.ipynb>`__
+