SimonGoring

library(neotoma)
library(reshape2)

pollen_data <- get_dataset(datasettype= 'pollen')
full_records <- get_download(pollen_data) # this takes a bit of time

pub.dates <- get_publication(pollen.data) # so does this

earliest.year <- do.call(rbind.data.frame, 
                         lapply(pub.dates, function(x)data.frame(id = NA, 

SimonGoring

library(neotoma)
library(ggplot2)
library(reshape2)

ds_upload <- get_dataset()

subyr <- lapply(ds_upload, function(x){
  if(nrow(x$submission) == 0){
    subdate <- NA
  } else {

SimonGoring

```{r figure1, fig.width=6, fig.height=5, echo = FALSE, warning = FALSE, message=FALSE}

#  This is the chunk where 'climate_values' is created (it's the one causing errors)

land_use$class[land_use$class == 'Water'] <- NA

land_use_plot <- natural[[2]] + 
  geom_tile(data = land_use, aes(x = x, y = y, fill = class)) +
  scale_fill_manual(values = c('#ff7f00', '#e41a1c', '#33a02c'))

SimonGoring

#  This executes the map figure shown for GEOG378 Section 2.1 using R.
#  The figure demonstrates the impact that changing datum may have on lat/long coordinates.

#  Load the package 'rgdal'.  If this package is missing on your system you can load it
#  using the call 'install.packages('rgdal')'

library(rgdal)

# This is a built-in GDAL command, implemented in R using the rgdal package loaded above.
datum_list  <- projInfo(type='datum')

SimonGoring

library(neotoma)
library(ggplot2)
library(lubridate)
library(reshape2)

all.ds <- get_dataset()

sub_tables <- function(x){
  
  dates <- try(as.Date(x$submission[,1]))

SimonGoring

library(neotoma)

ostracode <- get_dataset(datasettype='ostracode surface sample', loc=c(-100,43,-92,48))
chemistry <- get_dataset(datasettype='water chemistry',          loc=c(-100,43,-92,48))
diatoms   <- get_dataset(datasettype='diatom surface sample',    loc=c(-100,43,-92,48))
pollen    <- get_dataset(datasettype='pollen surface sample',    loc=c(-100,43,-92,48))

ostracode_dl <- get_download(ostracode)
chemistry_dl <- get_download(chemistry)
diamtom_dl   <- get_download(diatoms)

SimonGoring

#  Scraping ECOLOG-L for job ads:
#  This is the format of an ecolog URL:
#  https://listserv.umd.edu/cgi-bin/wa?A1=ind1412e&L=ecolog-l
#
#  most of it is pretty common.  The key portion is A1=ind[YY][MM][a-e] where we
#  insert the YY year and MM month, and then cycle a - e by week.
#
#  This then returns an HTML page where the unique messages are 
library(plyr)

SimonGoring

license: MIT

SimonGoring

<resource xmlns:xmlns="http://datacite.org/schema/kernel-3" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://datacite.org/schema/kernel-3 http://schema.datacite.org/meta/kernel-3/metadata.xsd">
  <creators>
    <Creator>
      <creatorName>Labelle, Claude</creatorName>
      <affiliation>1804 Tupper No. 2, Montreal, PQ H3H 1N4, CANADA</affiliation>
    </Creator>
    <Creator>
      <creatorName>Larouche, Alayn C.</creatorName>
      <affiliation>Laboratoire Jacques-Rousseau, Département de géographie, Université de Montréal, C.P. 6128 Succursale A, Montréal, PQ H3C 3J7, CANADA</affiliation>
    </Creator>

SimonGoring

# SQL queries:
default_call <- function(x) {
  paste0("SELECT CONCAT(SiteName, ' ', DatasetType, ' dataset') AS SiteName,
  'Title' AS titleType, ContactName AS creatorName, 'ORCID' AS nameIdentifierScheme, 
  'http://orcid.org' AS schemeURI, Address AS affiliation, YEAR(ds.RecDateCreated) as publicationyear 
  FROM (SELECT * FROM datasets WHERE DatasetID = ", x, ") AS ds INNER JOIN datasetpis ON ds.DatasetID = datasetpis.DatasetID
  INNER JOIN collectionunits AS cu ON ds.CollectionUnitID = cu.CollectionUnitID INNER JOIN sites AS sts ON cu.SiteID = sts.SiteID
  INNER JOIN datasettypes AS dst ON ds.DatasetTypeID = dst.DatasetTypeID INNER JOIN contacts ON datasetpis.ContactID = contacts.ContactID;")
}