Researcher in Machine learning, Data Mining, Social Science, and Natural Language Processing
Programming languages: Python, Java, and Java Script
Published
Edited
Dec 11, 2020
md`# Tokenize text and generate n-grams`
viewof data = form(html`<form>
<div>
<label><input name="min_n" type="text" value=2> <i>min_n</i></label>
<label><input name="max_n" type="text" value=3> <i>max_n</i></label>
</div>
<div>
<textarea name="text" cols=100>This is a great work @jack wow.</textarea>
</div>
</form>`)
data
Array.from(new Set(ngrams));
ngrams = tokenize("This is a great work @jack wow");
Array.from({length:max_n-min_n+1},(v,k)=>k+min_n)
function get_ngrams(chunks, max_n=3, min_n=2){
const nvalues = Array.from({length:max_n-min_n+1},(v,k)=>k+min_n)
const ngrams = chunks.flatMap(chunk => {
const ng = chunk.flatMap((x,i) => {
return nvalues
.filter((j) => (i+j < chunk.length))
.map((j) => {
return chunk.slice(i, j+i)
.map(x => x.toString()).join(" ").toLowerCase()
});
});
return ng;
});
return ngrams;
}
function tokenize(text) {
let tokens = [
...text.matchAll(
/(?<url>[\w]+:\/\/[\S]+)|(?<mention>@\w+)|(?<word>[\w]+)|(?<space>[\s\n]+)|(?<noword>((?!\s)[\W])+)/g
)
];
tokens = tokens.map(({input, ...t}) => {
return { ...t, end_index: t.index + t[0].length };
});
tokens = tokens.filter(t => !t.groups.space)
const chunks = get_chunks(tokens);
const ngrams = get_ngrams(chunks, max_n, min_n);
return Array.from(new Set(ngrams));
}
import {form} from "@mbostock/form-input"
One platform to build and deploy the best data apps
Experiment and prototype by building visualizations in live JavaScript notebooks. Collaborate with your team and decide which concepts to build out.
Use Observable Framework to build data apps locally. Use data loaders to build in any language or library, including Python, SQL, and R.
Seamlessly deploy to Observable. Test before you ship, use automatic deploy-on-commit, and ensure your projects are always up-to-date.