Get bigrams and trigrams in word2vec Gensim

Question

I am currently using uni-grams in my word2vec model as follows.

def review_to_sentences( review, tokenizer, remove_stopwords=False ):
    #Returns a list of sent         


        

Answer 1

from gensim.models import Phrases

from gensim.models.phrases import Phraser

documents = 
["the mayor of new york was there", "machine learning can be useful sometimes","new york mayor was present"]

sentence_stream = [doc.split(" ") for doc in documents]
print(sentence_stream)

bigram = Phrases(sentence_stream, min_count=1, threshold=2, delimiter=b' ')

bigram_phraser = Phraser(bigram)


print(bigram_phraser)

for sent in sentence_stream:
    tokens_ = bigram_phraser[sent]

    print(tokens_)