The avatar for @mbostock
Mike Bostock
Visualization toolmaker. Founder @observablehq. Creator @d3. Former @nytgraphics. Pronounced BOSS-tock.
Published unlisted
Edited
Nov 6, 2019
Fork of Losing My Religion: Using TF-IDF to Analyze a Church in Crisis
Insert cell
Insert cell
Insert cell
tfidf = import("tiny-tfidf")
Insert cell
Insert cell
Insert cell
Insert cell
metadata = d3.csv(
"https://raw.githubusercontent.com/jameshahn2/synod-documents/master/index.csv"
)
Insert cell
Insert cell
popes = metadata.map(d => d.pope);
Insert cell
Insert cell
files = metadata.map(d => `https://raw.githubusercontent.com/jameshahn2/synod-documents/master/writings/${d.filename}`);
Insert cell
writings = Promise
.all(files.map(d => d3.text(d).catch(() => null)))
.then(texts => texts.filter(t => t !== null))
Insert cell
Insert cell
corpus = new tfidf.Corpus(
popes,
writings,
useStopwords,
customStopwords,
K1,
b
)
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
similarity = new tfidf.Similarity(corpus)
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell

Purpose-built for displays of data

Observable is your go-to platform for exploring data and creating expressive data visualizations. Use reactive JavaScript notebooks for prototyping and a collaborative canvas for visual data exploration and dashboard creation.
Learn more