entrypoint and readme update to main

Dockerfile

@@ -3,7 +3,7 @@ FROM rocker/r-ver:4.3.0
 
 # DeGAUSS container metadata
  ENV degauss_name="daymet"
- ENV degauss_version="0.1.1"
+ ENV degauss_version="0.1.2"
  ENV degauss_description="daymet climate variables"
  ENV degauss_argument="short description of optional argument [default: 'insert_default_value_here']"
 

README.md

@@ -16,10 +16,10 @@ Note: The Daymet calendar is based on a standard calendar year. All Daymet years
 If `my_addresses.csv` is a file in the current working directory with ID column `id`, start and end date columns `start_date` and `end_date`, and coordinate columns named `lat` and `lon`, then the [DeGAUSS command](https://degauss.org/using_degauss.html#DeGAUSS_Commands):
 
 ```sh
-docker run --rm -v $PWD:/tmp ghcr.io/degauss-org/daymet:0.1.1 my_addresses.csv
+docker run --rm -v $PWD:/tmp ghcr.io/degauss-org/daymet:0.1.2 my_addresses.csv
 ```
 
-will produce `my_addresses_daymet_0.1.1.csv` with added columns:
+will produce `my_addresses_daymet_0.1.2.csv` with added columns:
 
 - **`tmax`**: maximum temperature
 - **`tmin`**: minimum temperature
@@ -29,7 +29,7 @@ will produce `my_addresses_daymet_0.1.1.csv` with added columns:
 - **`prcp`**: precipitation
 - **`dayl`**: day length
 
-Other columns may be present in the input `my_addresses.csv` file, and these other columns will be linked in and included in the output `my_addresses_daymet_0.1.1.csv` file.
+Other columns may be present in the input `my_addresses.csv` file, and these other columns will be linked in and included in the output `my_addresses_daymet_0.1.2.csv` file.
 
 ### Optional Arguments
 
@@ -43,14 +43,15 @@ Other columns may be present in the input `my_addresses.csv` file, and these oth
 An example DeGAUSS command with all optional arguments used would be:
 
 ```sh
-docker run --rm -v $PWD:/tmp ghcr.io/degauss-org/daymet:0.1.1 my_addresses.csv tmax,vp,prcp -88.263390 -87.525706 41.470117 42.154247 na
+docker run --rm -v $PWD:/tmp ghcr.io/degauss-org/daymet:0.1.2 my_addresses.csv tmax,vp,prcp -88.263390 -87.525706 41.470117 42.154247 na
 ```
 
-which will return maximum temperature, vapor pressure, and precipitation for observations within a bounding box of Cook County, IL. It is important to specify bounding box coordinates in the order of: `min_lon`, `max_lon`, `min_lat`, `max_lat`.
+which will return maximum temperature, vapor pressure, and precipitation for observations within a boundary box of Cook County, IL. It is important to specify bounding box coordinates in the order of: `min_lon`, `max_lon`, `min_lat`, `max_lat`.
 
 ## Geomarker Methods
 
 Daymet data on a specified date is linked to coordinate data within the `my_addresses.csv` file by matching on the Daymet 1 km x 1 km raster cell number.
+If the boundary box coordinate data is not supplied in the optional arguments, they will be inferred from the .csv file with an added 0.1 degree latitude and longitude buffer to the outermost points to enhance data privacy.
 
 ## Geomarker Data
 
@@ -59,8 +60,9 @@ Daymet data on a specified date is linked to coordinate data within the `my_addr
 
 ## Warning
 
-If the bounding box for Daymet data download is inferred from address coordinates, then the size of the Daymet data download may be quite large if the address coordinates are very spread out. If a wide spread of coordinates is desired, then it may be best to stratify your input dataset to coordinates within separate geographic regions.
+If the boundary box for Daymet data download is inferred from address coordinates, then the size of the Daymet data download may be quite large if the address coordinates are very spread out. If a wide spread of coordinates is desired, then it may be best to stratify your input dataset to coordinates within separate geographic regions.
 
 ## DeGAUSS Details
 
+The Daymet DeGAUSS package was created by Ben Barrett and Peter Graffy, with contributions from Erika Rasnick and Luke Rasmussen.
 For detailed documentation on DeGAUSS, including general usage and installation, please see the [DeGAUSS homepage](https://degauss.org).

entrypoint.R

@@ -37,7 +37,6 @@ if (is.null(opt$vars)) {
 
 day_var <- str_remove_all(opt$vars, " ") 
 day_var <- str_split(day_var, ",", simplify = TRUE)
-
 if (! all(day_var %in% c("tmax", "tmin", "srad", "vp", "swe", "prcp", "dayl", "capricorn"))) {
   opt$vars <- "tmax, tmin, srad, vp, swe, prcp, dayl"
   cli::cli_alert_warning("Invalid argument for Daymet variable selection. Will return all Daymet variables. Please see {.url https://degauss.org/daymet/} for more information.")
@@ -74,13 +73,13 @@ if (! opt$region %in% c("na", "hi", "pr")) {
 }
 
 if (opt$vars %in% c("capricorn")) {
-  opt$vars <- "tmax, tmin"
-  opt$min_lon <- -88.263390
-  opt$max_lon <- -87.525706
-  opt$min_lat <- 41.470117
-  opt$max_lat <- 42.154247
-  opt$region <- "na"
-  cli::cli_alert_warning("Returning tmax and tmin for lat/lon coordinates of Cook County. Please see {.url https://degauss.org/daymet/} for more information.")
+    opt$vars <- "tmax, tmin"
+    opt$min_lon <- -88.263390
+    opt$max_lon <- -87.525706
+    opt$min_lat <- 41.470117
+    opt$max_lat <- 42.154247
+    opt$region <- "na"
+    cli::cli_alert_warning("Returning tmax and tmin for lat/lon coordinates of Cook County. Please see {.url https://degauss.org/daymet/} for more information.")
 }
 
 # Writing functions
@@ -183,9 +182,6 @@ import_data <- function(.csv_filename = opt$filename, .min_lon = opt$min_lon, .m
     print(w)
     stop(call. = FALSE)
   })
-  # Inferring the start and end year of Daymet data to download from start_date and end_date
-  year_start <- year(min(input_data$start_date))
-  year_end <- year(max(input_data$end_date))
   # Expanding the dates between start_date and end_date into a daily series
   input_data <- expand_dates(input_data, by = "day") %>%
     select(-start_date, -end_date)
@@ -200,14 +196,17 @@ import_data <- function(.csv_filename = opt$filename, .min_lon = opt$min_lon, .m
   # Throwing an error if no observations are remaining
   if (nrow(input_data) == 0) {
     stop(call. = FALSE, 'Zero observations where the start_date is within or after the first year of available Daymet data.')
-  }
+  }  
   # Filtering out any rows in the input data where the date year is equal to the current date year
   input_data <- input_data %>%
     filter(!(year(date) == year(Sys.Date())))
   # Throwing an error if no observations are remaining
   if (nrow(input_data) == 0) {
     stop(call. = FALSE, 'Zero observations where the end_date is within or before the last year of available Daymet data.')
   }
+  # Inferring the start and end year of Daymet data to download from date
+  year_start <- year(min(input_data$date))
+  year_end <- year(max(input_data$date))
   # Removing any columns in the input data where everything is NA
   input_data <- input_data %>%
     select_if(~ !all(is.na(.)))