Merge branch 'PM4PY-1552' into 'integration'

PMPY-1552 Rebase functionality (wrapper) See merge request process-mining/pm4py/pm4py-core!593
process-intelligence-solutions · Jan 25, 2022 · 7359807 · 7359807
2 parents f9ad1a4 + a1dd53e
commit 7359807
Show file tree

Hide file tree

Showing 2 changed files with 43 additions and 1 deletion.
diff --git a/pm4py/__init__.py b/pm4py/__init__.py
@@ -35,7 +35,7 @@
     get_case_arrival_average, get_rework_cases_per_activity, get_case_overlap, get_cycle_time, \
     get_all_case_durations, get_case_duration, get_activity_position_summary
 from pm4py.utils import format_dataframe, parse_process_tree, serialize, deserialize, set_classifier, parse_event_log_string, project_on_event_attribute, \
-    sample_cases, sample_events
+    sample_cases, sample_events, rebase
 from pm4py.vis import view_petri_net, save_vis_petri_net, view_dfg, save_vis_dfg, view_process_tree, \
     save_vis_process_tree, \
     view_ocdfg, save_vis_ocdfg, view_heuristics_net, save_vis_heuristics_net, view_bpmn, save_vis_bpmn, view_sna, save_vis_sna,\

diff --git a/pm4py/utils.py b/pm4py/utils.py
@@ -93,6 +93,48 @@ def format_dataframe(df: pd.DataFrame, case_id: str = constants.CASE_CONCEPT_NAM
     return df
 
 
+def rebase(log_obj: Union[EventLog, EventStream, pd.DataFrame], case_id: str = constants.CASE_CONCEPT_NAME,
+                     activity_key: str = xes_constants.DEFAULT_NAME_KEY,
+                     timestamp_key: str = xes_constants.DEFAULT_TIMESTAMP_KEY,
+                     start_timestamp_key: str = xes_constants.DEFAULT_START_TIMESTAMP_KEY):
+    """
+    Re-base the log object, changing the case ID, activity and timestamp attributes.
+
+    Parameters
+    -----------------
+    log_obj
+        Log object
+    case_id
+        Case identifier
+    activity_key
+        Activity
+    timestamp_key
+        Timestamp
+    start_timestamp_key
+        Start timestamp
+
+    Returns
+    -----------------
+    rebased_log_obj
+        Rebased log object
+    """
+    import pm4py
+
+    if isinstance(log_obj, pd.DataFrame):
+        return format_dataframe(log_obj, case_id=case_id, activity_key=activity_key, timestamp_key=timestamp_key,
+                                start_timestamp_key=start_timestamp_key)
+    elif isinstance(log_obj, EventLog):
+        log_obj = pm4py.convert_to_dataframe(log_obj)
+        log_obj = format_dataframe(log_obj, case_id=case_id, activity_key=activity_key, timestamp_key=timestamp_key,
+                                   start_timestamp_key=start_timestamp_key)
+        return pm4py.convert_to_event_log(log_obj)
+    elif isinstance(log_obj, EventStream):
+        log_obj = pm4py.convert_to_dataframe(log_obj)
+        log_obj = format_dataframe(log_obj, case_id=case_id, activity_key=activity_key, timestamp_key=timestamp_key,
+                                   start_timestamp_key=start_timestamp_key)
+        return pm4py.convert_to_event_stream(log_obj)
+
+
 def parse_process_tree(tree_string: str) -> ProcessTree:
     """
     Parse a process tree from a string