First version

Author: lulinbing

.gitignore

@@ -3,6 +3,7 @@
 *.log
 _build/
 temp/
+data/
 
 # pycharm temp files
 .idea/

README.md

@@ -1,72 +1,11 @@
-# 评论情感极性判断模型
-基于京东评论的情感极性判断模型，采用了fasttext进行分类。
+# 前言
+一些关于自然语言的基本模型
 
-## 模型效果
-使用京东80w条评论数据训练，10ｗ条评论数据测试:
-#### 模型参数
+# 目录
+* 基于HMM的中文分词模型
+* 基于fasttext的情感极性判断模型
 
-    lr = 0.01
-    lr_update_rate = 100
-    dim = 300
-    ws = 5
-    epoch = 10
-    word_ngrams = 3
-    loss = hs
-    bucket = 2000000
-    thread = 4
-
-#### 效果
-
-    ('precision:', 0.85055)
-    ('recall:', 0.85055)
-    ('examples:', 100000)
-
-## 快速开始
-#### 语料分词
-
-    python manage.py cut
-
-#### 模型训练
-
-    python manage.py train
-
-#### 模型测试
-
-    python manage.py test
-
-## 文档
-#### 代码文档
-基于sphnix生成,请确保已经安装
-
-    cd doc
-    make html
-
-#### 博客
-博客地址:http://blog.csdn.net/sinat_33741547/article/details/78803766
-
-## 参考
-#### Enriching Word Vectors with Subword Information
-
-[1] P. Bojanowski\*, E. Grave\*, A. Joulin, T. Mikolov, [*Enriching Word Vectors with Subword Information*](https://arxiv.org/pdf/1607.04606v1.pdf)
-
-```
-@article{bojanowski2016enriching,
-  title={Enriching Word Vectors with Subword Information},
-  author={Bojanowski, Piotr and Grave, Edouard and Joulin, Armand and Mikolov, Tomas},
-  journal={arXiv preprint arXiv:1607.04606},
-  year={2016}
-}
-```
-
-#### Bag of Tricks for Efficient Text Classification
-
-[2] A. Joulin, E. Grave, P. Bojanowski, T. Mikolov, [*Bag of Tricks for Efficient Text Classification*](https://arxiv.org/pdf/1607.01759v2.pdf)
-
-```
-@article{joulin2016bag,
-  title={Bag of Tricks for Efficient Text Classification},
-  author={Joulin, Armand and Grave, Edouard and Bojanowski, Piotr and Mikolov, Tomas},
-  journal={arXiv preprint arXiv:1607.01759},
-  year={2016}
-}
-```
+# 历史版本
+## 2017.12.21
+* 增加基于HMM的中文分词模型
+* 增加基于fasttext的情感极性判断模型

data/.gitkeep

@@ -0,0 +1,29 @@
+# 中文分词模型
+一个纯粹使用HMM的中文分词模型
+
+# 模型效果
+
+    准确率：0.7416711648494009
+    召回率：0.6686293783881109
+    F1：0.7032587944456672
+
+# 快速开始
+### 模型训练
+
+    python manage.py train
+
+### 模型测试
+
+    python manage.py test
+
+# 文档
+### 代码文档
+基于sphnix生成,请确保已经安装
+
+    cd doc
+    make html
+
+### 博客
+博客地址
+
+# 参考

segment/README.md

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line.
+SPHINXOPTS    =
+SPHINXBUILD   = sphinx-build
+SPHINXPROJ    = segment
+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)

segment/doc/Makefile

@@ -0,0 +1,162 @@
+# -*- coding: utf-8 -*-
+#
+# segment documentation build configuration file, created by
+# sphinx-quickstart on Tue Dec 19 14:03:29 2017.
+#
+# 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.
+
+# 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('.'))
+root_path = os.path.join(os.path.abspath(os.path.dirname(__file__)), '..')
+sys.path.insert(0, root_path)
+
+
+# -- 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']
+
+# 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 master toctree document.
+master_doc = 'index'
+
+# General information about the project.
+project = u'segment'
+copyright = u'2017, lpty'
+author = u'lpty'
+
+# 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 = u'0.1'
+# The full version, including alpha/beta/rc tags.
+release = u'0.1'
+
+# 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
+
+# List of patterns, relative to source directory, that match files and
+# directories to ignore when looking for source files.
+# This patterns also effect to html_static_path and html_extra_path
+exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+
+# The name of the Pygments (syntax highlighting) style to use.
+pygments_style = 'sphinx'
+
+# 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 = 'alabaster'
+
+# 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 = {
+    'description': u'segment',
+    'font_family': u'"Hiragino Sans GB","STHeiti","Microsoft Yahei"',
+    'caption_font_family': u'"Hiragino Sans GB","STHeiti","Microsoft Yahei"',
+}
+
+# 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']
+
+
+# -- Options for HTMLHelp output ------------------------------------------
+
+# Output file base name for HTML help builder.
+htmlhelp_basename = 'segmentdoc'
+
+
+# -- 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, 'segment.tex', u'segment Documentation',
+     u'lpty', 'manual'),
+]
+
+
+# -- 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, 'segment', u'segment Documentation',
+     [author], 1)
+]
+
+
+# -- 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, 'segment', u'segment Documentation',
+     author, 'segment', 'One line description of project.',
+     'Miscellaneous'),
+]
+
+
+

segment/doc/conf.py

@@ -0,0 +1,49 @@
+.. sentiment documentation master file, created by
+   sphinx-quickstart on Thu Dec 14 14:42:17 2017.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+基于HMM的中文分词模型的文档
+========================
+
+中文分词模型主要由CORPUS、MODEL、API组成
+
+１.CORPUS
+--------
+
+封装了一套关于语料处理的API,具体内容请看:
+
+.. toctree::
+   :maxdepth: 1
+
+   segment.corpus
+
+
+2.MODEL
+--------
+
+封装了模型的代码,具体内容请看:
+
+.. toctree::
+   :maxdepth: 1
+
+   segment.model
+
+
+3.API
+--------
+
+封装了工程对外提供接口,具体内容请看:
+
+.. toctree::
+   :maxdepth: 1
+
+   segment.api
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

segment/doc/index.rst

@@ -0,0 +1,36 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=.
+set BUILDDIR=_build
+set SPHINXPROJ=segment
+
+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%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS%
+
+:end
+popd

segment/doc/make.bat

@@ -0,0 +1,4 @@
+.. automodule:: segment.api
+    :members:
+    :undoc-members:
+    :show-inheritance: