def demo():
from nltk.corpus import toolbox
from itertools import islice
lexicon = toolbox.xml('rotokas.dic')
print 'first field in fourth record:'
print lexicon[3][0].tag
print lexicon[3][0].text
print '\nfields in sequential order:'
for field in islice(lexicon.find('record'), 10):
print field.tag, field.text
print '\nlx fields:'
for field in islice(lexicon.findall('record/lx'), 10):
print field.text
def demo():
from nltk.corpus import toolbox
from itertools import islice
lexicon = toolbox.xml('rotokas.dic')
print 'first field in fourth record:'
print lexicon[3][0].tag
print lexicon[3][0].text
print '\nfields in sequential order:'
for field in islice(lexicon.find('record'), 10):
print field.tag, field.text
print '\nlx fields:'
for field in islice(lexicon.findall('record/lx'), 10):
print field.text
from collections import defaultdict
abbreviate = defaultdict(lambda: 'OTH')
for speaker, _ in top5:
abbreviate[speaker] = speaker[:4]
speaker_seq2 = [abbreviate[speaker] for speaker in speaker_seq]
cfd = nltk.ConditionalFreqDist(nltk.bigrams(speaker_seq2))
cfd.tabulate()
# 11.4.4 使用ElementTree访问Toolbox的数据
from nltk.corpus import toolbox
# 访问lexicon对象的内容的两种方法
# 1） 通过索引
# 索引访问：lexicon[3]返回3号条目（从0开始算起的第4个条目），lexicon[3][0]返回它的第一个字段
lexicon = toolbox.xml('rotokas.dic')
lexicon[3][0]
lexicon[3][0].tag
lexicon[3][0].text
# 2） 通过路径
# 路径访问：'record/lx'的所有匹配，并且访问该元素的文本内容，将其规范化为小写
[lexeme.text.lower() for lexeme in lexicon.findall('record/lx')]
# Toolbox数据是XML格式。
import sys
from nltk.util import elementtree_indent
from xml.etree.ElementTree import ElementTree
elementtree_indent(lexicon)
tree = ElementTree(lexicon[3])
# Natural Language Toolkit: Toolbox Data demonstration
#
# Copyright (C) 2001-2006 NLTK Project
# Author: Greg Aumann <*****@*****.**>
# URL: <http://www.nltk.org/>
# For license information, see LICENSE.TXT
"""
corresponds to
12.3.1 Accessing Toolbox Data
in http://nltk.sourceforge.net/lite/doc/en/data.html
"""
from nltk.corpus import toolbox
lexicon = toolbox.xml('rotokas.dic')
sum_size = num_entries = 0
for entry in lexicon.findall('record'):
num_entries += 1
sum_size += len(entry)
print sum_size/num_entries
from nltk.etree.ElementTree import ElementTree
import sys
fourth_entry = lexicon.findall('record')[3]
tree = ElementTree(fourth_entry)
tree.write(sys.stdout)
# Natural Language Toolkit: Toolbox Data demonstration
#
# Copyright (C) 2001-2006 NLTK Project
# Author: Greg Aumann <*****@*****.**>
# URL: <http://www.nltk.org/>
# For license information, see LICENSE.TXT
"""
corresponds to
12.3.1 Accessing Toolbox Data
in http://nltk.sourceforge.net/lite/doc/en/data.html
"""
from nltk.corpus import toolbox
lexicon = toolbox.xml('rotokas.dic')
lexemes = []
for lexeme in lexicon.findall('record/lx'):
normalised_lexeme = lexeme.text.lower()
lexemes.append(normalised_lexeme)
# list comprehension approach
lexemes2 = [lexeme.text.lower() for lexeme in lexicon.findall('record/lx')]
##if lexemes != lexemes2:
## print 'error two lists not equal'
##else:
## print repr(lexemes)
import re