Код: Выделить всё
object.routine1().routine2().routine3()
Код: Выделить всё
object.Layer1.routine1().routine2().Layer2.routine3()
Код: Выделить всё
text = "This is an example foo text with some special characters!!!! And some sentences"
pr = TextPreprocessor(text)
processed_text = (
pr.text_level.lower_case()
.sentence_level.split_sentences().remove_special_characters()
.token_level.tokenize()
.text
)
Код: Выделить всё
import re
class TextLevelPreprocessor:
def __init__(self, parent):
self.parent = parent
def lower_case(self):
self.parent.text = self.parent.text.lower()
return self.parent
class SentenceLevelPreprocessor:
def __init__(self, parent):
self.parent = parent
def split_sentences(self):
self.parent.text = self.parent.text.split('. ')
return self.parent
def remove_special_characters(self):
self.parent.text = [re.sub('[!@#$]', '', s) for s in self.parent.text]
return self.parent
class TokenLevelPreprocessor:
def __init__(self, parent):
self.parent = parent
def tokenize(self):
self.parent.text = [t.split() for t in self.parent.text]
return self.parent
class TextPreprocessor:
def __init__(self, text):
self.text = text
self.text_level = TextLevelPreprocessor(self)
self.sentence_level = SentenceLevelPreprocessor(self)
self.token_level = TokenLevelPreprocessor(self)
Код: Выделить всё
pr = TextPreprocessor(text)
processed_text = (
pr.text_level.lower_case()
.sentence_level.split_sentences().
.sentence_level.remove_special_characters()
.token_level.tokenize()
.text
)
Подробнее здесь: https://stackoverflow.com/questions/793 ... -in-python
Мобильная версия