Overview # A ridgeline plot (previously referred to as as a “joyplot”) is a way to examine the distributions of a numerical variable for several different groups. Ridgeline plots can present values in absolute terms (i.e., the heights of the ridges correspond to the actual values) or as densities (i.e., the heights of the ridges correspond to proportions within edge ridge component). Ridgeline plots showing absolute values is sort of like a filled line plot. ...
Overview # Well, this one’s a fun one. Parliament plots are a way to visualize the composition or votes of legislatures, with the shapes representing seats positioned in a manner reminiscent of the actual seating arrangements. Those seats can be mapped to party or faction affiliations, or even voting alignments. Once mapped, associations can be reflected using such features as colors or shape types. In terms of application, parliament plots are very similar to waffle plots. ...
Overview # Venn diagrams are used to visually show commonalities between groups. Usually, distinct groups are represented in Venn diagrams as circles or ellipses. Where these shapes overlap represent commonalities between groups. Oftentimes, the different parts of a Venn diagram are labeled with the groups' defining features and with counts of the number of things that fall within each part of the Venn diagram. So if there’s a circle for Group A, and another circle for Group B, and there’s some overlap of those two circles, where there is overlap represents individuals that are part of both Group A and Group B. ...
Overview # A donut chart is more or less a pie chart. Similar to a pie chart, a donut chart conveys a senses of relative proportions of different categories or groups. Like a pie chart, a donut chart suffers from the same major flaw: its design makes it inherently difficult for people to visually draw clear comparisons between categories. Data # Donut charts require a categorical field and a numerical field. ...
Overview # Well, this is potentially a controversial one: pie charts. A pie chart is a circular plot that is divided into wedges, where the wedges reflect categories, and the size of the wedge corresponds to the proportion of the categories. The major criticism of pie charts is that humans do a very poor job of visually comparing angular wedges. The whole point of data visualization is to convey dense data clearly, and pie charts fail at that, especially if there are too many categories. ...
Overview # A box and whisker plot (aka boxplot) is a way to show data distribution. The dividing lines along the “box” part of box and whisker plot typically represent the median (the middle observation in a sequentially sorted dataset), the upper quartile (the observation that is the middle point of the upper half of the dataset), and the lower quarter (the observation that is the middle in the lower half of the dataset). ...
Overview # Correlation refers to the tendency for different data fields (or variables) to move together. Here’s a simple conceptual example: we typically expect that as a person’s height goes up (such as when the person ages and grows), that person’s weight would go up as well. In this case, we could say there is a strong positive correlation between height and weight. If the fields move in the same direction (e. ...
Overview # A histogram is a visualization that shows the spread of a numerical variable. The way histograms are assembled is by taking a numerical variable, and chunking the data up into bins. Each bin reflects a count of the number of observations that fall within a range. For example, if we have a super simple numerical variable made up of 1, 3, 5, 7, 11, 13, and we define two bins, where one bin includes everything from 0 to 10, and the other bin containing everything everything above 10 to 20, then the bin from 0 to 10 includes 4 observations, and the bin from above 10 to 20 includes two observations. ...
Overview # A stream graph is a variation of a stacked area chart. Stream graphs shows proportions of different categories along some other piece of sequenced data. If you look at the data as vertical slices, the width of each section represents how much of something there is at each particular vertical slice. You could call it a “stream plot” I suppose, but “stream graph” seems to be much more common. ...
Overview # A beeswarm plot is a way to display the spread of a numerical data field. Think of it as a histogram, but rather than having heights of bars corresponding to the number of points within particular ranges, a beeswarm shows individual data points. The data points in a beeswarm plot are spread out along a cross section to minimize point overlap so it’s visually easy to identify clusters of data points along a single continuous variable. ...