def tokenize_english_document(input_text):
"""
This is a crude tokenizer for input conversations in English.
:param input_text:
:return:
"""
end_list = []
block_tokenizer = BlanklineTokenizer()
sentence_tokenizer = PunktSentenceTokenizer()
word_tokenizer = WhitespaceTokenizer()
# using the 38 characters in one line rule from ITV subtitle guidelines
characters_per_line = 38
lines_per_subtitle = 2
blocks = block_tokenizer.tokenize(input_text)
for block in blocks:
# We have one speaker
sentences = sentence_tokenizer.tokenize(block)
# We have the sentences
for sentence in sentences:
words = word_tokenizer.tokenize(sentence)
reverse_words = words[::-1]
lines = []
current_line = ''
line_full = False
while reverse_words:
word = reverse_words.pop()
longer_line = ' '.join([current_line, word]).strip()
if len(longer_line) > characters_per_line and len(
current_line):
# The longer line is overreaching boundaries
reverse_words.append(word)
line_full = True
elif len(word) >= characters_per_line:
# Very long words
current_line = longer_line
line_full = True
else:
current_line = longer_line
if line_full:
lines.append(current_line)
current_line = ''
line_full = False
if len(lines) >= lines_per_subtitle:
end_list.append(lines)
lines = []
if current_line:
lines.append(current_line)
if lines:
end_list.append(lines)
return end_list
def tokenize_english_document(input_text):
"""
This is a crude tokenizer for input conversations in English.
:param input_text:
:return:
"""
end_list = []
block_tokenizer = BlanklineTokenizer()
sentence_tokenizer = PunktSentenceTokenizer()
word_tokenizer = WhitespaceTokenizer()
# using the 38 characters in one line rule from ITV subtitle guidelines
characters_per_line = 38
lines_per_subtitle = 2
blocks = block_tokenizer.tokenize(input_text)
for block in blocks:
# We have one speaker
sentences = sentence_tokenizer.tokenize(block)
# We have the sentences
for sentence in sentences:
words = word_tokenizer.tokenize(sentence)
reverse_words = words[::-1]
lines = []
current_line = ''
line_full = False
while reverse_words:
word = reverse_words.pop()
longer_line = ' '.join([current_line, word]).strip()
if len(longer_line) > characters_per_line and len(current_line):
# The longer line is overreaching boundaries
reverse_words.append(word)
line_full = True
elif len(word) >= characters_per_line:
# Very long words
current_line = longer_line
line_full = True
else:
current_line = longer_line
if line_full:
lines.append(current_line)
current_line = ''
line_full = False
if len(lines) >= lines_per_subtitle:
end_list.append(lines)
lines = []
if current_line:
lines.append(current_line)
if lines:
end_list.append(lines)
return end_list
def read(self, file_path):
logger.info('Reading instances from file %s', file_path)
reader = TaggedCorpusReader(*os.path.split(file_path),
sep='\t',
word_tokenizer=RegexpTokenizer(r'\n',
gaps=True),
sent_tokenizer=BlanklineTokenizer(),
para_block_reader=lambda s: [s.read()])
return Dataset([
self.text_to_instance(*tuple(zip(*tagged_sent)))
for tagged_sent in reader.tagged_sents()
])
def fun_1_1_5():
import nltk
from nltk.tokenize import RegexpTokenizer
from nltk.tokenize import regexp_tokenize
tokenizer = RegexpTokenizer("[\w]+")
print "RegexpTokenizer:", tokenizer.tokenize(
"Don't hesitate to ask questions")
print "regexp_tokenizer:", regexp_tokenize(
"Don't hesitate to ask questions", pattern="\w+|\$[\d\.]+|\S+")
# 通过空格来执行切分
tokenizer = RegexpTokenizer('\s+', gaps=True)
print "RegexpTokenizer:", tokenizer.tokenize(
"Don't hesitate to ask questions")
# 筛选以大写字母开头的单词
sent = " She secured 90.56 % in class X \n. She is a meritorious student"
capt = RegexpTokenizer('[A-Z]\w+')
print "RegexpTokenizer:", capt.tokenize(sent)
# RegexpTokenizer 的一个子类是如何使用预定义正则表达式的
from nltk.tokenize import BlanklineTokenizer
print "BlanklineTokenizer:", BlanklineTokenizer().tokenize(sent)
# 字符串的切分可以通过空格、间隔、换行等来完成
from nltk.tokenize import WhitespaceTokenizer
print "WhitespaceTokenizer:", WhitespaceTokenizer().tokenize(sent)
# WordPunctTokenizer 使用正则表达式\w+|[^\w\s]+来执行文本的切分,并将其
# 切分为字母与非字母字符
from nltk.tokenize import WordPunctTokenizer
print "WordPunctTokenizer:", WordPunctTokenizer().tokenize(sent)
# 使用 split()方法进行切分
print "split():", sent.split()
print "split(' '):", sent.split(' ')
print "split('\n'):", sent.split('\n')
# 类似于 sent.split('\n')方法,LineTokenizer 通过将文本切分为行来执行切分
from nltk.tokenize import LineTokenizer
print "LineTokenizer:", LineTokenizer().tokenize(sent)
print "LineTokenizer:", LineTokenizer(blanklines='keep').tokenize(sent)
print "LineTokenizer:", LineTokenizer(blanklines='discard').tokenize(sent)
# SpaceTokenizer 与 sent.split('')方法的工作原理类似
from nltk.tokenize import SpaceTokenizer
print "SpaceTokenizer:", SpaceTokenizer().tokenize(sent)
# nltk.tokenize.util 模块通过返回元组形式的序列来执行切分,该序列为标识符
# 在语句中的位置和偏移量
print "标识符序列：", list(WhitespaceTokenizer().span_tokenize(sent))
# 给定一个标识符的序列,则可以返回其跨度序列
from nltk.tokenize.util import spans_to_relative
print "位置和偏移：", list(
spans_to_relative(WhitespaceTokenizer().span_tokenize(sent)))
# 通过在每一个分隔符的连接处进行分割,nltk.tokenize.util.string_span_tokenize(sent,separator)将返回 sent 中标识符的偏移量:
from nltk.tokenize.util import string_span_tokenize
print "标识符序列：", list(string_span_tokenize(sent, " "))
def __init__(
self,
path: str,
encoding: str = 'utf8',
lower: bool = True,
replace_digits: bool = True,
) -> None:
self.__lower = lower
self.__replace_digits = replace_digits
word_tokenizer = RegexpTokenizer(r'\n', gaps=True)
sent_tokenizer = BlanklineTokenizer()
def para_block_reader(stream):
return [stream.read()]
super().__init__(*os.path.split(path),
sep='\t',
word_tokenizer=word_tokenizer,
sent_tokenizer=sent_tokenizer,
para_block_reader=para_block_reader,
encoding=encoding)
class CorpusReader(TaggedCorpusReader):
DIGITS = re.compile(r'\d+')
WORD_TOK = RegexpTokenizer(r'\n', gaps=True)
SENT_TOK = BlanklineTokenizer()
def __init__(
self,
path: str,
encoding: str = 'utf8',
max_sent_len: int = -1,
) -> None:
self.__max_sent_len = max_sent_len
def para_block_reader(stream):
return [stream.read()]
super().__init__(*os.path.split(path),
sep='\t',
word_tokenizer=self.WORD_TOK,
sent_tokenizer=self.SENT_TOK,
para_block_reader=para_block_reader,
encoding=encoding)
def paras(self) -> List[List[List[str]]]:
paras = []
for para in super().paras():
sents = []
for sent in para:
if self.__max_sent_len != -1 and len(
sent) > self.__max_sent_len:
continue
sents.append(sent)
paras.append(sents)
return paras
def sents(self) -> List[List[str]]:
return list(itertools.chain.from_iterable(self.paras()))
def words(self) -> List[str]:
return list(itertools.chain.from_iterable(self.sents()))
def tagged_paras(self) -> List[List[List[Tuple[str, str]]]]:
tagged_paras = []
for tagged_para in super().tagged_paras():
tagged_sents = []
for tagged_sent in tagged_para:
if self.__max_sent_len != -1 and len(
tagged_sent) > self.__max_sent_len:
continue
tagged_sents.append(tagged_sent)
tagged_paras.append(tagged_sents)
return tagged_paras
def tagged_sents(self) -> List[List[Tuple[str, str]]]:
return list(itertools.chain.from_iterable(self.tagged_paras()))
def tagged_words(self) -> List[Tuple[str, str]]:
return list(itertools.chain.from_iterable(self.tagged_sents()))
@classmethod
def to_sents(cls, text: str) -> List[List[str]]:
return [[word for word in cls.WORD_TOK.tokenize(sent)]
for sent in cls.SENT_TOK.tokenize(text)] # yapf: disable
from nltk.tag import brill_trainer
import pickle
# Brill tagger parameters
max_rules = 300
min_score = 3
# Training parameters
development_size = 5110
train = .85
# Read data from development.sdx
data = TaggedCorpusReader('.',
r'.*\.sdx',
sep='|',
sent_tokenizer=BlanklineTokenizer())
# Get the list of tagged sentences
tagged_data = data.tagged_sents()
# Lower words and return as a list
tagged_data_list = [[t for t in sent] for sent in tagged_data]
tagged_data_list = [[(w.lower(), t) for (w, t) in s] for s in tagged_data_list]
## print "Data is read! "
# Randomize training and evaluation set
random.seed(len(tagged_data_list))
random.shuffle(tagged_data_list)
cutoff = int(development_size * train)
def init_line_tokenizer():
global line_tokenizer
if line_tokenizer is None:
line_tokenizer = BlanklineTokenizer()
import nltk sent = " She secured 90.56 % in class X . She is a meritorious student" from nltk.tokenize import BlanklineTokenizer print(BlanklineTokenizer().tokenize(sent))
from nltk.tag import UnigramTagger
from nltk.tag import brill
from nltk.tag import brill_trainer
from nltk.tbl import Template
from nltk.tokenize import BlanklineTokenizer
# Brill tagger parameters
max_rules = 300
min_score = 3
# Training parameters
development_size = 5110
train = .85
# Read data from development.sdx
data = TaggedCorpusReader('.', r'.*\.sdx', sep='|', sent_tokenizer=BlanklineTokenizer(), encoding='ISO-8859-9')
# Get the list of tagged sentences
tagged_data = data.tagged_sents()
# Lower words and return as a list
tagged_data_list = [[t for t in sent] for sent in tagged_data]
tagged_data_list = [[(w.lower(), t) for (w, t) in s] for s in tagged_data_list]
# print "Data is read! "
# Randomize training and evaluation set
random.seed(len(tagged_data_list))
random.shuffle(tagged_data_list)
cutoff = int(development_size * train)
text2 = "This is a breaking news.\n A godzilla has been discovered in Tokyo city."
tokenizer = RegexpTokenizer('[\w]+')
print tokenizer.tokenize(text)
print regexp_tokenize(text, pattern='\w+|\$[\d\.]+\S+')
# Tokenize whitespace
tokenizer = RegexpTokenizer('\s+', gaps=True)
print tokenizer.tokenize(text)
# Select only words starting with capital letters
capt = RegexpTokenizer('[A-Z]\w+')
print capt.tokenize(text2)
print BlanklineTokenizer().tokenize(text2)
print WhitespaceTokenizer().tokenize(text2)
print LineTokenizer(blanklines='keep').tokenize(text2)
print LineTokenizer(blanklines='discard').tokenize(text2)
# SpaceTokenizer works similar to .split('')
print SpaceTokenizer().tokenize(text2)
# Returns the sequence of tuples that are offsets of the tokens
# in a sentence:
print list(WhitespaceTokenizer().span_tokenize(text2))
# Returns the sequence of relative spans
print list(spans_to_relative(WhitespaceTokenizer().span_tokenize(text2)))
# Example 2 # A simple sentence tokenizer. Uses the regular expression '.(s+|$)', # which means, look for a period, followed by a space, # and use that as the delimiter. tokens = nltk.regexp_tokenize(text, pattern=r'\.(\s+|$)', gaps=True) # print(*tokens, sep='\n') # Example 3 # A slightly smarter sentence tokenizer. The regular expression used means # 'Look for a period, exclamation point, question mark, or semicolon, # followed by a space, and use that as the delimiter.' tokens = nltk.regexp_tokenize(text, pattern=r'[\.!?;](\s+|$)', gaps=True) # print(*tokens, sep='\n') # Example 4 # Split text with spaces only, preserving punctuation: tokenizer = RegexpTokenizer(r'\s+', gaps=True) tokens = tokenizer.tokenize(text) # print(*tokens, sep='\n') # Example 5 # Retrieve all capitalized words using a regular expression capword_tokenizer = RegexpTokenizer(r'[A-Z]\w+') tokens = capword_tokenizer.tokenize(text) # print(*tokens, sep='\n') # Example 6 # Example 4: Chunk text by paragraph breaks" tokens = BlanklineTokenizer().tokenize(text) # print(tokens)
import nltk
from nltk.stem import WordNetLemmatizer
nltk.download('popular', quiet=True) # for downloading packages
#Reading in the corpus
with open('Corpus.txt', 'r', encoding='utf8', errors='ignore') as fin:
raw = fin.read().lower()
#nltk.download('punkt') # first-time use only
#nltk.download('wordnet') # first-time use only
#nltk.download('regexptokenizer')
#Tokenisation
#sent_tokens = nltk.sent_tokenize(raw)# converts to list of sentences
sent_tokens = BlanklineTokenizer().tokenize(
raw) # Should convert to text blocks
word_tokens = nltk.word_tokenize(raw) # converts to list of words
# Preprocessing
lemmer = WordNetLemmatizer()
def LemTokens(tokens):
return [lemmer.lemmatize(token) for token in tokens]
remove_punct_dict = dict((ord(punct), None) for punct in string.punctuation)
def LemNormalize(text):
return LemTokens(
def tweet_content():
"""Generate tweet string (140 characters or less)
"""
# with open('basho.txt', 'r') as content_file:
# content = content_file.read()
r = requests.get("http://novicevagabond.com/projects/haiku/basho.txt")
content = r.content
nltk.data.path.append("nltk_data/")
nltk.data.path.append("nltk_data/punkt")
nltk.data.path.append("fizzle_dizzle/")
# nltk.download()
#print content
tokenizer = BlanklineTokenizer()
cleaned_content = content.lower()
corpus = TextBlob(cleaned_content, tokenizer=tokenizer)
haiku = corpus.sentences
#print haiku
bigrams = corpus.ngrams(n=2)
trigrams = corpus.ngrams(n=3)
#print bigrams
dict = {}
for bigram in bigrams:
k = bigram[0]
v = bigram[1]
if k in dict:
if v in dict[k]:
dict[k][v] = dict[k][v] + 1
else:
dict[k][v] = 1
else:
dict[k] = { v : 1}
#print dict
def weighted_choice(map):
choices = []
for k in map:
#print k
for n in range(1, map[k] + 1):
choices.append(k)
#print choices
choice = random.choice(choices)
#print choice
return choice
seed = random.choice(dict.keys())
length = random.randint(11,15)
output = [seed]
#print output
for i in range(length):
output.append(weighted_choice(dict[output[i]]))
whitespace = " "
line1 = whitespace.join(output[0:4])
line2 = whitespace.join(output[4:9])
line3 = whitespace.join(output[9:])
line4 = "-- #markov_basho_haiku"
sep = "\n"
tweet = sep.join([line1, line2, line3, line4]);
# print tweet
return tweet
