from nltk.corpus import stopwords | |
from nltk.tokenize import word_tokenize | |
import nltk | |
from nltk.stem import WordNetLemmatizer | |
set(stopwords.words('english')) | |
text = """He determined to drop his litigation with the monastry, and relinguish his claims to the wood-cuting and | |
fishery rihgts at once. He was the more ready to do this becuase the rights had become much less valuable, and he had | |
indeed the vaguest idea where the wood and river in question were.""" | |
stop_words = set(stopwords.words('english')) | |
word_tokens = word_tokenize(text) | |
filtered_sentence = [] | |
for w in word_tokens: | |
if w not in stop_words: | |
filtered_sentence.append(w) | |
print(filtered_sentence) | |
lemma_word = [] | |
import nltk | |
from nltk.stem import WordNetLemmatizer | |
wordnet_lemmatizer = WordNetLemmatizer() | |
for w in filtered_sentence: | |
word1 = wordnet_lemmatizer.lemmatize(w, pos = "n") | |
word2 = wordnet_lemmatizer.lemmatize(word1, pos = "v") | |
word3 = wordnet_lemmatizer.lemmatize(word2, pos = ("a")) | |
lemma_word.append(word3) | |
print(lemma_word) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment