diff --git a/code/01_preprocessing_haum.R b/code/01_preprocessing_haum.R
index 55ba519..a7feea8 100644
--- a/code/01_preprocessing_haum.R
+++ b/code/01_preprocessing_haum.R
@@ -41,7 +41,7 @@ write.table(datraw, paste0("results/haum/raw_logfiles_", now, ".csv"),
 
 datlogs <- create_eventlogs(datraw,
            #xmlpath = "../data/haum/ContentEyevisit/eyevisit_cards_light/",
-           glossar = FALSE)
+           glossar = FALSE, save = TRUE)
 # 2,136,694 no change moves removed
 
 # OLD:
diff --git a/code/04_modeling_haum.R b/code/04_modeling_haum.R
index 5124f4f..400f8e0 100644
--- a/code/04_modeling_haum.R
+++ b/code/04_modeling_haum.R
@@ -2,78 +2,148 @@
 
 # Read data
 
-dat0 <- read.table("results/haum/event_logfiles_2023-10-25_17-29-52.csv",
+dat <- read.table("results/haum/event_logfiles_2024-01-02_19-44-50.csv",
+                  colClasses = c("character", "character", "POSIXct",
+                                 "POSIXct", "character", "integer",
+                                 "numeric", "character", "character",
+                                 rep("numeric", 3), "character",
+                                 "character", rep("numeric", 11),
+                                 "character", "character"),
                   sep = ";", header = TRUE)
-dat0$date.start <- as.POSIXct(dat0$date.start)
-dat0$date.stop <- as.POSIXct(dat0$date.stop)
-dat0$artwork <- sprintf("%03d", dat0$artwork)
 
-table(dat0[!duplicated(dat0$trace), "event"])
+dat$event <- factor(dat$event, levels = c("move", "flipCard", "openTopic",
+                                          "openPopup"))
 
-proportions(table(dat0[!duplicated(dat0$trace), "event"]))
+dat$weekdays <- factor(weekdays(dat$date.start),
+                       levels = c("Montag", "Dienstag", "Mittwoch",
+                                  "Donnerstag", "Freitag", "Samstag",
+                                  "Sonntag"),
+                       labels = c("Monday", "Tuesday", "Wednesday",
+                                  "Thursday", "Friday", "Saturday",
+                                  "Sunday"))
 
-tmp <- dat0[!duplicated(dat0$trace) & dat0$event %in% c("openTopic",
-                                                        "openPopup"), ]
+# Select data pre Corona
+dat <- dat[as.Date(dat$date.start) < "2020-03-13", ]
+dat <- dat[dat["path"] != 81621, ]
 
-dat <- dat0
-i <- 1
-stop <- 1
+table(dat$event)
+proportions(table(dat$event))
 
-while (stop > 0) {
-  stop <- sum(!duplicated(dat$trace) & dat$event %in% c("openTopic", "openPopup"))
-  dat <- dat[!(!duplicated(dat$trace) &
-              dat$event %in% c("openTopic", "openPopup")), ]
-  print(i)
-  i <- i + 1
-  print(table(dat[!duplicated(dat$trace), "event"]))
+# Investigate paths (will separate items and give clusters of artworks!)
+length(unique(dat$path))
+
+datpath <- aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~
+                     path, dat, function(x) mean(x, na.rm = TRUE), na.action = NULL)
+
+datpath$length <- aggregate(item ~ path, dat, length)$item
+datpath$nitems <- aggregate(item ~ path, dat, function(x)
+                            length(unique(x)), na.action = NULL)$item
+datpath$ntopics <- aggregate(topic ~ path, dat,
+                             function(x) ifelse(all(is.na(x)), NA, length(unique(na.omit(x)))),
+                             na.action = NULL)$topic
+
+datpath$vacation <- aggregate(vacation ~ path, dat,
+                              function(x) ifelse(all(is.na(x)), 0, 1),
+                              na.action = NULL)$vacation
+datpath$holiday <- aggregate(holiday ~ path, dat,
+                             function(x) ifelse(all(is.na(x)), 0, 1),
+                             na.action = NULL)$holiday
+datpath$weekend <- aggregate(weekdays ~ path, dat,
+                             function(x) ifelse(any(x %in% c("Saturday", "Sunday")), 1, 0),
+                             na.action = NULL)$weekdays
+datpath$morning <- aggregate(date.start ~ path, dat,
+                             function(x) ifelse(lubridate::hour(x[1]) > 13, 0, 1),
+                             na.action = NULL)$date.start
+
+
+# Investigate cases (= interactions per time intervall)
+length(unique(dat$case))
+
+datcase <- aggregate(cbind(duration, distance, scaleSize, rotationDegree) ~
+                     case, dat, function(x) mean(x, na.rm = TRUE), na.action = NULL)
+
+datcase$length <- aggregate(item ~ case, dat, length)$item
+datcase$nitems <- aggregate(item ~ case, dat, function(x)
+                            length(unique(x)), na.action = NULL)$item
+datcase$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)$vacation
+datcase$holiday <- aggregate(holiday ~ case, dat,
+                             function(x) ifelse(all(is.na(x)), 0, 1),
+                             na.action = NULL)$holiday
+datcase$weekend <- aggregate(weekdays ~ case, dat,
+                             function(x) ifelse(any(x %in% c("Saturday", "Sunday")), 1, 0),
+                             na.action = NULL)$weekdays
+datcase$morning <- aggregate(date.start ~ case, dat,
+                             function(x) ifelse(lubridate::hour(x[1]) > 13, 0, 1),
+                             na.action = NULL)$date.start
+
+
+
+# Paths with more than one case associated
+tmp <- aggregate(case ~ path, dat, function(x) length(unique(x)))
+sum(tmp$case > 1)
+table(tmp$case)
+
+dat$date <- as.Date(dat$date.start)
+
+tmp <- aggregate(date ~ path, dat, function(x) length(unique(x)))
+sum(tmp$date > 1)
+table(tmp$date)
+tmp[tmp$date > 1, ]
+
+for (p in tmp$path[tmp$date > 1]) {
+  print(dat[dat$path == p, 3:9])
+  cat("\n\n")
 }
 
+
+dat[dat$date == "2017-02-28" & dat$item == "503", ]
+
+
 # Creating event logs
 
 library(bupaverse)
 
-names(dat)[names(dat) %in% c("date.start", "date.stop")] <- c("start",
-                                                              "complete")
+dat$start <- dat$date.start
+dat$complete <- dat$date.stop
 
 table(table(dat$start))
 # --> hmm...
 
-summary(aggregate(duration ~ trace, dat, mean))
-
-# TODO: Find trace that has flipCard --> openPopup --> openTopic
-dato <- dat[dat$event != "move", ]
-dato_split <- split(dato, ~ trace)
-tmp <- lapply(dato_split, function(x) unique(x$event))
-#tmp <- lapply(unique(dato$trace), function(x) unique(dato[dato$trace == x, "event"]))
-
-ids <- sapply(tmp, length) == 3
-tmp2 <- as.data.frame(do.call(rbind, tmp[ids]))
-names(tmp2) <- c("flipCard", "openTopic", "openPopup")
-
-table(tmp2$flipCard)
-table(tmp2$openTopic)
-table(tmp2$openPopup)
-
-frag_ids <- which(tmp2$openTopic == "openPopup")
-
-tmp3 <- dat[dat$trace %in% rownames(tmp2)[frag_ids], ]
-
-tmp4 <- tmp3[!tmp3$glossar == 1, ]
-
-dat6 <- rbind(dat[!dat$trace %in% rownames(tmp2)[frag_ids], ], tmp4)
-
+summary(aggregate(duration ~ path, dat, mean))
 
 alog <- activitylog(dat,
-                    case_id = "trace",
+                    case_id = "path",
                     activity_id = "event",
-                    #resource_id = "case",
-                    resource_id = "artwork",
+                    resource_id = "item",
                     timestamps = c("start", "complete"))
 
-process_map(alog)
+process_map(alog,
+            type_nodes = frequency("absolute"),
+            sec_nodes  = frequency("relative"),
+            type_edges = frequency("absolute"),
+            sec_edges  = frequency("relative"),
+            rankdir    = "LR")
+
+
+alog2 <- activitylog(dat,
+                     case_id = "case",
+                     activity_id = "event",
+                     resource_id = "item",
+                     timestamps = c("start", "complete"))
+process_map(alog2,
+            type_nodes = frequency("absolute"),
+            sec_nodes  = frequency("relative"),
+            type_edges = frequency("absolute"),
+            sec_edges  = frequency("relative"),
+            rankdir    = "LR")
+
 
-process_map(alog, frequency("relative"))
-process_map(alog, frequency("relative_consequent"))
 
 library(processanimateR)
 
@@ -112,30 +182,4 @@ animate_process(elog[elog$artwork %in% c("080", "054"), ],
                 mapping = token_aes(color = token_scale("artwork",
                                                 scale = "ordinal",
                                                 range = c("black", "gray"))))
-# --> not sure, yet, how to interpret this...
-
-alog080 <- activitylog(dat[dat$artwork %in% "080", ],
-                    #case_id = "case",
-                    case_id = "trace",
-                    activity_id = "event",
-                    #resource_id = "trace",
-                    resource_id = "case",
-                    timestamps = c("start", "complete"))
-
-process_map(alog080, frequency("relative"))
-
-
-
-alog054 <- activitylog(dat[dat$artwork %in% "054", ],
-                    #case_id = "case",
-                    case_id = "trace",
-                    activity_id = "event",
-                    #resource_id = "trace",
-                    resource_id = "case",
-                    timestamps = c("start", "complete"))
-
-process_map(alog054, frequency("relative"))
-
-
-
 
diff --git a/code/plots_petri-nets.py b/code/plots_petri-nets.py
index 4d467a1..e1acdb7 100644
--- a/code/plots_petri-nets.py
+++ b/code/plots_petri-nets.py
@@ -10,24 +10,7 @@ net_con.places
 net_con.transitions
 net_con.arcs
 
-help(pm4py.objects.petri_net.obj.Marking)
-
-# Places
-source = PetriNet.Place("source")
-sink = PetriNet.Place("sink")
-p_1 = PetriNet.Place("p_1")
-p_2 = PetriNet.Place("p_2")
-p_3 = PetriNet.Place("p_3")
-p_4 = PetriNet.Place("p_4")
-p_5 = PetriNet.Place("p_5")
-p_6 = PetriNet.Place("p_6")
-p_7 = PetriNet.Place("p_7")
-p_8 = PetriNet.Place("p_8")
-p_9 = PetriNet.Place("p_9")
-p_10 = PetriNet.Place("p_10")
-p_11 = PetriNet.Place("p_11")
-p_12 = PetriNet.Place("p_12")
-
+final_marking = Marking()
 
 # Add tokens for traces
 # ('flipCard', 'openTopic', 'openPopup', 'openTopic', 'move'): 14
@@ -75,7 +58,8 @@ pm4py.vis.save_vis_petri_net(net_con, marking, final_marking, file_path="../figu
 marking = pm4py.generate_marking(net_con, {'p_5': 1, 'p_12' : 1})
 pm4py.vis.save_vis_petri_net(net_con, marking, final_marking, file_path="../figures/processmaps/conformative_net_con_markings_1_15.png")
 #pm4py.view_petri_net(net_con, marking)
-pm4py.vis.save_vis_petri_net(net_con, final_marking, final_marking, file_path="../figures/processmaps/conformative_net_con_markings_1_16.png")
+marking = pm4py.generate_marking(net_con, {'sink': 1})
+pm4py.vis.save_vis_petri_net(net_con, marking, final_marking, file_path="../figures/processmaps/conformative_net_con_markings_1_16.png")
 #pm4py.view_petri_net(net_con, final_marking)
 
 # ('move', 'move', 'flipCard', 'move', 'openTopic', 'openPopup'): 14
@@ -110,5 +94,6 @@ marking = pm4py.generate_marking(net_con, {'p_4': 1, 'p_12' : 1})
 pm4py.vis.save_vis_petri_net(net_con, marking, final_marking, file_path="../figures/processmaps/conformative_net_con_markings_2_15.png")
 marking = pm4py.generate_marking(net_con, {'p_5': 1, 'p_12' : 1})
 pm4py.vis.save_vis_petri_net(net_con, marking, final_marking, file_path="../figures/processmaps/conformative_net_con_markings_2_16.png")
-pm4py.vis.save_vis_petri_net(net_con, final_marking, final_marking, file_path="../figures/processmaps/conformative_net_con_markings_2_17.png")
+marking = pm4py.generate_marking(net_con, {'sink': 1})
+pm4py.vis.save_vis_petri_net(net_con, marking, final_marking, file_path="../figures/processmaps/conformative_net_con_markings_2_17.png")
 
diff --git a/code/00_pm.py b/code/pm.py
similarity index 100%
rename from code/00_pm.py
rename to code/pm.py
diff --git a/code/conformance-checking.py b/code/pm_conformance-checking.py
similarity index 83%
rename from code/conformance-checking.py
rename to code/pm_conformance-checking.py
index a4508de..bc37867 100644
--- a/code/conformance-checking.py
+++ b/code/pm_conformance-checking.py
@@ -15,7 +15,7 @@ dat = dat[dat["date.start"] < "2020-03-13"]
 
 event_log = pm4py.format_dataframe(dat, case_id='path', activity_key='event',
                                    timestamp_key='date.start')
-event_log = event_log.rename(columns={'artwork': 'case:artwork'})
+event_log = event_log.rename(columns={'item': 'case:item'})
 
 ###### Descrptives of log data ######
 
@@ -34,10 +34,10 @@ sorted_variants = dict(sorted(variants.items(), key=lambda item: item[1], revers
 {k: sorted_variants[k] for k in list(sorted_variants)[:20]}
 
 filtered_log = event_log[event_log["event"] != "move"]
-variants = pm4py.get_variants(filtered_log)
-len(variants)
-sorted_variants = dict(sorted(variants.items(), key=lambda item: item[1], reverse = True))
-{k: sorted_variants[k] for k in list(sorted_variants)[:20]}
+variants_no_move = pm4py.get_variants(filtered_log)
+len(variants_no_move)
+sorted_variants_no_move = dict(sorted(variants_no_move.items(), key=lambda item: item[1], reverse = True))
+{k: sorted_variants_no_move[k] for k in list(sorted_variants_no_move)[:20]}
 
 # Path length
 event_log.path.value_counts()
@@ -94,8 +94,11 @@ l4[index_broken]
 
 replayed_traces[index_broken]
 
-# 216295  # --> broken trace! Must be in artwork 176!!!!!
-
+event_log[event_log['@@case_index'] == index_broken].event
+event_log[event_log['@@case_index'] == index_broken].path
+event_log[event_log['@@case_index'] == index_broken].item
+event_log[event_log['@@case_index'] == index_broken]["fileId.start"]
+# --> logging error in file!
 
 from pm4py.algo.conformance.tokenreplay import algorithm as token_based_replay
 parameters_tbr = {token_based_replay.Variants.TOKEN_REPLAY.value.Parameters.DISABLE_VARIANTS: True, token_based_replay.Variants.TOKEN_REPLAY.value.Parameters.ENABLE_PLTR_FITNESS: True}
@@ -156,9 +159,9 @@ pm4py.save_vis_dfg(dfg, start_activities, end_activities, '../figures/processmap
 
 ## Heuristics Miner
 h_net, im, fm = pm4py.discover_petri_net_heuristics(event_log)
-h_eval = eval_pm(event_log, h_net, im, fm)
 pm4py.vis.view_petri_net(h_net, im, fm)
-pm4py.vis.save_vis_petri_net(h_net, im, fm, "../figures/processmaps/pn_heuristics_complete.png")
+pm4py.vis.save_vis_petri_net(h_net, im, fm, "../figures/processmaps/petrinet_heuristics_complete.png")
+h_eval = eval_pm(event_log, h_net, im, fm)
 
 is_sound = pm4py.check_soundness(h_net, im, fm)
 is_sound[0]
@@ -172,7 +175,7 @@ len(h_net.places)
 from pm4py.visualization.petri_net import visualizer as pn_visualizer
 parameters = {pn_visualizer.Variants.FREQUENCY.value.Parameters.FORMAT: "png"}
 gviz = pn_visualizer.apply(h_net, im, fm, parameters=parameters, variant=pn_visualizer.Variants.FREQUENCY, log=event_log)
-pn_visualizer.save(gviz, "../figures/processmaps/pn_heuristics_complete_decorated.png")
+pn_visualizer.save(gviz, "../figures/processmaps/petrinet_heuristics_complete_decorated.png")
 
 # convert to BPMN
 bpmn = pm4py.convert.convert_to_bpmn(h_net, im, fm)
@@ -180,9 +183,9 @@ pm4py.vis.view_bpmn(bpmn)
 
 ## Alpha Miner
 a_net, im, fm = pm4py.discover_petri_net_alpha(event_log)
-a_eval = eval_pm(event_log, a_net, im, fm)
 pm4py.vis.view_petri_net(a_net, im, fm)
-pm4py.vis.save_vis_petri_net(a_net, im, fm, "../figures/processmaps/pn_alpha_complete.png")
+pm4py.vis.save_vis_petri_net(a_net, im, fm, "../figures/processmaps/petrinet_alpha_complete.png")
+a_eval = eval_pm(event_log, a_net, im, fm)
 
 is_sound = pm4py.check_soundness(a_net, im, fm)
 is_sound[0]
@@ -193,9 +196,9 @@ len(a_net.places)
 
 ## Inductive Miner
 i_net, im, fm = pm4py.discover_petri_net_inductive(event_log)
-i_eval = eval_pm(event_log, i_net, im, fm)
 pm4py.vis.view_petri_net(i_net, im, fm)
-pm4py.vis.save_vis_petri_net(i_net, im, fm, "../figures/processmaps/pn_induction_complete.png")
+pm4py.vis.save_vis_petri_net(i_net, im, fm, "../figures/processmaps/petrinet_induction_complete.png")
+i_eval = eval_pm(event_log, i_net, im, fm)
 
 # as process tree (does not work for heuristics miner!)
 pt = pm4py.discover_process_tree_inductive(event_log)
@@ -217,9 +220,9 @@ pm4py.view_bpmn(bpmn)
 from pm4py.algo.conformance.tokenreplay import algorithm as token_based_replay
 parameters_tbr = {token_based_replay.Variants.TOKEN_REPLAY.value.Parameters.DISABLE_VARIANTS: True, token_based_replay.Variants.TOKEN_REPLAY.value.Parameters.ENABLE_PLTR_FITNESS: True}
 replayed_traces, place_fitness, trans_fitness, unwanted_activities = token_based_replay.apply(event_log, i_net,
-                                                                                                  im,
-                                                                                                  fm,
-                                                                                                  parameters=parameters_tbr)
+                                                                                              im,
+                                                                                              fm,
+                                                                                              parameters=parameters_tbr)
 
 l1 = list()
 l2 = list()
@@ -232,15 +235,29 @@ for i in range(len(replayed_traces)):
     l4.append(replayed_traces[i]["transitions_with_problems"])
 
 np.mean(l1)
+set(l1)
+index_broken = l1.index(1)
 np.mean(l2)
+set(l2)
+l2.index(1)
 set(l3)
 l4.count([])
 
+l3[index_broken]
+l4[index_broken]
+
+replayed_traces[index_broken]
+
+event_log[event_log['@@case_index'] == index_broken].event
+event_log[event_log['@@case_index'] == index_broken].path
+event_log[event_log['@@case_index'] == index_broken].item
+event_log[event_log['@@case_index'] == index_broken]["fileId.start"]
+
 ## ILP Miner
 ilp_net, im, fm = pm4py.discover_petri_net_ilp(event_log)
-ilp_eval = eval_pm(event_log, ilp_net, im, fm)
 pm4py.vis.view_petri_net(ilp_net, im, fm)
-pm4py.vis.save_vis_petri_net(ilp_net, im, fm, "../figures/processmaps/pn_ilp_complete.png")
+pm4py.vis.save_vis_petri_net(ilp_net, im, fm, "../figures/processmaps/petrinet_ilp_complete.png")
+ilp_eval = eval_pm(event_log, ilp_net, im, fm)
 
 is_sound = pm4py.check_soundness(ilp_net, im, fm)
 is_sound[0]
@@ -257,6 +274,27 @@ eval
 
 eval.to_csv("results/eval_all-miners_complete.csv", sep=";")
 
+## Without broken trace
+event_log_clean = event_log[event_log['@@case_index'] != index_broken]
+h_net, a_im, h_fm = pm4py.discover_petri_net_heuristics(event_log_clean)
+a_net, h_im, a_fm = pm4py.discover_petri_net_alpha(event_log_clean)
+i_net, i_im, i_fm = pm4py.discover_petri_net_inductive(event_log_clean)
+ilp_net, ilp_im, ilp_fm = pm4py.discover_petri_net_ilp(event_log_clean)
+
+baseline_eval = eval_pm(event_log_clean, basenet, initial_marking, final_marking)
+h_eval = eval_pm(event_log_clean, h_net, h_im, h_fm)
+a_eval = eval_pm(event_log_clean, a_net, a_im, a_fm)
+i_eval = eval_pm(event_log_clean, i_net, i_im, i_fm)
+ilp_eval = eval_pm(event_log_clean, ilp_net, ilp_im, ilp_fm)
+
+eval = pd.DataFrame(np.row_stack([baseline_eval, h_eval, a_eval, i_eval, ilp_eval]))
+eval.columns = ["fitness", "precision", "generalizability", "simplicity"]
+eval.index = ["conformative", "heuristics", "alpha", "inductive", "ilp"]
+eval
+
+eval.to_csv("results/eval_all-miners_clean.csv", sep=";")
+
+
 ###### Process Mining - individual artworks ######
 
 def pm_artworks(miner):
@@ -308,40 +346,4 @@ for miner in ["heuristics", "inductive", "alpha", "ilp"]:
 
 eval_art = pm_artworks(miner = "inductive")
 
-##### Clustering ######
-
-## KMeans
-
-#eval_artworks = eval_art[eval_art.nettype == "alldata"].iloc[:,range(1,5)]
-eval_artworks = eval_art[eval_art.nettype == "subdata"].iloc[:,range(1,5)]
-
-kmeans = KMeans(n_clusters=4, max_iter=1000).fit(eval_artworks)
-
-#from sklearn.manifold import MDS
-#coord = pd.DataFrame(MDS(normalized_stress='auto').fit_transform(eval_artworks))
-
-coord = eval_artworks
-coord["clusters"] = kmeans.labels_
-
-for i in coord.clusters.unique():
-    #plt.scatter(coord[coord.clusters == i].iloc[:,0], coord[coord.clusters == i].iloc[:,1],
-    plt.scatter(coord[coord.clusters == i].iloc[:,1], coord[coord.clusters == i].iloc[:,2],
-    #plt.scatter(coord[coord.clusters == i].iloc[:,2], coord[coord.clusters == i].iloc[:,4],
-                 label = i)
-plt.legend()
-plt.show()
-
-### Scree plot
-
-sse = {}
-for k in range(1, 10):
-    kmeans = KMeans(n_clusters=k, max_iter=1000).fit(eval_artworks[["precision", "generalizability"]])
-    #data["clusters"] = kmeans.labels_
-    #print(data["clusters"])
-    sse[k] = kmeans.inertia_ # Inertia: Sum of distances of samples to their closest cluster center
-plt.figure()
-plt.plot(list(sse.keys()), list(sse.values()))
-plt.xlabel("Number of clusters")
-plt.ylabel("SSE")
-plt.show()
 
diff --git a/code/pm_navigation-behavior.py b/code/pm_navigation-behavior.py
new file mode 100644
index 0000000..9aec338
--- /dev/null
+++ b/code/pm_navigation-behavior.py
@@ -0,0 +1,57 @@
+%reset
+
+import pm4py
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+from pm4py.visualization.petri_net import visualizer as pn_visualizer
+parameters = {pn_visualizer.Variants.FREQUENCY.value.Parameters.FORMAT: "png"}
+
+###### Load data and create event logs ######
+
+dat = pd.read_csv("results/haum/event_logfiles_2024-01-02_19-44-50.csv", sep = ";")
+dat = dat[dat["date.start"] < "2020-03-13"]
+dat = dat[dat["path"] != 81621]       # exclude broken trace
+# --> only pre corona (before artworks were updated)
+
+event_log = pm4py.format_dataframe(dat, case_id='case', activity_key='event',
+                                   timestamp_key='date.start')
+
+event_log.event.value_counts()
+event_log.event.value_counts(normalize=True)
+
+dfg, start_activities, end_activities = pm4py.discover_dfg(event_log)
+pm4py.view_dfg(dfg, start_activities, end_activities)
+
+#filtered_log = pm4py.filter_event_attribute_values(event_log, 'item', [80])
+
+i_net, im, fm = pm4py.discover_petri_net_inductive(event_log)
+pm4py.vis.view_petri_net(i_net, im, fm)
+gviz = pn_visualizer.apply(i_net, im, fm, parameters=parameters,
+                            variant=pn_visualizer.Variants.FREQUENCY,
+                            log=event_log)
+pn_visualizer.view(gviz)
+
+len(i_net.places)
+len(i_net.transitions)
+len(i_net.arcs)
+
+a_net, im, fm = pm4py.discover_petri_net_alpha(event_log)
+pm4py.vis.view_petri_net(a_net, im, fm)
+gviz = pn_visualizer.apply(a_net, im, fm, parameters=parameters,
+                            variant=pn_visualizer.Variants.FREQUENCY,
+                            log=event_log)
+pn_visualizer.view(gviz)
+
+
+len(a_net.places)
+len(a_net.transitions)
+len(a_net.arcs)
+
+h_net, im, fm = pm4py.discover_petri_net_heuristics(filtered_log)
+pm4py.vis.view_petri_net(h_net, im, fm)
+
+len(h_net.places)
+len(h_net.transitions)
+len(h_net.arcs)
diff --git a/code/trace-clustering.py b/code/trace-clustering.py
new file mode 100644
index 0000000..f35cb2f
--- /dev/null
+++ b/code/trace-clustering.py
@@ -0,0 +1,41 @@
+from sklearn.cluster import KMeans
+
+import matplotlib.pyplot as plt
+
+
+##### Clustering ######
+
+## KMeans
+
+#eval_artworks = eval_art[eval_art.nettype == "alldata"].iloc[:,range(1,5)]
+eval_artworks = eval_art[eval_art.nettype == "subdata"].iloc[:,range(1,5)]
+
+kmeans = KMeans(n_clusters=4, max_iter=1000).fit(eval_artworks)
+
+#from sklearn.manifold import MDS
+#coord = pd.DataFrame(MDS(normalized_stress='auto').fit_transform(eval_artworks))
+
+coord = eval_artworks
+coord["clusters"] = kmeans.labels_
+
+for i in coord.clusters.unique():
+    #plt.scatter(coord[coord.clusters == i].iloc[:,0], coord[coord.clusters == i].iloc[:,1],
+    plt.scatter(coord[coord.clusters == i].iloc[:,1], coord[coord.clusters == i].iloc[:,2],
+    #plt.scatter(coord[coord.clusters == i].iloc[:,2], coord[coord.clusters == i].iloc[:,4],
+                 label = i)
+plt.legend()
+plt.show()
+
+### Scree plot
+
+sse = {}
+for k in range(1, 10):
+    kmeans = KMeans(n_clusters=k, max_iter=1000).fit(eval_artworks[["precision", "generalizability"]])
+    #data["clusters"] = kmeans.labels_
+    #print(data["clusters"])
+    sse[k] = kmeans.inertia_ # Inertia: Sum of distances of samples to their closest cluster center
+plt.figure()
+plt.plot(list(sse.keys()), list(sse.values()))
+plt.xlabel("Number of clusters")
+plt.ylabel("SSE")
+plt.show()