jhnwllr

library(dplyr)
library(readr)
library(rgbif)
library(taxize)
library(CoordinateCleaner)

# 4 Odonata scientific names
name_list = 
c(
"Cordulegaster charpentieri Kolenati, 1846",

jhnwllr

import sys.process._
import org.apache.spark.sql.SaveMode

val save_table_name = "ocean_export_france"

df_export.
write.format("csv").
option("sep", "\t").
option("header", "false"). // add header later
mode(SaveMode.Overwrite).

jhnwllr

# null island figure 

library(ggplot2)
library(sf)
library(rnaturalearth)

worldmap = ne_countries(scale = 'medium', type = 'map_units',returnclass = 'sf')

cropped = st_crop(worldmap, xmin = -20, xmax = 45,ymin = -35, ymax = 40)
point_data = data.frame(long=0,lat=0,NAME="null island")

jhnwllr

val sqlContext = new org.apache.spark.sql.SQLContext(sc)

val df_occ = sqlContext.sql("SELECT * FROM prod_h.occurrence").
select(
"gbifid",
"datasetkey",
"occurrenceid",
"kingdom",
"phylum",
"class",

jhnwllr

val table_name = "gridded_datasets.tsv" 

val df = spark.read.
option("sep", "\t").
option("header", "true").
option("inferSchema", "true").
csv(table_name)

jhnwllr

library(dplyr)
library(ggplot2)
library(rnaturalearth)

worldmap = ne_countries(scale = 'medium', type = 'map_units',returnclass = 'sf')

zoom_to = c(70, 40)  # Berlin
zoom_level = 1
lon_span = 360 / 2^zoom_level
lat_span = 180 / 2^zoom_level

jhnwllr

gbifID	datasetKey	occurrenceID	kingdom	phylum	class	order	family	genus	species	infraspecificEpithet	taxonRank	scientificName	verbatimScientificName	verbatimScientificNameAuthorship	countryCode	locality	stateProvince	occurrenceStatus	individualCount	publishingOrgKey	decimalLatitude	decimalLongitude	coordinateUncertaintyInMeters	coordinatePrecision	elevation	elevationAccuracy	depth	depthAccuracy	eventDate	day	month	year	taxonKey	speciesKey	basisOfRecord	institutionCode	collectionCode	catalogNumber	recordNumber	identifiedBy	dateIdentified	license	rightsHolder	recordedBy	typeStatus	establishmentMeans	lastInterpreted	mediaType	issue
2988338871	50c9509d-22c7-4a22-a47d-8c48425ef4a7	https://www.inaturalist.org/observations/64782270	Animalia	Arthropoda	Insecta	Odonata	Calopterygidae	Mnais	Mnais mneme		SPECIES	Mnais mneme Ris, 1916	Mnais mneme		VN		Cao Bằng	PRESENT		28eb1a3f-1c15-4a95-931a-4af90ecb574d	22.616667	105.866667	2002.0						2018-06-05T10:26:00	5	6	2018	1427284	1427284	HUMAN_OBSERVATION	iNaturalist	Observatio

jhnwllr

import org.apache.spark.sql.Column
import org.apache.spark.sql.catalyst.expressions.aggregate.ApproximatePercentile
import org.apache.spark.sql.functions.lit
import org.apache.spark.SparkContext
import org.apache.spark.mllib.random.RandomRDDs._
import org.apache.spark.sql.functions._
import org.apache.spark.sql.functions.sqrt
import org.apache.spark.sql.expressions.Window

val sqlContext = new org.apache.spark.sql.SQLContext(sc)

jhnwllr

// rjack in scala spark

import org.apache.spark.sql.Column
import org.apache.spark.sql.catalyst.expressions.aggregate.ApproximatePercentile
import org.apache.spark.sql.functions.lit
import org.apache.spark.SparkContext
import org.apache.spark.mllib.random.RandomRDDs._
import org.apache.spark.sql.functions._
import org.apache.spark.sql.functions.sqrt
import org.apache.spark.sql.expressions.Window

jhnwllr

library(geotidy)
library(sf)

x = "POLYGON((-111.10988792012594 45.01964833538098,-104.12258323262594 45.01964833538098,-104.12258323262594 40.97209835959628,-111.10988792012594 40.97209835959628,-111.10988792012594 45.01964833538098))"

geotidy::st_geomfromtext(x, crs = 4326) %>% 
sf::st_area() %>%
units::set_units(km^2) # approximate area of wyoming 

# 256028.3 [km^2]