People have already answered pretty nicely for the scenario where you need bigrams or trigrams but if you need everygram for the sentence in that case you can use nltk.util.everygrams
>>> from nltk.util import everygrams>>> message = "who let the dogs out">>> msg_split = message.split()>>> list(everygrams(msg_split))[('who',), ('let',), ('the',), ('dogs',), ('out',), ('who', 'let'), ('let', 'the'), ('the', 'dogs'), ('dogs', 'out'), ('who', 'let', 'the'), ('let', 'the', 'dogs'), ('the', 'dogs', 'out'), ('who', 'let', 'the', 'dogs'), ('let', 'the', 'dogs', 'out'), ('who', 'let', 'the', 'dogs', 'out')]Incase you have a limit like in case of trigrams where the max length should be 3 then you can use max_len param to specify it.
>>> list(everygrams(msg_split, max_len=2))[('who',), ('let',), ('the',), ('dogs',), ('out',), ('who', 'let'), ('let', 'the'), ('the', 'dogs'), ('dogs', 'out')]You can just modify the max_len param to achieve whatever gram i.e four gram, five gram, six or even hundred gram.
The previous mentioned solutions can be modified to implement the above mentioned solution but this solution is much straight forward than that.
For further reading click here
And when you just need a specific gram like bigram or trigram etc you can use the nltk.util.ngrams as mentioned in M.A.Hassan's answer.