Public
Edited
Jul 31, 2023
crabs = FileAttachment("fiddlerCrabBodySize.csv").csv({typed: true})
// ^ using typed: true parses the values; otherwise FileAttachment would assume they're all strings
// Access Adélie data here:
adelie = d3.csv("https://portal.edirepository.org/nis/dataviewer?packageid=knb-lter-pal.219.5&entityid=002f3893385f710df69eeebe893144ff", d3.autoType)
// Access chinstrap data here:
chinstrap = d3.csv("https://portal.edirepository.org/nis/dataviewer?packageid=knb-lter-pal.221.8&entityid=fe853aa8f7a59aa84cdd3197619ef462", d3.autoType)
// Make combined version, penguinsCombo, here
// this is like a row-bind? function in R or Python
penguinsCombo = adelie.concat(gentoo, chinstrap)
// Create the wrangled version of penguins here:
penguins = penguinsCombo.map(({
Species: species,
Island: island,
Sex: sex,
"Culmen Length (mm)": bill_length_mm,
"Culmen Depth (mm)": bill_depth_mm,
"Body Mass (g)": body_mass_g,
"Flipper Length (mm)": flipper_length_mm
}) => ({
species: species.split(" ")[0],
island,
sex: sex == null || sex == "." ? null : sex.toLowerCase(),
bill_length_mm,
bill_depth_mm,
body_mass_g,
flipper_length_mm
}))
// penguins = penguinsKeyCopy
import {chart} from "@d3/zoomable-sunburst"
import {aq, op} from "@uwdata/arquero"
// Convert your array of objects to an Arquero table here:
penguinsTable = aq.from(penguins)
penguinsTableView = penguinsTable.view()
// Write Arquero code to perform the steps above here:
penguinsTable
.filter((d) => d.sex == "female")
.select("species", "bill_depth_mm", "bill_length_mm")
.derive({bill_ratio: d => d.bill_length_mm / d.bill_depth_mm})
.groupby("species")
.rollup({mean_bill_ratio: d => op.mean(d.bill_ratio)}) // summarze
.view()
penguins
X
bill_length_mm
Y
bill_depth_mm
Color
species
Size
—
Facet X
—
Facet Y
—
Mark
Auto
Type Chart, then Shift-Enter. Ctrl-space for more options.
Plot.plot({
color: { legend: true },
marks: [
Plot.dot(penguins, {
x: "bill_length_mm",
y: "bill_depth_mm",
fill: "species",
tip: true,
r: "body_mass_g",
opacity: 0.5,
}),
Plot.frame(),
Plot.linearRegressionX({x: "bill_length_mm", y: "bill_depth_mm"})
],
color: {range: ["teal", "darkorange", "orchid" ]},
r: { domain: d3.extent(penguins.map(({body_mass_g}) => body_mass_g)), range: [1, 10]}
})
import {PlotMatrix} with {data} from "@observablehq/autoplot-matrix"
// Make a copy of penguins here, stored as data:
data = penguins
// Make the pairplot with PlotMatrix here:
PlotMatrix(data)
penguins
X
body_mass_g
Y
—
Color
species
Size
—
Facet X
—
Facet Y
species
Mark
Auto
Type Chart, then Shift-Enter. Ctrl-space for more options.
viewof chooseVariable = Inputs.radio(
["bill_depth_mm", "bill_length_mm", "flipper_length_mm", "body_mass_g"],
{ label: "Select one", value: "body_mass_g" }
)
Plot.plot({
color: { legend: true },
marks: [
Plot.frame({ strokeOpacity: 0.1 }),
Plot.rectY(
penguins,
Plot.binX(
{ y: "count" },
{ fy: "species", x: chooseVariable, fill: "species", tip: true }
)
),
Plot.ruleY([0])
]
})
import {scale} from "@chrispahm/hierarchical-clustering"
// Make a subset of penguins with complete cases (filter out values where bill length is null):
penguinsComplete = penguins.filter(({bill_length_mm, sex}) => bill_length_mm !== null) // && sex == "female")
// Create a scaled version of the values (non-numeric will be NaN, which is fine..):
penguinsScale = scale(penguinsComplete )
// Convert the array of objects to an array of arrays:
penguinsArray = penguinsScale.map(
({bill_length_mm, bill_depth_mm, body_mass_g, flipper_length_mm}) => [
bill_length_mm, bill_depth_mm, body_mass_g, flipper_length_mm
]
)
// Use ml.js KMeans() method to perform k-means clustering for k centroids:
penguinsClusters = ML.KMeans(penguinsArray, 3)
penguinsClusters.clusters
penguinsKmeans = penguinsComplete.map((d, i) => ({...d, clusterNo: penguinsClusters.clusters[i]}))
penguinsKmeans
Type Table, then Shift-Enter. Ctrl-space for more options.
kmeanschart = Plot.plot({
marks: [
Plot.text(penguinsKmeans, {
x: "body_mass_g",
y: "flipper_length_mm",
text: "clusterNo",
fontSize: "15px",
fontWeight: "500",
fill: "species",
tip: true
})
],
color: {legend: true}
})
clusterCounts = d3.rollup(penguinsKmeans, ({length}) => length, ({species}) => species, ({clusterNo}) => clusterNo)
ML = require("https://www.lactame.com/lib/ml/6.0.0/ml.min.js")
import {penguinsKeyCopy} from "@observablehq/ds-workflows-in-js-session-2-key"
noUse = FileAttachment("fiddlerCrabBodySize.csv") // Note: this is only added here so that the file is attached in the forked version
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.
