Data Engineering and BI courses are free this week!
scatterPlot(mydata, x = "nox", y = "no2", z = NA, method = "scatter",
group = NA, avg.time = "default", data.thresh = 0, statistic = "mean",
percentile = NA, type = "default", smooth = FALSE, spline = FALSE,
linear = FALSE, ci = TRUE, mod.line = FALSE, cols = "hue",
plot.type = "p", key = TRUE, key.title = group, key.columns = 1,
key.position = "right", strip = TRUE, log.x = FALSE, log.y = FALSE,
x.inc = 10, y.inc = 10, limits = NULL, y.relation = "same",
x.relation = "same", ref.x = NULL, ref.y = NULL, k = 100,
map = FALSE, auto.text = TRUE, ...)x can be
one of the openair built in types such as
"year" or "season".method = "scatter" or method = "level".
Note that for method = "scatter" points will be
coloured according to a continuous colour scale, whereas
for method = "hexbin package). avg.time. A value
of zero means that all available data will be used in a
particular period regardless if of the number of values
available. Conversely, a value of 100statistic = "percentile" and when aggregating the
data with avg.time. The default is 95. Not used if
avg.time = "default".type determines how the data are split
i.e. conditioned, and then plotted. The default is will
produce a single plot using the entire data. Type can be
one of the built-in types as detailed in cutData
e.g. TRUE; optionally with 95% confidence intervals
shown. For method = "level" a smooth surface will
be fitted to binned data.TRUE. This is particularly useful when there are
fewer data points or when a connection line between a
sequence of points is required.TRUE; optionally with 95% confidence intervals
shown. The equation of the line and R2 value is also
shown.TRUE three lines are added to
the scatter plot to help inform model evaluation. The 1:1
line is solid and the 1:0.5 and 1:2 lines are dashed.
Together these lines help show how close a group of
points are to a 1:1 relationship and RColorBrewer
colours --- see the openair openColours
funclattice plot type. Can be
TRUE.columns to be less than the number of
pollutants.TRUE.FALSE. If TRUE a well-formatted
log10 scale is used. This can be useful for checking
linearity once logged.FALSE. If TRUE a well-formatted
log10 scale is used. This can be useful for checking
linearity once logged.method = "level".method = "level".method = "level" the function
does its best to choose sensible limits automatically.
However, there are circumstances when the user will wish
to set different ones. The limits are set in the form
c(lower, upper), so <gam for
fitting a smooth surface when method = "level".TRUE (default) or
FALSE. If TRUE titles and axis labels will
automatically try and format pollutant names and units
properly e.g. by subscripting the cutData and an appropriate lattice plot
function (xyplot, levelplot or
hexbinplot depending on method). For
example, scascatterPlot
also returns an object of class ``openair''. The object
includes three main components: call, the command
used to generate the plot; data, the data frame of
summarised information used to make the plot; and
plot, the plot itself. If retained, e.g. using
output <- scatterPlot(mydata, "nox", "no2"), this
output can be used to recover the data, reproduce or rework
the original plot or undertake further analysis.An openair output can be manipulated using a number of
generic operations, including print, plot and
summary. See openair.generics for
further details.
scatterPlot is the basic function for plotting
scatterPlots in flexible ways in openair. It is
flexible enough to consider lots of conditioning variables
and takes care of fitting smooth or linear relationships to
the data.There are four main ways of plotting the relationship
between two variables, which are set using the
method option. The default "scatter" will
plot a conventional scatterPlot. In cases where there are
lots of data and over-plotting becomes a problem, then
method = "hexbin" or method = "density" can
be useful. The former requires the hexbin package to
be installed.
There is also a method = "level" which will bin the
x and y data according to the intervals set
for x.inc and y.inc and colour the bins
according to levels of a third variable, z.
Sometimes however, a far better understanding of the
relationship between three variables (x, y
and z) is gained by fitting a smooth surface through
the data. See examples below.
A smooth fit is shown if smooth = TRUE which can
help show the overall form of the data e.g. whether the
relationship appears to be linear or not. Also, a linear
fit can be shown using linear = TRUE as an option.
The user has fine control over the choice of colours and symbol type used.
Another way of reducing the number of points used in the
plots which can sometimes be useful is to aggregate the
data. For example, hourly data can be aggregated to daily
data. See timePlot for examples here.
By default plots are shown with a colour key at the bottom
and in the case of conditioning, strips on the top of each
plot. Sometimes this may be overkill and the user can opt
to remove the key and/or the strip by setting key
and/or strip to FALSE. One reason to do this
is to maximise the plotting area and therefore the
information shown.
linearRelation, timePlot and
timeAverage for details on selecting
averaging times and other statistics in a flexible way# load openair data if not loaded already
data(mydata)
# basic use, single pollutant
scatterPlot(mydata, x = "nox", y = "no2")
# scatterPlot by year
scatterPlot(mydata, x = "nox", y = "no2", type = "year")
# scatterPlot by day of the week, removing key at bottom
scatterPlot(mydata, x = "nox", y = "no2", type = "weekday", key =
FALSE)
# example of the use of continuous where colour is used to show
# different levels of a third (numeric) variable
# plot daily averages and choose a filled plot symbol (pch = 16)
# select only 2004
dat2004 <- selectByDate(mydata, year = 2004)
scatterPlot(dat2004, x = "nox", y = "no2", z = "co", avg.time = "day", pch = 16)
# show linear fit, by year
scatterPlot(mydata, x = "nox", y = "no2", type = "year", smooth =
FALSE, linear = TRUE)
# do the same, but for daily means...
scatterPlot(mydata, x = "nox", y = "no2", type = "year", smooth =
FALSE, linear = TRUE, avg.time = "day")
# log scales
scatterPlot(mydata, x = "nox", y = "no2", type = "year", smooth =
FALSE, linear = TRUE, avg.time = "day", log.x = TRUE, log.y = TRUE)
# also works with the x-axis in date format (alternative to timePlot)
scatterPlot(mydata, x = "date", y = "no2", avg.time = "month",
key = FALSE)
## multiple types and grouping variable and continuous colour scale
scatterPlot(mydata, x = "nox", y = "no2", z = "o3", type = c("season", "weekend"))
# use hexagonal binning
library(hexbin)
# basic use, single pollutant
scatterPlot(mydata, x = "nox", y = "no2", method = "hexbin")
# scatterPlot by year
scatterPlot(mydata, x = "nox", y = "no2", type = "year", method =
"hexbin")
## bin data and plot it - can see how for high NO2, O3 is also high
\dontrun{
scatterPlot(mydata, x = "nox", y = "no2", z = "o3", method = "level", x.inc = 10, y.inc = 2)
}
## fit surface for clearer view of relationship - clear effect of
## increased O3
\dontrun{
scatterPlot(mydata, x = "nox", y = "no2", z = "o3", method = "level",
x.inc = 10, y.inc = 2, smooth = TRUE)
}Run the code above in your browser using DataLab