ds %>%
filter(location=="Canberra") %>%
ggplot(aes(x=date, y=max_temp)) +
geom_point(shape=".") +
geom_smooth(method="gam", formula=y~s(x, bs="cs")) +
labs(x=vnames["date"], y=vnames["max_temp"])
This scatter plot of x=date against
y=max_temp shows a pattern of seasonality over
the dataset and a trend line over the period of the dataset.
The scatter plot is again created using ggplot2::geom_point().
Typical of scatter plots of big data there will be many overlaid
points. To reduce the impact the points are reduced to a small dot
using shape="." .
An additional layer is added consisting of a smooth fitted curve using
ggplot2::geom_smooth(). The dataset has many points and so a
smoothing method recommended is method="gam" which
will automatically be chosen if not specified but with a message to
that effect. The formula specified using formula= is also
the default for method="gam".
|