25:["$","title",null,{"children":"MCA II | elias | Observable"}] 49:T671,mca_norm = { const data = await mca_data(); // Cargar datos originales // --- Variables económicas y culturales --- const econ = [ "Gross Value Added (million €)", "Business Turnover (million €)", "Number of Employees", "2-Year Business Survival Rate (%)", "Tourism Revenue (thousand €)", "Hotel Establishments (n)" ]; const cult = [ "Cultural and Creative Activities Expenditure (thousand €)", "Heritage Expenditure (thousand €)", "Library and Archives Expenditure (thousand €)", "Performing Arts Expenditure (thousand €)", "Interdisciplinary Activities Expenditure (thousand €)", "Cultural and Creative Activities Expenditure per capita (€)" ]; const allVars = econ.concat(cult); // --- Filtro para eliminar filas vacías o de encabezado --- const filtered = data.filter(row => row.Municipality && row.Municipality.trim() !== "" && // Municipio no vacío row.Code && String(row.Code).trim() !== "" // Código no vacío ); // --- Calcular medias y desviaciones --- let stats = {}; allVars.forEach(k => { // Solo valores numéricos const arr = filtered .map(d => +d[k]) .filter(v => v != null && !Number.isNaN(v)); stats[k] = { mean: d3.mean(arr), std: d3.deviation(arr) }; }); // --- Generar z-scores --- return filtered.map(d => { let nd = { ...d }; allVars.forEach(k => { const val = +d[k]; nd[k + "_z"] = stats[k].std && !Number.isNaN(val) ? (val - stats[k].mean) / stats[k].std : null; // null si no hay dato válido }); return nd; }); } 4a:T950,RadarPlotMuni = (labels_econ, vals_econ, labels_cult, vals_cult, clase, municipio) => { const width = Math.min(window.innerWidth * 0.97, 1400); const div = html`

`; // Busca el objeto muni_sel según municipio const muni = mca_norm.find(d => d.Municipality === municipio); // Construye el hover con los datos demográficos const demoHover = muni ? `Residents INE-2025: ${muni["Resident Population"]}
Male: ${muni["Male"]}
Female: ${muni["Female"]}
Population Aged <15: ${muni["Population Aged <15 Years"]}
Population Aged ≥65: ${muni["Population Aged ≥65 Years"]}
` : ""; const empty = ( !municipio || !muni || vals_econ.some(v => v === undefined || isNaN(v)) || vals_cult.some(v => v === undefined || isNaN(v)) ); Plotly.newPlot(div, [ { type: "scatterpolar", r: empty ? Array(labels_econ.length + 1).fill(0) : vals_econ.concat(vals_econ[0]), theta: labels_econ.concat(labels_econ[0]), fill: "toself", name: "Economic Investment", line: {color: "#1f77b4"}, hoverinfo: empty ? "skip" : "all", hovertemplate: empty ? null : `Municipio: ${municipio}
` + `Clase: ${clase}
` + `Variable: %{theta}
` + `Z-score: %{r:.2f}
` + demoHover + "" }, { type: "scatterpolar", r: empty ? Array(labels_cult.length + 1).fill(0) : vals_cult.concat(vals_cult[0]), theta: labels_cult.concat(labels_cult[0]), fill: "toself", name: "Cultural Investment", line: {color: "#ff7f0e"}, hoverinfo: empty ? "skip" : "all", hovertemplate: empty ? null : `Municipio: ${municipio}
` + `Clase: ${clase}
` + `Variable: %{theta}
` + `Z-score: %{r:.2f}
` + demoHover + "" } ], { title: empty ? "Please select a municipality" : `Economic and cultural capital: ${municipio}`, polar: {radialaxis: {visible: true, tickfont: {size: 12}}}, showlegend: true, autosize: true, width: width, height: Math.round(width * 0.65) }, {responsive: true}); return div; } 4b:T57d,// Centred Plotly violin plot with controlled width and spacing violin_by_group = { const groups = {}; mca_norm.forEach(d => { const g = d[groupfield]; const v = +d[variable]; if (g != null && g !== "" && Number.isFinite(v)) { if (!groups[g]) groups[g] = []; groups[g].push(v); } }); const traces = Object.entries(groups).map(([g, vals]) => ({ type: "violin", name: g, y: vals, box: { visible: true }, meanline: { visible: true }, points: "all", jitter: 0.35, pointpos: 0, opacity: 0.85, scalemode: "count" })); // Ancho máximo controlado para que no se estiren demasiado const maxWidth = 1000; // px const vh = (typeof window !== "undefined") ? window.innerHeight : 900; const heightPx = Math.min(Math.max(620, 90 * Object.keys(groups).length), Math.round(vh * 0.8)); const div = html`

`; const layout = { title: `${String(variable).replace("_z","")} by ${groupfield}`, yaxis: { title: "Z-score", zeroline: true }, xaxis: { title: "Class/Cluster", automargin: true }, margin: { t: 90, l: 80, r: 30, b: 90 }, violinmode: "group", hovermode: "closest", autosize: false, width: maxWidth, height: heightPx }; Plotly.react(div, traces, layout, { responsive: true }); return div; } 4c:T728,barchart_muni = { let group_values = {}; let class_map = {}; mca_norm.forEach(d => { let muni = d.Municipality; if (muni !== undefined && muni !== "" && muni !== null) { if (!group_values[muni]) group_values[muni] = []; group_values[muni].push(d[variable]); class_map[muni] = d.classes; } }); let muni_vals = Object.entries(group_values) .map(([muni, vals]) => ({ muni, val: vals.length === 1 ? vals[0] : vals.reduce((a, b) => a + b, 0) / vals.length, clase: class_map[muni] })) .filter(d => d.val !== undefined && d.val !== null && !isNaN(d.val)); muni_vals.sort((a, b) => b.val - a.val); let trace = { x: muni_vals.map(d => d.muni), y: muni_vals.map(d => d.val), customdata: muni_vals.map(d => [d.clase]), type: "bar", marker: {line: {width: 1, color: '#333'}}, hovertemplate: "%{x}
" + "Value: %{y:.2f}
" + "Class: %{customdata[0]}" }; const min_y = Math.min(0, ...muni_vals.map(d => d.val)); const max_y = Math.max(0, ...muni_vals.map(d => d.val)); const div = html`

`; Plotly.newPlot(div, [trace], { title: `${variable.replace("_z", "")} by municipality (sorted in descending order)`, yaxis: { title: "Z-score", zeroline: true, range: [min_y, max_y], tickfont: {family: 'Arial, sans-serif', size: 14} }, xaxis: { title: {text: "Municipality", standoff: 50}, showticklabels: true, tickangle: -90, tickfont: {family: 'Arial, sans-serif', size: 12}, automargin: true // ← esto habilita el standoff }, showlegend: false, height: 700, width: 1100 }, {responsive: true}); return div; } 4d:Tb91,{ let data = []; if (pm_year === "All years") { // Une todos los años: crea un punto por municipio por año let years = ["2019", "2020", "2021", "2022", "2023", "2024", "2025"]; years.forEach(y => { mca_norm.forEach(d => { let xval = d[inv_var]; let yval = d[`${y}pm`]; let gval = d[groupfield]; if ( gval !== undefined && gval !== "" && gval !== null && xval !== undefined && xval !== "" && !isNaN(parseFloat(xval)) && yval !== undefined && yval !== "" && !isNaN(parseFloat(yval)) ) { data.push({ x: parseFloat(xval), y: parseFloat(yval), municipio: d.Municipality, year: y, group: gval }); } }); }); } else { // Caso individual por año let pm_var = `${pm_year}pm`; data = mca_norm .filter(d => { let xval = d[inv_var]; let yval = d[pm_var]; let gval = d[groupfield]; return ( gval !== undefined && gval !== "" && gval !== null && xval !== undefined && xval !== "" && !isNaN(parseFloat(xval)) && yval !== undefined && yval !== "" && !isNaN(parseFloat(yval)) ); }) .map(d => ({ x: parseFloat(d[inv_var]), y: parseFloat(d[pm_var]), municipio: d.Municipality, year: pm_year, group: d[groupfield] })); } // Si no hay datos válidos, muestra aviso if (data.length === 0) return html`

No hay datos válidos para la selección.

`; let groups = [...new Set(data.map(d => d.group))] .filter(g => g !== undefined && g !== "" && g !== null); let colores = {class1: "#1f77b4", class2: "#ff7f0e", class3: "#2ca02c"}; let traces = groups.map(g => ({ x: data.filter(d => d.group === g).map(d => d.x), y: data.filter(d => d.group === g).map(d => d.y), text: data.filter(d => d.group === g).map(d => `${d.municipio} (${d.year})`), mode: 'markers', type: 'scatter', name: g, marker: { size: 12, opacity: 0.7, color: colores[g] || undefined }, //hovertemplate: "%{text}
X: %{x:.2f}
PM2.5: %{y:.2f}" hovertemplate: "%{text}
" + "Clase: %{customdata[0]}
" + // <-- clase/cluster "X: %{x:.2f}
PM2.5: %{y:.2f}", customdata: data.filter(d => d.group === g).map(d => [d.group]), })); const div = html`

`; Plotly.newPlot(div, traces, { title: `${inv_var.replace("_z", "")} vs. PM2.5 (${pm_year === "All years" ? "All years" : pm_year})`, xaxis: { title: inv_var.replace("_z", "") + " (z-score)" }, yaxis: { title: `PM2.5` }, height: 700, // <-- altura forzada width: 1100 // <-- (opcional, fuerza un ancho aún si el panel es chico) }, {responsive:true}); return div; } 4e:T16da,barchart_pm25 = { // Define the cell that renders the PM2.5 bar chart // --- Compute average PM2.5 by municipality for the selected year(s) --- const pm_values = {}; // Map: municipality → average PM2.5 const class_map = {}; // Map: municipality → class label const yearsSel = (pm_year === "All years") // Determine which years to aggregate ? ["2019","2020","2021","2022","2023","2024","2025"] // Use all years if requested : [pm_year]; // Otherwise use the single selected year mca_norm.forEach(d => { // Iterate over the MCA-normalised table const muni = d.Municipality; // Read municipality name if (muni != null && muni !== "") { // Guard against empty/undefined names const vals = yearsSel // Build the list of PM2.5 values for the selected years .map(y => parseFloat(d[`${y}pm`])) // Parse each yearly PM2.5 value as float .filter(v => Number.isFinite(v)); // Keep only finite numbers if (vals.length) { // If there is at least one valid value const avg = vals.reduce((a,b) => a + b, 0) / vals.length; // Compute the arithmetic mean pm_values[muni] = avg; // Store the average PM2.5 by municipality class_map[muni] = d.classes; // Store the class label for the municipality } } }); const muni_vals = Object.entries(pm_values) // Convert the map into an array of rows .map(([muni, val]) => ({ muni, val, clase: class_map[muni] })) // Attach class label to each row .sort((a, b) => b.val - a.val); // Sort municipalities by descending PM2.5 // --- Define the bar trace --- const trace = { // Plotly trace configuration x: muni_vals.map(d => d.muni), // X-axis categories: municipality names y: muni_vals.map(d => d.val), // Y-axis values: average PM2.5 customdata: muni_vals.map(d => [d.clase]), // Custom data for hover (class label) type: "bar", // Bar chart hovertemplate: // Academic hover: municipality, PM2.5 with units, class "%{x}
" + "PM2.5: %{y:.2f} μg/m³
" + "Class: %{customdata[0]}" }; // --- Create a container DIV and render the chart --- const div = html`

`; // Responsive container Plotly.newPlot(div, [trace], { // Render the chart with a fixed Y scale title: "PM2.5 by municipality (sorted in descending order)", // Chart title (European academic English) yaxis: { // Y-axis configuration title: "PM2.5 (μg/m³)", // Axis title with units range: [5, 9], // FIXED scale from 5 to 9 as requested tickmode: "linear", // Linear tick spacing tick0: 5, // Start ticks at 5.0 dtick: 0.5, // Tick every 0.5 → 5.0, 5.5, 6.0, … tickformat: ".1f", // Show one decimal (e.g., 5.0, 5.5) zeroline: false, // Hide zero line (outside the fixed range) fixedrange: true // Prevent zoom from changing the scale }, xaxis: { // X-axis configuration title: "Municipality", // Axis title showticklabels: false // Hide long municipality labels to avoid clutter }, showlegend: false, // No legend needed for a single trace height: 700, // Fixed height for consistency width: 1100, // Fixed width (container still responsive horizontally) margin: {t: 60, r: 20, b: 60, l: 80} // Adequate margins for axis labels and title }, {responsive:true}); // Enable responsiveness for the container return div; // Return the DIV so Observable displays the chart } 4f:T4b5,// Helpers: Pearson and Spearman correlations (pairwise, ignoring missing rows) function pearson(x, y) { // Compute Pearson's r const n = Math.min(x.length, y.length); // Use aligned arrays of same length if (n === 0) return {r: NaN, n: 0}; // Guard: no data const mx = x.reduce((a,b)=>a+b,0)/n; // Mean of x const my = y.reduce((a,b)=>a+b,0)/n; // Mean of y let num = 0, sx = 0, sy = 0; // Numerator and sums of squares for (let i=0;i v === null || v === "" || Number.isNaN(+v);// Helper: detect missing/invalid numbers // For each variable, extract a SAME-LENGTH array aligned with `data` rows // Keep `null` for missing entries so indexing stays aligned across variables const cols = corr_vars.map(v => data.map(row => { const val = row[v]; // Raw value for this row and variable if (isMissing(val)) return null; // Preserve missing as null (no row drop) const num = +val; // Convert to number return Number.isFinite(num) ? num : null; // Keep number or null if not finite })); return cols; // Arrays remain aligned to `mca_norm` } 51:T9d8,// Compute correlation (Pearson/Spearman) with N = rows having data for BOTH variables (pairwise complete) corr_result = { // >>> set this to your base table (e.g., mca_norm) that contains all variables <<< const corr_data = mca_norm; // Underlying rows (records) const p = corr_vars.length; // Number of variables const R = Array.from({length: p}, () => Array(p).fill(1)); // Correlation matrix const N = Array.from({length: p}, () => Array(p).fill(0)); // Pairwise sample sizes const isNum = v => v !== null && v !== "" && Number.isFinite(+v); // Valid-number check for (let i = 0; i < p; i++) { // Loop over variables for (let j = i; j < p; j++) { // Upper triangle (incl. diag) const xi = []; // Pairwise-aligned X const yj = []; // Pairwise-aligned Y // Build pairwise-complete vectors (both finite on the same row) for (const row of corr_data) { // Iterate table rows const a = +row[corr_vars[i]]; // Value of var i const b = +row[corr_vars[j]]; // Value of var j if (isNum(a) && isNum(b)) { xi.push(a); yj.push(b); } // Keep only valid pairs } const nn = xi.length; // N = rows with both values let r = 1; // Diagonal defaults to 1 if (i !== j && nn >= 2) { // Off-diagonal with data const out = (corr_method === "Spearman") ? spearman(xi, yj) : pearson(xi, yj); // Compute r r = out.r; // Use returned correlation } R[i][j] = R[j][i] = (i === j ? 1 : r); // Symmetric assignment N[i][j] = N[j][i] = nn; // Pairwise N } } return { R, N }; // Return matrices } 52:T894,// Heatmap of the correlation matrix (Plotly) with academic labels and readable ticks corr_heatmap = { const labels = corr_vars.map(v => v.replace("_z","")); // Clean labels without "_z" const z = corr_result.R; // Correlation values const text = z.map((row,i) => row.map((r,j) => // Hover text per cell `${labels[i]} × ${labels[j]}
r = ${Number.isFinite(r) ? r.toFixed(2) : "NA"}
N = ${corr_result.N[i][j]}` )); const trace = { // Heatmap trace type: "heatmap", z, // Matrix of r x: labels, // Column labels y: labels, // Row labels text, // Hover text hoverinfo: "text", // Show custom hover only zmin: -1, zmax: 1 // Correlation range }; const div = html`

`; // Container Plotly.newPlot(div, [trace], { // Render the heatmap title: `Correlation matrix (${corr_method}) — Economic & Cultural variables (z-scores)`, // Title xaxis: { tickangle: -45, automargin: true, title: "" }, // X axis styling yaxis: { automargin: true, autorange: "reversed", title: "" }, // Y axis styling margin: {t: 80, l: 160, r: 20, b: 140}, // Margins for long labels height: 800 // Fixed height }, {responsive:true}); // Responsive behavior return div; // Return the DIV } 53:T712,// Ranked list of strongest associations (absolute r), excluding the diagonal; helpful as a compact summary corr_top_pairs = { const labels = corr_vars.map(v => v.replace("_z","")); // Clean labels const out = []; // Collector for pairs for (let i=0;i Math.abs(v.r) - Math.abs(u.r)); // Sort by |r| descending // Build a simple HTML table (top 20) const rows = out.slice(0, 20).map(d => ` ${d.a}${d.b} ${d.r.toFixed(2)} ${d.n} `).join(""); const table = html`${rows}

Top absolute correlations (${corr_method})
Variable A	Variable B	r	N

`; return table; // Show the table } 54:T107c,// Correlation network plot (Plotly) — readable multi-line labels via annotations corr_network_plot = { // --- Helpers ---------------------------------------------------------------- const wrap = (s, max=18) => { // Insert
at word boundaries const words = String(s).split(" "); let lines = [], line = ""; for (const w of words) { if ((line + (line ? " " : "") + w).length <= max) line += (line ? " " : "") + w; else { if (line) lines.push(line); line = w; } } if (line) lines.push(line); return lines.join("
"); }; // --- Nodes ------------------------------------------------------------------ const nodes = corr_network_nodes; // [{id, group, x, y}, ...] const x = nodes.map(d => d.x); // X coordinates const y = nodes.map(d => d.y); // Y coordinates const colors = nodes.map(d => d.group === "Economic" ? "#1f77b4" : d.group === "Cultural" ? "#ff7f0e" : "#7f7f7f"); // Group colours const hover = nodes.map(d => `${d.id} (${d.group})`); // Hover per node // --- Edges ------------------------------------------------------------------ const ex = [], ey = [], etext = []; corr_network_data.forEach(l => { const s = nodes.find(n => n.id === l.source); const t = nodes.find(n => n.id === l.target); ex.push(s.x, t.x, null); // Segment X + null ey.push(s.y, t.y, null); // Segment Y + null etext.push(`${l.source} ↔ ${l.target}
r = ${l.r.toFixed(2)}`); // Hover text etext.push(null); }); // --- Traces ----------------------------------------------------------------- const edgeTrace = { type: "scatter", mode: "lines", x: ex, y: ey, // Lines line: { width: 2, color: "#bfbfbf" }, hoverinfo: "text", text: etext, hovertemplate: "%{text}" }; const nodeTrace = { type: "scatter", mode: "markers", x, y, // Markers only (no text) marker: { size: 30, color: colors, line: { width: 2, color: "#333" } }, hovertext: hover, hoverinfo: "text" }; // --- Annotations for readable labels --------------------------------------- const annotations = nodes.map((d, i) => ({ // One annotation per node x: x[i], y: y[i], text: wrap(d.id, 20), // Wrapped multi-line label showarrow: false, xanchor: "center", yanchor: "bottom", yshift: 14, // Offset above node align: "center", font: { size: 14 }, // Label font size bgcolor: "rgba(255,255,255,0.35)", bordercolor: "rgba(0,0,0,0.15)", borderwidth: 1, // Readability borderpad: 2 })); // --- Layout & sizing -------------------------------------------------------- const xmin = Math.min(...x), xmax = Math.max(...x); const ymin = Math.min(...y), ymax = Math.max(...y); const padX = 0.12 * (xmax - xmin || 1), padY = 0.16 * (ymax - ymin || 1); const heightPx = Math.max(760, Math.min(1200, nodes.length * 36)); // Taller for many labels const layout = { title: { text: "Economic–Cultural Correlation Network (|r| ≥ 0.5)", font: { size: 22 } }, xaxis: { visible: false, range: [xmin - padX, xmax + padX], constrain: "domain" }, yaxis: { visible: false, range: [ymin - padY, ymax + padY], scaleanchor: "x" }, margin: { t: 90, b: 20, l: 20, r: 20 }, hovermode: "closest", dragmode: "pan", showlegend: false, height: heightPx, annotations }; // --- Container full width --------------------------------------------------- const div = html`

`; Plotly.newPlot(div, [edgeTrace, nodeTrace], layout, { responsive: true, scrollZoom: true }); // Enable zoom return div; } 55:T723,// Build the correlation matrix (R) and sample size matrix (N) for the selected class tc_corr = { // Main correlation computation const vars = tc_corr_vars; // Variables to include const p = vars.length; // Number of variables if (!p || !tc_rows.length) return {labels: [], R: [], N: []}; // Guard: nothing to compute const cols = vars.map(v => tc_getColumnZ(tc_rows, v)); // Extract numeric columns const R = Array.from({length:p}, () => Array(p).fill(1)); // Init correlation matrix const N = Array.from({length:p}, () => Array(p).fill(0)); // Init sample-size matrix for (let i=0;i v.replace("_z","")); // Clean labels for display return {labels, R, N}; // Return matrices and labels } 56:T438,tc_corr_heatmap = { if (!tc_corr.labels.length) return html`

No data for the selected class or variables.

`; const labels = tc_corr.labels; const z = tc_corr.R; const txt = z.map((row, i) => row.map((r, j) => `${labels[i]} × ${labels[j]}
r = ${Number.isFinite(r) ? r.toFixed(2) : "NA"}
N = ${tc_corr.N[i][j]}` )); const trace = { type: "heatmap", z, x: labels, y: labels, text: txt, hoverinfo: "text", zmin: -1, zmax: 1 }; // Contenedor con ancho fijo para evitar que se achique const div = html`

`; const layout = { title: `Correlation matrix (${tc_corr_method}) — Class: ${traj_class}`, xaxis: { tickangle: -45, automargin: true, title: "Variables" }, yaxis: { automargin: true, autorange: "reversed", title: "Variables" }, margin: { t: 100, l: 100, r: 40, b: 140 }, height: 800, width: 1100 // 🔹 Fija el ancho }; Plotly.react(div, [trace], layout, { responsive: true }); return div; } 57:T650,// Ranked summary: strongest |r| within the selected class (top 20 pairs) tc_corr_top_pairs = { // Table of top absolute correlations const L = tc_corr.labels; // Labels const out = []; // Collector for (let i=0;iMath.abs(v.r)-Math.abs(u.r)); // Sort by |r| desc const rows = out.slice(0,20).map(d => // Build HTML rows `${d.a}${d.b}${d.r.toFixed(2)}${d.n}` ).join(""); return html`${rows}

Top absolute correlations — Class: ${traj_class} (${tc_corr_method})
Variable A	Variable B	r	N

`; // Show the table } 58:T2963,// --- Radar plot with horizontal legend below the chart ------------------------- // Changes: display selected class as traj1/traj2/traj3 instead of class1/2/3. // All analysis logic remains intact; only labels/titles are transformed. RadarPlotByClass = (labels_econ, labels_cult, selectedClass = class_selector) => { const width = Math.min(window.innerWidth * 0.97, 1400); // Responsive width capped for readability const div = html`

`; // Container for Plotly const selRaw = (selectedClass ?? "").toString().trim(); // Normalised raw selector value const toTraj = (c) => { // Helper to convert any class label to "traj#" const s = String(c ?? "").toLowerCase().trim(); // Lowercase and trim const num = s.match(/\d+/)?.[0]; // Extract first number if present if (num) return `traj${num}`; // If a number exists, build traj# const cleaned = s.replace(/class/i, "").replace(/\s+/g, ""); // Otherwise, strip "class" and spaces return `traj${cleaned || s || "?"}`; // Fallback to a safe label }; const selTraj = selRaw ? toTraj(selRaw) : ""; // Trajectory label for titles/legends const plotTitle = selTraj ? `Economic and Cultural Investments: ${selTraj}` // Title when a class is selected : "Economic and Cultural Investments"; // Title when blank const legendCfg = { // Legend configuration at the bottom orientation: "h", // Horizontal legend x: 0.5, xanchor: "center", // Centred horizontally y: -0.18, yanchor: "top", // Positioned below the plot area font: { size: 25, family: "Roboto, Arial, sans-serif", color: "#222"} // Requested typography }; // ----- EMPTY FRAME MODE (no data, axes visible) ---------------------------- if (!selRaw) { // If no class is selected, draw an empty frame const emptyEcon = { // Invisible economic placeholder type: "scatterpolar", // Polar trace r: labels_econ.map(() => 0).concat(0), // Zeros to close the polygon theta: labels_econ.concat(labels_econ[0]), // Economic axis labels (closed loop) fill: "toself", // Polygon fill (invisible due to opacity) line: { width: 0 }, // No visible line opacity: 0, // Fully transparent showlegend: false // Do not show in legend }; const emptyCult = { // Invisible cultural placeholder type: "scatterpolar", // Polar trace r: labels_cult.map(() => 0).concat(0), // Zeros to close the polygon theta: labels_cult.concat(labels_cult[0]), // Cultural axis labels (closed loop) fill: "toself", // Polygon fill (invisible due to opacity) line: { width: 0 }, // No visible line opacity: 0, // Fully transparent showlegend: false // Do not show in legend }; Plotly.newPlot( // Render empty frame with axes div, // Target container [emptyEcon, emptyCult], // Placeholder traces { title: { // Styled title, as requested text: `${plotTitle} (z-score)`, // Title text with suffix font: { size: 35, family: "Roboto, Arial, sans-serif", color: "#222" } // Title font styling }, width, // Explicit width height: Math.round(width * 0.65), // Aspect ratio preserved polar: { // Polar layout styling radialaxis: { // Radial axis visible: true, // Show radial axis tickfont: { size: 25, family: "Roboto, Arial, sans-serif", color: "#222" } // Tick font styling }, angularaxis: { // Angular axis tickfont: { size: 25, family: "Roboto, Arial, sans-serif", color: "#222" }, // Tick font styling rotation: 90, // Start at the top direction: "clockwise" // Clockwise direction } }, legend: legendCfg, // Legend layout (not shown in empty mode) showlegend: false, // Hide legend for the empty frame margin: { t: 80, l: 40, r: 40, b: 140 } // Extra bottom margin for legend area }, { responsive: true } // Responsive redraw on resize ); return div; // Return the empty frame } // ----- DATA MODE (class selected) ----------------------------------------- const rows = mca_norm.filter(d => (d.classes ?? d.class ?? "").toString().trim() === selRaw); // Filter rows for the selected class const econStats = econ.map((v,i) => ({ v, label: labels_econ[i], m: meanZ(rows, v) })) // Compute means for economic variables .filter(d => Number.isFinite(d.m)); // Keep only finite means const econTheta = econStats.map(d => d.label).concat(econStats[0]?.label ?? ""); // Close polygon by repeating first label const econR = econStats.map(d => d.m).concat(econStats[0]?.m ?? 0); // Close polygon by repeating first value const cultStats = cult.map((v,i) => ({ v, label: labels_cult[i], m: meanZ(rows, v) })) // Compute means for cultural variables .filter(d => Number.isFinite(d.m)); // Keep only finite means const cultTheta = cultStats.map(d => d.label).concat(cultStats[0]?.label ?? ""); // Close polygon by repeating first label const cultR = cultStats.map(d => d.m).concat(cultStats[0]?.m ?? 0); // Close polygon by repeating first value const traces = [ // Build two traces { type: "scatterpolar", r: econR, theta: econTheta, fill: "toself", // Economic trace name: `Economic Inv. `, // Legend label using traj# line: { color: "#1f77b4" }, // Blue line hovertemplate: `Variable: %{theta}
Z-score: %{r:.2f}` }, // Academic English hover { type: "scatterpolar", r: cultR, theta: cultTheta, fill: "toself", // Cultural trace name: `Cultural Inv. `, // Legend label using traj# line: { color: "#d62728" }, // Red line hovertemplate: `Variable: %{theta}
Z-score: %{r:.2f}` } // Academic English hover ]; Plotly.newPlot( // Render chart with data div, // Target container traces, // Data traces { title: { // Styled title, as requested text: `${plotTitle} (z-score)`, // Title with suffix font: { size: 35, family: "Roboto, Arial, sans-serif", color: "#222" } // Title font styling }, width, // Explicit width height: Math.round(width * 0.65), // Aspect ratio preserved polar: { // Polar layout styling radialaxis: { visible: true, tickfont: { size: 25, family: "Roboto, Arial, sans-serif", color: "#222" } }, // Radial axis styling angularaxis:{ tickfont: { size: 25, family: "Roboto, Arial, sans-serif", color: "#222" }, rotation: 90, direction: "clockwise" } // Angular axis styling }, legend: legendCfg, // Bottom-centred horizontal legend showlegend: true, // Show legend in data mode margin: { t: 90, l: 40, r: 40, b: 140 } // Extra bottom margin for legend }, { responsive: true } // Responsive redraw on resize ); return div; // Return the chart container }; 59:[{"id":"274714bb5608f066b6d12a740b10910ce0ad2d32fdec1f636da6ae6c9be74533f4610a1f7e672749e9dab1426d74400dd86dd7784b679ac960dfec067dd5edab","href":"https://static.observableusercontent.com/files/274714bb5608f066b6d12a740b10910ce0ad2d32fdec1f636da6ae6c9be74533f4610a1f7e672749e9dab1426d74400dd86dd7784b679ac960dfec067dd5edab","name":"mca.csv","type":"text/csv","lastModified":1754127507900.086,"size":7261}] 29:{"id":"b867ea6c0b152873","slug":null,"title":"MCA II","thumbnail":"49e3b8e7b5c25c76853ac31b4ed41e895e2facb91573182f4e68e995d0ccb899","access_level":"public","create_time":"$D2025-08-02T09:36:15.013Z","update_time":"$D2025-10-30T12:09:20.404Z","view_time":null,"first_public_time":"$D2025-08-28T10:47:25.232Z","has_unpublished_edits":null,"fork":false,"stars":0,"starred":false,"owner":{"type":"team","id":"9570a53233b8c1b4","login":"debianalt","name":"elias","avatar_url":"https://avatars-next.observableusercontent.com/ea9b57a210e8a6a242adaf1c67bf187d1ed8642ac2f51a3e6358b801ec683e0b","tier":"starter_2024","bio":"","followed_by_you":false,"follows_you":false},"version":621,"publish_version":null,"role":null,"authored":false,"authors":[{"type":"individual","id":"79596a9e81db54aa","login":"debianalt","name":"elias","avatar_url":"https://avatars-next.observableusercontent.com/ea9b57a210e8a6a242adaf1c67bf187d1ed8642ac2f51a3e6358b801ec683e0b","tier":null,"bio":"","followed_by_you":false,"follows_you":false}],"members":[{"type":"individual","id":"79596a9e81db54aa","login":"debianalt","name":"elias","avatar_url":"https://avatars-next.observableusercontent.com/ea9b57a210e8a6a242adaf1c67bf187d1ed8642ac2f51a3e6358b801ec683e0b","tier":null,"role":"editor"},{"type":"team","id":"9570a53233b8c1b4","login":"debianalt","name":"elias","avatar_url":"https://avatars-next.observableusercontent.com/ea9b57a210e8a6a242adaf1c67bf187d1ed8642ac2f51a3e6358b801ec683e0b","tier":"starter_2024","role":"editor"}],"comments":[],"custom_thumbnail":false,"trashed":false,"lapsed":null,"subscribed":null,"forks":1,"collection":null,"type":"notebook","body":{"titling":"auto","title":"MCA II","cells":[{"id":0,"value":"# MCA II","pinned":false,"hidden":false,"mode":"md","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"","database":"$undefined"},{"id":9,"value":"mca_data = async function() {\n const txt = await FileAttachment(\"mca.csv\").text();\n let data = d3.dsvFormat(\";\").parse(txt);\n const toNumberPT = v => v && v !== \"-\" && v !== \"\" ? parseFloat(String(v).replace(\",\", \".\")) : null;\n\n // Usa los nombres largos originales\n const econ = [\n \"Gross Value Added (million €)\",\n \"Business Turnover (million €)\",\n \"Number of Employees\",\n \"2-Year Business Survival Rate (%)\",\n \"Tourism Revenue (thousand €)\",\n \"Hotel Establishments (n)\"\n ];\n const cult = [\n \"Cultural and Creative Activities Expenditure (thousand €)\",\n \"Heritage Expenditure (thousand €)\",\n \"Library and Archives Expenditure (thousand €)\",\n \"Performing Arts Expenditure (thousand €)\",\n \"Interdisciplinary Activities Expenditure (thousand €)\",\n \"Cultural and Creative Activities Expenditure per capita (€)\"\n ];\n\n data.forEach(d => {\n econ.forEach(k => d[k] = toNumberPT(d[k]));\n cult.forEach(k => d[k] = toNumberPT(d[k]));\n });\n return data;\n}\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":13,"value":"$49","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":70,"value":"valores_econ = [\n muni_sel[\"Gross Value Added (million €)_z\"],\n muni_sel[\"Business Turnover (million €)_z\"],\n muni_sel[\"Number of Employees_z\"],\n muni_sel[\"2-Year Business Survival Rate (%)_z\"],\n muni_sel[\"Tourism Revenue (thousand €)_z\"],\n muni_sel[\"Hotel Establishments (n)_z\"]\n]","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":72,"value":"valores_cult = [\n muni_sel[\"Cultural and Creative Activities Expenditure (thousand €)_z\"],\n muni_sel[\"Heritage Expenditure (thousand €)_z\"],\n muni_sel[\"Library and Archives Expenditure (thousand €)_z\"],\n muni_sel[\"Performing Arts Expenditure (thousand €)_z\"],\n muni_sel[\"Interdisciplinary Activities Expenditure (thousand €)_z\"],\n muni_sel[\"Cultural and Creative Activities Expenditure per capita (€)_z\"]\n]\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":86,"value":"econ = [\n \"Gross Value Added (million €)\",\n \"Business Turnover (million €)\",\n \"Number of Employees\",\n \"2-Year Business Survival Rate (%)\",\n \"Tourism Revenue (thousand €)\",\n \"Hotel Establishments (n)\"\n]\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":88,"value":"cult = [\n \"Cultural and Creative Activities Expenditure (thousand €)\",\n \"Heritage Expenditure (thousand €)\",\n \"Library and Archives Expenditure (thousand €)\",\n \"Performing Arts Expenditure (thousand €)\",\n \"Interdisciplinary Activities Expenditure (thousand €)\",\n \"Cultural and Creative Activities Expenditure per capita (€)\"\n]","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":15,"value":"viewof municipio = Inputs.select(\n [...new Set(mca_norm.map(d => d.Municipality))].sort(),\n {label: \"Municipio\"}\n)\n\n\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":63,"value":"muni_sel = mca_norm.find(d => d.Municipality === municipio)\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":23,"value":"labels_cult = [\"Culture Exp. (€/inh)\",\"Library (€K)\",\"Perform. Arts (€K)\",\"Sec. Enroll (%)\",\"Sec. Compl. (%)\",\"Inv. Dropout (%)\"]","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":66,"value":"labels_econ = [\"GVA (€M)\",\"Turnover (€M)\",\"Employees\",\"Biz Survival (%)\",\"Tourism (€K)\",\"Hotels (n)\"]\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":27,"value":"Plotly = require(\"https://cdn.plot.ly/plotly-2.27.0.min.js\")\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":25,"value":"$4a","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":29,"value":"RadarPlotMuni(labels_econ, valores_econ, labels_cult, valores_cult, muni_sel.classes, municipio)\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":31,"value":"mca_norm[0]\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":33,"value":"Object.keys(mca_norm[0])\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":102,"value":"radar_embebible = RadarPlotMuni(\n labels_econ,\n valores_econ,\n labels_cult,\n valores_cult,\n muni_sel.classes,\n municipio\n)\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":118,"value":"viewof variable = Inputs.select(\n Object.keys(mca_norm[0]).filter(k => k.endsWith(\"_z\")),\n {label: \"Variable z-score\"}\n)\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":123,"value":"$4b","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":224,"value":"$4c","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":125,"value":"// Selector para variable de inversión (x axis)\nviewof inv_var = Inputs.select(\n Object.keys(mca_norm[0]).filter(k => k.endsWith(\"_z\")),\n {label: \"Variable de inversión (z-score, eje X)\"}\n)\n\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":127,"value":"// Selector para agrupador (color)\nviewof groupfield = Inputs.select(\n [\"classes\", \"cluster\"].filter(k => mca_norm[0][k] !== undefined),\n {label: \"Agrupar/color por\"}\n)","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":129,"value":"pm_years = [\"2019\", \"2020\", \"2021\", \"2022\", \"2023\", \"2024\", \"2025\"]","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":135,"value":"viewof pm_year = Inputs.select(pm_years, {label: \"Año PM2.5 (eje Y)\"})","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":142,"value":"pm_var = `${pm_year}pm`","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":144,"value":"$4d","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":203,"value":"$4e","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":264,"value":"// === Correlation analysis (add these cells BELOW your notebook) ==============================\n// UI: choose variable groups to include and correlation method\nviewof corr_groups = Inputs.checkbox(\n [\"Economic\", \"Cultural\"], // Two groups available\n {label: \"Variable groups to include\", value: [\"Economic\",\"Cultural\"]} // Default: both\n)\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":266,"value":"viewof corr_method = Inputs.radio(\n [\"Pearson\", \"Spearman\"], // Correlation methods\n {label: \"Correlation method\", value: \"Pearson\"} // Default: Pearson (z-scores suit Pearson)\n)\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":268,"value":"// Build the list of z-score variables to correlate, based on selected groups\ncorr_vars = {\n // Collect base names for each group\n const econVars = corr_groups.includes(\"Economic\") ? econ : []; // Economic base names (from your notebook)\n const cultVars = corr_groups.includes(\"Cultural\") ? cult : []; // Cultural base names (from your notebook)\n const allBase = [...econVars, ...cultVars]; // Concatenate bases\n // Return z-score field names in the same order\n return allBase.map(k => `${k}_z`); // Append \"_z\" suffix\n}\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":270,"value":"// Helper: extract a clean column (array) for a given z-score variable, skipping nulls/NaN\nfunction getColumnZ(varName) { // varName like \"Gross Value Added (million €)_z\"\n const col = []; // Output values\n for (const d of mca_norm) { // Iterate all municipalities\n const v = d[varName]; // Read z-score field\n if (v !== undefined && v !== null && Number.isFinite(+v)) col.push(+v); // Keep finite numbers only\n }\n return col; // Return numeric array\n}\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":272,"value":"$4f","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":275,"value":"function rankArray(a) { // Convert numeric array to average ranks\n const idx = a.map((v,i)=>({v,i})).sort((p,q)=>p.v-q.v); // Sort by value\n const ranks = Array(a.length); // Output ranks\n for (let i=0;i= 0.5)\ncorr_network_data = {\n const threshold = 0.5; // Umbral mínimo de correlación absoluta para mostrar un enlace\n const labels = corr_vars.map(v => v.replace(\"_z\",\"\")); // Nombres limpios de variables\n const edges = [];\n\n for (let i = 0; i < labels.length; i++) {\n for (let j = i+1; j < labels.length; j++) {\n const r = corr_result.R[i][j];\n if (Number.isFinite(r) && Math.abs(r) >= threshold) {\n edges.push({\n source: labels[i],\n target: labels[j],\n r\n });\n }\n }\n }\n return edges;\n}\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":290,"value":"// 2. Asignamos posiciones iniciales (en un círculo) y colores según grupo\ncorr_network_nodes = {\n const labels = corr_vars.map(v => v.replace(\"_z\",\"\"));\n const n = labels.length;\n const radius = 2; // radio del círculo\n const angleStep = (2 * Math.PI) / n;\n\n // Determinar grupo por nombre de variable\n function getGroup(varName) {\n if (econ.some(e => varName.includes(e))) return \"Economic\";\n if (cult.some(c => varName.includes(c))) return \"Cultural\";\n return \"Other\";\n }\n\n return labels.map((label, i) => ({\n id: label,\n group: getGroup(label),\n x: radius * Math.cos(i * angleStep),\n y: radius * Math.sin(i * angleStep)\n }));\n}\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":292,"value":"$54","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":294,"value":"// === Trajectory-class correlation heatmap (ADD BELOW; non-breaking) ==========================\n// UI: choose the trajectory class, variable groups, and correlation method\nviewof traj_class = Inputs.select( // Dropdown for trajectory class\n Array.from(new Set( // Unique set of classes\n mca_norm.map(d => (d.classes ?? d.class ?? \"\").toString().trim()) // Read class from 'classes' or 'class'\n .filter(s => s.length) // Keep non-empty values\n )).sort(), // Sort alphabetically\n {label: \"Select trajectory class\"} // UI label\n)\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":297,"value":"viewof tc_corr_groups = Inputs.checkbox( // Checkbox for variable groups\n [\"Economic\",\"Cultural\"], // Available groups\n {label: \"Include variable groups\", value: [\"Economic\",\"Cultural\"]} // Default: both groups on\n)\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":299,"value":"viewof tc_corr_method = Inputs.radio( // Radio for correlation method\n [\"Pearson\",\"Spearman\"], // Methods\n {label: \"Correlation method\", value: \"Pearson\"} // Default: Pearson (z-scores suit Pearson)\n)\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":301,"value":"// Resolve the list of z-score variables to correlate for the selected groups\ntc_corr_vars = { // Compute variable names for the heatmap\n const econVars = tc_corr_groups.includes(\"Economic\") ? econ : []; // Economic variable base names (from your notebook)\n const cultVars = tc_corr_groups.includes(\"Cultural\") ? cult : []; // Cultural variable base names (from your notebook)\n return [...econVars, ...cultVars].map(k => `${k}_z`); // Append \"_z\" suffix (z-score fields)\n}\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":303,"value":"// Filter rows by the selected trajectory class (robust to 'classes' or 'class' field names)\ntc_rows = mca_norm.filter(d => { // Subset of municipalities in the chosen class\n const cls = (d.classes ?? d.class ?? \"\").toString().trim(); // Read class robustly and trim\n return traj_class ? cls === traj_class : true; // Match exactly if a class is selected\n})\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":305,"value":"// Helpers: extract numeric columns, Pearson and Spearman correlations (pairwise complete)\nfunction tc_getColumnZ(rows, varName) { // Extract a numeric array for a z-score field\n const out = []; // Holder for numeric values\n for (const d of rows) { // Iterate filtered municipalities\n const v = d[varName]; // Read z-score field\n const n = +v; // Coerce to number\n if (Number.isFinite(n)) out.push(n); // Keep finite values only\n }\n return out; // Return numeric column\n}\n\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":308,"value":"function tc_pearson(x, y) { // Pearson's r\n const n = Math.min(x.length, y.length); // Align lengths\n if (n === 0) return {r: NaN, n: 0}; // Guard: no data\n const mx = x.reduce((a,b)=>a+b,0)/n, my = y.reduce((a,b)=>a+b,0)/n; // Means\n let num = 0, sx = 0, sy = 0; // Accumulators\n for (let i=0;i({v,i})).sort((p,q)=>p.v-q.v); // Sort by value\n const r = Array(a.length); // Output ranks\n for (let i=0;i (d.classes ?? d.class ?? \"\").toString().trim())\n .filter(s => s.length)\n )).sort()\n ],\n { label: \"Select class (trajectory)\" } // Academic English label\n);\n","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":565,"value":"class_selector;\n","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":567,"value":"// --- Helper: mean z-score for fields named like \"_z\" ---------------------\nmeanZ = (rows, varBase) => {\n const f = `${varBase}_z`; // Compose field name\n const vals = rows.map(r => +r[f]).filter(Number.isFinite); // Keep only numbers\n return vals.length ? vals.reduce((a,b)=>a+b,0)/vals.length : null; // Arithmetic mean or null\n};\n","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":569,"value":"$58","pinned":false,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":571,"value":"// --- Display cell: call the renderer ------------------------------------------\nradar_by_class = RadarPlotByClass(labels_econ, labels_cult, class_selector);\n","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":573,"value":"\n// --- Embeddable cell (optional): identical output, convenient for iframes ------\nradar_by_class_embeddable = RadarPlotByClass(labels_econ, labels_cult, class_selector);","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"},{"id":611,"value":"","pinned":true,"hidden":false,"mode":"ojs","author":"$undefined","summary":"$undefined","tool":"$undefined","providerMetadata":"$undefined","attachments":"$undefined","output":"$undefined","database":"$undefined"}],"files":"$W59","stdlib":"1"}} 24:null