update README

Author: bact

README-pypi.md

@@ -10,20 +10,14 @@
 
 PyThaiNLP is a Python library for natural language processing (NLP) of Thai language.
 
-PyThaiNLP features include Thai word and subword segmentations, soundex, romanization, part-of-speech taggers, and spelling corrections.
-
-## What's new in version 1.7 ?
-
-- Deprecate Python 2 support. (Python 2 compatibility code will be completely dropped in PyThaiNLP 1.8)
-- 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 ThaiTransliterator
-- Retrain POS-tagging model
-- Improved word_tokenize (newmm, mm) and dict_word_tokenize
-- Documentation added
+PyThaiNLP includes Thai word tokenizers, transliterators, soundex converters, part-of-speech taggers, and spell checkers.
+
+## What's new in version 1.8 ?
+
+- New NorvigSpellChecker spell checker class, which can be initialized with custom dictionary.
+- Terminate Python 2 support. Remove all Python 2 compatibility code.
+- Remove old, obsolated, deprecated, and experimental code.
+- see [PyThaiNLP 1.8 change log](https://github.com/PyThaiNLP/pythainlp/issues/118)
 
 ## Install
 

README.md

@@ -12,9 +12,9 @@ Thai Natural Language Processing in Python.
 
 PyThaiNLP is a Python package for text processing and linguistic analysis, similar to `nltk` but with focus on Thai language.
 
-PyThaiNLP supports Python 3.4+.
-Since version 1.7, PyThaiNLP deprecates its support for Python 2. The future PyThaiNLP 1.8 will completely drop all supports for Python 2.
-Python 2 users can still use PyThaiNLP 1.6.
+PyThaiNLP 1.8 supports Python 3.6+. Some functions may work with older version of Python 3, but it is not well-tested and will not be supported. See [PyThaiNLP 1.8 change log](https://github.com/PyThaiNLP/pythainlp/issues/118).
+
+Python 2 users can use PyThaiNLP 1.6, our latest released that tested with Python 2.7.
 
 **This is a document for development branch (post 1.7.x). Things will break. For a document for stable branch, see [master](https://github.com/PyThaiNLP/pythainlp/tree/master).**
 

tests/__init__.py

@@ -113,14 +113,18 @@ def test_wordnet(self):
 
         self.assertIsNotNone(wordnet.lemmas("นก"))
         self.assertIsNotNone(wordnet.all_lemma_names(pos=wn.ADV))
-        self.assertIsNotNone(wordnet.lemma('cat.n.01.cat'))
+        self.assertIsNotNone(wordnet.lemma("cat.n.01.cat"))
 
         self.assertEqual(wordnet.morphy("dogs"), "dog")
 
-        bird = wordnet.synset('bird.n.01')
-        mouse = wordnet.synset('mouse.n.01')
-        self.assertEqual(wordnet.path_similarity(bird, mouse), bird.path_similarity(mouse))
-        self.assertEqual(wordnet.wup_similarity(bird, mouse), bird.wup_similarity(mouse))
+        bird = wordnet.synset("bird.n.01")
+        mouse = wordnet.synset("mouse.n.01")
+        self.assertEqual(
+            wordnet.path_similarity(bird, mouse), bird.path_similarity(mouse)
+        )
+        self.assertEqual(
+            wordnet.wup_similarity(bird, mouse), bird.wup_similarity(mouse)
+        )
 
         cat_key = wordnet.synsets("แมว")[0].lemmas()[0].key()
         self.assertIsNotNone(wordnet.lemma_from_key(cat_key))
@@ -542,7 +546,10 @@ def test_thai2vec(self):
         self.assertGreaterEqual(thai2vec.similarity("แบคทีเรีย", "คน"), 0)
         self.assertIsNotNone(thai2vec.sentence_vectorizer(""))
         self.assertIsNotNone(thai2vec.sentence_vectorizer("เสรีภาพในการชุมนุม"))
-        self.assertIsNotNone(thai2vec.sentence_vectorizer("I think therefore I am ผ็ฎ์"))
+        self.assertIsNotNone(
+            thai2vec.sentence_vectorizer("เสรีภาพในการสมาคม", use_mean=True)
+        )
+        self.assertIsNotNone(thai2vec.sentence_vectorizer("I คิด therefore I am ผ็ฎ์"))
         self.assertEqual(
             thai2vec.most_similar_cosmul(["ราชา", "ผู้ชาย"], ["ผู้หญิง"])[0][0],
             "ราชินี",