import spacy
# from terminal
python -m spacy download en_core_web_lg # or some other model
nlp = spacy.load("en_core_web_lg")
stop_words = nlp.Defaults.stop_wordsfrom spacy.lang.fr.stop_words import STOP_WORDS as fr_stop
from spacy.lang.en.stop_words import STOP_WORDS as en_stop
final_stopwords_list = list(fr_stop) + list(en_stop)
tfidf_vectorizer = TfidfVectorizer(max_df=0.8, max_features=200000, min_df=0.2, stop_words=final_stopwords_list, use_idf=True, tokenizer=tokenize_and_stem, ngram_range(1,3))
from nltk.corpus import stopwords
final_stopwords_list = stopwords.words('english') + stopwords.words('french')
tfidf_vectorizer = TfidfVectorizer(max_df=0.8, max_features=200000, min_df=0.2, stop_words=final_stopwords_list, use_idf=True, tokenizer=tokenize_and_stem, ngram_range(1,3))