Worked on variants in user navigation

code/09_user-navigation.R

@@ -1,14 +1,15 @@
-# 09_case-clustering.R
+# 09_user_navigation.R
 #
 # content: (1) Read data
 #           (1.1) Read log event data
 #           (1.2) Extract additional infos for clustering
 #          (2) Clustering
+#          (3) Investigate variants
 #
 # input:  results/haum/event_logfiles_2024-01-18_09-58-52.csv
 # output: results/haum/event_logfiles_pre-corona_with-clusters_cases.csv
 #
-# last mod: 2024-02-04
+# last mod: 2024-02-07
 
 
 # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
@@ -58,7 +59,7 @@ datcase$npaths <- aggregate(path ~ case, dat, function(x)
 # datcase$ntopics <- aggregate(topic ~ case, dat,
 #                              function(x) ifelse(all(is.na(x)), NA, length(unique(na.omit(x)))),
 #                              na.action = NULL)$topic
-# 
+#
 datcase$vacation <- aggregate(vacation ~ case, dat,
                               function(x) ifelse(all(is.na(x)), 0, 1),
                               na.action = NULL)$vacation
@@ -79,20 +80,16 @@ datcase <- na.omit(datcase)
 df <- datcase[, c("duration", "distance", "scaleSize", "rotationDegree",
                   "length", "nitems", "npaths")] |>
        scale()
-df <- cbind(df, datcase[, c("vacation", "holiday", "weekend", "morning")])       
+#df <- cbind(df, datcase[, c("vacation", "holiday", "weekend", "morning")])
 mat <- dist(df)
 
 hc <- hclust(mat, method = "ward.D2")
-hc <- hclust(mat)
 
-grp <- cutree(hc, k = 3)
+grp <- cutree(hc, k = 6)
 datcase$grp <- grp
 
 table(grp)
 
-# k1 <- kmeans(mat, 4)
-# datcase$kcluster <- k1$cluster
-
 fviz_cluster(list(data = df, cluster = grp),
              palette = c("#78004B", "#000000", "#3CB4DC", "#91C86E",
                          "#FF6900", "#434F4F"),
@@ -123,7 +120,8 @@ write.table(res,
             quote = FALSE,
             row.names = FALSE)
 
-# Look at variants
+#--------------- (2) Investigate variants ---------------
+
 res$start <- res$date.start
 res$complete <- res$date.stop
 
@@ -133,7 +131,7 @@ alog <- activitylog(res,
                     resource_id = "path",
                     timestamps  = c("start", "complete"))
 
-trace_explorer(alog, n_traces = 30)
+trace_explorer(alog, n_traces = 25)
 # --> sequences of artworks are just too rare
 
 tr <- traces(alog)
@@ -145,22 +143,19 @@ tr[trace_varied > 1, ]
 table(tr[trace_varied > 2, "absolute_frequency"])
 table(tr[trace_varied > 3, "absolute_frequency"])
 
-longest_case <- datcase[datcase$length == max(datcase$length), "case"]
+summary(tr$absolute_frequency)
-
+vioplot::vioplot(tr$absolute_frequency)
-alog_often <- activitylog(res[res$case == longest_case, ],
-                          case_id     = "case",
-                          activity_id = "item",
-                          resource_id = "path",
-                          timestamps  = c("start", "complete"))
-
-process_map(alog_often)
 
 # Power law for frequencies of traces
 tab <- table(tr$absolute_frequency)
 x <- as.numeric(tab)
 y <- as.numeric(names(tab))
-plot(log(y) ~ log(x))
+
-abline(lm(log(y) ~ log(x)))
+plot(x, y, log = "xy")
+p1 <- lm(log(y) ~ log(x))
+pre <- exp(coef(p1)[1]) * x^coef(p1)[2]
+lines(x, pre)
+
 
 # Look at individual traces as examples
 tr[trace_varied == 5 & trace_length > 50, ]
@@ -169,17 +164,32 @@ datcase[datcase$nitems == 5 & datcase$length > 50,]
 
 sapply(datcase[, -c(1, 9)], median)
 
-ex <- datcase[datcase$nitems == 10 & datcase$length == 30,]
+#ex <- datcase[datcase$nitems == 4 & datcase$length == 15,]
+ex <- datcase[datcase$nitems == 5,]
+ex <- ex[sample(1:nrow(ex), 20), ]
 # --> pretty randomly chosen... TODO:
 
+case_ids <- NULL
+
 for (case in ex$case) {
+  if ("080" %in% res$item[res$case == case] | "503" %in% res$item[res$case == case]) {
+    case_ids <- c(case_ids, TRUE)
+  } else {
+    case_ids <- c(case_ids, FALSE)
+  }
+}
+
+cases <- ex$case[case_ids]
+
+
+for (case in cases) {
 
   alog <- activitylog(res[res$case == case, ],
                       case_id     = "case",
                       activity_id = "item",
                       resource_id = "path",
                       timestamps  = c("start", "complete"))
-  
+
   dfg <- process_map(alog,
                      type_nodes = frequency("absolute", color_scale = "Greys"),
                      type_edges = frequency("absolute", color_edges = "#FF6900"),
@@ -193,29 +203,3 @@ for (case in ex$case) {
 
 }
 
-## --> not interesting!
-# Just "flipCard"
-res_case <- res[!duplicated(res[, c("case", "path")]), ]
-
-for (case in ex$case) {
-
-  alog <- activitylog(res_case[res_case$case == case, ],
-                      case_id     = "case",
-                      activity_id = "item",
-                      resource_id = "path",
-                      timestamps  = c("start", "complete"))
-  
-  dfg <- process_map(alog,
-                     type_nodes = frequency("absolute", color_scale = "Greys"),
-                     type_edges = frequency("absolute", color_edges = "#FF6900"),
-                     rankdir    = "LR",
-                     render     = FALSE)
-  export_map(dfg,
-             file_name = paste0("results/processmaps/dfg_example_cases_", case, "_fc_R.pdf"),
-             file_type = "pdf",
-             title     = paste("Single case", case))
-
-
-}
-
-