Skip to main content

Dependency-parser for Thai language

Project description

Current PyPI packages


Tokenizer, POS-tagger, and dependency-parser for Thai language, working on Universal Dependencies.

Basic Usage

>>> import spacy_thai
>>> nlp=spacy_thai.load()
>>> doc=nlp("แผนกนี้กำลังเผชิญกับความท้าทายใหม่")
>>> for t in doc:
...   print("\t".join([str(t.i+1),t.orth_,t.lemma_,t.pos_,t.tag_,"_",str(0 if t.head==t else t.head.i+1),t.dep_,"_","_" if t.whitespace_ else "SpaceAfter=No"]))
1	แผนก	แผนก	NOUN	NCMN	_	4	nsubj	_	SpaceAfter=No
2	นี้	นี้	DET	DDAC	_	1	det	_	SpaceAfter=No
3	กำลัง	กำลัง	AUX	XVBM	_	4	aux	_	SpaceAfter=No
4	เผชิญ	เผชิญ	VERB	VSTA	_	0	ROOT	_	SpaceAfter=No
5	กับ	กับ	ADP	RPRE	_	6	case	_	SpaceAfter=No
6	ความ	ความ	PART	FIXN	_	4	obl	_	SpaceAfter=No
7	ท้าทาย	ท้าทาย	VERB	VACT	_	6	acl	_	SpaceAfter=No
8	ใหม่	ใหม่	ADV	ADVN	_	7	advmod	_	SpaceAfter=No
>>> import deplacy
>>> deplacy.render(doc,WordRight=True)
 nsubj ╔════════>╔═ NOUN แผนก
   det          > DET  นี้
   aux  ╔════════> AUX  กำลัง
  ROOT ╚═╚═╔═══════ VERB เผชิญ
  case      ╔════> ADP  กับ
   obl     >╚═╔═══ PART ความ
   acl         >╔═ VERB ท้าทาย
advmod           > ADV  ใหม่

Installation for Linux

pip3 install spacy_thai --user

Installation for Cygwin

Make sure to get python37-devel python37-pip python37-numpy python37-cython gcc-g++, and then:

pip3.7 install spacy_thai

Installation for Google Colaboratory

!pip install spacy_thai

Try notebook.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release. See tutorial on generating distribution archives.

Built Distribution

spacy_thai-0.7.3-py3-none-any.whl (6.0 MB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page