Removing config$data_path

First attempt at removing instances of `config$data_path` from R files.

datasetup/build_US_setup.R

@@ -51,13 +51,10 @@ if (length(config) == 0) {
   stop("no configuration found -- please set CONFIG_PATH environment variable or use the -c command flag")
 }
 
-outdir <- config$data_path
-dir.create(outdir, showWarnings = FALSE, recursive = TRUE)
 
 # Aggregation to state level if in config
 state_level <- ifelse(!is.null(config$subpop_setup$state_level) && config$subpop_setup$state_level, TRUE, FALSE)
 
-dir.create(outdir, showWarnings = FALSE, recursive = TRUE)
 # commute_data <- arrow::read_parquet(file.path(opt$p,"datasetup", "usdata","united-states-commutes","commute_data.gz.parquet"))
 # census_data <- arrow::read_parquet(file.path(opt$p,"datasetup", "usdata","united-states-commutes","census_tracts_2010.gz.parquet"))
 
@@ -156,8 +153,8 @@ if (length(config$subpop_setup$geodata) > 0) {
 # manually remove PR
 census_data <- census_data %>% filter(USPS != "PR")
 
-write.csv(file = file.path(outdir, geodata_file), census_data, row.names=FALSE)
-print(paste("Wrote geodata file:", file.path(outdir, geodata_file)))
+write.csv(file = file.path(geodata_file), census_data, row.names=FALSE)
+print(paste("Wrote geodata file:", file.path(geodata_file)))
 
 
 
@@ -209,21 +206,21 @@ if(state_level & !file.exists(paste0(config$data_path, "/", config$subpop_setup$
       print(census_data$subpop)
       stop("There was a problem generating the mobility matrix")
     }
-    write.table(file = file.path(outdir, mobility_file), as.matrix(rc[,-1]), row.names=FALSE, col.names = FALSE, sep = " ")
+    write.table(file = file.path(mobility_file), as.matrix(rc[,-1]), row.names=FALSE, col.names = FALSE, sep = " ")
 
     } else if(endsWith(mobility_file, '.csv')) {
 
       rc <- commute_data
       names(rc) <- c("ori","dest","amount")
 
       rc <- rc[rc$ori != rc$dest,]
-      write.csv(file = file.path(outdir, mobility_file), rc, row.names=FALSE)
+      write.csv(file = file.path(mobility_file), rc, row.names=FALSE)
 
     } else {
       stop("Only .txt and .csv extensions supported for mobility matrix. Please check config's subpop_setup::mobility.")
     }
 
-    print(paste("Wrote mobility file:", file.path(outdir, mobility_file)))
+    print(paste("Wrote mobility file:", file.path(mobility_file)))
 }
 
 

datasetup/build_covid_data.R

@@ -30,17 +30,14 @@ if (exists("config$inference$gt_source")) {
     opt$gt_data_source <- config$inference$gt_source
 }
 
-outdir <- config$data_path
 # filterUSPS <- config$subpop_setup$modeled_states
 filterUSPS <- c("WY","VT","DC","AK","ND","SD","DE","MT","RI","ME","NH","HI","ID","WV","NE","NM",
                 "KS","NV","MS","AR","UT","IA","CT","OK","OR","KY","LA","AL","SC","MN","CO","WI",
                 "MD","MO","IN","TN","MA","AZ","WA","VA","NJ","MI","NC","GA","OH","IL","PA","NY","FL","TX","CA")
-dir.create(outdir, showWarnings = FALSE, recursive = TRUE)
 
 # Aggregation to state level if in config
 state_level <- ifelse(!is.null(config$subpop_setup$state_level) && config$subpop_setup$state_level, TRUE, FALSE)
 
-dir.create(outdir, showWarnings = FALSE, recursive = TRUE)
 
 # source data functions
 source(file.path(opt$path, "datasetup/data_setup_source.R"))
@@ -221,7 +218,7 @@ if (any(grepl("fluview", opt$gt_data_source))){
 
     max(fluview_data$Update)
 
-    census_data <- read_csv(file = file.path(config$data_path, config$subpop_setup$geodata))
+    census_data <- read_csv(file = file.path(config$subpop_setup$geodata))
     fluview_data <- fluview_data %>%
         dplyr::inner_join(census_data %>% dplyr::select(source = USPS, FIPS = subpop)) %>%
         dplyr::select(Update, source, FIPS, incidD)
@@ -286,7 +283,7 @@ if (any(grepl("fluview", opt$gt_data_source))){
 #
 #     max(fluview_data$Update)
 #
-#     census_data <- read_csv(file = file.path(config$data_path, config$subpop_setup$geodata))
+#     census_data <- read_csv(file = file.path(config$subpop_setup$geodata))
 #     fluview_data <- fluview_data %>%
 #         left_join(census_data %>% dplyr::select(source = USPS, FIPS = subpop)) %>%
 #         dplyr::select(Update, source, FIPS, incidD)

datasetup/build_flu_data.R

@@ -31,14 +31,11 @@ if (length(config) == 0) {
     stop("no configuration found -- please set CONFIG_PATH environment variable or use the -c command flag")
 }
 
-outdir <- config$data_path
 filterUSPS <- config$subpop_setup$modeled_states
-dir.create(outdir, showWarnings = FALSE, recursive = TRUE)
 
 # Aggregation to state level if in config
 state_level <- ifelse(!is.null(config$subpop_setup$state_level) && config$subpop_setup$state_level, TRUE, FALSE)
 
-dir.create(outdir, showWarnings = FALSE, recursive = TRUE)
 
 
 
@@ -59,7 +56,7 @@ source("https://raw.githubusercontent.com/cdcepi/Flusight-forecast-data/master/d
 
 # Pull daily hospitalizations for model run
 us_data <- load_flu_hosp_data(temporal_resolution = 'daily', na.rm = TRUE)
-locs <- read_csv(file.path(config$data_path, config$subpop_setup$geodata))
+locs <- read_csv(file.path(config$subpop_setup$geodata))
 
 # fix string pad issue on left side
 us_data <- us_data %>%
@@ -100,7 +97,7 @@ adjust_for_variant <- !is.null(variant_props_file)
 # if (adjust_for_variant){
 #
 #     # Variant Data (need to automate this data pull still)
-#     #variant_data <- read_csv(file.path(config$data_path, "variant/WHO_NREVSS_Clinical_Labs.csv"), skip = 1)
+#     #variant_data <- read_csv(file.path("variant/WHO_NREVSS_Clinical_Labs.csv"), skip = 1)
 #     variant_data <- cdcfluview::who_nrevss(region="state", years = 2022)$clinical_labs
 #
 #     # location data

datasetup/build_nonUS_setup.R

@@ -41,16 +41,14 @@ if (length(config) == 0) {
   stop("no configuration found -- please set CONFIG_PATH environment variable or use the -c command flag")
 }
 
-outdir <- config$data_path
 filterADMIN0 <- config$subpop_setup$modeled_states
 
-dir.create(outdir, showWarnings = FALSE, recursive = TRUE)
 
 # Read in needed data
-commute_data <- readr::read_csv(file.path(config$data_path, "geodata", opt$mobility)) %>%
+commute_data <- readr::read_csv(file.path("geodata", opt$mobility)) %>%
   mutate(OGEOID = as.character(OGEOID),
          DGEOID = as.character(DGEOID))
-census_data <- readr::read_csv(file.path(config$data_path, "geodata", opt$population)) %>%
+census_data <- readr::read_csv(file.path("geodata", opt$population)) %>%
   mutate(GEOID = as.character(GEOID))
 
 # Filter if needed
@@ -97,22 +95,22 @@ if(opt$w){
   if(!isTRUE(all(rc$OGEOID == census_data$GEOID))){
     stop("There was a problem generating the mobility matrix")
   }
-  write.table(file = file.path(outdir,'mobility.txt'), as.matrix(rc[,-1]), row.names=FALSE, col.names = FALSE, sep = " ")
+  write.table(file = file.path('mobility.txt'), as.matrix(rc[,-1]), row.names=FALSE, col.names = FALSE, sep = " ")
 } else {
   names(rc) <- c("ori","dest","amount")
   rc <- rc[rc$ori != rc$dest,]
-  write.csv(file = file.path(outdir,'mobility.csv'), rc, row.names=FALSE)
+  write.csv(file = file.path('mobility.csv'), rc, row.names=FALSE)
 }
 
 # Save population geodata
 names(census_data) <- c("subpop","admin2","admin0","pop")
-write.csv(file = file.path(outdir,'geodata.csv'), census_data,row.names=FALSE)
+write.csv(file = file.path('geodata.csv'), census_data,row.names=FALSE)
 
 print("Census Data Check (up to 6 rows)")
 print(head(census_data))
 print("Commute Data Check (up to 6 rows)")
 print(head(commute_data))
 
-print(paste0("mobility.csv/.txt and geodata.csv saved to: ", outdir))
+#print(paste0("mobility.csv/.txt and geodata.csv saved to: ", outdir))
 
 

flepimop/R_packages/flepicommon/R/config_test_new.R

@@ -122,7 +122,7 @@ validation_list$subpop_setup$geodata <- function(value, full_config,config_name)
     print("No geodata path mentioned in the configuration file")
     return(FALSE)
   }else{
-    path=paste(full_config$data_path,'/',value,sep='')
+    path=paste(full_config$subpop_setup$geodata,'/',value,sep='')
     if (!file.exists(path)) {
       print(paste("The mentioned geodata file :", value, "could not be found."))
       return(FALSE)
@@ -136,7 +136,7 @@ validation_list$subpop_setup$mobility <- function(value, full_config,config_name
     print("No mobility path mentioned in the configuration file")
     return(FALSE)
   }else{
-    path=paste(full_config$data_path,'/',value,sep='')
+    path=paste(full_config$subpop_setup$mobility,'/',value,sep='')
     if (!file.exists(path)) {
       print(paste("The mentioned mobility file :", value, "could not be found."))
       return(FALSE)

flepimop/main_scripts/create_seeding.R

@@ -302,7 +302,7 @@ all_times <- lubridate::ymd(config$start_date) +
     seq_len(lubridate::ymd(config$end_date) - lubridate::ymd(config$start_date))
 
 geodata <- flepicommon::load_geodata_file(
-    file.path(config$data_path, config$subpop_setup$geodata),
+    file.path(config$subpop_setup$geodata),
     5,
     "0",
     TRUE

flepimop/main_scripts/create_seeding_added.R

@@ -264,7 +264,7 @@ all_times <- lubridate::ymd(config$start_date) +
     seq_len(lubridate::ymd(config$end_date) - lubridate::ymd(config$start_date))
 
 geodata <- flepicommon::load_geodata_file(
-    file.path(config$data_path, config$subpop_setup$geodata),
+    file.path(config$subpop_setup$geodata),
     5,
     "0",
     TRUE

flepimop/main_scripts/inference_slot.R

@@ -139,7 +139,6 @@ state_level <- ifelse(!is.null(config$subpop_setup$state_level) && config$subpop
 suppressMessages(
   geodata <- flepicommon::load_geodata_file(
     paste(
-      config$data_path,
       config$subpop_setup$geodata, sep = "/"
     ),
     subpop_len = ifelse(config$name == "USA", opt$subpop_len, 0),
@@ -152,10 +151,6 @@ obs_subpop <- "subpop"
 
 ##Define data directory and create if it does not exist
 gt_data_path <- config$inference$gt_data_path
-data_dir <- dirname(config$data_path)
-if (!dir.exists(data_dir)){
-  suppressWarnings(dir.create(data_dir, recursive = TRUE))
-}
 
 ## backwards compatibility with configs that don't have inference$gt_source parameter will use the previous default data source (USA Facts)
 if (is.null(config$inference$gt_source)){

postprocessing/postprocess_snapshot.R

@@ -60,7 +60,7 @@ print(opt$select_outputs)
 config <- flepicommon::load_config(opt$config)
 
 # Pull in subpop data
-geodata <- setDT(read.csv(file.path(config$data_path, config$subpop_setup$geodata))) %>%
+geodata <- setDT(read.csv(file.path(config$subpop_setup$geodata))) %>%
   .[, subpop := stringr::str_pad(subpop, width = 5, side = "left", pad = "0")]
 
 subpops <- unique(geodata$subpop)

postprocessing/run_sim_processing_FluSightExample.R

@@ -101,7 +101,7 @@ scenario_s3_buckets <- scenario_s3_buckets[scenario_num] # automatically pull fr
 override_pull_from_s3 <- override_pull_from_s3[scenario_num] # !!!! VERY IMPORTANT - LEAVE FALSE UNLESS YOU ARE REWRITING THE CURRENT S3 DATA !!!!
 
 
-geodata_file_path = file.path(config$data_path, config$subpop_setup$geodata)
+geodata_file_path = file.path(config$subpop_setup$geodata)
 
 
 # SUBMISSION & PROCESSING SPECIFICS ----------------------------------------------------

postprocessing/run_sim_processing_SLURM.R

@@ -164,7 +164,7 @@ if(tolower(smh_or_fch) == "fch"){
 }
 scenarios <- scenarios[scenario_num]
 
-geodata_file_path = file.path(config$data_path, config$subpop_setup$geodata)
+geodata_file_path = file.path(config$subpop_setup$geodata)
 
 print(disease)
 

postprocessing/run_sim_processing_TEMPLATE.R

@@ -101,7 +101,7 @@ scenario_s3_buckets <- scenario_s3_buckets[scenario_num] # automatically pull fr
 override_pull_from_s3 <- override_pull_from_s3[scenario_num] # !!!! VERY IMPORTANT - LEAVE FALSE UNLESS YOU ARE REWRITING THE CURRENT S3 DATA !!!!
 
 
-geodata_file_path = file.path(config$data_path, config$subpop_setup$geodata)
+geodata_file_path = file.path(config$subpop_setup$geodata)