# linux, run the script:
    pip install deepnlp

    # linux, run the script:
    tar zxvf deepnlp-0.1.7.tar.gz
    cd deepnlp-0.1.7
    python setup.py install

    # install crf++0.58 package using the script
    sh ./deepnlp/segment/install_crfpp.sh
    # download all the pre-trained models
    python ./test/test_install.py

    # ./deepnlp/test folder
    cd test
    python test_segment.py    # segmentation
    python test_pos_en.py       # POS tag
    python test_ner_zh.py       # NER Zh
    python test_ner_domain.py   # NER domain-specific models
    python test_ner_dict_udf.py # NER load user dict and UDF for disambiguation
    python test_nn_parser.py    # dependency parsing
    python test_api_v1_module.py
    python test_api_v1_pipeline.py

#coding=utf-8
from __future__ import unicode_literals # compatible with python3 unicode

import deepnlp
# Download all the modules
deepnlp.download()

# Download specific module
deepnlp.download('segment')
deepnlp.download('pos')
deepnlp.download('ner')
deepnlp.download('parse')

# Download module and domain-specific model
deepnlp.download(module = 'pos', name = 'en') 
deepnlp.download(module = 'ner', name = 'zh_entertainment')

#coding=utf-8
from __future__ import unicode_literals
from deepnlp import segmenter

tokenizer = segmenter.load_model(name = 'zh_entertainment')
text = "我刚刚在浙江卫视看了电视剧老九门，觉得陈伟霆很帅"
segList = tokenizer.seg(text)
text_seg = " ".join(segList)

#Results
# 我 刚刚 在 浙江卫视 看 了 电视剧 老九门 ， 觉得 陈伟霆 很 帅

#coding:utf-8
from __future__ import unicode_literals

import deepnlp
deepnlp.download('pos')

## English Model
from deepnlp import pos_tagger
tagger = pos_tagger.load_model(name = 'en')  # Loading English model, lang code 'en', English Model Brown Corpus

text = "I want to see a funny movie"
words = text.split(" ")     # unicode
print (" ".join(words))

tagging = tagger.predict(words)
for (w,t) in tagging:
    pair = w + "/" + t
    print (pair)
    
#Results
#I/nn want/vb to/to see/vb a/at funny/jj movie/nn

## Chinese Model
from deepnlp import segmenter
from deepnlp import pos_tagger
tagger = pos_tagger.load_model(name = 'zh') # Loading Chinese model, lang code 'zh', China Daily Corpus

text = "我爱吃北京烤鸭"
words = segmenter.seg(text) # words in unicode coding
print (" ".join(words))

tagging = tagger.predict(words)  # input: unicode coding
for (w,t) in tagging:
    pair = w + "/" + t
    print (pair)

#Results
#我/r 爱/v 吃/v 北京/ns 烤鸭/n

from __future__ import unicode_literals   # compatible with python3 unicode

import deepnlp
deepnlp.download('ner')  # download the NER pretrained models from github if installed from pip

from deepnlp import ner_tagger

# Example: Entertainment Model
tagger = ner_tagger.load_model(name = 'zh_entertainment')   # Base LSTM Based Model
#Load Entertainment Dict
tagger.load_dict("zh_entertainment")
text = "你 最近 在 看 胡歌 演的 猎场 吗 ?"
words = text.split(" ")
tagset_entertainment = ['actor', 'role_name', 'teleplay', 'teleplay_tag']
tagging = tagger.predict(words, tagset = tagset_entertainment)
for (w,t) in tagging:
    pair = w + "/" + t
    print (pair)

#Result
#你/nt
#最近/nt
#在/nt
#看/nt
#胡歌/actor
#演的/nt
#猎场/teleplay
#吗/nt
#?/nt

from __future__ import unicode_literals # compatible with python3 unicode coding

from deepnlp import nn_parser
parser = nn_parser.load_model(name = 'zh')

#Example 1, Input Words and Tags Both
words = ['它', '熟悉', '一个', '民族', '的', '历史']
tags = ['r', 'v', 'm', 'n', 'u', 'n']

#Parsing
dep_tree = parser.predict(words, tags)

#Fetch result from Transition Namedtuple
num_token = dep_tree.count()
print ("id\tword\tpos\thead\tlabel")
for i in range(num_token):
    cur_id = int(dep_tree.tree[i+1].id)
    cur_form = str(dep_tree.tree[i+1].form)
    cur_pos = str(dep_tree.tree[i+1].pos)
    cur_head = str(dep_tree.tree[i+1].head)
    cur_label = str(dep_tree.tree[i+1].deprel)
    print ("%d\t%s\t%s\t%s\t%s" % (cur_id, cur_form, cur_pos, cur_head, cur_label))

# Result
id	word	pos	head	label
1	它	r	2	SBV
2	熟悉	v	0	HED
3	一个	m	4	QUN
4	民族	n	5	DE
5	的	u	6	ATT
6	历史	n	2	VOB

#coding:utf-8
from __future__ import unicode_literals

from deepnlp import pipeline
p = pipeline.load_model('zh')

#Segmentation
text = "我爱吃北京烤鸭"
res = p.analyze(text)

print (res[0].encode('utf-8'))
print (res[1].encode('utf-8'))
print (res[2].encode('utf-8'))

words = p.segment(text)
pos_tagging = p.tag_pos(words)
ner_tagging = p.tag_ner(words)

print (pos_tagging.encode('utf-8'))
print (ner_tagging.encode('utf-8'))

#coding:utf-8
from __future__ import unicode_literals

import json, requests, sys, os
if (sys.version_info>(3,0)): from urllib.parse import quote 
else : from urllib import quote

from deepnlp import api_service
login = api_service.init()          # registration, if failed, load default empty login {} with limited access
conn = api_service.connect(login)   # save the connection with login cookies

# Sample URL
# http://www.deepnlp.org/api/v1.0/pipeline/?lang=zh&annotators=segment,pos,ner&text=我爱吃上海小笼包

# Define text and language
text = ("我爱吃上海小笼包").encode("utf-8")  # convert text from unicode to utf-8 bytes

# Set up URL for POS tagging
url_pos = 'http://www.deepnlp.org/api/v1.0/pos/?"+ "lang=" + quote('zh') + "&text=" + quote(text)
web = requests.get(url_pos, cookies = conn)
tuples = json.loads(web.text)
print (tuples['pos_str'].encode('utf-8'))    # POS json {'pos_str', 'w1/t1 w2/t2'} return string

    pip install deepnlp

    # linux, run the script:
    tar zxvf deepnlp-0.1.7.tar.gz
    cd deepnlp-0.1.7
    python setup.py install

    # 运行脚本安装 crf++0.58 包
    sh ./deepnlp/segment/install_crfpp.sh
    # 运行脚本下载预训练模型测试
    python ./test/test_install.py