Merge pull request #1 from PyThaiNLP/dev

Merge from PyThaiNLP project

.circleci/config.yml

@@ -1,51 +1,33 @@
-# Python CircleCI 2.0 configuration file
-#
-# Check https://circleci.com/docs/2.0/language-python/ for more details
-#
 version: 2
 jobs:
   build:
     docker:
-      # specify the version you desire here
-      # use `-browsers` prefix for selenium tests, e.g. `3.6.1-browsers`
       - image: circleci/python:3.6.1
-
-      # Specify service dependencies here if necessary
-      # CircleCI maintains a library of pre-built images
-      # documented at https://circleci.com/docs/2.0/circleci-images/
-      # - image: circleci/postgres:9.4
-
-    working_directory: ~/repo
-
+    working_directory: ~/pythainlp
     steps:
       - checkout
-
-      # Download and cache dependencies
       - restore_cache:
           keys:
-          - v1-dependencies-{{ checksum "requirements.txt" }}
-          # fallback to using the latest cache if no exact match is found
+          - v1-dependencies-{{ .Branch }}-{{ checksum "requirements.txt" }}
           - v1-dependencies-
-
       - run:
-          name: install dependencies
+          name: Install Dependencies
           command: |
             python3 -m venv venv
             . venv/bin/activate
             pip install -r requirements.txt
-
       - save_cache:
           paths:
             - ./venv
-          key: v1-dependencies-{{ checksum "requirements.txt" }}
-
-      # run tests!
+          key: v1-dependencies-{{ .Branch }}-{{ checksum "requirements.txt" }}
       - run:
-          name: run tests
+          name: Run Static Analysis
           command: |
             . venv/bin/activate
-            python manage.py test
-
-      - store_artifacts:
-          path: test-reports
-          destination: test-reports
+            pip install flake8
+            make lint
+      - run:
+          name: Run Tests
+          command: |
+            . venv/bin/activate
+            make test

.gitignore

@@ -9,6 +9,7 @@ __pycache__/
 # Distribution / packaging
 .Python
 env/
+venv/
 build/
 develop-eggs/
 dist/

CONTRIBUTING.md

@@ -1,6 +1,6 @@
 # Contributing to PyThaiNLP
 
-Hi! Thanks for your interest in contributing to [PyThaiNLP](https://github.com/wannaphongcom/pythainlp).
+Hi! Thanks for your interest in contributing to [PyThaiNLP](https://github.com/PyThaiNLP/pythainlp).
 In this document we'll try to summarize everything that you need to know to
 do a good job.
 
@@ -38,13 +38,8 @@ branches.
 - Try to write both Python 2 and Python3-friendly code so won't be a pain for
   us to support both versions.
 
-## Code Guidelines
-
-- Use [PEP8](http://www.python.org/dev/peps/pep-0008/);
-- Write tests for your new features (please see "Tests" topic below);
-
 # Discussion
 
-https://www.facebook.com/groups/1997970287091118/ and https://github.com/wannaphongcom/pythainlp/issues
+https://www.facebook.com/groups/thainlp and https://github.com/wannaphongcom/pythainlp/issues
 
 Happy hacking! (;

README-pythainlp.md

@@ -0,0 +1,43 @@
+![PyThaiNLP Logo](https://avatars0.githubusercontent.com/u/32934255?s=200&v=4)
+
+# PyThaiNLP 1.7
+
+[![Codacy Badge](https://api.codacy.com/project/badge/Grade/cb946260c87a4cc5905ca608704406f7)](https://www.codacy.com/app/pythainlp/pythainlp_2?utm_source=github.com&utm_medium=referral&utm_content=PyThaiNLP/pythainlp&utm_campaign=Badge_Grade)[![pypi](https://img.shields.io/pypi/v/pythainlp.svg)](https://pypi.python.org/pypi/pythainlp)
+[![Build Status](https://travis-ci.org/PyThaiNLP/pythainlp.svg?branch=develop)](https://travis-ci.org/PyThaiNLP/pythainlp)
+[![Build status](https://ci.appveyor.com/api/projects/status/9g3mfcwchi8em40x?svg=true)](https://ci.appveyor.com/project/wannaphongcom/pythainlp-9y1ch)
+[![Coverage Status](https://coveralls.io/repos/github/PyThaiNLP/pythainlp/badge.svg?branch=dev)](https://coveralls.io/github/PyThaiNLP/pythainlp?branch=dev)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+
+
+
+PyThaiNLP is a Python library for natural language processing (NLP) of Thai language.
+
+## What's new in PyThaiNLP 1.7 ?
+
+- Deprecate Python 2 support
+- Refactor pythainlp.tokenize.pyicu for readability
+- Add Thai NER model to pythainlp.ner
+- thai2vec v0.2 - larger vocab, benchmarking results on Wongnai dataset
+- Sentiment classifier based on ULMFit and various product review datasets
+- Add ULMFit utility to PyThaiNLP
+- Add Thai romanization model thai2rom
+- Retrain POS-tagging model
+- Improve word tokenize (newmm,mm) and dict_word_tokenize
+- Documentation added
+
+## Install
+
+```
+pip install pythainlp
+```
+
+**Note for Windows**: marisa-trie wheels can be obtained from https://www.lfd.uci.edu/~gohlke/pythonlibs/#marisa-trie , then install it with pip, for example: `pip install marisa_trie‑0.7.5‑cp36‑cp36m‑win32.whl`
+
+
+
+Docs : https://thainlp.org/pythainlp/docs/1.7/ 
+
+GitHub : https://github.com/PyThaiNLP/pythainlp
+
+Issues : https://github.com/PyThaiNLP/pythainlp/issues
+

README.md

@@ -1,11 +1,15 @@
-![PyThaiNLP Logo](https://avatars0.githubusercontent.com/u/32934255?s=200&v=4)
+
+<p align="center">
+  <img src="https://avatars0.githubusercontent.com/u/32934255?s=200&v=4">
+</p>
 
 # PyThaiNLP
 
 [![Codacy Badge](https://api.codacy.com/project/badge/Grade/cb946260c87a4cc5905ca608704406f7)](https://www.codacy.com/app/pythainlp/pythainlp_2?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=PyThaiNLP/pythainlp&amp;utm_campaign=Badge_Grade)[![pypi](https://img.shields.io/pypi/v/pythainlp.svg)](https://pypi.python.org/pypi/pythainlp)
 [![Build Status](https://travis-ci.org/PyThaiNLP/pythainlp.svg?branch=develop)](https://travis-ci.org/PyThaiNLP/pythainlp)
 [![Build status](https://ci.appveyor.com/api/projects/status/9g3mfcwchi8em40x?svg=true)](https://ci.appveyor.com/project/wannaphongcom/pythainlp-9y1ch)
 [![Coverage Status](https://coveralls.io/repos/github/PyThaiNLP/pythainlp/badge.svg?branch=dev)](https://coveralls.io/github/PyThaiNLP/pythainlp?branch=dev)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
 
 Thai natural language processing in Python.
 
@@ -38,7 +42,7 @@ $ pip install pythainlp
 
 ### Documentation
 
-Read on [https://github.com/PyThaiNLP/pythainlp/tree/dev/docs](https://github.com/PyThaiNLP/pythainlp/tree/dev/docs)
+Read on [https://thainlp.org/pythainlp/docs/1.7/](https://thainlp.org/pythainlp/docs/1.7/)
 
 ### License
 
@@ -89,7 +93,7 @@ $ pip install https://github.com/PyThaiNLP/pythainlp/archive/dev.zip
 
 ### เอกสารการใช้งาน
 
-อ่านได้ที่  [https://github.com/PyThaiNLP/pythainlp/tree/dev/docs](https://github.com/PyThaiNLP/pythainlp/tree/dev/docs)
+อ่านได้ที่  [https://thainlp.org/pythainlp/docs/1.7/](https://thainlp.org/pythainlp/docs/1.7/)
 
 ### License
 

docs/_build/html/.buildinfo

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: d10d70373c4606c2e550783653de1080
+config: 5300c0d48fad8e89843f69ff64431cfa
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/_build/html/_modules/index.html

@@ -8,7 +8,7 @@
 
   <meta name="viewport" content="width=device-width, initial-scale=1.0">
 
-  <title>Overview: module code &mdash; PyThaiNLP 20180622 documentation</title>
+  <title>Overview: module code &mdash; PyThaiNLP 1.7 documentation</title>
 
 
 
@@ -83,13 +83,19 @@
 </ul>
 <p class="caption"><span class="caption-text">Package reference:</span></p>
 <ul>
-<li class="toctree-l1"><a class="reference internal" href="../api/collation.html">pythainlp.tokenize</a></li>
-<li class="toctree-l1"><a class="reference internal" href="../api/date.html">pythainlp.tokenize</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../api/change.html">pythainlp.change</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../api/collation.html">pythainlp.collation</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../api/date.html">pythainlp.date</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../api/ner.html">pythainlp.ner</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../api/number.html">pythainlp.number</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../api/romanization.html">pythainlp.romanization</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../api/sentiment.html">pythainlp.sentiment</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../api/soundex.html">pythainlp.soundex</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../api/spell.html">pythainlp.spell</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../api/summarize.html">pythainlp.summarize</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../api/tag.html">pythainlp.tag</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../api/tokenizer.html">pythainlp.tokenize</a></li>
+<li class="toctree-l1"><a class="reference internal" href="../api/ulmfit.html">pythainlp.ulmfit</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../api/word_vector.html">pythainlp.word_vector</a></li>
 </ul>
 
@@ -152,13 +158,20 @@
            <div itemprop="articleBody">
 
   <h1>All modules for which code is available</h1>
-<ul><li><a href="pythainlp/collation.html">pythainlp.collation</a></li>
+<ul><li><a href="pythainlp/change.html">pythainlp.change</a></li>
+<li><a href="pythainlp/collation.html">pythainlp.collation</a></li>
 <li><a href="pythainlp/date.html">pythainlp.date</a></li>
+<li><a href="pythainlp/ner.html">pythainlp.ner</a></li>
 <li><a href="pythainlp/number.html">pythainlp.number</a></li>
 <li><a href="pythainlp/romanization.html">pythainlp.romanization</a></li>
+<ul><li><a href="pythainlp/romanization/thai2rom.html">pythainlp.romanization.thai2rom</a></li>
+</ul><li><a href="pythainlp/sentiment.html">pythainlp.sentiment</a></li>
+<li><a href="pythainlp/soundex.html">pythainlp.soundex</a></li>
 <li><a href="pythainlp/spell.html">pythainlp.spell</a></li>
+<li><a href="pythainlp/summarize.html">pythainlp.summarize</a></li>
 <li><a href="pythainlp/tag.html">pythainlp.tag</a></li>
 <li><a href="pythainlp/tokenize.html">pythainlp.tokenize</a></li>
+<li><a href="pythainlp/ulmfit/utils.html">pythainlp.ulmfit.utils</a></li>
 <li><a href="pythainlp/word_vector/thai2vec.html">pythainlp.word_vector.thai2vec</a></li>
 </ul>
 
@@ -172,7 +185,7 @@ <h1>All modules for which code is available</h1>
 
   <div role="contentinfo">
     <p>
-        &copy; Copyright 2018-2018, PyThaiNLP (GPL license).
+        &copy; Copyright 2017-2018, PyThaiNLP (Apache Software License 2.0).
 
     </p>
   </div>
@@ -194,7 +207,7 @@ <h1>All modules for which code is available</h1>
     <script type="text/javascript">
         var DOCUMENTATION_OPTIONS = {
             URL_ROOT:'../',
-            VERSION:'20180622',
+            VERSION:'1.7',
             LANGUAGE:'None',
             COLLAPSE_INDEX:false,
             FILE_SUFFIX:'.html',