I have a list of lists as follows.
mylist = [["the", "and" "fresh milk", "a loaf of bread", "the butter"], ["an apple", "eggs", "oranges", "cup of tea"]]
Now I want to remove the stop words in mylist
, so that my new list would be as follows.
mylist = [["fresh milk", "loaf bread", "butter"], ["apple", "eggs", "oranges", "cup tea"]]
My current code is as follows.
cleaned_mylist= []
stops = ['a', 'an', 'of', 'the']
pattern = re.compile(r'|'.join([r'(\s|\b){}\b'.format(x) for x in stops]))
for item in mylist:
inner_list= []
for words in item:
inner_list.append(pattern.sub('', item).strip())
cleaned_mylist.append(inner_list)
However, the code seems to be not working. Please help me.
You don't need to use regex in this example.
mylist = [["the", "and", "fresh milk", "a loaf of bread", "the butter"], ["an apple", "eggs", "oranges", "cup of tea"]]
expected = [["fresh milk", "loaf bread", "butter"], ["apple", "eggs", "oranges", "cup tea"]]
cleaned_mylist= []
stops = ['a', 'an', 'of', 'the', 'and']
for item in mylist:
inner_list= []
for sentence in item:
out_sentence = []
for word in sentence.split():
if word not in stops:
out_sentence.append(word)
if len(out_sentence) > 0:
inner_list += [' '.join(out_sentence)]
cleaned_mylist.append(inner_list)
print expected == cleaned_mylist
# True
Your pattern is matching with Sublist (item) and not with the words
mylist = [["the", "and","fresh milk", "a loaf of bread", "the butter"], ["an apple", "eggs", "oranges", "cup of tea"]]
cleaned_mylist= []
stops = ['a', 'an', 'of', 'the','and']
pattern = re.compile(r'|'.join([r'(\s|\b){}\b'.format(x) for x in stops]))
for item in mylist:
inner_list= []
for words in item:
if pattern.sub('', words).strip() != '':
inner_list.append(pattern.sub('', words).strip())
cleaned_mylist.append(inner_list)
Use if not
import re
mylist = [["the", "and", "fresh milk", "a loaf of bread", "the butter"], ["an apple", "eggs", "oranges", "cup of tea"]]
cleaned_mylist= []
stops = ['a', 'an', 'of', 'the','and']
pattern = '|'.join([r'\b{}\b\s?'.format(x) for x in stops])
for item in mylist:
inner_list= []
for words in item:
words = re.sub(pattern,'',words)
if(words != ""):
inner_list.append(words)
cleaned_mylist.append(inner_list)
print cleaned_mylist
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.