imputeTS (version 1.5)

plotNA.distributionBar: Visualize Distribution of Missing Values (Barplot)

Description

Visualization of missing values in barplot form. Especially useful for time series with a lot of observations.

Usage

plotNA.distributionBar(x, breaks = 10, breaksize = NULL, percentage = T,
  legend = T, axis = T, space = 0, col = c("indianred2", "green2"),
  main = "Distribution of NAs", xlab = "Time", ylab = NULL, ...)

Arguments

x

Numeric Vector (vector) or Time Series (ts) object containing NAs

breaks

Defines the number of bins to be created. If breaksize isn't NULL it is overpowered by this parameter

breaksize

Defines how many observations should be in one bin. The required number of overall bins is afterwards calculated automatically.

percentage

Whether the NA / non-NA ration should be given as percent or absolute numbers

legend

If TRUE a legend is shown at the bottom of the plot. A custom legend can be obtained by setting this parameter to FALSE and using legend function

axis

If TRUE a axis with labels is added. A custom axis can be obtained by setting this parameter to FALSE and using axis function

space

The amount of space (as a fraction of the average bar width) left before each bar.

col

A vector of colors for the bars or bar components.

main

Main title for the plot

xlab

Label for x axis of the plot

ylab

Label for y axis of plot

...

Additional graphical parameters that can be passed through to barplot

Details

This function visualizes the distribution of missing values within a time series. Therefore the time series is plotted and whenever a value is NA the background is colored differently. This gives a nice overview, where in the time series most of the missing values occur.

See Also

plotNA.distribution, plotNA.gapsize, plotNA.imputations

Examples

#Prerequisite: Load a time series with missing values
x <- tsHeating

#Example 1: Visualize the missing values in this time series
plotNA.distributionBar(x, breaks = 20)