Retired Computer Scientist: SRI-ARC (Engelbart),
Xerox PARC, Xerox SDS, Electronic Arts, SGI, Google, Box
Public
Edited
Jul 25, 2023
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
Type SQL, then Shift-Enter. Ctrl-space for more options.
marCasadoDB
marCasado
// Write Plot code to create a heatmap of sea surface temperature (SST) by year and month, starting from the 'cell'
Plot.plot({
marks: [
Plot.cell(marCasado, {
y: (d) => d.month.getUTCFullYear(),
x: (d) => d.month.getUTCMonth(),
fill: "SST",
tip: true
})
],
width: 500,
height: 250,
y: { tickFormat: "Y", padding: 0 },
x: { padding: 0, tickFormat: Plot.formatMonth() }
})
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()
// Get cumulative variance explained:
marCasadoPCA.getCumulativeVariance()
// 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) => ({
...d,
Name: marCasado[i].month,
season: marCasado[i].season
}))
scalingFactor = 5
// Create a PCA biplot with the scores and loadings
Plot.plot({
marks: [
Plot.dot(scoresCombined, { x: "PC1", y: "PC2", fill: "season", r: 5 }),
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,
y: (d) => d.PC2 * scalingFactor,
text: "Variable",
dy: -5,
dx: 30,
fill: "black",
stroke: "white"
})
],
color: { legend: true }
})
// 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.
