overcome mutatet vowels

params/provinceInfo/provinces2.csv

+"code_metsa";"forest_land";"NUTS2";"NFIGrid"
+1;518000;"FI1B";"South"
+2;569000;"FI1C";"South"
+4;517000;"FI19";"South"
+5;347000;"FI1C";"South"
+6;912000;"FI19";"South"
+7;359000;"FI1C";"South"
+8;334000;"FI1C";"South"
+9;402000;"FI1C";"South"
+10;1212000;"FI1D";"South"
+11;1325000;"FI1D";"Central"
+12;1486000;"FI1D";"Central"
+13;1369000;"FI19";"Central"
+14;905000;"FI19";"Central"
+15;508000;"FI19";"Central"
+16;336000;"FI1D";"Central"
+17;2480000;"FI1D";"North"
+18;1630000;"FI1D";"North"
+19;4998000;"FI1D";"Lapland"
+21;69000;"XXXXX";"XXXXX"
+

prepare_opt_data_KE.R

@@ -340,45 +340,67 @@ print("*** values rounded ***")
 # NFI plots falling into the same forest stand of Metsään.fi that were simulated only once!!!
 # Inclued "NEW UNIQUE ID" since the stand id can now be represented multiple times, important for optimization.
 
-# List the csv files that are in the output folder
-NFIxy.files <- list.files(paste0(path,"/params/NFI_xy/"), pattern = "_xy.csv")
-
-
-# read and combine the files
-read_data_NFIxy <- function (i) {
-  df <- read.csv(paste0(path,"/params/NFI_xy/", i ), sep = ";", header = TRUE, stringsAsFactors = FALSE, fileEncoding="UTF-8-BOM")
-  df <- df[, c("NUTS_NAME", "standid", "coords.x1", "coords.x2") ]  %>%
-    rename(region = NUTS_NAME,
-           id = standid,
-           X = coords.x1,
-           Y = coords.x2)
-  return(df)
-}
-
-
-if(on_cPouta == TRUE) {
-  NFIxy.t <- mclapply(NFIxy.files, read_data_NFIxy, mc.cores = numCores)
-} else {
-  NFIxy.t <- lapply(NFIxy.files, read_data_NFIxy)
-}
-
-NFIxy = NULL
-
-for (part_data in NFIxy.t) {
-
-NFIxy <- rbind(NFIxy,part_data)
-
-}
-
-rm(NFIxy.t)
-
 
-# create a  unique id
-NFIxy <- NFIxy %>% mutate(unique_id = 99000000 + 1:nrow(NFIxy))
-
-# Check: according to SIMO input preparation, the lenght of all NFI plots should be: 39445
-length(unique(NFIxy$unique_id))
-length(unique(NFIxy$id))
+### SAVE EXTRA NEW FILE with code_metsa as identifier for merge
+### mutated vowels cause problems on cPouta
+
+# # List the csv files that are in the output folder
+# NFIxy.files <- list.files(paste0(path,"/params/NFI_xy/"), pattern = "_xy.csv")
+# 
+# 
+# # read and combine the files
+# read_data_NFIxy <- function (i) {
+#   df <- read.csv(paste0(path,"/params/NFI_xy/", i ), sep = ";", header = TRUE, stringsAsFactors = FALSE, fileEncoding="UTF-8-BOM")
+#   df <- df[, c("NUTS_NAME", "standid", "coords.x1", "coords.x2") ]  %>%
+#     rename(region = NUTS_NAME,
+#            id = standid,
+#            X = coords.x1,
+#            Y = coords.x2)
+#   return(df)
+# }
+# 
+# 
+# if(on_cPouta == TRUE) {
+#   NFIxy.t <- mclapply(NFIxy.files, read_data_NFIxy, mc.cores = numCores)
+# } else {
+#   NFIxy.t <- lapply(NFIxy.files, read_data_NFIxy)
+# }
+# 
+# NFIxy = NULL
+# 
+# for (part_data in NFIxy.t) {
+# 
+# NFIxy <- rbind(NFIxy,part_data)
+# 
+# }
+# 
+# rm(NFIxy.t)
+# 
+# 
+# # create a  unique id
+# NFIxy <- NFIxy %>% mutate(unique_id = 99000000 + 1:nrow(NFIxy))
+# 
+# 
+# province <- read.csv(paste0(path,"/params/provinceInfo/provinces.csv"), sep = ";", header = TRUE, stringsAsFactors = FALSE)
+# province <- province %>% rename(region = province_name)
+# head(province)
+# 
+# 
+# NFIxy <- NFIxy %>%
+#   left_join(province[,c("code_metsa", "region")], by = "region") %>% 
+#   select(!region)
+# 
+# # check quickly - compare with SImO input data analysis
+# head(NFIxy)
+# length(unique(NFIxy$id))
+# length(unique(NFIxy$unique_id))
+# 
+# write.table(NFIxy,paste0(path, "/params/NFI_xy_tot/tot_NFI_xy.csv"), sep = ";", row.names = F, col.names = TRUE)
+
+
+### READ THE NEW FILE code_metsa as identifier for merge
+
+NFIxy <- read.csv(paste0(path,"/params/NFI_xy_tot/tot_NFI_xy.csv"), sep = ";", header = TRUE, stringsAsFactors = FALSE)
 
 # Merge the province and XY coordinates by stand id !!
 rslt <- rslt %>%
@@ -387,14 +409,15 @@ rslt <- rslt %>%
 # check quickly - compare with SImO input data analysis
 length(unique(rslt$id))
 length(unique(rslt$unique_id))
-unique(rslt$region) # GIVES for region NA ???
+unique(rslt$code_metsa) # GIVES for region NA ???
 
 stand_NA <- rslt %>% 
-  filter(is.na(region)) # NA for 23968059
+  filter(is.na(code_metsa)) # NA for 23968059
 
 cat("NAs by XYmerge, for standid:", unique(stand_NA$id))
 cat("NUmber of rows removed:", nrow(stand_NA))
 
+# filter NA regions
 rslt <- rslt %>% 
   filter(id != unique(stand_NA$id))
 rm(stand_NA)
@@ -404,26 +427,6 @@ print("*** XY-coordinates added ***")
 
 
 
-# -------------------
-# Switch region name by code metsatilastot
-# -------------------
-
-province <- read.csv(paste0(path,"/params/provinceInfo/provinces.csv"), sep = ";", header = TRUE, stringsAsFactors = FALSE)
-province <- province %>% rename(region = province_name)
-
-rslt <- rslt %>% 
-  left_join(province[,c("code_metsa", "region")], by = "region")
-
-# check quickly - compare with SImO input data analysis
-length(unique(rslt$id))
-length(unique(rslt$unique_id))
-
-
-print("*** region code metsatilastot added ***")
-
-
-
-
 # ---------------
 # Add NUTs 2 region
 # ---------------
@@ -431,6 +434,8 @@ print("*** region code metsatilastot added ***")
 # This information might be required if results are optimized for certain regions.
 # https://en.wikipedia.org/wiki/NUTS_statistical_regions_of_Finland
 
+province <- read.csv(paste0(path,"/params/provinceInfo/provinces2.csv"), sep = ";", header = TRUE, stringsAsFactors = FALSE)
+
 rslt <- rslt %>%
   left_join(province[,c("code_metsa", "NUTS2")], by= "code_metsa")
 
@@ -524,10 +529,10 @@ cat("Number of stands status commercial:" , length(unique(rslt[rslt$protection %
 
 areabyregion <- NFIxy %>%
   # number of plots by region
-  group_by(region) %>%
+  group_by(code_metsa) %>%
   summarise(nr_plots = n_distinct(unique_id)) %>%
   # merge total forest area by region
-  left_join(province[,c("region", "code_metsa","forest_land")], by="region") %>%
+  left_join(province[,c("code_metsa","forest_land")], by="code_metsa") %>%
   # are by NFI plot
   mutate(represented_area_by_NFIplot = round(forest_land / nr_plots))
 
@@ -556,14 +561,15 @@ print("*** represented forest area added ***")
 
 rslt <- rslt %>%
   rename(standid = id,
-         id = unique_id)
+         id = unique_id,
+         region = code_metsa)
 
 
 ### NOT needed for Optimization
 # the output can be used to merge standid and XY coordinates after optimization
 # use id (unique_ID) for merge
 rslt.xy_no <- rslt  %>%
-  select(id, year, regime, X, Y, standid, ES_GAME, CARBON_STORAGE, scenario, region, code_metsa)
+  select(id, year, regime, X, Y, standid, ES_GAME, CARBON_STORAGE, scenario, region)
 
 
 ### Data for Optimization
@@ -586,12 +592,11 @@ rslt.final <- rslt %>%
          # Recreation
          Recreation, Scenic,
          # Additional
-         scenario, represented_area_by_NFIplot, code_metsa ,NUTS2, protection)
-
-cat("Output contains all 39445 stand:", 39445 == length(unique(rslt.final$id)))
+         scenario, represented_area_by_NFIplot, region ,NUTS2, protection)
 
 
 print("*** rslt.final created ***")
+cat("Output contains all 39445 stand:", 39445 == length(unique(rslt.final$id)))