SimonGoring/neotoma_and_bacon

## neotoma_and_bacon
#  This needs to run in the directory in which you have Bacon installed.
#  If you do not currently have the `neotoma` package installed then uncomment
#  and run the following code. Right now you will need to install the package from GitHub
#  because our latest bug fixes haven't been pushed up into CRAN.
#
#  install.packages('devtools')
#  library(devtools)
#  install_github('ropensci/neotoma')
#
#  The Neotoma package is described more fully here:
#
#  Goring, S., Dawson, A., Simpson, G. L., Ram, K., Graham, R. W., Grimm, E. C., &
#    Williams, J. W.. (2015). neotoma: A Programmatic Interface to the Neotoma
#    Paleoecological Database, 1(1), Art. 2. DOI: http://doi.org/10.5334/oq.ab
#
#

library(neotoma)
library(maps)  # you may also want to install this.

#  There are (surprisingly?) no data records from Nevada currently.  Instead we will
#  pull records from California. In this call I want to find high elevation sites
#  because they're kind of interesting.

ca_pollen <- get_dataset(gpid = 'California', datasettype = 'pollen',
                         ageold = 10000,  altmin=1000)

plot(get_site(ca_pollen)[,c('long', 'lat')],
     xlim = c(-125, -115), ylim=c(30, 45),
     pch=19, col=2)
map('world', add=TRUE)
map("state", add=TRUE)

#  Now we can download the records.
#  You should see the site names running by.  As you do this, reflect on all the work
#  that's gone into these records and give thanks to the named and unnamed workers who
#  toiled behind a microscope for months at a time so that you could download their data
#  in mere seconds.
ca_download <- get_download(ca_pollen)

#  For this example we should find the one that gives us the most dated material.
dated_samples <- get_chroncontrol(ca_download)

#  This next line is just FYI - we're getting a vector of the number of dates in each core.
#  Some will return a NULL if there is no associated control table.  This happens for single
#  stratigraphic pollen sections for example.
sapply(dated_samples, function(x)nrow(x$chron.control))

#  The last core (Taquitz Meadow) has 6, controls:
#  The number is quotes is the dataset number.  To choose a different dataset look at the
#  available datasets and enter in a different number.

plot(dated_samples[['15594']]$chron.control[,c('depth', 'age')])
#  You can try a few different ones to see how things look.

#  So Taquitz Meadow looks good.  We can look at it in the Neotoma Explorer like this:
#  http://apps.neotomadb.org/explorer/?datasetid=15594

# The original model was generated in Bacon, let's see how well we do:
write_agefile(ca_download[['15594']], chronology = 1,
              path = '.', corename = 'TAQUITZ', cal.prog = 'Bacon')

#  Source Bacon . . .
source('Bacon.R')

#  Please note that this will actually take a very very long time.  It might be worth picking a different site.
Bacon('TAQUITZ')
	# This needs to run in the directory in which you have Bacon installed.
	# If you do not currently have the `neotoma` package installed then uncomment
	# and run the following code. Right now you will need to install the package from GitHub
	# because our latest bug fixes haven't been pushed up into CRAN.
	#
	# install.packages('devtools')
	# library(devtools)
	# install_github('ropensci/neotoma')
	#
	# The Neotoma package is described more fully here:
	#
	# Goring, S., Dawson, A., Simpson, G. L., Ram, K., Graham, R. W., Grimm, E. C., &
	# Williams, J. W.. (2015). neotoma: A Programmatic Interface to the Neotoma
	# Paleoecological Database, 1(1), Art. 2. DOI: http://doi.org/10.5334/oq.ab
	#
	#

	library(neotoma)
	library(maps) # you may also want to install this.

	# There are (surprisingly?) no data records from Nevada currently. Instead we will
	# pull records from California. In this call I want to find high elevation sites
	# because they're kind of interesting.

	ca_pollen <- get_dataset(gpid = 'California', datasettype = 'pollen',
	ageold = 10000, altmin=1000)

	plot(get_site(ca_pollen)[,c('long', 'lat')],
	xlim = c(-125, -115), ylim=c(30, 45),
	pch=19, col=2)
	map('world', add=TRUE)
	map("state", add=TRUE)

	# Now we can download the records.
	# You should see the site names running by. As you do this, reflect on all the work
	# that's gone into these records and give thanks to the named and unnamed workers who
	# toiled behind a microscope for months at a time so that you could download their data
	# in mere seconds.
	ca_download <- get_download(ca_pollen)

	# For this example we should find the one that gives us the most dated material.
	dated_samples <- get_chroncontrol(ca_download)

	# This next line is just FYI - we're getting a vector of the number of dates in each core.
	# Some will return a NULL if there is no associated control table. This happens for single
	# stratigraphic pollen sections for example.
	sapply(dated_samples, function(x)nrow(x$chron.control))

	# The last core (Taquitz Meadow) has 6, controls:
	# The number is quotes is the dataset number. To choose a different dataset look at the
	# available datasets and enter in a different number.

	plot(dated_samples[['15594']]$chron.control[,c('depth', 'age')])
	# You can try a few different ones to see how things look.

	# So Taquitz Meadow looks good. We can look at it in the Neotoma Explorer like this:
	# http://apps.neotomadb.org/explorer/?datasetid=15594

	# The original model was generated in Bacon, let's see how well we do:
	write_agefile(ca_download[['15594']], chronology = 1,
	path = '.', corename = 'TAQUITZ', cal.prog = 'Bacon')

	# Source Bacon . . .
	source('Bacon.R')

	# Please note that this will actually take a very very long time. It might be worth picking a different site.
	Bacon('TAQUITZ')