Merge branch 'release' into release-github

# Conflicts:
#	pm4py/algo/discovery/minimum_self_distance/__init__.py
#	pm4py/algo/discovery/performance_spectrum/variants/dataframe.py
#	pm4py/algo/discovery/performance_spectrum/variants/dataframe_disconnected.py
#	pm4py/algo/discovery/performance_spectrum/variants/log_disconnected.py
#	pm4py/meta.py
#	pm4py/objects/log/util/sorting.py
#	pm4py/vis.py
#	pm4py/visualization/graphs/variants/__init__.py
#	pm4py/visualization/graphs/visualizer.py

Author: fit-sebastiaan-van-zelst

CHANGELOG.md

@@ -1,5 +1,52 @@
 # PM4Py Changelog
 
+## PM4PY 2.2.9 (2021.06.25)
+
+### Fixed
+
+* daf74e83
+    * update imports in feature extraction
+* 74be3e3c
+    * minor bug fix in alpha plus (place that was created was not always added to the resulting Petri net)
+
+### Removed
+
+### Deprecated
+
+### Changed
+
+* d97b1790
+    * drop deepcopy in event log sorting (enhances performance)
+* 1d4e625b
+    * revised IMf implementation (more close to ProM / PhD thesis Sander Leemans)
+* 20aabd95
+    * calculation of minimum self distance now adheres to the standard invocation structure
+
+### Added
+
+* 598c6ecb
+    * simplified interface now stores properties (using attr attribute) to dataframes
+* 1f7a3fa8
+    * add computation of rework statistic (cases containing the same activity more than once)
+* 32c7d330
+    * add computation of cycle time (active time of process divided by the number of instances of the process)
+* 8187f0e9
+    * add distribution plots over different time-frames (matplotlib)
+* 269d826c
+    * add batch detection based on Martin, N., Swennen, M., Depaire, B., Jans, M., Caris, A., & Vanhoof, K. (2015,
+      December). Batch Processing: Definition and Event Log Identification. In SIMPDA (pp. 137-140).
+* d5326d46
+    * compute case overlap of a case with all other cases
+
+### Other
+
+* 92a70586
+    * performance optimization for calculation of performance spectrum
+* b0fc57c4
+    * performance optimization for Pandas datetime conversion non-ISO8601 (regular formats)
+
+---
+
 ## PM4PY 2.2.8 (2021.06.11)
 
 ### Fixed

docs/source/conf.py

@@ -26,7 +26,7 @@
 # The short X.Y version
 version = '2.2'
 # The full version, including alpha/beta/rc tags
-release = '2.2.8'
+release = '2.2.9'
 
 # -- General configuration ---------------------------------------------------
 

examples/bath_detection.py

@@ -0,0 +1,18 @@
+import pm4py
+from pm4py.algo.discovery.batches import algorithm
+import os
+
+
+def execute_script():
+    log = pm4py.read_xes(os.path.join("..", "tests", "input_data", "receipt.xes"))
+    # detect the batches from the event log
+    batches = algorithm.apply(log)
+    # print the batches (complete information) in a single row
+    print(batches)
+    # print a summary information (size) for each activity-resource combination that is performed in batches
+    for batch in batches:
+        print(batch[0], batch[1])
+
+
+if __name__ == "__main__":
+    execute_script()

examples/case_overlap_stat.py

@@ -0,0 +1,15 @@
+import pm4py
+import os
+from pm4py.statistics.traces.case_overlap.log import get as wip_get
+
+
+def execute_script():
+    log = pm4py.read_xes(os.path.join("..", "tests", "input_data", "receipt.xes"))
+    # calculates the WIP statistics from the event log object.
+    # The WIP statistic associates to each case the number of cases open during the lifecycle of the case
+    wip = wip_get.apply(log)
+    print(wip)
+
+
+if __name__ == "__main__":
+    execute_script()

examples/cycle_time.py

@@ -0,0 +1,14 @@
+import os
+
+import pm4py
+from pm4py.statistics.traces.cycle_time.log import get as cycle_time_get
+
+
+def execute_script():
+    log = pm4py.read_xes(os.path.join("..", "tests", "input_data", "interval_event_log.xes"))
+    print(cycle_time_get.apply(log, parameters={cycle_time_get.Parameters.START_TIMESTAMP_KEY: "start_timestamp",
+                                                cycle_time_get.Parameters.TIMESTAMP_KEY: "time:timestamp"}))
+
+
+if __name__ == "__main__":
+    execute_script()

examples/decisiontree_trivial_example.py

@@ -3,19 +3,17 @@
 from sklearn import tree
 
 from pm4py.objects.log.importer.xes import importer as xes_importer
-from pm4py.objects.log.util import get_log_representation, get_class_representation
+from pm4py.objects.log.util import get_class_representation
+from pm4py.algo.transformation.log_to_features import algorithm as log_to_features
 from pm4py.visualization.decisiontree import visualizer as dt_vis
 
 
 def execute_script():
     log_path = os.path.join("..", "tests", "input_data", "roadtraffic50traces.xes")
     # log_path = os.path.join("..", "tests", "input_data", "receipt.xes")
     log = xes_importer.apply(log_path)
-    # gets a log representation by including the concept:name event attribute (string) and the amount event attribute
-    # (float)
-    # data, feature_names = get_log_representation.get_representation(log, [], ["concept:name"], [], ["amount"])
     # now, it is possible to get a default representation of an event log
-    data, feature_names = get_log_representation.get_default_representation(log)
+    data, feature_names = log_to_features.apply(log, variant=log_to_features.Variants.TRACE_BASED)
     # gets classes representation by final concept:name value (end activity)
     target, classes = get_class_representation.get_class_representation_by_str_ev_attr_value_value(log, "concept:name")
     # mine the decision tree given 'data' and 'target'

examples/events_distribution.py

@@ -0,0 +1,46 @@
+import os
+
+import pandas as pd
+
+import pm4py
+from pm4py.statistics.attributes.pandas import get as attr_get
+from pm4py.visualization.graphs import visualizer
+
+
+def execute_script():
+    df = pd.read_csv(os.path.join("..", "tests", "input_data", "receipt.csv"))
+    df = pm4py.format_dataframe(df)
+    # plots the distribution of the events over the days of a month
+    x0, y0 = attr_get.get_events_distribution(df, distr_type="days_month")
+    gviz = visualizer.apply(x0, y0, variant=visualizer.Variants.BARPLOT,
+                            parameters={"format": "svg", "title": "Distribution of the Events over the Days of a Month",
+                                        "x_axis": "Day of month", "y_axis": "Number of Events"})
+    visualizer.view(gviz)
+    # plots the distribution of the events over the months
+    x1, y1 = attr_get.get_events_distribution(df, distr_type="months")
+    gviz = visualizer.apply(x1, y1, variant=visualizer.Variants.BARPLOT,
+                            parameters={"format": "svg", "title": "Distribution of the Events over the Months",
+                                        "x_axis": "Month", "y_axis": "Number of Events"})
+    visualizer.view(gviz)
+    # plots the distribution of the events over the years
+    x2, y2 = attr_get.get_events_distribution(df, distr_type="years")
+    gviz = visualizer.apply(x2, y2, variant=visualizer.Variants.BARPLOT,
+                            parameters={"format": "svg", "title": "Distribution of the Events over the Years",
+                                        "x_axis": "Year", "y_axis": "Number of Events"})
+    visualizer.view(gviz)
+    # plots the distribution of the events over the hours (of the day)
+    x3, y3 = attr_get.get_events_distribution(df, distr_type="hours")
+    gviz = visualizer.apply(x3, y3, variant=visualizer.Variants.BARPLOT,
+                            parameters={"format": "svg", "title": "Distribution of the Events over the Hours",
+                                        "x_axis": "Hour (of day)", "y_axis": "Number of Events"})
+    visualizer.view(gviz)
+    # plots the distribution of the events over the days of the week
+    x4, y4 = attr_get.get_events_distribution(df, distr_type="days_week")
+    gviz = visualizer.apply(x4, y4, variant=visualizer.Variants.BARPLOT,
+                            parameters={"format": "svg", "title": "Distribution of the Events over the Days of a Week",
+                                        "x_axis": "Day of the Week", "y_axis": "Number of Events"})
+    visualizer.view(gviz)
+
+
+if __name__ == "__main__":
+    execute_script()

examples/rework.py

@@ -0,0 +1,13 @@
+import pm4py
+import os
+from pm4py.statistics.rework.log import get as rework_get
+
+
+def execute_script():
+    log = pm4py.read_xes(os.path.join("..", "tests", "input_data", "receipt.xes"))
+    rework = rework_get.apply(log)
+    print(rework)
+
+
+if __name__ == "__main__":
+    execute_script()