A node.js module that creates a term vector from tokenized text. Use term-vector when implementing a vector space model
Works with Unicode!
Does ngrams!
const tv = require('term-vector')
// alternatively if you are all fancy and new-fangled:
// import tv from 'term-vector'
const tokens = 'this is really really really cool'.split(' ')
// just make a simple term vector
tv(tokens)
// [
// { term: [ 'cool' ], positions: [ 5 ] },
// { term: [ 'is' ], positions: [ 1 ] },
// { term: [ 'really' ], positions: [ 2, 3, 4 ] },
// { term: [ 'this' ], positions: [ 0 ] }
// ]
// make a term vector with ngrams of length 1 and 2
tv(tokens, { ngramLengths: [ 1, 2 ] })
// [
// { term: [ 'cool' ], positions: [ 5 ] },
// { term: [ 'is' ], positions: [ 1 ] },
// { term: [ 'is', 'really' ], positions: [ 1 ] },
// { term: [ 'really' ], positions: [ 2, 3, 4 ] },
// { term: [ 'really', 'cool' ], positions: [ 4 ] },
// { term: [ 'really', 'really' ], positions: [ 2, 3 ] },
// { term: [ 'this' ], positions: [ 0 ] },
// { term: [ 'this', 'is' ], positions: [ 0 ] }
// ]