// A function to summarize a single column SummarizeColumn = ( data, col, { subset = [], split_attr = "", split_values = [], split_data_sets = [], split_subset_sets = [], split_colors = [] } = {} ) => { let content, value, format, el, chart, missing_label, pct_missing, min, max, median, mean, sd; // Construct content based on type const type = getType(data, col); const col1 = htl.html`${icon_fns[ type ]()}${ col === "" ? "unlabeled" : col }`; switch (type) { // Categorical columns case "ordinal": format = d3.format(",.0f"); let combined_categories_lst = []; for (let i = 0; i < split_data_sets.length; i++) { combined_categories_lst[i] = get_combined_categoryData( get_subset_categories( split_data_sets[i], col, split_data_sets[i].length ), get_subset_categories( split_subset_sets[i], col, split_data_sets[i].length ), col ); } // Calculate category percent and count const categories = d3 .rollups( data, (v) => ({ count: v.length, pct: v.length / data.length || 1, domain: "whole" }), (d) => d[col] ) .sort((a, b) => b[1].count - a[1].count) .map((d) => { let obj = {}; obj[col] = d[0] === null || d[0] === "" ? "(missing)" : d[0]; obj.count = d[1].count; obj.pct = d[1].pct; obj.domain = d[1].domain; return obj; }); const subset_categories = subset.length != 0 ? d3 .rollups( subset, (v) => ({ count: v.length, pct: v.length / data.length || 1, domain: "subset" }), (d) => d[col] ) .sort((a, b) => b[1].count - a[1].count) .map((d) => { let obj = {}; obj[col] = d[0] === null || d[0] === "" ? "(missing)" : d[0]; obj.count = d[1].count; obj.pct = d[1].pct; obj.domain = d[1].domain; return obj; }) : []; const combined_categories = subset_categories.length != 0 ? get_combined_categoryData(categories, subset_categories, col) : []; // Calculate pct. missing pct_missing = data.filter((d) => d[col] === null || d[col] === "").length / data.length; // Create the chart const stack_chart = combined_categories.length != 0 ? SmallStack(combined_categories, col) : SmallStack(categories, col); // element to return el = htl.html` ${col1} ${ combined_categories_lst.length != 0 ? combined_categories_lst.map( (d, index) => htl.html`

${SmallStack( d, col, { split_color: split_colors.length != 0 ? split_colors[index] : "" } )}

` ) : htl.html`

${stack_chart}

` } `; value = { column: col, type, missing: pct_missing, n_categories: categories.length }; break; // Date columns // Not configured for split_attr case "date": // Calculate and format start / end const start = d3.min(data, (d) => +d[col]); const end = d3.max(data, (d) => +d[col]); mean = d3.mean(data, (d) => +d[col]); median = d3.median(data, (d) => +d[col]); sd = d3.deviation(data, (d) => +d[col]); // Calculate pct. missing pct_missing = data.filter((d) => d[col] === null || d[col] === "").length / data.length; chart = Histogram(data, col, { type: type, subset: subset }); // Element to return el = htl.html` ${col1}

${chart}

${ split_data_sets.length != 0 ? split_data_sets.map( (d, index) => htl.html`

${Histogram( d, col, { type: type, subset: split_subset_data_sets[index] } )}

` ) : htl.html`

${chart}

` } `; value = { column: col, type, missing: pct_missing, n_categories: null }; break; // Continuous columns default: // Compute values min = d3.min(data, (d) => +d[col]); max = d3.max(data, (d) => +d[col]); mean = d3.mean(data, (d) => +d[col]); median = d3.median(data, (d) => +d[col]); sd = d3.deviation(data, (d) => +d[col]); format = d3.format(",." + d3.precisionFixed(sd / 10) + "f"); pct_missing = data.filter((d) => d[col] === null || isNaN(d[col])).length / data.length; chart = Histogram(data, col, { type: type, subset: subset }); // Element to return el = htl.html` ${col1} ${ split_data_sets.length != 0 ? split_data_sets.map( (d, index) => htl.html`

${Histogram( d, col, { type: type, subset: split_subset_sets[index], split_color: split_colors.length != 0 ? split_colors[index] : "" } )}

` ) : htl.html`

${chart}

` } `; value = { column: col, type, missing: pct_missing, n_categories: null }; break; } el.value = value; el.appendChild(html``); return el; }