cboettig

library(arrow)

s3 <- s3_bucket("neon4cast-scores/parquet/aquatics", endpoint_override = "data.ecoforecast.org", anonymous=TRUE)


bench::bench_time( # very slow
  ds <- open_dataset(s3)
)

bench::bench_time( # very slow, but available via S3 Inventory

cboettig

library(rstac)
library(gdalcubes)

# let's pick some spatial extent, say, a bbox around "India"
loc <- spData::world |> dplyr::filter(name_long == "India")
box <- sf::st_bbox(loc)

matches <-
  stac("https://planetarycomputer.microsoft.com/api/stac/v1") |>
  stac_search(collections = "io-biodiversity",

cboettig

library(tidyverse)
direct <- read_csv("https://www.livingplanetindex.org/session/2ccf2bec98c16e6ee8f9ed6bbd8a514d/download/downloadData?w=")
direct |>
  ggplot(aes(Year, LPI_final)) + geom_line() + geom_ribbon(aes(ymin=CI_low, ymax=CI_high), fill="blue", alpha=0.1)

direct |> rename(year = Year) |>  mutate(sample = LPI_final + ((CI_high - CI_low)/2) * (runif(n(), -10,10))/10 ) |> 
ggplot(aes(x = year, y = 1, fill = sample)) +
  geom_tile(show.legend = FALSE) +
  #scale_fill_steps2(low = "#c7cca5", mid="#ddff03", high="#53de02", midpoint = median(lpi_df$LPI_final)) + 
  scale_fill_stepsn(colors = c("#c7cca5", "#ddff03", "#53de02"), values = rescale(c(min(lpi_df$sample), 0, max(lpi_df$sample))),

cboettig

library(duckdb)
library(DBI)
library(glue)
library(dplyr)
conn <- DBI::dbConnect(duckdb(), ":memory:",
                       config=list("memory_limit"="12GB",
                                   "temp_directory" = "/tmp"))
DBI::dbExecute(conn, "INSTALL 'httpfs';")
DBI::dbExecute(conn, "LOAD 'httpfs';")

cboettig

#url <- "https://dap.tern.org.au/thredds/ncss/ecosystem_process/ozflux/AdelaideRiver/2022_v2/L5/default/AdelaideRiver_L5_20071017_20090524.nc"

library(tidync)
library(lubridate)
library(dplyr)
url <- "https://dap.tern.org.au/thredds/dodsC/ecosystem_process/ozflux/AdelaideRiver/2022_v2/L5/default/AdelaideRiver_L5_20071017_20090524.nc"

# peek at metadata for time units
nc_atts(url) |> filter(variable=="time") |> mutate(value = unlist(value))

cboettig

library(rstac)
library(gdalcubes)
library(stars)
library(tmap)

## STAC Search over 400 million assets.
box <- c(xmin=-122.51006, ymin=37.70801, xmax=-122.36268, ymax=37.80668) 
start_date <- "2022-06-01"
end_date <- "2022-08-01"

cboettig

# remotes::install_github("OldLipe/rstac@b-0.9.1")
# remotes::install_github("appelmar/gdalcubes_R")
# remotes::install_github("r-spatial/stars")
library(tidyverse)
library(rstac)
library(gdalcubes)
library(tmap)
library(stars)
data(World) #polygons

cboettig

library(gdalcubes)
library(gefs4cast) # remotes::install_github("neon4cast/gefs4cast")
library(stringr)
library(lubridate)

## 3-hr period up to 10 days, (then every 6 hrs up to 35 day horizon)
gefs_cog("~/gefs_cog", ens_avg=TRUE,
                    max_horizon=240, date = Sys.Date() - 1) |> system.time()

# 000 file has different bands and so cannot be stacked into the collection

cboettig

# My preferred defaults (may be changed in individual chunks)
opts_chunk$set(tidy=FALSE, warning=FALSE, message=FALSE, cache=TRUE, 
               comment=NA, verbose=TRUE, fig.width=6, fig.height=4)

# Name the cache path and fig.path based on filename...
opts_chunk$set(fig.path = paste("figure/",
                                gsub(".Rmd", "", knitr:::knit_concord$get('infile')),
                                "-", sep=""),
               cache.path = paste(gsub(".Rmd", "", knitr:::knit_concord$get('infile') ), 
                                "/", sep=""))

cboettig

library(rstac)
library(gdalcubes)

## STAC Search over 400 million assets.
box <- c(xmin=-122.51006, ymin=37.70801, xmax=-122.36268, ymax=37.80668) 
items = 
  stac("https://earth-search.aws.element84.com/v0/") |>
  stac_search(collections = "sentinel-s2-l2a-cogs",
              bbox = box,
              datetime = "2020-06-01/2020-08-01",