Engineer on the Shiny team at RStudio. Biostats Ph.D. from Vanderbilt.
make_centroid = (ndim) => {
const low = -spread/2;
const high = spread/2;
const point_gen = d3.randomUniform(low, high);
return () => [...(new Array(ndim))].map(point_gen);
}
gen_centroids = (n, ndim) => {
const center_maker = make_centroid(ndim);
return [...(new Array(n))].map(center_maker)
}
centroids = gen_centroids(number_of_centroids, number_of_dimensions)
sample_from_centroid = (nsamples, centroid, centroid_id) => {
const rnorm = d3.randomNormal(0, sample_std_dev);
const get_sample = () => ({group:centroid_id, location : centroid.map(d => d + rnorm())});
return [...(new Array(nsamples))].map(get_sample);
}
// Generate a bunch of data samples from our array of centroids keeping info on their centroid id with them.
function gen_data_from_centroids(centroids, nsamples){
return centroids.reduce(
(data, d, i) => [...data, ...sample_from_centroid(nsamples, d, i)],
[])
.map((d,i) => (Object.assign({id: i},d,{}))) // add in node id in addition to the centroid one.
}
// generate our data
point_data = gen_data_from_centroids(centroids, number_of_samples)
pairwise_distances = {
const distances = [];
for(let i = 0; i < point_data.length; i++){
for(let j = i; j < point_data.length; j++){
const p1_loc = point_data[i].location;
const p2_loc = point_data[j].location;
const sum_of_square_diffs = p1_loc
.map((d, ind) => Math.pow(d - p2_loc[ind], 2))
.reduce((summed, d) => summed + d, 0);
distances.push({source: i, target: j, value: Math.sqrt(sum_of_square_diffs)})
}
}
// filter out the self links as they are not needed.
return distances.filter(({value}) => value > 0)
}
number_of_dimensions = 10 // dimensionality of our generated data
spread = 25 // width of the distribution determining each centroids location on the dimensions
sample_std_dev = 1 // standard deviation of the normal samples around each centroid
number_of_samples = 25 // how many samples we have per centroid
number_of_centroids = 4 // how many centroids we have
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.