Removed NA removal since it is not needed

code/07_item-clustering.R

@@ -47,7 +47,7 @@ datitem$scaleSize <- aggregate(scaleSize ~ item, dat, mean)$scaleSize
 datitem$rotationDegree <- aggregate(rotationDegree ~ item, dat, mean)$rotationDegree
 datitem$npaths <- aggregate(path ~ item, dat, function(x) length(unique(x)))$path
 datitem$ncases <- aggregate(case ~ item, dat, function(x) length(unique(x)))$case
-datitem$nmoves <- aggregate(event ~ item, dat, table)$event[,"move"]
+datitem$nmove <- aggregate(event ~ item, dat, table)$event[,"move"]
 datitem$nflipCard <- aggregate(event ~ item, dat, table)$event[,"flipCard"]
 datitem$nopenTopic <- aggregate(event ~ item, dat, table)$event[,"openTopic"]
 datitem$nopenPopup <- aggregate(event ~ item, dat, table)$event[,"openPopup"]
@@ -58,7 +58,7 @@ rm(datpath)
 
 df <- datitem[, c("precision", "generalizability", "nvariants", "duration",
                   "distance", "scaleSize", "rotationDegree", "npaths",
-                  "ncases", "nmoves", "nflipCard", "nopenTopic",
+                  "ncases", "nmove", "nflipCard", "nopenTopic",
                   "nopenPopup")] |>
       scale()
 
@@ -112,12 +112,12 @@ factoextra::fviz_cluster(list(data = df, cluster = cluster),
                          ggtheme = ggplot2::theme_bw())
 
 aggregate(cbind(precision, generalizability, nvariants, duration, distance,
-                scaleSize , rotationDegree, npaths, ncases, nmoves,
+                scaleSize , rotationDegree, npaths, ncases, nmove,
                 nflipCard, nopenTopic, nopenPopup) ~ cluster, datitem,
           mean)
 
 aggregate(cbind(duration, distance, scaleSize , rotationDegree, npaths,
-                ncases, nmoves, nflipCard, nopenTopic, nopenPopup) ~ cluster,
+                ncases, nmove, nflipCard, nopenTopic, nopenPopup) ~ cluster,
           datitem, max)
 
 item <- sprintf("%03d", as.numeric(gsub("item_([0-9]{3})", "\\1",

code/08_case-characteristics.R

@@ -9,7 +9,7 @@
 # output: results/dataframes_case_2019.RData
 #         results/centrality_cases.RData
 #
-# last mod: 2024-04-17
+# last mod: 2024-04-25
 
 # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/")
 
@@ -91,21 +91,6 @@ datcase$max_time <- NULL
 artworks <- unique(dat$item)[!unique(dat$item) %in% c("501", "502", "503")]
 datcase$infocardOnly <- pbapply::pbsapply(dat_split, check_infocards, artworks = artworks)
 
-# Clean up NAs
-datcase$distance <- ifelse(is.na(datcase$distance), 0, datcase$distance)
-datcase$scaleSize <- ifelse(is.na(datcase$scaleSize), 1, datcase$scaleSize)
-datcase$rotationDegree <- ifelse(is.na(datcase$rotationDegree), 0, datcase$rotationDegree)
-datcase$artist <- ifelse(is.na(datcase$artist), 0, datcase$artist)
-datcase$details <- ifelse(is.na(datcase$details), 0, datcase$details)
-datcase$extra_info <- ifelse(is.na(datcase$extra_info), 0, datcase$extra_info)
-datcase$komposition <- ifelse(is.na(datcase$komposition), 0, datcase$komposition)
-datcase$leben_des_kunstwerks <- ifelse(is.na(datcase$leben_des_kunstwerks), 0, datcase$leben_des_kunstwerks)
-datcase$licht_und_farbe <- ifelse(is.na(datcase$licht_und_farbe), 0, datcase$licht_und_farbe)
-datcase$technik <- ifelse(is.na(datcase$technik), 0, datcase$technik)
-datcase$thema <- ifelse(is.na(datcase$thema), 0, datcase$thema)
-datcase$ntopics <- ifelse(is.na(datcase$ntopics), 0, datcase$ntopics)
-datcase$ntopiccards <- ifelse(is.na(datcase$ntopiccards), 0, datcase$ntopiccards)
-
 #--------------- (3) Select features for navigation behavior ---------------
 
 # Features for navigation types for MTT:
@@ -159,7 +144,7 @@ rm(tmp)
 dattree$InfocardOnly <- factor(datcase$infocardOnly, levels = 0:1,
                                labels = c("no", "yes"))
 
-# Add pattern to datcase; loosely based on Bousbia et al. (2009)
+# Add pattern to dattree; loosely based on Bousbia et al. (2009)
 dattree$Pattern <- "Dispersion"
 dattree$Pattern <- ifelse(dattree$PathLinearity > 0.8, "Scholar",
                           dattree$Pattern)

code/10_validation.R

@@ -10,7 +10,7 @@
 # output: ../thesis/results/clustering_cases_2018.RData
 #         ../thesis/results/clustering_cases.RData
 #
-# last mod: 2024-04-17
+# last mod: 2024-04-25
 
 # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/")
 
@@ -61,11 +61,6 @@ datcase18$max_time <- NULL
 artworks <- unique(dat$item)[!unique(dat$item) %in% c("501", "502", "503")]
 datcase18$infocardOnly <- pbapply::pbsapply(dat_split, check_infocards, artworks = artworks)
 
-# Clean up NAs
-datcase18$distance <- ifelse(is.na(datcase18$distance), 0, datcase18$distance)
-datcase18$scaleSize <- ifelse(is.na(datcase18$scaleSize), 1, datcase18$scaleSize)
-datcase18$rotationDegree <- ifelse(is.na(datcase18$rotationDegree), 0, datcase18$rotationDegree)
-
 #--------------- (3) Select features for navigation behavior ---------------
 
 dattree18 <- data.frame(case = datcase18$case,