Some script cleaning

code/11_investigate-variants.R

@@ -1,34 +1,38 @@
 # 11_investigate-variants.R
 #
 # content: (1) Read data
-#          (2) Extract characteristics for cases
-#          (3) Select features for navigation behavior
-#          (4) Export data frames
+#          (2) Investigate variants
 #
-# input:  results/haum/event_logfiles_2024-02-21_16-07-33.csv
-# output: results/haum/eventlogs_pre-corona_case-clusters.csv
+# input:  results/haum/eventlogs_pre-corona_case-clusters.RData
+# output: 
 #
-# last mod: 2024-03-08
+# last mod: 2024-03-12
 
 # setwd("C:/Users/nwickelmaier/Nextcloud/Documents/MDS/2023ss/60100_master_thesis/analysis/code")
 
+library(bupaverse)
+
 #--------------- (1) Read data ---------------
 
 load("results/haum/eventlogs_pre-corona_cleaned.RData")
 
-#--------------- (4) Investigate variants ---------------
+#--------------- (2) Investigate variants ---------------
 
-res$start <- res$date.start
-res$complete <- res$date.stop
+dat$start <- dat$date.start
+dat$complete <- dat$date.stop
 
-alog <- activitylog(res,
+alog <- activitylog(dat,
                     case_id     = "case",
                     activity_id = "item",
                     resource_id = "path",
                     timestamps  = c("start", "complete"))
 
+pdf("results/figures/freq-traces.pdf", height = 7, width = 6, pointsize = 10)
 trace_explorer(alog, n_traces = 25)
 # --> sequences of artworks are just too rare
+dev.off()
+
+trace_explorer(alog, n_traces = 10, type = "infrequent")
 
 tr <- traces(alog)
 trace_length <- pbapply::pbsapply(strsplit(tr$trace, ","), length)
@@ -52,50 +56,7 @@ 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, ]
 # --> every variant exists only once, of course
-datcase[datcase$nitems == 5 & datcase$length > 50,]
-
-pbapply::pbsapply(datcase[, -c(1, 9)], median)
-
-#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"),
-                     rankdir    = "LR",
-                     render     = FALSE)
-  export_map(dfg,
-             file_name = paste0("results/processmaps/dfg_example_cases_", case, "_R.pdf"),
-             file_type = "pdf",
-             title     = paste("Case", case))
-
-
-}
 

code/12_pm-case-clusters.py

@@ -7,7 +7,7 @@
 # input:  results/haum/eventlogs_pre-corona_item-clusters.csv
 # output: results/haum/pn_infos_clusters.csv
 #
-# last mod: 2024-03-06
+# last mod: 2024-03-10
 
 import pm4py
 import pandas as pd
@@ -16,9 +16,9 @@ from python_helpers import eval_pm, pn_infos
 
 #--------------- (1) Load data and create event logs ---------------
 
-dat = pd.read_csv("results/haum/eventlogs_2019_case-clusters.csv", sep = ";")
+dat = pd.read_csv("results/haum/eventlogs_2019_case-clusters_new.csv", sep = ";")
 
-event_log = pm4py.format_dataframe(dat, case_id = "case", activity_key = "item",
+event_log = pm4py.format_dataframe(dat, case_id = "case", activity_key = "event_new",
                                   timestamp_key = "date.start")
 
 #--------------- (2) Infos for clusters ---------------
@@ -37,9 +37,10 @@ eval.to_csv("results/haum/pn_infos_clusters.csv", sep = ";")
 
 for cluster in event_log.cluster.unique().tolist():
     subdata = event_log[event_log.cluster == cluster]
-    subnet, subim, subfm = pm4py.discover_petri_net_inductive(subdata, noise_threshold=.3)
+    subnet, subim, subfm = pm4py.discover_petri_net_inductive(subdata, noise_threshold = .7)
     pm4py.save_vis_petri_net(subnet, subim, subfm,
        "results/processmaps/petrinet_cluster" + str(cluster) + "_cases.png")
     bpmn = pm4py.convert.convert_to_bpmn(subnet, subim, subfm)
     pm4py.vis.save_vis_bpmn(bpmn, "results/processmaps/bpmn_cluster" +
             str(cluster) + "_cases.png")
+