Merge branch 'develop' of https://github.com/DongchenZ/pecan into dev…

…elop

modules/data.atmosphere/R/download.AmerifluxLBL.R

@@ -5,7 +5,7 @@
 ##' to the given outfolder. Details about amf_download_base function can be found here:
 ##' https://github.com/chuhousen/amerifluxr/blob/master/R/amf_download_base.R
 ##' 
-##' Uses Ameirflux LBL JSON API to download met data from Ameriflux towers in CSV format
+##' Uses Ameriflux LBL JSON API to download met data from Ameriflux towers in CSV format
 ##' 
 ##' @export
 ##' @param sitename the Ameriflux ID of the site to be downloaded, used as file name prefix. 

modules/data.atmosphere/R/download.ERA5.R

@@ -51,7 +51,7 @@ download.ERA5.old <- function(outfolder, start_date, end_date, lat.in, lon.in,
     "This function is an incomplete prototype! Use with caution!"
   )
 
-  need_packages("reticulate")
+  PEcAn.utils::need_packages("reticulate")
 
   if (!is.null(reticulate_python)) {
     reticulate::use_python(reticulate_python)

modules/data.atmosphere/R/download.US_WCr.R

@@ -2,7 +2,7 @@
 ##' 
 ##' @section General Description:
 ##' Obtains data from Ankur Desai's Willow Creek flux tower, and selects certain variables (NEE and LE) to return
-##' Data is retruned at the given timestep in the given range.
+##' Data is returned at the given timestep in the given range.
 ##' 
 ##' This data includes information on a number of flux variables.
 ##' 

modules/data.atmosphere/R/download.US_Wlef.R

@@ -2,7 +2,7 @@
 ##' 
 ##' @section General Description:
 ##' Obtains data from Ankur Desai's WLEF/ Parks Fall flux tower, and selects certain variables (NEE and LE) to return
-##' Data is retruned at the given timestep in the given range.
+##' Data is returned at the given timestep in the given range.
 ##' 
 ##' This data includes information on a number of flux variables.
 ##' 

modules/data.atmosphere/R/extract_ERA5.R

@@ -8,7 +8,7 @@
 #' @param outfolder Path to directory where nc files need to be saved.
 #' @param in.prefix initial portion of the filename that does not vary by date. Does not include directory; specify that as part of in.path.
 #' @param newsite site name.
-#' @param vars variables to be extarcted. If NULL all the variables will be returned.
+#' @param vars variables to be extracted. If NULL all the variables will be returned.
 #' @param overwrite Logical if files needs to be overwritten.
 #' @details For the list of variables check out the documentation at \link{https://confluence.ecmwf.int/display/CKB/ERA5+data+documentation#ERA5datadocumentation-Spatialgrid}
 #'

modules/data.atmosphere/R/extract_local_CMIP5.R

@@ -24,7 +24,7 @@
 ##' @param date.origin (optional) specify the date of origin for timestamps in the files being read.  
 ##'                    If NULL defaults to 1850 for historical simulations (except MPI-ESM-P) and 
 ##'                    850 for p1000 simulations (plus MPI-ESM-P historical).  Format: YYYY-MM-DD
-##' @param adjust.pr - adjustment factor fore preciptiation when the extracted values seem off
+##' @param adjust.pr - adjustment factor fore precipitation when the extracted values seem off
 ##' @param overwrite logical. Download a fresh version even if a local file with the same name already exists?
 ##' @param verbose logical. to control printing of debug info
 ##' @param ... Other arguments, currently ignored

modules/data.atmosphere/R/extract_local_NLDAS.R

@@ -7,7 +7,7 @@
 ##' @description This function extracts NLDAS data from grids that have been downloaded and stored locally.
 ##'              Once upon a time, you could query these files directly from the internet, but now they're 
 ##'              behind a tricky authentication wall. Files are saved as a netCDF file in CF conventions. 
-##'              These files are ready to be used in the general PEcAn workflow or fed into the downscalign 
+##'              These files are ready to be used in the general PEcAn workflow or fed into the downscaling 
 ##'              workflow.
 # ----------------------------------- 
 # Parameters

modules/data.atmosphere/R/metgapfill.R

@@ -5,14 +5,14 @@
 ##' Future version will first downscale and fill with NARR, then REddyProc
 ##'
 ##' @export
-##' @param in.path location on disk where inputs are stord
+##' @param in.path location on disk where inputs are stored
 ##' @param in.prefix prefix of input and output files
 ##' @param outfolder location on disk where outputs will be stored
 ##' @param start_date the start date of the data to be downloaded (will only use the year part of the date)
 ##' @param end_date the end date of the data to be downloaded (will only use the year part of the date)
 ##' @param overwrite should existing files be overwritten
 ##' @param verbose should the function be very verbose
-##' @param lst is timezone offset from UTC, if timezone is available in time:units atribute in file, it will use that, default is to assume UTC
+##' @param lst is timezone offset from UTC, if timezone is available in time:units attribute in file, it will use that, default is to assume UTC
 ##' @author Ankur Desai
 metgapfill <- function(in.path, in.prefix, outfolder, start_date, end_date, lst = 0,
                        overwrite = FALSE, verbose = FALSE, ...) {

modules/data.atmosphere/R/tdm_predict_subdaily_met.R

@@ -30,7 +30,7 @@
 ##' @param ens.labs - vector containing the labels (suffixes) for each ensemble member; this allows you to add to your 
 ##'                   ensemble rather than overwriting with a default naming scheme
 ##' @param resids - logical stating whether to pass on residual data or not
-##' @param adjust.pr - adjustment factor fore preciptiation when the extracted values seem off
+##' @param adjust.pr - adjustment factor fore precipitation when the extracted values seem off
 ##' @param force.sanity - (logical) do we force the data to meet sanity checks?                             
 ##' @param sanity.tries - how many time should we try to predict a reasonable value before giving up?  We don't want to end up in an infinite loop
 ##' @param overwrite logical: replace output file if it already exists?

modules/data.atmosphere/R/tdm_temporal_downscale_functions.R

@@ -19,7 +19,7 @@
 # -----------------------------------
 ##' @param dat.train - training data generated by tdm_nc2dat.train.R
 ##' @param n.beta - number of betas to generate
-##' @param resids - whether or not to propogate residuals, set to FALSE
+##' @param resids - whether or not to propagate residuals, set to FALSE
 ##' @param parallel - whether or not to run in parallel. this is a feature
 ##'                   still being worked on, set to FALSE
 ##' @param n.cores - number of cores to use parallel processing on, set to NULL

modules/data.atmosphere/inst/integrationTests/test.download.CRUNCEP.R

@@ -0,0 +1,129 @@
+library(testthat)
+library(ncdf4)
+
+test_download_CRUNCEP <- function(start_date, end_date, lat.in, lon.in, method, maxErrors, sleep) {
+  # putting logger to debug mode
+  PEcAn.logger::logger.setUseConsole(TRUE, FALSE)
+  on.exit(PEcAn.logger::logger.setUseConsole(TRUE, TRUE), add = TRUE)
+  PEcAn.logger::logger.setLevel("DEBUG")
+
+  # mocking functions
+  mockery::stub(PEcAn.DB::convert_input, 'dbfile.input.check', data.frame())
+  mockery::stub(PEcAn.DB::convert_input, 'db.query', data.frame(id = 1))
+
+  withr::with_dir(tempdir(), {
+    tmpdir <- getwd()
+    PEcAn.DB::convert_input(
+      input.id = NA,
+      outfolder = tmpdir,
+      formatname = NULL,
+      mimetype = NULL,
+      site.id = 1,
+      start_date = start_date,
+      end_date = end_date,
+      pkg = 'PEcAn.data.atmosphere',
+      fcn = 'download.CRUNCEP',
+      con = NULL,
+      host = data.frame(name = "localhost"),
+      browndog = NULL,
+      write = FALSE,
+      lat.in = lat.in,
+      lon.in = lon.in,
+      method = method,
+      maxErrors = maxErrors,
+      sleep = sleep
+    )
+
+    test_that("File exists at desired location", {
+      # Set the desired file path
+      file_path <- paste0(tmpdir, "/cruncep_landwater_mask.nc")
+
+      # Check if file exists at desired location
+      expect_true(file.exists(file_path))
+    })
+
+    test_that("NetCDF file contains lat and lon variables", {
+
+      mask_nc <- ncdf4::nc_open(paste0(tmpdir, "/cruncep_landwater_mask.nc"))
+      on.exit(ncdf4::nc_close(mask_nc), add = TRUE)
+      expect_true("land_water_mask" %in% names(mask_nc$var))
+
+      # Check the dimensions of "land_water_mask" variable
+      expect_equal(mask_nc$var$land_water_mask$dim[[1]]$name, "lon")
+      expect_equal(mask_nc$var$land_water_mask$dim[[2]]$name, "lat")
+    })
+
+    test_that("All the required files are downloaded and stored at desired location", {
+      # Cached raw CRUNCEP files 
+      expect_true(file.exists(paste0(tmpdir, "/cruncep-raw-2000-40--88-tair.nc")))
+      expect_true(file.exists(paste0(tmpdir, "/cruncep-raw-2000-40--88-lwdown.nc")))
+      expect_true(file.exists(paste0(tmpdir, "/cruncep-raw-2000-40--88-press.nc")))
+      expect_true(file.exists(paste0(tmpdir, "/cruncep-raw-2000-40--88-swdown.nc")))
+      expect_true(file.exists(paste0(tmpdir, "/cruncep-raw-2000-40--88-uwind.nc")))
+      expect_true(file.exists(paste0(tmpdir, "/cruncep-raw-2000-40--88-vwind.nc")))
+      expect_true(file.exists(paste0(tmpdir, "/cruncep-raw-2000-40--88-qair.nc")))
+      expect_true(file.exists(paste0(tmpdir, "/cruncep-raw-2000-40--88-rain.nc")))
+
+      # CRUNCEP file
+      expect_true(file.exists(paste0(tmpdir, "/CRUNCEP.2000.nc")))
+    })
+
+    test_that("All cruncep raw data files have the correct variable units", {
+      nc <- nc_open(paste0(tmpdir, "/cruncep-raw-2000-40--88-tair.nc"))
+      expect_equal(nc$var$tair$units, "K")
+      nc_close(nc)
+
+      nc <- nc_open(paste0(tmpdir, "/cruncep-raw-2000-40--88-lwdown.nc"))
+      expect_equal(nc$var$lwdown$units, "W/m2")
+      nc_close(nc)
+
+      nc <- nc_open(paste0(tmpdir, "/cruncep-raw-2000-40--88-press.nc"))
+      expect_equal(nc$var$press$units, "Pa")
+      nc_close(nc)
+
+      nc <- nc_open(paste0(tmpdir, "/cruncep-raw-2000-40--88-swdown.nc"))
+      expect_equal(nc$var$swdown$units, "W/m2")
+      nc_close(nc)
+
+      nc <- nc_open(paste0(tmpdir, "/cruncep-raw-2000-40--88-uwind.nc"))
+      expect_equal(nc$var$uwind$units, "m/s")
+      nc_close(nc)
+
+      nc <- nc_open(paste0(tmpdir, "/cruncep-raw-2000-40--88-vwind.nc"))
+      expect_equal(nc$var$vwind$units, "m/s")
+      nc_close(nc)
+
+      nc <- nc_open(paste0(tmpdir, "/cruncep-raw-2000-40--88-qair.nc"))
+      expect_equal(nc$var$qair$units, "g/g")
+      nc_close(nc)
+
+      nc <- nc_open(paste0(tmpdir, "/cruncep-raw-2000-40--88-rain.nc"))
+      expect_equal(nc$var$rain$units, "mm/6h")
+      nc_close(nc)
+    })
+
+    test_that("Combined data file has the correct variable units", {
+      nc <- nc_open(paste0(tmpdir, "/CRUNCEP.2000.nc"))
+      expect_equal(nc$var$air_temperature$units, "Kelvin")
+      expect_equal(nc$var$surface_downwelling_longwave_flux_in_air$units, "W/m2")
+      expect_equal(nc$var$air_pressure$units, "Pascal")
+      expect_equal(nc$var$surface_downwelling_shortwave_flux_in_air$units, "W/m2")
+      expect_equal(nc$var$eastward_wind$units, "m/s")
+      expect_equal(nc$var$northward_wind$units, "m/s")
+      expect_equal(nc$var$specific_humidity$units, "g/g")
+      expect_equal(nc$var$precipitation_flux$units, "kg/m2/s")
+      nc_close(nc)
+    })
+  })
+}
+
+
+test_download_CRUNCEP(
+  start_date = "2000-01-01",
+  end_date = "2000-12-31",
+  lat.in = 40,
+  lon.in = -88,
+  method = "ncss",
+  maxErrors = 10,
+  sleep = 2
+)