How to iterate each word through nltk synsets and

问题:

I am trying to take a text file with messages and iterate each word through NLTK wordnet synset function. I want to do this because I want to create a list of mispelled words. For example if I do:

wn.synsets('dog')

I get output:

[Synset('dog.n.01'),
 Synset('frump.n.01'),
 Synset('dog.n.03'),
 Synset('cad.n.01'),
 Synset('frank.n.02'),
 Synset('pawl.n.01'),
 Synset('andiron.n.01'),
 Synset('chase.v.01')]

now if the word is mispelled like so:

wn.synsets('doeg')

I get output:

[]

If I am returned an empty list I want to save the misspelled word in another list like so and while continuing to iterate through rest of the file:

mispelled_words = ['doeg']

I am at a loss how to do this, here is my code below, I would need to do the iterating after variable "chat_message_tokenize". The name path is words I want to drop:

import nltk
import csv
from nltk.tag import pos_tag
from nltk.corpus import wordnet as wn
from nltk.stem.snowball import SnowballStemmer


def text_function():
    #nltk.download('punkt')
    #nltk.download('averaged_perceptron_tagger')

    # Read in chat messages and names files
    chat_path = 'filepath.csv'
    try:
        with open(chat_path) as infile:
            chat_messages = infile.read()
    except Exception as error:
        print(error)
        return

    name_path = 'filepath.txt'
    try:
        with open(names_path) as infile:
            names = infile.read()
    except Exception as error:
        print(error)
        return

    chat_messages = chat_messages.split('Chats:')[1].strip()
    names = names.split('Name:')[1].strip().lower()

    chat_messages_tokenized = nltk.word_tokenize(chat_messages)
    names_tokenized = nltk.word_tokenize(names)

    # adding part of speech(pos) tag and dropping proper nouns
    pos_drop = pos_tag(chat_messages_tokenized)
    chat_messages_tokenized = [SnowballStemmer('english').stem(word.lower()) for word, pos in pos_drop if pos != 'NNP' and word not in names_tokenized]

    for chat_messages_tokenized 

    if not wn.synset(chat_messages_tokenized):
        print('empty list')

if __name__ == '__main__':
    text_function()    

#    for s in wn.synsets('dog'):
#          lemmas = s.lemmas()
#    for l in lemmas:
#          if l.name() == stemmer:
#              print (l.synset())


    csv_path ='OutputFilePath.csv'
    try:
        with open(csv_path, 'w') as outfile:
            writer = csv.writer(outfile)
            for word in chat_messages_tokenized:
                writer.writerow([word])
    except Exception as error:
        print(error)
        return


if __name__ == '__main__':
    text_function()

Thank you in advance.

回答1:

You already have the pseudocode in your explanation, you can just code it as you have explained, as follows:

misspelled_words = []                 # The list to store misspelled words
for word in chat_messages_tokenized:  # loop through each word
    if not wn.synset(word):           # if there is no synset for this word
        misspelled_words.append(word) # add it to misspelled word list

print(misspelled_words)