Add docs (#18)

* Add QRNN-based classifier (#14)

* Add PRAD (#14)

* Add a setting file for GitHub action

* Fix

* Fix yaml format

* Add install

* Add requirements.txt

* Update requirements.txt

* Unsupport 3.5

* Unsupport 3.6

* setup.py develop

* Add docs

bunruija/__init__.py

@@ -8,6 +8,7 @@
 import bunruija.tokenizers
 import bunruija.trainer
 
+from .binarizer import Binarizer
 from .evaluator import Evaluator
 from .predictor import Predictor
 from .trainer import Trainer

bunruija/binarizer.py

@@ -10,6 +10,8 @@
 
 
 class Binarizer:
+    """Binarizes data
+    """
     def __init__(self, config_file):
         self.config_file = config_file
         with open(config_file) as f:

bunruija/evaluator.py

@@ -11,6 +11,8 @@
 
 
 class Evaluator:
+    """Evaluates a trained model
+    """
     def __init__(self, args):
         with open(args.yaml) as f:
             self.config = yaml.load(f, Loader=yaml.SafeLoader)

bunruija/trainer.py

@@ -10,7 +10,9 @@
 
 
 class Trainer:
-    def __init__(self, config_file):
+    """Trains a text classification model.
+    """
+    def __init__(self, config_file: str):
         with open(config_file) as f:
             self.config = yaml.load(f, Loader=yaml.SafeLoader)
 

docs/binarizer.rst

@@ -0,0 +1,9 @@
+Binarizer
+====================================
+
+================
+Binarizer module
+================
+
+.. automodule:: bunruija.Binarizer
+   :members:

docs/conf.py

@@ -0,0 +1,57 @@
+# 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 = 'Bunruija'
+copyright = '2021, Takuya Makino'
+author = 'Takuya Makino'
+
+# The full version, including alpha/beta/rc tags
+release = '0.0.0'
+
+
+# -- 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.napoleon',
+]
+
+# 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 = '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']

docs/evaluator.rst

@@ -0,0 +1,10 @@
+Evaluator
+====================================
+
+================
+Evaluator module
+================
+
+.. automodule:: bunruija.Evaluator
+   :members:
+

docs/index.rst

@@ -0,0 +1,25 @@
+.. Bunruija documentation master file, created by
+   sphinx-quickstart on Sun Aug 15 11:49:32 2021.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to Bunruija's documentation!
+====================================
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Contents:
+
+   tutorial
+
+   binarizer
+   evaluator
+   trainer
+
+
+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/trainer.rst

@@ -0,0 +1,10 @@
+Trainer
+====================================
+
+==============
+Trainer module
+==============
+
+.. automodule:: bunruija.Trainer
+   :members:
+

docs/tutorial.rst

@@ -0,0 +1,57 @@
+Tutorial
+====================================
+
+================
+Data file format
+================
+
+.. code-block:: sh
+
+   label1,text
+   label2,text
+   label2,text
+   label3,text
+   label4,text
+
+=================
+Model file format
+=================
+
+
+.. code-block:: yaml
+
+  preprocess:
+    data:
+      train: train.csv
+      dev: dev.csv
+      test: test.csv
+  
+  tokenizer:
+    type: mecab
+    args:
+      lemmatize: true
+      exclude_pos:
+        - 助詞
+        - 助動詞
+  
+  bin_dir: models/svm-model
+  
+  classifier:
+    - type: tfidf
+      args:
+        max_features: 10000
+        min_df: 3
+        ngram_range:
+          - 1
+          - 3
+    - type: svm
+      args:
+        verbose: false
+        C: 10.
+
+
+.. code-block:: sh
+
+   bunruija-preprocess -y settings/model.yaml
+   bunruija-train -y settings/model.yaml
+   bunruija-evaluate -y settings/model.yaml