Add Matt Kim's R scripts to data.remote/inst

modules/data.remote/inst/download_updated.R

@@ -0,0 +1,34 @@
+#DAAC_Set_Credential(replace = TRUE)
+
+# California bounding box is:
+# up_lat <- 42.0095082699265845
+# up_lon <- -124.4820168611238245
+# low_lat <- 32.5288367369123748
+# low_lon <- -114.1312224747231312
+
+ul_lat <- 42.0095082699265845 # y = 4651894 in crs
+ul_lon <- -124.4820168611238245 # x = 377279.7 in crs
+lr_lat <- 32.5288367369123748 # y = 3633946 in crs
+lr_lon <- -114.1312224747231312 # x = 1334269 in crs
+
+from <- "2019-01-01"
+to <- "2019-12-31"
+doi <- "10.5067/HLS/HLSS30.002"
+outdir <- "//projectnb/dietzelab/XinyuanJi/State_of_California_HLSS/2019_Fmask"
+# SWIR - Landsat (B6&7), Sentinel (B11&12)
+band <- "Fmask"
+credential.folder <- "~/projectnb/XinyuanJi"
+paths <- NASA_DAAC_download(ul_lat = ul_lat, 
+                            ul_lon = ul_lon, 
+                            lr_lat = lr_lat, 
+                            lr_lon = lr_lon,
+                            ncore = 16,
+                            from = from, 
+                            to = to,
+                            outdir = outdir,
+                            band = band,
+                            credential.folder = credential.folder,
+                            doi = doi,
+                            just_path = F)
+
+provider_conceptID <- NASA_CMR_finder("10.5067/HLS/HLSS30.002")

modules/meta.analysis/inst/magic/extract_rows_traitID.R

@@ -0,0 +1,30 @@
+library(readxl)
+library(dplyr)
+
+extract_rows_traitID <- function(excel_path, sheet_name = 1, trait_ID) {
+
+  #reads the excel sheet
+  data <- readxl::read_excel(excel_path, sheet = sheet_name, col_types = NULL)
+
+  #throws an error if TraitID is not within the sheet
+  if (!"TraitID" %in% colnames(data)) {
+    stop("Column TraitID not found within the excel sheet")
+  }
+
+  # finds the rows with the desired TraitID
+  matched_rows <- which(data$TraitID == trait_ID)
+
+  if (length(matched_rows) > 0) {
+    filtered_rows <- data[matched_rows, ]
+  } else {
+    filtered_rows <- data.frame()
+    message("No rows found with TraitID of ", trait_ID)
+  }
+
+
+  # df2 now has a `common_name` column right after `SpeciesName`
+
+  return (filtered_rows)
+}
+
+

modules/meta.analysis/inst/magic/get_stats.R

@@ -0,0 +1,26 @@
+library(dplyr)
+
+get_stats <- function(data, value_column, group_column, species_column = "SpeciesName", species_name) {
+
+  # Filter by species
+  data_filtered <- data %>%
+    filter(.data[[species_column]] == species_name)
+
+  # Convert value column to numeric
+  data_filtered[[value_column]] <- as.numeric(data_filtered[[value_column]])
+
+  # Summarize statistics
+  summary_df <- data_filtered %>%
+    group_by(across(all_of(group_column))) %>%
+    summarise(
+      mean_value = mean(.data[[value_column]], na.rm = TRUE),
+      sd         = sd(.data[[value_column]], na.rm = TRUE),
+      n          = sum(!is.na(.data[[value_column]])),
+      .groups    = "drop"
+    ) %>%
+    rename(TraitID = 1)
+
+  return(summary_df)
+}
+
+

modules/meta.analysis/inst/magic/initialize_planting.R

@@ -0,0 +1,24 @@
+library(dplyr)
+
+initialize_planting <- function(species_name) {
+
+  species_stats <- data.frame(
+    get_stats(planting_df, "OrigValueStr", "TraitID", "SpeciesName", species_name)
+  )
+  return(species_stats)
+
+  #calculate for each trait 
+
+  #3441 leafC
+
+  #128 wood/stemC
+
+  #3450 rootC
+
+  #2005 fine-rootC
+
+  #1534 coarse-rootC
+
+  #output a table with the information
+
+}

modules/meta.analysis/inst/magic/main.R

@@ -0,0 +1,18 @@
+#this will be the main file where the entire program will be run
+library(readxl)
+library(dplyr)
+
+source("extract_rows_traitID.R")
+
+main <- function(files, trait_IDs, sheet_name = 1) {
+  combined_data <- data.frame()
+
+  for (file in files) {
+    for (id in trait_IDs) {
+      temp <- extract_rows_traitID(file, sheet_name = 1, trait_ID = id) 
+      combined_data <- bind_rows(combined_data, temp)
+    }
+  }
+  return (combined_data)
+}
+

modules/meta.analysis/inst/magic/run_program.R

@@ -0,0 +1,35 @@
+#this will run the entire program
+
+#example run: test_df1 <- run_program(time = "planting", species = "Rubus idaeus")
+
+library(readxl)
+library(dplyr)
+library(taxize)
+
+source("get_stats.R")
+
+run_program <- function(time, species) {
+  #time is harvest/planting
+  #pool is part of plant
+  #species is species
+
+  temp_plant_df <- get_stats(master_data, value_column = "OrigValueStr", trait_column = "TraitID", species_column = "SpeciesName", species_name = species)
+
+  #need to implement if NA, return species with like traits
+
+  if (time == "planting") {
+    temp_plant_df <- temp_plant_df[temp_plant_df$TraitID %in% c("3441", "128", "2005", "1534"),]
+  }
+  else if (time == "harvest") {
+    temp_plant_df <- temp_plant_df[temp_plant_df$TraitID %in% c("3962", "470"),]
+
+  }
+
+  if (nrow(temp_plant_df) == 0) {
+    return(paste(species, "has nothing"))
+  }
+
+  return (temp_plant_df)
+
+}
+