Single dataset

Data Package on KNB: https://doi.org/10.5063/F1CJ8BPH

library(metajam)

# Download info
dataset_url <- "https://knb.ecoinformatics.org/knb/d1/mn/v2/object/urn%3Auuid%3A7fc6f6db-c5ea-426a-a743-1f2edafb43b8"
data_path <- "~/Desktop"

# Download
prod_path <- download_d1_data(data_url = dataset_url, path = data_path)
hh_lang <- read_d1_files(folder_path  = prod_path)

How many German speakers?

library(tidyverse)

# Get the sum accross region per year
german_sp <- hh_lang$data %>% 
  group_by(Year) %>% 
  summarize(n_german = sum(german))

# plot it                                           
plot(german_sp)

Single dataset - with header

Data Package on ADC: https://doi.org/10.18739/A25X25C37

Download

library(metajam)

# Download info
dataset_url <- "urn%3Auuid%3Aec05ab95-844c-4cf0-95b0-40e02ba44f63"
data_path <- "~/Desktop"

# Download
prod_path <- download_d1_data(data_url = dataset_url, path = data_path)

Read into R

data_transect <- read_d1_files(prod_path)
View(data_transect$data)

Does not look right!! Let us check the metadata!

data_transect$attribute_metadata

Does not match what we imported…

Let us look at the data. There is a header!! since read_d1_files use readr::read_csv by default we can pass all the options this function has:

data_transect <- read_d1_files(prod_path, skip=7)

View(data_transect$data)

Even better:

# Read only the data
data_transect <- read_d1_files(prod_path, skip=9, col_names=FALSE)
# View(data_transect$data)

# We have the header in the attribute level metadata!
View(data_transect$attribute_metadata)

# Add headers to the data set
names(data_transect$data) <- data_transect$attribute_metadata$attributeName
# View(data_transect$data)

Changing the function to read files - Excel

Data package on KNB: https://doi.org/10.5063/F19W0CQ5

Download

library(metajam)

# Download info
dataset_url <- "https://knb.ecoinformatics.org/knb/d1/mn/v2/object/urn%3Auuid%3Ab04cd4ce-ee5f-416a-89d4-83ac80180a26"
data_path <- "~/Desktop"

# Download
yield_path <- download_d1_data(data_url = dataset_url, path = data_path)

# View(yield_data$data)

Read the data

library(readxl)

yield_data <- read_d1_files(yield_path, "read_excel")

Check version

check_version("doi:10.18739/A2HF7Z", formatType = "metadata")

Not limited to tabular data

Data package on KNB: https://doi.org/10.5063/F1KD1VVS

# download_d1_data("https://knb.ecoinformatics.org/knb/d1/mn/v2/object/karakoenig.31.1", "~/Desktop")

# Read the geojson
nm_wells <- geojsonio::geojson_read("~/Desktop/brun.34.23__nmwells/nmwellsNA.json", what="sp")

# Map it
leaflet::leaflet(nm_wells) %>%
  leaflet::setView(-98, 40, zoom = 4) %>%
  leaflet::addTiles() %>% 
  leaflet::addCircleMarkers()
  
# Still works to load metadata
read_d1_files("~/Desktop/brun.34.23__nmwells")