Tests FE also for n_variants

config_files/pipeline_steps/feature_extraction.json

@@ -2,7 +2,7 @@
   {
     "pipeline_step": "feature_extraction",
     "input_path": "data/test",
-    "feature_params": {"feature_set":["ratio_variants_per_number_of_traces", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]},
+    "feature_params": {"feature_set":["n_variants", "ratio_most_common_variant", "ratio_top_10_variants", "epa_normalized_variant_entropy", "epa_normalized_sequence_entropy", "epa_normalized_sequence_entropy_linear_forgetting", "epa_normalized_sequence_entropy_exponential_forgetting"]},
     "output_path": "output/plots",
     "real_eventlog_path": "data/BaselineED_feat.csv",
     "plot_type": "boxplot",

data/validation/test_feat.csv

@@ -1,3 +1,3 @@
-log,ratio_most_common_variant,ratio_top_10_variants,epa_normalized_variant_entropy,epa_normalized_sequence_entropy,epa_normalized_sequence_entropy_linear_forgetting,epa_normalized_sequence_entropy_exponential_forgetting,ratio_variants_per_number_of_traces
-gen_el_168,0.13580246913580246,0.5709876543209876,0.6920749183939835,0.6241163465815115,0.06011912975523125,0.2577500062839078,0.44135802469135804
-gen_el_169,0.25813692480359146,0.6846240179573513,0.6517697077716751,0.4929433574247866,0.06332152226023505,0.21109493857555106,0.3153759820426487
+log,n_variants,ratio_most_common_variant,ratio_top_10_variants,epa_normalized_variant_entropy,epa_normalized_sequence_entropy,epa_normalized_sequence_entropy_linear_forgetting,epa_normalized_sequence_entropy_exponential_forgetting
+gen_el_168,143,0.13580246913580246,0.5709876543209876,0.6920749183939835,0.6241163465815115,0.06011912975523125,0.2577500062839078
+gen_el_169,281,0.25813692480359146,0.6846240179573513,0.6517697077716751,0.4929433574247866,0.06332152226023505,0.21109493857555106