remove log(R0) and update figures

nmfs-fish-tools · Jun 25, 2024 · 5501818 · 5501818
1 parent bd5104c
commit 5501818
Show file tree

Hide file tree

Showing 102 changed files with 2,121 additions and 1,667 deletions.
diff --git a/TextAnalysis/top10_barplot_mean.jpg b/TextAnalysis/top10_barplot_mean.jpg
diff --git a/TextAnalysis/top10_frequency.csv b/TextAnalysis/top10_frequency.csv
diff --git a/TextAnalysis/top10_presence.csv b/TextAnalysis/top10_presence.csv
diff --git a/TextAnalysis/top10_proportion.csv b/TextAnalysis/top10_proportion.csv
diff --git a/TextAnalysis/top20_analysis.R → TextAnalysis/top19_analysis.R b/TextAnalysis/top20_analysis.R → TextAnalysis/top19_analysis.R
@@ -83,7 +83,6 @@ if (authorize_GoogleDrive) {
   )
 }
 
-
 # run_text_mining function ------------------------------------------------
 
 run_text_mining <- function(keyword, xlabels, working_path, 
@@ -199,9 +198,9 @@ run_text_mining <- function(keyword, xlabels, working_path,
     )
     proportion_database[nrow(proportion_database), "ID"] <- "Sum"
 
-    write.csv(frequency_database, file=here::here("TextAnalysis", paste0("top20_frequency_", names(subfolder_info)[org], "_", scenario_name, ".csv")), row.names=FALSE)
-    write.csv(presence_database, file=here::here("TextAnalysis", paste0("top20_presence_", names(subfolder_info)[org], "_", scenario_name, ".csv")), row.names=FALSE)
-    write.csv(proportion_database, file=here::here("TextAnalysis", paste0("top20_proportion_", names(subfolder_info)[org], "_", scenario_name, ".csv")), row.names=FALSE)
+    write.csv(frequency_database, file=here::here("TextAnalysis", paste0("top19_frequency_", names(subfolder_info)[org], "_", scenario_name, ".csv")), row.names=FALSE)
+    write.csv(presence_database, file=here::here("TextAnalysis", paste0("top19_presence_", names(subfolder_info)[org], "_", scenario_name, ".csv")), row.names=FALSE)
+    write.csv(proportion_database, file=here::here("TextAnalysis", paste0("top19_proportion_", names(subfolder_info)[org], "_", scenario_name, ".csv")), row.names=FALSE)
     # Upload xlsx to Google Drive
     if (authorize_GoogleDrive) {
       # Google Drive folder id
@@ -210,17 +209,17 @@ run_text_mining <- function(keyword, xlabels, working_path,
     }
 
     # Plot results ------------------------------------------------------------
-    frequency_database <- read.csv(file=here::here("TextAnalysis", paste0("top20_frequency_", names(subfolder_info)[org], "_", scenario_name, ".csv")))
-    presence_database<-read.csv(file=here::here("TextAnalysis", paste0("top20_presence_", names(subfolder_info)[org], "_", scenario_name, ".csv")))
-    proportion_database<-read.csv(file=here::here("TextAnalysis", paste0("top20_proportion_", names(subfolder_info)[org], "_", scenario_name, ".csv")))
+    frequency_database <- read.csv(file=here::here("TextAnalysis", paste0("top19_frequency_", names(subfolder_info)[org], "_", scenario_name, ".csv")))
+    presence_database<-read.csv(file=here::here("TextAnalysis", paste0("top19_presence_", names(subfolder_info)[org], "_", scenario_name, ".csv")))
+    proportion_database<-read.csv(file=here::here("TextAnalysis", paste0("top19_proportion_", names(subfolder_info)[org], "_", scenario_name, ".csv")))
 
     word_frequency <- as.matrix(frequency_database[frequency_database$ID == "Sum", 4:ncol(frequency_database)])
     word_presence <- as.matrix(presence_database[presence_database$ID == "Sum", 4:ncol(presence_database)])
     word_presence_mean <- as.matrix(presence_database[presence_database$ID == "Sum", 4:ncol(presence_database)])/(nrow(presence_database)-1)*100
     word_proportion <- as.matrix(proportion_database[proportion_database$ID == "Sum", 4:ncol(proportion_database)])
 
     # barplot
-    jpeg(filename = here::here("TextAnalysis", paste0("top20_barplot_", names(subfolder_info)[org], "_", scenario_name, ".jpg")), width = 200, height = 120, units = "mm", res = 1200)
+    jpeg(filename = here::here("TextAnalysis", paste0("top19_barplot_", names(subfolder_info)[org], "_", scenario_name, ".jpg")), width = 200, height = 120, units = "mm", res = 1200)
     par(mar = c(6, 4, 1, 1), mfrow = c(3, 1))
     frequency_barplot <- barplot(height = word_frequency, xaxt = "n", ylab = "Frequency")
     text(frequency_barplot - 0.25, par("usr")[3] - 0.25, xlabels, xpd = TRUE, srt = 40, adj = 1, cex = 0.8)
@@ -234,20 +233,20 @@ run_text_mining <- function(keyword, xlabels, working_path,
 
     dev.off()
 
-    jpeg(filename = here::here("TextAnalysis", paste0("top20_presence_", names(subfolder_info)[org], "_", scenario_name, ".jpg")), width = 200, height = 120, units = "mm", res = 1200)
+    jpeg(filename = here::here("TextAnalysis", paste0("top19_presence_", names(subfolder_info)[org], "_", scenario_name, ".jpg")), width = 200, height = 120, units = "mm", res = 1200)
     par(mar = c(6, 4, 1, 1), mfrow = c(1, 1))
     presence_barplot <- barplot(height = word_presence, xaxt = "n", ylab = "Presence (%)") 
     text(presence_barplot - 0.25, par("usr")[3] - 0.25, xlabels, xpd = TRUE, srt = 40, adj = 1, cex = 0.7)
     dev.off()
 
-    jpeg(filename = here::here("TextAnalysis", paste0("top20_presence_mean_", names(subfolder_info)[org], "_", scenario_name, ".jpg")), width = 200, height = 120, units = "mm", res = 1200)
+    jpeg(filename = here::here("TextAnalysis", paste0("top19_presence_mean_", names(subfolder_info)[org], "_", scenario_name, ".jpg")), width = 200, height = 120, units = "mm", res = 1200)
     par(mar = c(6, 4, 1, 1), mfrow = c(1, 1))
     presence_barplot <- barplot(height = word_presence_mean, xaxt = "n", ylab = "Presence (%)") 
     text(presence_barplot - 0.25, par("usr")[3] - 0.25, xlabels, xpd = TRUE, srt = 40, adj = 1, cex = 0.7)
     dev.off()
 
     # wordcloud figure
-    jpeg(filename = here::here("TextAnalysis", paste0("top20_wordcloud_", names(subfolder_info)[org], "_mean_presence_grays", "_", scenario_name, ".jpg")), width = 200, height = 200, units = "mm", res = 1200)
+    jpeg(filename = here::here("TextAnalysis", paste0("top19_wordcloud_", names(subfolder_info)[org], "_mean_presence_grays", "_", scenario_name, ".jpg")), width = 200, height = 200, units = "mm", res = 1200)
     par(mar = c(0.1, 0.1, 0.1, 0.1), mfrow = c(1, 1))
     set.seed(123)
     wordcloud(
@@ -261,7 +260,7 @@ run_text_mining <- function(keyword, xlabels, working_path,
     text(0.1, 0.8, scenario_name)
     dev.off()
 
-    jpeg(filename = here::here("TextAnalysis", paste0("top20_wordcloud_", names(subfolder_info)[org], "_mean_presence_black", "_", scenario_name, ".jpg")), width = 200, height = 200, units = "mm", res = 1200)
+    jpeg(filename = here::here("TextAnalysis", paste0("top19_wordcloud_", names(subfolder_info)[org], "_mean_presence_black", "_", scenario_name, ".jpg")), width = 200, height = 200, units = "mm", res = 1200)
     par(mar = c(0.1, 0.1, 0.1, 0.1), mfrow = c(1, 1))
     set.seed(123)
     wordcloud(
@@ -281,52 +280,56 @@ working_path <- here::here("StockAssessment")
 subfolder_path_all <- list.dirs(path = working_path, full.names = TRUE, recursive = FALSE)
 subfolder_name_all <- list.dirs(path = working_path, full.names = FALSE, recursive = FALSE)
 
-subfolder_info <- list(1, 2, 3:length(subfolder_path_all), 1:length(subfolder_path_all))
+subfolder_info <- list(
+  grep("Australia", subfolder_name_all),
+  grep("ICES", subfolder_name_all),
+  grep("NOAA", subfolder_name_all), 
+  1:length(subfolder_name_all)
+)
+
 names(subfolder_info) <- c("Australia", "ICES", "NOAA", "All")
 
 keyword <- c(
   "biomass|b", "abundance",
-  "spawning biomass|sb", "spawning stock biomass|ssb", "spawning output", "spawning stock output|sso", "mature biomass", "spawners", "effective spawning output",
+  "spawning biomass|sb", "spawning stock biomass|ssb", "mature biomass", "spawners", "effective spawning output",
   "unfished", "virgin", "initial equilibrium", "unfished equilibrium",
   "recruitment",
   "recruits", "recruit", "age 0 fish", "age 1 fish",
-  "catch", "total mortality", "harvest", "total removals",
+  "catch", "harvest", "total removals",
   "catch per unit effort|cpue", "catch rate", "index of abundance", "catch per effort", "fishing success",
   "landings", "retained catch",
-  "spawner per recruit|spr", "spawning potential ratio|spr",
+  "spawner per recruit|spr", "spawning potential ratio",
   "maximum sustainable yield|msy",
   "instantaneous total mortality rate|z",
   "fishing mortality|f", "instantaneous fishing mortality rate", "harvest rate", "exploitation rate", "finite fishing mortality", "apical f",
   "fishing mortality at maximum sustainable yield|fmsy",
-  "mass", "weight",
+  "mass",
   "length composition", "length frequency", "length observation", "size frequency", "size composition",
   "age composition", "age frequency", "age observation",
-  "projection", "forecast", "prediction",
+  "projection",
   "sex", "gender",
-  "natural log of unfished recruitment|lnr0", "logr0","logr_0", "log(r0)", "r0",
   "plus group"
 )
 
 xlabels <- c(
   "Biomass", "Abundance",
-  "Spawning biomass", "Spawning stock biomass", "Spawning output", "Spawning stock output", "Mature biomass", "Spawners", "Effective spawning output",
+  "Spawning biomass", "Spawning stock biomass", "Mature biomass", "Spawners", "Effective spawning output",
   "Unfished", "Virgin", "Initial equilibrium", "Unfished equilibrium",
   "Recruitment",
   "Recruits", "Recruit", "Age 0 fish", "Age 1 fish",
-  "Catch", "Total mortality", "Harvest", "Total removals",
+  "Catch", "Harvest", "Total removals",
   "Catch per unit effort", "Catch rate", "Index of abundance", "Catch per effort", "Fishing success",
   "Landings", "Retained catch",
   "Spawner per recruit", "Spawning potential ratio",
   "Maximum sustainable yield",
   "Instantaneous total mortality rate",
   "Fishing mortality", "Instantaneous fishing mortality rate", "Harvest rate", "Exploitation rate", "Finite fishing mortality", "Apical f",
   "Fishing mortality at maximum sustainable yield",
-  "Mass", "Weight", 
+  "Mass",  
   "Length composition", "Length frequency", "Length observation", "Size frequency", "Size composition",
   "Age composition", "Age frequency", "Age observation",
-  "Projection", "Forecast", "Prediction",
+  "Projection", 
   "Sex", "Gender",
-  "Natural log of unfished recruitment", "LogR0","LogR_0", "Log(R0)", "R0",
   "Plus group"
 )
 
@@ -336,24 +339,23 @@ run_text_mining(keyword = keyword, xlabels = xlabels, working_path = working_pat
 
 keyword <- c(
   "biomass|b|abundance",
-  "spawning biomass|sb|spawning stock biomass|ssb|spawning output|spawning stock output|sso|mature biomass|spawners|effective spawning output",
+  "spawning biomass|sb|spawning stock biomass|ssb|mature biomass|spawners|effective spawning output",
   "unfished|virgin|initial equilibrium|unfished equilibrium",
   "recruitment",
   "recruits|recruit|age 0 fish|age 1 fish",
-  "catch|total mortality|harvest|total removals",
+  "catch|harvest|total removals",
   "catch per unit effort|cpue|catch rate|index of abundance|catch per effort|fishing success",
   "landings|retained catch",
   "spawner per recruit|spawning potential ratio|spr",
   "maximum sustainable yield|msy",
   "instantaneous total mortality rate|z",
   "fishing mortality|f|instantaneous fishing mortality rate|harvest rate|exploitation rate|finite fishing mortality|apical f",
   "fishing mortality at maximum sustainable yield|fmsy",
-  "mass|weight",
+  "mass",
   "length composition|length frequency|length observation|size frequency|size composition",
   "age composition|age frequency|age observation",
-  "projection|forecast|prediction",
+  "projection",
   "sex|gender",
-  "natural log of unfished recruitment|lnr0|logr0|logr_0|log(r0)|r0",
   "plus group"
 )
 
@@ -376,7 +378,6 @@ xlabels <- c(
   "Age composition",
   "Projection",
   "Sex",
-  "Natural log of unfished recruitment",
   "Plus group"
 )
 
@@ -385,25 +386,24 @@ run_text_mining(keyword = keyword, xlabels = xlabels, working_path = working_pat
                 subfolder_info = subfolder_info, scenario_name = "B")
 
 
-jpeg(filename = here::here("TextAnalysis", "top20_wordcloud_All_mean_presence_grays_AB.jpg"), 
+jpeg(filename = here::here("TextAnalysis", "top19_wordcloud_All_mean_presence_grays_AB.jpg"), 
      width = 200, height = 120, units = "mm", res = 1200)
-before_img <-  rasterGrob(as.raster(jpeg::readJPEG(here::here("TextAnalysis", 
-                                                              "top20_wordcloud_All_mean_presence_grays_A.jpg"))), 
+before_img <-  grid::rasterGrob(as.raster(jpeg::readJPEG(here::here("TextAnalysis", 
+                                                              "top19_wordcloud_All_mean_presence_grays_A.jpg"))), 
                           interpolate = FALSE)
-after_img <-  rasterGrob(as.raster(jpeg::readJPEG(here::here("TextAnalysis", 
-                                                             "top20_wordcloud_All_mean_presence_grays_B.jpg"))), 
+after_img <-  grid::rasterGrob(as.raster(jpeg::readJPEG(here::here("TextAnalysis", 
+                                                             "top19_wordcloud_All_mean_presence_grays_B.jpg"))), 
                          interpolate = FALSE)
 gridExtra::grid.arrange(before_img, after_img, ncol = 2)
 dev.off()
 
-jpeg(filename = here::here("TextAnalysis", "top20_wordcloud_All_mean_presence_black_AB.jpg"), 
+jpeg(filename = here::here("TextAnalysis", "top19_wordcloud_All_mean_presence_black_AB.jpg"), 
      width = 200, height = 120, units = "mm", res = 1200)
-before_img <-  rasterGrob(as.raster(jpeg::readJPEG(here::here("TextAnalysis", 
-                                                              "top20_wordcloud_All_mean_presence_black_A.jpg"))), 
+before_img <-  grid::rasterGrob(as.raster(jpeg::readJPEG(here::here("TextAnalysis", 
+                                                              "top19_wordcloud_All_mean_presence_black_A.jpg"))), 
                           interpolate = FALSE)
-after_img <-  rasterGrob(as.raster(jpeg::readJPEG(here::here("TextAnalysis", 
-                                                             "top20_wordcloud_All_mean_presence_black_B.jpg"))), 
+after_img <-  grid::rasterGrob(as.raster(jpeg::readJPEG(here::here("TextAnalysis", 
+                                                             "top19_wordcloud_All_mean_presence_black_B.jpg"))), 
                          interpolate = FALSE)
 gridExtra::grid.arrange(before_img, after_img, ncol = 2)
 dev.off()
-
diff --git a/TextAnalysis/top19_barplot_All_A.jpg b/TextAnalysis/top19_barplot_All_A.jpg
diff --git a/TextAnalysis/top19_barplot_All_B.jpg b/TextAnalysis/top19_barplot_All_B.jpg
diff --git a/TextAnalysis/top19_barplot_Australia_A.jpg b/TextAnalysis/top19_barplot_Australia_A.jpg
diff --git a/TextAnalysis/top19_barplot_Australia_B.jpg b/TextAnalysis/top19_barplot_Australia_B.jpg
diff --git a/TextAnalysis/top19_barplot_ICES_A.jpg b/TextAnalysis/top19_barplot_ICES_A.jpg
diff --git a/TextAnalysis/top19_barplot_ICES_B.jpg b/TextAnalysis/top19_barplot_ICES_B.jpg
diff --git a/TextAnalysis/top19_barplot_NOAA_A.jpg b/TextAnalysis/top19_barplot_NOAA_A.jpg
diff --git a/TextAnalysis/top19_barplot_NOAA_B.jpg b/TextAnalysis/top19_barplot_NOAA_B.jpg