Data graphics developer at Gapminder. Teacher at DIS Stockholm. Escaping flatland one chart at a time.
marCasadoAir = FileAttachment("marCasadoAir@5.csv").csv({typed: true}) // Date issue
marCasadoSea = FileAttachment("marCasadoSea@4.csv").csv({typed: true}) // Date issue
// Write code to create a database called marCasadoDB, with tables 'air' and 'sea':
marCasadoDB = DuckDBClient.of({air: marCasadoAir, sea: marCasadoSea})
marCasadoDB
// Write Plot code to create a heatmap of sea surface temperature (SST) by year and month, starting from the 'cell' snippet:
marCasado
Plot.plot({
y: {tickFormat: "Y", padding: 0},
x: {tickFormat: Plot.formatMonth(), padding: 0},
marks: [
Plot.cell(marCasado, {
x: d => d.month.getUTCMonth(),
y: d => d.month.getUTCFullYear(),
fill: "SST",
tip: true
})
]
})
import {PlotMatrix} with {marCasado as data} from "@observablehq/autoplot-matrix"
// Use the PlotMatrix function (expecting marCasado) to create a pair plot:
PlotMatrix(marCasado)
ML = require("https://www.lactame.com/lib/ml/6.0.0/ml.min.js")
import {scale, asMatrix} from "@chrispahm/hierarchical-clustering"
// Create a scaled version of the numeric variables
marCasadoScaled = scale(marCasado.map(({season, month, ...rest}) => rest))
// Convert to an array of arrays, just containing the values (no keys):
marCasadoArray = marCasadoScaled.map(Object.values)
// Perform principal component analysis:
marCasadoPCA = new ML.PCA(marCasadoArray)
// Get variance explained by each PC:
marCasadoPCA.getExplainedVariance()
Plot.plot({
marks: [
Plot.barY( marCasadoPCA.getExplainedVariance(), {x: (d,i) => i, y: d => d }),
Plot.ruleY([0])
]
})
// Get cumulative variance explained:
marCasadoPCA.getCumulativeVariance()
Plot.plot({
marks: [
Plot.barY( marCasadoPCA.getCumulativeVariance(), {x: (d,i) => i, y: d => d }),
Plot.ruleY([0])
]
})
// Import viewof loadings from the notebook, with marCasadoScaled as food_scaled:
import {viewof loadings} with {marCasadoScaled as food_scaled} from "@chrispahm/principal-component-analysis"
// Look at viewof loadings:
viewof loadings
// import viewof scores from the notebook, with marCasadoScaled as food_scaled and marCasado as food:
import {viewof scores} with {marCasadoScaled as food_scaled, marCasado as food} from "@chrispahm/principal-component-analysis"
// Look at viewof scores:
viewof scores
// Do some wrangling to get the month and season alongside scores:
scoresCombined = scores.map((d, i) => ({month: marCasado[i].month, season: marCasado[i].season, ...d}))
scoresCombined
X
PC1
Y
PC2
Color
season
Size
—
Facet X
—
Facet Y
—
Mark
Auto
Type Chart, then Shift-Enter. Ctrl-space for more options.
chart = Plot.plot({
color: { legend: true },
marks: [
Plot.dot(scoresCombined, {
x: "PC1",
y: "PC2",
stroke: "season",
tip: true
}),
Plot.arrow(loadings, {x1: 0, x2: (d) => d.PC1 * scalingFactor, y1: 0, y2: (d) => d.PC2 * scalingFactor}),
Plot.text(loadings, {x: d => d.PC1 * scalingFactor * 1.1, y: d => d.PC2 * scalingFactor * 1.1, text: "Variable"})
]
})
scalingFactor = 5;
Plot.plot({
marks: [
Plot.density(scoresCombined, { x: "PC1", y: "PC2", stroke: "season" })
]
})
// Create a PCA biplot with the scores and loadings
import {PlotMatrix as PM} with {scoresCombined as data} from "@observablehq/autoplot-matrix"
PM(scoresCombined)
// Alternatively (without an import):
// loadingsOption = marCasadoPCA
// .getEigenvectors()
// .data.map((d, i) => ({
// PC1: d[0],
// PC2: d[1],
// Variable: Object.keys(marCasadoScaled[0])[i]
// }))
// Alternatively to get score (projections into PC space):
// scoresOption = marCasadoPCA.predict(marCasadoArray).data.map((d,i) => ({month: marCasado[i].month,
// season: marCasado[i].season,
// PC1: d[0],
// PC2: d[1]}))
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.
