loom-data-visualization

# Data Visualization ## Overview Match the chart to the data relationship, encode quantities in perceptually accurate channels, avoid distortion, and make it accessible. This skill is the design layer above the plotting library. ## Chart selection by data relationship | Goal | Prefer | Avoid | | --- | --- | --- | | Compare across categories | horizontal bar (sorted), dot plot | pie with >~5 slices | | Part-to-whole | stacked bar, treemap; pie only ≤5 slices | many pies / donuts for precise comparison | | Distribution | histogram, box, violin, ECDF | bar of means (hides spread) | | Two-variable relationship | scatter (+ trend), 2D density/hexbin when dense | scatter with 100k overplotted points | | Correlation matrix | heatmap (diverging scale) | 3D surface | | Trend over time | line; area for cumulative | connecting unordered categories with lines | | Ranking | ordered bar / lollipop | pie | | Performance vs target | bullet chart | gauge cluster | | Geographic | choropleth (normalized), point/flow map | raw-count choropleth (just shows population) | ## Perceptual accuracy (why bars beat pies) Cleveland–McGill ranking of how accurately humans decode a quantity: **position on common scale > position on non-aligned scale > length > angle/slope > area > volume > color hue/saturation.** - Encode the *most important* quantity in position/length (bar, dot, line), not area or color. - Pie/donut = angle+area (weak); bubble = area (people underestimate large circles — area scal...