Updated labels for power law plots

code/11_investigate-variants.R

@@ -60,7 +60,7 @@ pdf("../../thesis/figures/freq-traces_powerlaw.pdf", height = 3.375,
     width = 3.375, pointsize = 10)
 par(mai = c(.6,.6,.1,.1), mgp = c(2.4, 1, 0))
 
-plot(x, y, log = "xy", xlab = "Absolute Frequency of Traces",
+plot(x, y, log = "xy", xlab = "Process variants sorted by frequency",
      ylab = "Frequency", pch = 16, col = rgb(0.262, 0.309, 0.309, 0.5))
 lines(x, pre, col = "#434F4F")
 legend("topright", paste0("Proportion of traces only occurring once: ",
@@ -73,7 +73,7 @@ pdf("../../thesis/figures/freq-traces_powerlaw_bw.pdf", height = 3.375,
     width = 3.375, pointsize = 10)
 par(mai = c(.6,.6,.1,.1), mgp = c(2.4, 1, 0))
 
-plot(x, y, log = "xy", xlab = "Absolute Frequency of Traces",
+plot(x, y, log = "xy", xlab = "Process variants sorted by frequency",
      ylab = "Frequency", pch = 16, col = rgb(0.3, 0.3, 0.3, 0.5))
 lines(x, pre, col = "#434F4F")
 legend("topright", paste0("Proportion of traces only occurring once: ",
@@ -129,7 +129,7 @@ pdf("../../thesis/figures/freq-traces_powerlaw_2019.pdf", height = 3.375,
     width = 3.375, pointsize = 10)
 par(mai = c(.6,.6,.1,.1), mgp = c(2.4, 1, 0))
 
-plot(x, y, log = "xy", xlab = "Absolute Frequency of Traces",
+plot(x, y, log = "xy", xlab = "Process variants sorted by frequency",
      ylab = "Frequency", pch = 16, col = rgb(0.262, 0.309, 0.309, 0.5))
 lines(x, pre, col = "#434F4F")
 legend("topright", paste0("Proportion of traces only occurring once: ",
@@ -142,7 +142,7 @@ pdf("../../thesis/figures/freq-traces_powerlaw_2019_bw.pdf", height = 3.375,
     width = 3.375, pointsize = 10)
 par(mai = c(.6,.6,.1,.1), mgp = c(2.4, 1, 0))
 
-plot(x, y, log = "xy", xlab = "Absolute Frequency of Traces",
+plot(x, y, log = "xy", xlab = "Process variants sorted by frequency",
      ylab = "Frequency", pch = 16, col = rgb(0.3, 0.3, 0.3, 0.5))
 lines(x, pre, col = "#434F4F")
 legend("topright", paste0("Proportion of traces only occurring once: ",

code/13_pm-case-clusters.py

@@ -0,0 +1,52 @@
+# 13_pm-case-clusters.py
+#
+# content: (1) Load data and create event log
+#          (2) Evaluation for clusters
+#
+# input:  results/eventlogs_2019_case-clusters.csv
+# output: results/eval_case_clusters.csv
+#
+# last mod: 2024-04-02
+
+import pm4py
+import pandas as pd
+
+from python_helpers import eval_pm
+
+#--------------- (1) Load data and create event logs ---------------
+
+dat = pd.read_csv("results/eventlogs_2019_case-clusters.csv", sep = ";")
+
+event_log = pm4py.format_dataframe(dat,
+                                   case_id = "case",
+                                   activity_key = "item",
+                                   timestamp_key = "date.start")
+
+#--------------- (2) Evaluation for clusters ---------------
+
+thresholds = [0.1, 0.2, 0.3, 0.4, 0.5]
+
+for nt in thresholds:
+
+  net, im, fm = pm4py.discover_petri_net_inductive(event_log, noise_threshold = nt)
+  
+  eval = pd.DataFrame(eval_pm(event_log, net, im, fm)).T
+  eval.columns = ["fitness", "generalization", "simplicity"]
+  #eval.columns = ["fitness", "precision", "generalization", "simplicity"]
+  
+  # Merge clusters into data frame
+  for cluster in [1, 2, 3, 4, 5]:
+      log_clst = pm4py.filter_event_attribute_values(event_log, "cluster", [cluster])
+      net_clst, im_clst, fm_clst = pm4py.discover_petri_net_inductive(log_clst, noise_threshold = nt)
+      eval_clst = pd.DataFrame(eval_pm(log_clst, net_clst, im_clst, fm_clst)).T
+      eval_clst.columns = ["fitness", "generalization", "simplicity"]
+      #eval_clst.columns = ["fitness", "precision", "generalization", "simplicity"]
+      eval = pd.concat([eval, eval_clst])
+      # Export process maps
+      bpmn = pm4py.convert.convert_to_bpmn(net_clst, im_clst, fm_clst)
+      pm4py.vis.save_vis_bpmn(bpmn, "results/processmaps/bpmn_cluster" + str(cluster) +
+            "_cases" + str(int(nt*10)).zfill(2) + ".png")
+  
+  eval.index = ["Complete", "Cluster 1", "Cluster 2", "Cluster 3", "Cluster 4", "Cluster 5"]
+  eval.to_csv("results/eval_case_clusters_" + str(int(nt*10)).zfill(2) + ".csv", sep = ";")
+

code/python_helpers.py

@@ -5,12 +5,17 @@ import pandas as pd
 
 def eval_pm(data, net, initial_marking, final_marking):
     """Caculate fitness, precision, generalizability, and simplicity for petri net"""
+    print("Fitness is calculated")
     fitness          = pm4py.fitness_token_based_replay(data, net, initial_marking, final_marking)
-    precisison       = pm4py.precision_token_based_replay(data, net, initial_marking, final_marking)
+    #print("Precision is calculated")
+    #precisison       = pm4py.precision_token_based_replay(data, net, initial_marking, final_marking)
+    print("Generalizability is calculated")
     generalizability = pm4py.algo.evaluation.generalization.algorithm.apply(data, net,
                                                                             initial_marking, final_marking)
+    print("Simplicity is calculated")
     simplicity       = pm4py.algo.evaluation.simplicity.algorithm.apply(net)
-    return [fitness['average_trace_fitness'], precisison, generalizability, simplicity]
+    #return [fitness['average_trace_fitness'], precisison, generalizability, simplicity]
+    return [fitness['average_trace_fitness'], generalizability, simplicity]
 
 
 def pn_infos(log, colname, filter):