With NLTK version 3.1 and Stanford NER tool 2015-12-09, it is possible to hack the StanfordNERTagger._stanford_jar to include other .jar files that are necessary for the new tagger.
First set up the environment variables as per instructed at https://github.com/nltk/nltk/wiki/Installing-Third-Party-Software
| sudo apt-get upgrade | |
| sudo apt-get update | |
| sudo pip install jupyter notebook | |
| jupyter notebook --generate-config | |
| ipython | |
| from notebook.auth import passwd | |
| passwd() |
| import csv | |
| import os | |
| def get_csv_writer(filename, rows, delimiter): | |
| with open(filename, 'w') as csvfile: | |
| fieldnames = rows[0].keys() | |
| writer = csv.DictWriter(csvfile, fieldnames=fieldnames, delimiter=delimiter) | |
| writer.writeheader() | |
| for row in rows: | |
| try: |
| from __future__ import absolute_import | |
| from __future__ import division | |
| from __future__ import print_function |
| import json | |
| import requests | |
| def tokenize_dparser(text): | |
| dparser_link = 'http://parser.datanada.com/parse?version=1&string=' | |
| url = dparser_link+text | |
| response = requests.get(url) |
| # -*- coding: utf-8 -*- | |
| class Hangul: | |
| BASE_CODE = 44032 | |
| CHOSUNG = 588 | |
| JUNGSUNG = 28 | |
| # 초성 리스트. 00 ~ 18 | |
| CHOSUNG_LIST = [ | |
| 'ㄱ', 'ㄲ', 'ㄴ', 'ㄷ', 'ㄸ', 'ㄹ', 'ㅁ', 'ㅂ', 'ㅃ', |
| import math | |
| def convertSize(size): | |
| """ | |
| Return filesize (in Bytes) in human-readable format | |
| """ | |
| if (size == 0): | |
| return '0B' | |
| units = ("B", "KB", "MB", "GB", "TB", "PB", "EB", "ZB", "YB") | |
| i = int(math.floor(math.log(size,1024))) |
| ZSH=$HOME/.zsh | |
| HISTFILE=$HOME/.history | |
| HISTSIZE=10000 | |
| SAVEHIST=10000 | |
| export TERM=xterm-256color | |
| export LANG=en_US.UTF-8 | |
| # added by Anaconda3 4.1.1 installer | |
| export PATH=$HOME/anaconda3/bin:$PATH |