Histograms

A histogram is a plot that summarizes the underlying frequency of a set of data with the variable of interest on one axis and the frequency distribution of that variable in the other axis. Histogram can be plotted on continuous or categorical variable.

From a data viewer session, click on New plot > Bar chart then select a data node of interest and the content data, which can be a feature or attribute in the data node .

If the content is a numeric, the X-axis in the histogram will display the value of the variable, Y-axis is the frequency of the values.

Change the data displayed on the histogram by using the Configure > Axes menu and selecting the desired variable to display.

Use the "Sort by" function to sort the plot. The default sorting is by Value on the x-axis and this default setting is sorted in ascending order. Users have the option to change that by changing the Default to value or frequency in the sort option.

Users can color the histograms by a categorical attribute using the Style > Color by function

The bars in the histogram can be configured as Stacked or not. When the stacked is turned off, the bars will be split into different group at each range.

Users also have the option to bin by either Count or Size. When binned by Count, the user specifies the number of bins for the data and the distribution is fit into the specified number of bins.

When binned by Size, the user specifies the number of items in the bin (size of a bin). This is used to calculate the number of bins required for the data. Data below is binned by Size.