Create preliminary exploratory data visualisations of an entire dataset to identify problems or unexpected features using 'ggplot2'.
Initially inspired by
vis_dat helps you visualise a dataframe and "get a look at the data" by displaying the variable classes in a dataframe as a plot with
vis_dat, and getting a brief look into missing data patterns using
visdat was chosen as I think in the future it could be integrated with
testdat. The idea being that first you visualise your data (
visdat), then you run tests from
testdat to fix them.
There are two main commands in the
vis_dat() visualises a dataframe showing you what the classes of the columns are, and also displaying the missing data.
vis_miss() visualises just the missing data, and allows for missingness to be clustered and columns rearranged.
vis_miss() is similar to
missing.pattern.plot from the
mi package. Unfortunately
missing.pattern.plot is no longer in the
mi package (as of 14/02/2016).
You can read more about visdat in the vignette, "using visdat"".
Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.
Let's see what's inside the
airquality dataset from base R, which contains information about daily air quality measurements in New York from May to September 1973. More information about the dataset can be found with
The plot above tells us that R reads this dataset as having numeric and integer values, with some missing data in
Solar.R. The classes are represented on the legend, and missing data represented by grey. The column/variable names are listed on the x axis.
vis_dat sorts the columns according to the type of the data in the vectors. You can turn this off by setting
sort_type = FALSE.
vis_dat(airquality,sort_type = FALSE)
To demonstrate what visdat looks like when you have different kinds of data, we can look at the dataset
typical_data, provided within
visdat, and created with the excellent
We can also look into using even wider data, looking at
We can explore the missing data further using
The percentages of missing/complete in
vis_miss are accurate to 1 decimal place.
You can cluster the missingness by setting
cluster = TRUE.
vis_miss(airquality,cluster = TRUE)
The columns can also just be arranged by columns with most missingness, by setting
sort_miss = TRUE.
vis_miss(airquality,sort_miss = TRUE)
vis_miss indicates when there is a very small amount of missing data at <0.1% missingness.
test_miss_df <- data.frame(x1 = 1:10000,x2 = rep("A", 10000),x3 = c(rep(1L, 9999), NA))vis_miss(test_miss_df)
vis_miss will also indicate when there is no missing data at all.
Thank you to Ivan Hanigan who first commented this suggestion after I made a blog post about an initial prototype
ggplot_missing, and Jenny Bryan, whose tweet got me thinking about
vis_dat, and for her code contributions that removed a lot of errors.
Thank you to Hadley Wickham for suggesting the use of the internals of
readr to make
Thank you to Miles McBain for his suggestions on how to improve
vis_guess. This resulted in making it at least 2-3 times faster.
Thanks also to Carson Sievert for writing the code that combined
visdat, and for Noam Ross for suggesting this in the first place.
add_vis_dat_pal()(internal) to add a palette for
vis_guessnow gets a palette argument like
plotlyvis_*_ly interactive graphs:
vis_compare_ly()These simply wrap
plotly::ggplotly(vis_*(data)). In the future they will be written in
plotlyso that they can be generated much faster
vis_family are now flipped by default
vis_missnow shows the % missingness in a column, can be disabled by setting
show_perc_colargument to FALSE
flipargument, as this should be the default
vdiffr. Code coverage is now at 99%
paper.mdwritten and submitted to JOSS
flip = TRUE, to
vis_miss. This flips the x axis and the ordering of the rows. This more closely resembles a dataframe.
vis_miss_lyis a new function that uses plotly to plot missing data, like
vis_miss, but interactive, without the need to call
plotly::ggplotlyon it. It's fast, but at the moment it needs a bit of love on the legend front to maintain the style and features (clustering, etc) of current
vis_missnow gains a
show_percargument, which displays the % of missing and complete data. This is switched on by default and addresses issue #19.
vis_compareis a new function that allows you to compare two dataframes of the same dimension. It gives a fairly ugly warning if they are not of the same dimension.
vis_datgains a "palette" argument in line with issue 26, drawn from http://colorbrewer2.org/, there are currently three arguments, "default", "qual", and "cb_safe". "default" provides the ggplot defaults, "qual" uses some colour blind unfriendly colours, and "cb_safe" provides some colours friendly for colour blindness.
1:rnow(x)and replaced with
vis_dat_ly, as it currently does not work.
vis_compareare very beta
vis_compareto be different to the ggplot2 standards.
vis_misslegend labels are created using the internal function
miss_guide_labelwill check if data is 100% missing or 100% present and display this in the figure. Additionally, if there is less than 0.1% missing data, "<0.1% missingness" will also be displayed. This sort of gets around issue #18 for the moment.
miss_guide_labellegend labels function.
mutate_each_(). This solves issue #3 where
vis_datcouldn't take variables with spaces in their name.
vis_misswere updated so that you can make them all interactive using the latest dev version of
plotlyfrom Carson Sievert.
vis_guess(), a function that uses the unexported function