Jm/docs (#13)

* Docs and supporting refactoring

* test updates

* add train section to docs

* docstring fix

* docs reqs

* install all reqs for docs build

* custom css for rtd....maybe?

* remove extra css import and use SSL for font download

* Version bump and README updates

* reset notebook

Co-authored-by: John Myers <john@gretel.ai>

.gitignore

@@ -133,4 +133,6 @@ dmypy.json
 .idea/
 venv*
 
-checkpoints
+checkpoints
+
+docs/_build

README.md

@@ -1,4 +1,9 @@
-# gretel-synthetics
+# Gretel Synthetics
+
+![gretel-synthetics workflows](https://github.com/gretelai/gretel-synthetics/workflows/gretel-synthetics%20workflows/badge.svg)
+
+[![Documentation Status](https://readthedocs.org/projects/gretel-synthetics/badge/?version=stable)](https://gretel-synthetics.readthedocs.io/en/stable/?badge=stable)
+
 
 This code has been developed and tested on Python 3.7. Python 3.8 is currently unsupported.
 

VERSION

@@ -1 +1 @@
-0.7.1
+0.8.0

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     = .
+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/_static/styles.css

@@ -0,0 +1 @@
+@import url('https://fonts.googleapis.com/css?family=Inter');

docs/api/config.rst

@@ -0,0 +1,5 @@
+Config
+======
+
+.. automodule:: gretel_synthetics.config
+    :members:

docs/api/generate.rst

@@ -0,0 +1,5 @@
+Generate
+========
+
+.. automodule:: gretel_synthetics.generate
+    :members:

docs/api/train.rst

@@ -0,0 +1,5 @@
+Train
+========
+
+.. automodule:: gretel_synthetics.train
+    :members:

docs/conf.py

@@ -0,0 +1,83 @@
+# 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
+
+import sphinx
+
+sys.path.insert(0, os.path.abspath('../src'))
+
+
+# -- Project information -----------------------------------------------------
+
+project = 'Gretel Synthetics'
+copyright = '2020, Gretel.ai'
+author = 'Gretel.ai'
+
+
+# -- 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', 'sphinx.ext.coverage', 'sphinx.ext.napoleon', 'm2r']
+
+source_suffix = ['.rst', '.md']
+
+# 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 = ['_build', 'Thumbs.db', '.DS_Store']
+
+
+# -- 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 = 'alabaster'
+
+# 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_theme_options = {
+    'sidebar_width': '250px',
+    'font_family': 'Inter'
+}
+
+html_css_files = [
+    'styles.css'
+]
+
+
+def monkeypatch(cls):
+    """ decorator to monkey-patch methods """
+    def decorator(f):
+        method = f.__name__
+        old_method = getattr(cls, method)
+        setattr(cls, method, lambda self, *args, **kwargs: f(old_method, self, *args, **kwargs))
+    return decorator
+
+# workaround until https://github.com/miyakogi/m2r/pull/55 is merged
+@monkeypatch(sphinx.registry.SphinxComponentRegistry)
+def add_source_parser(_old_add_source_parser, self, *args, **kwargs):
+    # signature is (parser: Type[Parser], **kwargs), but m2r expects
+    # the removed (str, parser: Type[Parser], **kwargs).
+    if isinstance(args[0], str):
+        args = args[1:]
+    return _old_add_source_parser(self, *args, **kwargs)

docs/index.rst

@@ -0,0 +1,26 @@
+.. image:: ./img/gretel-logo.png
+   :alt: Gretel Logo
+
+.. mdinclude:: ../README.md
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+
+Modules
+=======
+.. toctree::
+   :maxdepth: 2
+
+   api/config.rst
+   api/train.rst
+   api/generate.rst
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

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=.
+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/requirements.txt

@@ -0,0 +1,3 @@
+m2r
+sphinx==3.0.3
+-r ../requirements.txt

examples/synthetic_records.ipynb

@@ -17,7 +17,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -110,15 +110,8 @@
     "        raise Exception('record not 6 parts')\n",
     "        \n",
     "for line in generate_text(config, line_validator=validate_record):\n",
-    "    print(line)\n"
+    "    print(line)"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {
@@ -137,7 +130,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.7"
+   "version": "3.7.5"
   }
  },
  "nbformat": 4,

src/gretel_synthetics/config.py

@@ -21,7 +21,7 @@
 
 
 @dataclass
-class BaseConfig:
+class _BaseConfig:
     """Base dataclass that contains all of the main parameters for
     training a model and generating data.  This base config generally
     should not be used directly. Instead you should use one of the
@@ -63,7 +63,7 @@ def _set_tokenizer(self):  # pragma: no cover
 
 
 @dataclass
-class PathSettings:
+class _PathSettings:
     """This dataclass stores path locations to
     store tokenizer and training data locations. It should not
     be used directly. It will be utilized by any configuration
@@ -75,7 +75,7 @@ class PathSettings:
 
 
 @dataclass
-class PathSettingsMixin:
+class _PathSettingsMixin:
     """If a specific config needs to make use of
     ``PathSettings``, this dataclass will make an
     attr of ``paths`` available and also bring in
@@ -85,7 +85,7 @@ class PathSettingsMixin:
     This makes it possible to easily remove the path
     settings when serializing the configuration.
     """
-    paths: PathSettings = field(default_factory=PathSettings)
+    paths: _PathSettings = field(default_factory=_PathSettings)
 
     @property
     def tokenizer_prefix(self):
@@ -101,15 +101,16 @@ def training_data(self):
 
 
 @dataclass
-class LocalConfig(BaseConfig, PathSettingsMixin):
+class LocalConfig(_BaseConfig, _PathSettingsMixin):
     """This configuration will use the local file system
     to store all models, training data, and checkpoints
 
     Args:
-        checkpoint_dir: The local directory where all checkpoints should be stored
+        checkpoint_dir: The local directory where all checkpoints and additional support
+            files for training and generation will be stored.
         input_data_path: A path to a file that will be used as initial training input.
             This file will be opened, annotated, and then written out to a path
-            that is generated from the ``training_data` attribute.
+            that is generated based on the ``checkpoint_dir.``
     """
     checkpoint_dir: str = None
     input_data_path: str = None