From ec9ffa8fe0184cb8fb6baf7302e70cb7706f47c8 Mon Sep 17 00:00:00 2001 From: Will McGinnis Date: Tue, 28 Apr 2020 21:34:52 -0400 Subject: [PATCH] docs added back --- docs/Makefile | 192 ++++++++++++++++++ docs/requirements.txt | 0 docs/source/backward_difference.rst | 5 + docs/source/basen.rst | 5 + docs/source/binary.rst | 5 + docs/source/catboost.rst | 5 + docs/source/conf.py | 293 ++++++++++++++++++++++++++++ docs/source/glmm.rst | 5 + docs/source/hashing.rst | 6 + docs/source/helmert.rst | 5 + docs/source/index.rst | 94 +++++++++ docs/source/jamesstein.rst | 5 + docs/source/leaveoneout.rst | 5 + docs/source/mestimate.rst | 5 + docs/source/onehot.rst | 5 + docs/source/ordinal.rst | 5 + docs/source/polynomial.rst | 5 + docs/source/sum.rst | 5 + docs/source/targetencoder.rst | 5 + docs/source/woe.rst | 5 + docs/source/wrapper.rst | 8 + 21 files changed, 668 insertions(+) create mode 100755 docs/Makefile mode change 100644 => 100755 docs/requirements.txt create mode 100755 docs/source/backward_difference.rst create mode 100755 docs/source/basen.rst create mode 100755 docs/source/binary.rst create mode 100755 docs/source/catboost.rst create mode 100755 docs/source/conf.py create mode 100755 docs/source/glmm.rst create mode 100755 docs/source/hashing.rst create mode 100755 docs/source/helmert.rst create mode 100755 docs/source/index.rst create mode 100755 docs/source/jamesstein.rst create mode 100755 docs/source/leaveoneout.rst create mode 100755 docs/source/mestimate.rst create mode 100755 docs/source/onehot.rst create mode 100755 docs/source/ordinal.rst create mode 100755 docs/source/polynomial.rst create mode 100755 docs/source/sum.rst create mode 100755 docs/source/targetencoder.rst create mode 100755 docs/source/woe.rst create mode 100755 docs/source/wrapper.rst diff --git a/docs/Makefile b/docs/Makefile new file mode 100755 index 00000000..39f29324 --- /dev/null +++ b/docs/Makefile @@ -0,0 +1,192 @@ +# Makefile for Sphinx documentation +# + +# You can set these variables from the command line. +SPHINXOPTS = +SPHINXBUILD = sphinx-build +PAPER = +BUILDDIR = build + +# User-friendly check for sphinx-build +ifeq ($(shell which $(SPHINXBUILD) >/dev/null 2>&1; echo $$?), 1) +$(error The '$(SPHINXBUILD)' command was not found. Make sure you have Sphinx installed, then set the SPHINXBUILD environment variable to point to the full path of the '$(SPHINXBUILD)' executable. Alternatively you can add the directory with the executable to your PATH. If you don't have Sphinx installed, grab it from http://sphinx-doc.org/) +endif + +# Internal variables. +PAPEROPT_a4 = -D latex_paper_size=a4 +PAPEROPT_letter = -D latex_paper_size=letter +ALLSPHINXOPTS = -d $(BUILDDIR)/doctrees $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source +# the i18n builder cannot share the environment and doctrees with the others +I18NSPHINXOPTS = $(PAPEROPT_$(PAPER)) $(SPHINXOPTS) source + +.PHONY: help clean html dirhtml singlehtml pickle json htmlhelp qthelp devhelp epub latex latexpdf text man changes linkcheck doctest coverage gettext + +help: + @echo "Please use \`make ' where is one of" + @echo " html to make standalone HTML files" + @echo " dirhtml to make HTML files named index.html in directories" + @echo " singlehtml to make a single large HTML file" + @echo " pickle to make pickle files" + @echo " json to make JSON files" + @echo " htmlhelp to make HTML files and a HTML help project" + @echo " qthelp to make HTML files and a qthelp project" + @echo " applehelp to make an Apple Help Book" + @echo " devhelp to make HTML files and a Devhelp project" + @echo " epub to make an epub" + @echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter" + @echo " latexpdf to make LaTeX files and run them through pdflatex" + @echo " latexpdfja to make LaTeX files and run them through platex/dvipdfmx" + @echo " text to make text files" + @echo " man to make manual pages" + @echo " texinfo to make Texinfo files" + @echo " info to make Texinfo files and run them through makeinfo" + @echo " gettext to make PO message catalogs" + @echo " changes to make an overview of all changed/added/deprecated items" + @echo " xml to make Docutils-native XML files" + @echo " pseudoxml to make pseudoxml-XML files for display purposes" + @echo " linkcheck to check all external links for integrity" + @echo " doctest to run all doctests embedded in the documentation (if enabled)" + @echo " coverage to run coverage check of the documentation (if enabled)" + +clean: + rm -rf $(BUILDDIR)/* + +html: + $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html + @echo + @echo "Build finished. The HTML pages are in $(BUILDDIR)/html." + +dirhtml: + $(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml + @echo + @echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml." + +singlehtml: + $(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml + @echo + @echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml." + +pickle: + $(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle + @echo + @echo "Build finished; now you can process the pickle files." + +json: + $(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json + @echo + @echo "Build finished; now you can process the JSON files." + +htmlhelp: + $(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp + @echo + @echo "Build finished; now you can run HTML Help Workshop with the" \ + ".hhp project file in $(BUILDDIR)/htmlhelp." + +qthelp: + $(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp + @echo + @echo "Build finished; now you can run "qcollectiongenerator" with the" \ + ".qhcp project file in $(BUILDDIR)/qthelp, like this:" + @echo "# qcollectiongenerator $(BUILDDIR)/qthelp/CategoryEncoders.qhcp" + @echo "To view the help file:" + @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/CategoryEncoders.qhc" + +applehelp: + $(SPHINXBUILD) -b applehelp $(ALLSPHINXOPTS) $(BUILDDIR)/applehelp + @echo + @echo "Build finished. The help book is in $(BUILDDIR)/applehelp." + @echo "N.B. You won't be able to view it unless you put it in" \ + "~/Library/Documentation/Help or install it in your application" \ + "bundle." + +devhelp: + $(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp + @echo + @echo "Build finished." + @echo "To view the help file:" + @echo "# mkdir -p $$HOME/.local/share/devhelp/CategoryEncoders" + @echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/CategoryEncoders" + @echo "# devhelp" + +epub: + $(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub + @echo + @echo "Build finished. The epub file is in $(BUILDDIR)/epub." + +latex: + $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex + @echo + @echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex." + @echo "Run \`make' in that directory to run these through (pdf)latex" \ + "(use \`make latexpdf' here to do that automatically)." + +latexpdf: + $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex + @echo "Running LaTeX files through pdflatex..." + $(MAKE) -C $(BUILDDIR)/latex all-pdf + @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." + +latexpdfja: + $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex + @echo "Running LaTeX files through platex and dvipdfmx..." + $(MAKE) -C $(BUILDDIR)/latex all-pdf-ja + @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex." + +text: + $(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text + @echo + @echo "Build finished. The text files are in $(BUILDDIR)/text." + +man: + $(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man + @echo + @echo "Build finished. The manual pages are in $(BUILDDIR)/man." + +texinfo: + $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo + @echo + @echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo." + @echo "Run \`make' in that directory to run these through makeinfo" \ + "(use \`make info' here to do that automatically)." + +info: + $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo + @echo "Running Texinfo files through makeinfo..." + make -C $(BUILDDIR)/texinfo info + @echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo." + +gettext: + $(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale + @echo + @echo "Build finished. The message catalogs are in $(BUILDDIR)/locale." + +changes: + $(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes + @echo + @echo "The overview file is in $(BUILDDIR)/changes." + +linkcheck: + $(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck + @echo + @echo "Link check complete; look for any errors in the above output " \ + "or in $(BUILDDIR)/linkcheck/output.txt." + +doctest: + $(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest + @echo "Testing of doctests in the sources finished, look at the " \ + "results in $(BUILDDIR)/doctest/output.txt." + +coverage: + $(SPHINXBUILD) -b coverage $(ALLSPHINXOPTS) $(BUILDDIR)/coverage + @echo "Testing of coverage in the sources finished, look at the " \ + "results in $(BUILDDIR)/coverage/python.txt." + +xml: + $(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml + @echo + @echo "Build finished. The XML files are in $(BUILDDIR)/xml." + +pseudoxml: + $(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml + @echo + @echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml." diff --git a/docs/requirements.txt b/docs/requirements.txt old mode 100644 new mode 100755 diff --git a/docs/source/backward_difference.rst b/docs/source/backward_difference.rst new file mode 100755 index 00000000..d863aab6 --- /dev/null +++ b/docs/source/backward_difference.rst @@ -0,0 +1,5 @@ +Backward Difference Coding +========================== + +.. autoclass:: category_encoders.backward_difference.BackwardDifferenceEncoder + :members: diff --git a/docs/source/basen.rst b/docs/source/basen.rst new file mode 100755 index 00000000..177e517d --- /dev/null +++ b/docs/source/basen.rst @@ -0,0 +1,5 @@ +BaseN +===== + +.. autoclass:: category_encoders.basen.BaseNEncoder + :members: diff --git a/docs/source/binary.rst b/docs/source/binary.rst new file mode 100755 index 00000000..e1d22cda --- /dev/null +++ b/docs/source/binary.rst @@ -0,0 +1,5 @@ +Binary +====== + +.. autoclass:: category_encoders.binary.BinaryEncoder + :members: diff --git a/docs/source/catboost.rst b/docs/source/catboost.rst new file mode 100755 index 00000000..1629ee7b --- /dev/null +++ b/docs/source/catboost.rst @@ -0,0 +1,5 @@ +CatBoost Encoder +============== + +.. autoclass:: category_encoders.cat_boost.CatBoostEncoder + :members: diff --git a/docs/source/conf.py b/docs/source/conf.py new file mode 100755 index 00000000..aa536986 --- /dev/null +++ b/docs/source/conf.py @@ -0,0 +1,293 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +# +# Category Encoders documentation build configuration file, created by +# sphinx-quickstart on Sat Jan 16 13:08:19 2016. +# +# This file is execfile()d with the current directory set to its +# containing dir. +# +# Note that not all possible configuration values are present in this +# autogenerated file. +# +# All configuration values have a default; values that are commented out +# serve to show the default. + +import sys +import os +import shlex + +# 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, os.path.abspath('.')) +sys.path.insert(0, str(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))) + os.sep + '') +sys.path.insert(0, str(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))) + os.sep + 'category_encoders') +# -- General configuration ------------------------------------------------ + +# If your documentation needs a minimal Sphinx version, state it here. +#needs_sphinx = '1.0' + +# 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.todo', + 'sphinx.ext.viewcode', + 'sphinx.ext.coverage', + 'sphinx.ext.doctest', + 'numpydoc' +] + +# Add any paths that contain templates here, relative to this directory. +templates_path = ['_templates'] + +# The suffix(es) of source filenames. +# You can specify multiple suffix as a list of string: +# source_suffix = ['.rst', '.md'] +source_suffix = '.rst' + +# The encoding of source files. +#source_encoding = 'utf-8-sig' + +# The master toctree document. +master_doc = 'index' + +# General information about the project. +project = 'Category Encoders' +copyright = '2016, Will McGinnis' +author = 'Will McGinnis' + +# The version info for the project you're documenting, acts as replacement for +# |version| and |release|, also used in various other places throughout the +# built documents. +# +# The short X.Y version. +version = 'latest' +# The full version, including alpha/beta/rc tags. +release = 'latest' + +# The language for content autogenerated by Sphinx. Refer to documentation +# for a list of supported languages. +# +# This is also used if you do content translation via gettext catalogs. +# Usually you set "language" from the command line for these cases. +language = None + +# There are two options for replacing |today|: either, you set today to some +# non-false value, then it is used: +#today = '' +# Else, today_fmt is used as the format for a strftime call. +#today_fmt = '%B %d, %Y' + +# List of patterns, relative to source directory, that match files and +# directories to ignore when looking for source files. +exclude_patterns = [] + +# The reST default role (used for this markup: `text`) to use for all +# documents. +#default_role = None + +# If true, '()' will be appended to :func: etc. cross-reference text. +add_function_parentheses = True + +# If true, the current module name will be prepended to all description +# unit titles (such as .. function::). +add_module_names = True + +# If true, sectionauthor and moduleauthor directives will be shown in the +# output. They are ignored by default. +show_authors = False + +# The name of the Pygments (syntax highlighting) style to use. +pygments_style = 'sphinx' + +# A list of ignored prefixes for module index sorting. +#modindex_common_prefix = [] + +# If true, keep warnings as "system message" paragraphs in the built documents. +#keep_warnings = False + +# If true, `todo` and `todoList` produce output, else they produce nothing. +todo_include_todos = False + + +# -- 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' + +# Theme options are theme-specific and customize the look and feel of a theme +# further. For a list of options available for each theme, see the +# documentation. +#html_theme_options = {} + +# Add any paths that contain custom themes here, relative to this directory. +#html_theme_path = [] + +# The name for this set of Sphinx documents. If None, it defaults to +# " v documentation". +#html_title = None + +# A shorter title for the navigation bar. Default is the same as html_title. +#html_short_title = None + +# The name of an image file (relative to this directory) to place at the top +# of the sidebar. +#html_logo = None + +# The name of an image file (within the static path) to use as favicon of the +# docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32 +# pixels large. +#html_favicon = None + +# 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'] +autoclass_content = 'both' +# Add any extra paths that contain custom files (such as robots.txt or +# .htaccess) here, relative to this directory. These files are copied +# directly to the root of the documentation. +#html_extra_path = [] + +# If not '', a 'Last updated on:' timestamp is inserted at every page bottom, +# using the given strftime format. +#html_last_updated_fmt = '%b %d, %Y' + +# If true, SmartyPants will be used to convert quotes and dashes to +# typographically correct entities. +#html_use_smartypants = True + +# Custom sidebar templates, maps document names to template names. +#html_sidebars = {} + +# Additional templates that should be rendered to pages, maps page names to +# template names. +#html_additional_pages = {} + +# If false, no module index is generated. +#html_domain_indices = True + +# If false, no index is generated. +#html_use_index = True + +# If true, the index is split into individual pages for each letter. +#html_split_index = False + +# If true, links to the reST sources are added to the pages. +#html_show_sourcelink = True + +# If true, "Created using Sphinx" is shown in the HTML footer. Default is True. +html_show_sphinx = True + +# If true, "(C) Copyright ..." is shown in the HTML footer. Default is True. +html_show_copyright = True + +# If true, an OpenSearch description file will be output, and all pages will +# contain a tag referring to it. The value of this option must be the +# base URL from which the finished HTML is served. +#html_use_opensearch = '' + +# This is the file name suffix for HTML files (e.g. ".xhtml"). +#html_file_suffix = None + +# Language to be used for generating the HTML full-text search index. +# Sphinx supports the following languages: +# 'da', 'de', 'en', 'es', 'fi', 'fr', 'h', 'it', 'ja' +# 'nl', 'no', 'pt', 'ro', 'r', 'sv', 'tr' +#html_search_language = 'en' + +# A dictionary with options for the search language support, empty by default. +# Now only 'ja' uses this config value +#html_search_options = {'type': 'default'} + +# The name of a javascript file (relative to the configuration directory) that +# implements a search results scorer. If empty, the default will be used. +#html_search_scorer = 'scorer.js' + +# Output file base name for HTML help builder. +htmlhelp_basename = 'CategoryEncodersdoc' + +# -- Options for LaTeX output --------------------------------------------- + +latex_elements = { +# The paper size ('letterpaper' or 'a4paper'). +#'papersize': 'letterpaper', + +# The font size ('10pt', '11pt' or '12pt'). +#'pointsize': '10pt', + +# Additional stuff for the LaTeX preamble. +#'preamble': '', + +# Latex figure (float) alignment +#'figure_align': 'htbp', +} + +# Grouping the document tree into LaTeX files. List of tuples +# (source start file, target name, title, +# author, documentclass [howto, manual, or own class]). +latex_documents = [ + (master_doc, 'CategoryEncoders.tex', 'Category Encoders Documentation', + 'Will McGinnis', 'manual'), +] + +# The name of an image file (relative to this directory) to place at the top of +# the title page. +#latex_logo = None + +# For "manual" documents, if this is true, then toplevel headings are parts, +# not chapters. +#latex_use_parts = False + +# If true, show page references after internal links. +#latex_show_pagerefs = False + +# If true, show URL addresses after external links. +#latex_show_urls = False + +# Documents to append as an appendix to all manuals. +#latex_appendices = [] + +# If false, no module index is generated. +#latex_domain_indices = True + + +# -- Options for manual page output --------------------------------------- + +# One entry per manual page. List of tuples +# (source start file, name, description, authors, manual section). +man_pages = [ + (master_doc, 'categoryencoders', 'Category Encoders Documentation', + [author], 1) +] + +# If true, show URL addresses after external links. +#man_show_urls = False + + +# -- Options for Texinfo output ------------------------------------------- + +# Grouping the document tree into Texinfo files. List of tuples +# (source start file, target name, title, author, +# dir menu entry, description, category) +texinfo_documents = [ + (master_doc, 'CategoryEncoders', 'Category Encoders Documentation', + author, 'CategoryEncoders', 'One line description of project.', + 'Miscellaneous'), +] + +# Documents to append as an appendix to all manuals. +#texinfo_appendices = [] + +# If false, no module index is generated. +#texinfo_domain_indices = True + +# How to display URL addresses: 'footnote', 'no', or 'inline'. +#texinfo_show_urls = 'footnote' + +# If true, do not generate a @detailmenu in the "Top" node's menu. +#texinfo_no_detailmenu = False diff --git a/docs/source/glmm.rst b/docs/source/glmm.rst new file mode 100755 index 00000000..3af76d54 --- /dev/null +++ b/docs/source/glmm.rst @@ -0,0 +1,5 @@ +Generalized Linear Mixed Model Encoder +====================================== + +.. autoclass:: category_encoders.glmm.GLMMEncoder + :members: diff --git a/docs/source/hashing.rst b/docs/source/hashing.rst new file mode 100755 index 00000000..def7f233 --- /dev/null +++ b/docs/source/hashing.rst @@ -0,0 +1,6 @@ +Hashing +======= + +.. autoclass:: category_encoders.hashing.HashingEncoder + :members: + diff --git a/docs/source/helmert.rst b/docs/source/helmert.rst new file mode 100755 index 00000000..073c2069 --- /dev/null +++ b/docs/source/helmert.rst @@ -0,0 +1,5 @@ +Helmert Coding +============== + +.. autoclass:: category_encoders.helmert.HelmertEncoder + :members: diff --git a/docs/source/index.rst b/docs/source/index.rst new file mode 100755 index 00000000..05f7312d --- /dev/null +++ b/docs/source/index.rst @@ -0,0 +1,94 @@ +.. Category Encoders documentation master file, created by + sphinx-quickstart on Sat Jan 16 13:08:19 2016. + You can adapt this file completely to your liking, but it should at least + contain the root `toctree` directive. + +Category Encoders +================= + +A set of scikit-learn-style transformers for encoding categorical variables into numeric with different +techniques. While ordinal, one-hot, and hashing encoders have similar equivalents in the existing scikit-learn version, the +transformers in this library all share a few useful properties: + + * First-class support for pandas dataframes as an input (and optionally as output) + * Can explicitly configure which columns in the data are encoded by name or index, or infer non-numeric columns regardless of input type + * Can drop any columns with very low variance based on training set optionally + * Portability: train a transformer on data, pickle it, reuse it later and get the same thing out. + * Full compatibility with sklearn pipelines, input an array-like dataset like any other transformer + +Usage +----- + +install as: + +.. code-block:: python + + pip install category_encoders + +or + +.. code-block:: python + + conda install -c conda-forge category_encoders + + +To use: + +.. code-block:: python + + import category_encoders as ce + + encoder = ce.BackwardDifferenceEncoder(cols=[...]) + encoder = ce.BaseNEncoder(cols=[...]) + encoder = ce.BinaryEncoder(cols=[...]) + encoder = ce.CatBoostEncoder(cols=[...]) + encoder = ce.GLMMEncoder(cols=[...]) + encoder = ce.HashingEncoder(cols=[...]) + encoder = ce.HelmertEncoder(cols=[...]) + encoder = ce.JamesSteinEncoder(cols=[...]) + encoder = ce.LeaveOneOutEncoder(cols=[...]) + encoder = ce.MEstimateEncoder(cols=[...]) + encoder = ce.OneHotEncoder(cols=[...]) + encoder = ce.OrdinalEncoder(cols=[...]) + encoder = ce.SumEncoder(cols=[...]) + encoder = ce.PolynomialEncoder(cols=[...]) + encoder = ce.TargetEncoder(cols=[...]) + encoder = ce.WOEEncoder(cols=[...]) + + encoder.fit(X, y) + X_cleaned = encoder.transform(X_dirty) + +All of these are fully compatible sklearn transformers, so they can be used in pipelines or in your existing scripts. If +the cols parameter isn't passed, every non-numeric column will be converted. See below for detailed documentation + +Contents: + +.. toctree:: + :maxdepth: 3 + + backward_difference + basen + binary + catboost + glmm + hashing + helmert + jamesstein + leaveoneout + mestimate + onehot + ordinal + polynomial + sum + targetencoder + woe + wrapper + + +Indices and tables +================== + +* :ref:`genindex` +* :ref:`modindex` +* :ref:`search` + diff --git a/docs/source/jamesstein.rst b/docs/source/jamesstein.rst new file mode 100755 index 00000000..30b889c3 --- /dev/null +++ b/docs/source/jamesstein.rst @@ -0,0 +1,5 @@ +James-Stein Encoder +============== + +.. autoclass:: category_encoders.james_stein.JamesSteinEncoder + :members: diff --git a/docs/source/leaveoneout.rst b/docs/source/leaveoneout.rst new file mode 100755 index 00000000..3b8dde32 --- /dev/null +++ b/docs/source/leaveoneout.rst @@ -0,0 +1,5 @@ +Leave One Out +============= + +.. autoclass:: category_encoders.leave_one_out.LeaveOneOutEncoder + :members: diff --git a/docs/source/mestimate.rst b/docs/source/mestimate.rst new file mode 100755 index 00000000..67a27a10 --- /dev/null +++ b/docs/source/mestimate.rst @@ -0,0 +1,5 @@ +M-estimate +============== + +.. autoclass:: category_encoders.m_estimate.MEstimateEncoder + :members: diff --git a/docs/source/onehot.rst b/docs/source/onehot.rst new file mode 100755 index 00000000..ec1f8a13 --- /dev/null +++ b/docs/source/onehot.rst @@ -0,0 +1,5 @@ +One Hot +======= + +.. autoclass:: category_encoders.one_hot.OneHotEncoder + :members: diff --git a/docs/source/ordinal.rst b/docs/source/ordinal.rst new file mode 100755 index 00000000..5316d73e --- /dev/null +++ b/docs/source/ordinal.rst @@ -0,0 +1,5 @@ +Ordinal +======= + +.. autoclass:: category_encoders.ordinal.OrdinalEncoder + :members: diff --git a/docs/source/polynomial.rst b/docs/source/polynomial.rst new file mode 100755 index 00000000..332392ce --- /dev/null +++ b/docs/source/polynomial.rst @@ -0,0 +1,5 @@ +Polynomial Coding +================= + +.. autoclass:: category_encoders.polynomial.PolynomialEncoder + :members: diff --git a/docs/source/sum.rst b/docs/source/sum.rst new file mode 100755 index 00000000..ae07a46d --- /dev/null +++ b/docs/source/sum.rst @@ -0,0 +1,5 @@ +Sum Coding +========== + +.. autoclass:: category_encoders.sum_coding.SumEncoder + :members: diff --git a/docs/source/targetencoder.rst b/docs/source/targetencoder.rst new file mode 100755 index 00000000..a44340ba --- /dev/null +++ b/docs/source/targetencoder.rst @@ -0,0 +1,5 @@ +Target Encoder +============== + +.. autoclass:: category_encoders.target_encoder.TargetEncoder + :members: diff --git a/docs/source/woe.rst b/docs/source/woe.rst new file mode 100755 index 00000000..8e3d29aa --- /dev/null +++ b/docs/source/woe.rst @@ -0,0 +1,5 @@ +Weight of Evidence +================== + +.. autoclass:: category_encoders.woe.WOEEncoder + :members: diff --git a/docs/source/wrapper.rst b/docs/source/wrapper.rst new file mode 100755 index 00000000..08466694 --- /dev/null +++ b/docs/source/wrapper.rst @@ -0,0 +1,8 @@ +Wrappers +======== + +.. autoclass:: category_encoders.wrapper.PolynomialWrapper + :members: + +.. autoclass:: category_encoders.wrapper.NestedCVWrapper + :members: \ No newline at end of file