Public
Edited
Aug 1, 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
marCasado
// Write Plot code to create a heatmap of sea surface temperature (SST) by year and month, starting from the 'cell' snippet:
Plot.plot({
marks: [
Plot.cell(marCasado, {
x: d => d.month.getUTCMonth(),
y: d => d.month.getUTCFullYear(),
fill: "meanPressure",
tip: true,
})
],
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((score, i) => ({...score, Name: marCasado[i].month, season: marCasado[i].season}))
// Create a PCA biplot with the scores and loadings
Plot.plot({
marks: [
Plot.dot(scoresCombined, {
x: "PC1",
y: "PC2",
fill: "season",
r: 4
}),
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" }),
],
color: { legend: true }
})
scalingFactor = 5
// 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]}))
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.