Public
Edited
Jul 25, 2023
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
marCasadoAir = FileAttachment("marCasadoAir@5.csv").csv({typed: true}) // Date issue
Insert cell
marCasadoSea = FileAttachment("marCasadoSea@4.csv").csv({typed: true}) // Date issue
Insert cell
Insert cell
// Write code to create a database called marCasadoDB, with tables 'air' and 'sea':
marCasadoDB = DuckDBClient.of({ air: marCasadoAir, sea: marCasadoSea })
Insert cell
marCasadoDB
Type SQL, then Shift-Enter. Ctrl-space for more options.

Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
marCasadoDB
SELECT air.month
, meanPressure
, windSpeed
, PAR
, meanHumidity
, windDirection
, sea.maxTide
, sea.minTide
, sea.salinity
, sea.seaSurfaceTemp as SST
, CASE WHEN date_part('month', air.month) IN (10, 11, 12, 1, 2, 3) THEN 'hot moist' ELSE 'cool dry' END AS "season"
FROM air
JOIN sea
ON air.month = sea.month
Insert cell
Insert cell
marCasado
SELECT date_part('month', month) as month
, mean(SST) as meanSST
FROM marCasado
GROUP BY date_part('month', month)
Insert cell
// 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() }
})
Insert cell
Insert cell
Insert cell
import {PlotMatrix} with {marCasado as data} from "@observablehq/autoplot-matrix"
Insert cell
// Use the PlotMatrix function (expecting marCasado) to create a pair plot:
PlotMatrix(marCasado)
Insert cell
Insert cell
Insert cell
Insert cell
ML = require("https://www.lactame.com/lib/ml/6.0.0/ml.min.js")
Insert cell
Insert cell
import {scale, asMatrix} from "@chrispahm/hierarchical-clustering"
Insert cell
Insert cell
Insert cell
// Create a scaled version of the numeric variables
marCasadoScaled = scale(marCasado.map(({ season, month, ...rest }) => rest))
Insert cell
Insert cell
// Convert to an array of arrays, just containing the values (no keys):
marCasadoArray = marCasadoScaled.map(Object.values)
Insert cell
Insert cell
// Perform principal component analysis:
marCasadoPCA = new ML.PCA(marCasadoArray)
Insert cell
Insert cell
Insert cell
// Get variance explained by each PC:
marCasadoPCA.getExplainedVariance()
Insert cell
Insert cell
// Get cumulative variance explained:
marCasadoPCA.getCumulativeVariance()
Insert cell
Insert cell
Insert cell
Insert cell
// Import viewof loadings from the notebook, with marCasadoScaled as food_scaled:
import { viewof loadings } with { marCasadoScaled as food_scaled } from "@chrispahm/principal-component-analysis"
Insert cell
// Look at viewof loadings:
viewof loadings
Insert cell
// 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"
Insert cell
// Look at viewof scores:
viewof scores
Insert cell
// 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
}))
Insert cell
scalingFactor = 5
Insert cell
// 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 }
})
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
Insert cell
// Alternatively (without an import):

// loadingsOption = marCasadoPCA
// .getEigenvectors()
// .data.map((d, i) => ({
// PC1: d[0],
// PC2: d[1],
// Variable: Object.keys(marCasadoScaled[0])[i]
// }))
Insert cell
// 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]}))
Insert cell

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.
Learn more