Merge pull request #6 from apache/sphinx-docs

First attempt at sphinx documentation

.asf.yaml

@@ -0,0 +1,4 @@
+github:
+  homepage: https://datasketches.apache.org
+  ghp_branch: gh-pages
+  ghp_path: /docs

.github/workflows/sphinx.yml

@@ -0,0 +1,32 @@
+name: Sphinx
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  build-documentation:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Install Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: '3.x'
+      - name: Install Datasketches and Sphinx
+        run: python -m pip install . sphinx==7.2.4 sphinx-rtd-theme
+      - name: Run Sphinx
+        run: cd docs; make html
+      - name: Pages Deployment
+        uses: peaceiris/actions-gh-pages@v3.9.3
+        with:
+          github_token: ${{ secrets.GITHUB_TOKEN }}
+          publish_dir: ./docs/build/html
+          destination_dir: docs/${{ github.ref_name }}
+          enable_jekyll: false
+          allow_empty_commit: false
+          force_orphan: false
+          publish_branch: gh-pages

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/README.md

@@ -0,0 +1,50 @@
+Follow these steps to build the documentation.
+1. Clone the directory in an appropriate location `git clone https://github.com/apache/datasketches-python.git`
+2. Switch to the correct branch: `git checkout python-docs`.
+3. In project root run `source python-docs-venv/bin/activate`
+
+If there are problems running the virtual env then you may need to install `virtualenv`
+and install the packages manually as below
+(nb my environment has `python` aliased to `python3` so just use whichever is appropriate for your installation)
+```
+python -m venv python-docs-venv # create a new virtual env named python-docs-venv
+source python-docs-venv/bin/activate
+python -m pip install sphinx 
+python -m pip install sphinx-rtd-theme
+```
+4. In project root run `python3 -m pip install .` to build the python bindings.
+5. Build and open the documentation:
+```
+cd python/docs
+make html
+open build/html/index.html
+```
+
+## Problems
+The `density_sketch` and `tuple_sketch` are not yet included.  
+I have not included the file to avoid cluttering the PR with things that may not work.
+You can easily include them by making a `density_sketch.rst` file in the same location as 
+all of the other `X.rst` files for the sketches and copying in the following:
+
+```
+Density Sketch
+--------------
+
+.. autoclass:: datasketches.density_sketch
+    :members:
+    :undoc-members:
+
+.. autoclass:: datasketches.GaussianKernel
+    :members:
+```
+Additionally, you will need to add the below to `index.rst`
+```
+Density Estimation
+##################
+
+.. toctree::
+   :maxdepth: 1 
+
+   density_sketch
+```
+

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
+
+%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.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/source/conf.py

@@ -0,0 +1,36 @@
+# 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
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+import sys
+import os 
+
+# need to fix the paths so that sphinx can find the source code.
+sys.path.insert(0, os.path.abspath("../../datasketches"))
+sys.path.insert(0, os.path.abspath("../../src"))
+
+
+project = 'datasketches'
+copyright = '2023'
+author = 'Apache Software Foundation'
+release = '0.1'
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = ["sphinx.ext.autodoc","sphinx.ext.autosummary"]
+
+templates_path = ['_templates']
+exclude_patterns = []
+
+
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = 'sphinx_rtd_theme'
+html_static_path = ['_static']

docs/source/count_min_sketch.rst

@@ -0,0 +1,6 @@
+CountMin Sketch
+---------------
+
+.. autoclass:: _datasketches.count_min_sketch
+    :members:
+    :undoc-members:

docs/source/cpc.rst

@@ -0,0 +1,7 @@
+Compressed Probabilistic Counting (CPC)
+---------------------------------------
+The *Compressed Probabilistic Counting* sketch is a space-efficient method for estimating cardinalities of sets.
+
+.. autoclass:: _datasketches.cpc_sketch
+    :members:
+    :undoc-members:

docs/source/frequent_items.rst

@@ -0,0 +1,6 @@
+Frequent Items
+--------------
+
+.. autoclass:: _datasketches.frequent_items_sketch
+    :members:
+    :undoc-members:

docs/source/hyper_log_log.rst

@@ -0,0 +1,7 @@
+HyperLogLog (HLL)
+-----------------
+The HyperLogLog (HLL) sketch is a space-efficient method for estimating cardinalities of sets.
+
+.. autoclass:: _datasketches.hll_sketch
+    :members:
+    :undoc-members:

docs/source/index.rst

@@ -0,0 +1,73 @@
+.. datasketches documentation master file, created by
+   sphinx-quickstart on Tue Jul 25 11:04:59 2023.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Apache DataSketches
+=================================================
+
+**DataSketches** are highly-efficient algorithms to analyze big data quickly.
+
+
+Counting Distincts
+##################
+..
+   maxdepth: 1 means only the heading is printed in the contents
+.. toctree::
+   :maxdepth: 1 
+
+   hyper_log_log
+   cpc
+   theta 
+
+Frequency Estimation
+##########################
+
+.. toctree::
+   :maxdepth: 1 
+
+   count_min_sketch
+
+
+Frequent Items
+##########################
+This problem may also be known as **heavy hitters** or **TopK**
+
+.. toctree::
+   :maxdepth: 1 
+
+   frequent_items
+
+Quantile Estimation
+###################
+
+.. toctree::
+   :maxdepth: 1 
+
+   kll
+   req
+   quantiles_depr
+
+.. note::
+
+   This project is under active development.
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`
+
+
+.. .. automodule:: datasketches    
+..    :members:
+
+.. .. automodule:: _datasketches
+..     :members:
+
+.. 
+.. 
+
+..    distinct_count

docs/source/kll.rst

@@ -0,0 +1,19 @@
+KLL Sketch
+----------
+
+.. autoclass:: _datasketches.kll_ints_sketch
+    :members:
+    :undoc-members:
+
+.. autoclass:: _datasketches.kll_floats_sketch
+    :members:
+    :undoc-members:
+
+.. autoclass:: _datasketches.kll_doubles_sketch
+    :members:
+    :undoc-members:
+
+.. autoclass:: _datasketches.kll_items_sketch
+    :members:
+    :undoc-members:
+

docs/source/quantiles_depr.rst

@@ -0,0 +1,19 @@
+Quantiles Sketch (Deprecated)
+-----------------------------
+This is a deprecated quantiles sketch that is included for cross-language compatability.
+
+.. autoclass:: _datasketches.quantiles_ints_sketch
+    :members:
+    :undoc-members:
+
+.. autoclass:: _datasketches.quantiles_floats_sketch
+    :members:
+    :undoc-members:
+
+.. autoclass:: _datasketches.quantiles_doubles_sketch
+    :members:
+    :undoc-members:
+
+.. autoclass:: _datasketches.quantiles_items_sketch
+    :members:
+    :undoc-members:

docs/source/req.rst

@@ -0,0 +1,14 @@
+Relative Error Quantiles (REQ) Sketch
+-------------------------------------
+
+.. autoclass:: _datasketches.req_ints_sketch
+    :members:
+    :undoc-members:
+
+.. autoclass:: _datasketches.req_floats_sketch
+    :members:
+    :undoc-members:
+
+.. autoclass:: _datasketches.req_items_sketch
+    :members:
+    :undoc-members:

docs/source/theta.rst

@@ -0,0 +1,8 @@
+Theta Sketch
+------------
+The *Theta Sketch* sketch is a space-efficient method for estimating cardinalities of sets.
+It can also easily handle set operations (such as union, intersection, difference) while maintaining good accuarcy.
+
+.. autoclass:: _datasketches.theta_sketch
+    :members:
+    :undoc-members: