Merge branch 'ft-1398-sampling-simplified-interface' into 'integration'

FT 1398 Sampling in simplified interface

See merge request process-mining/pm4py/pm4py-core!556

pm4py/__init__.py

@@ -34,7 +34,8 @@
     get_minimum_self_distances, get_minimum_self_distance_witnesses, \
     get_case_arrival_average, get_rework_cases_per_activity, get_case_overlap, get_cycle_time, \
     get_all_case_durations, get_case_duration
-from pm4py.utils import format_dataframe, parse_process_tree, serialize, deserialize, set_classifier, parse_event_log_string, project_on_event_attribute
+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
 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,\

pm4py/objects/ocel/util/__init__.py

@@ -1 +1 @@
-from pm4py.objects.ocel.util import attributes_names, extended_table, flattening, related_objects, related_events, filtering_utils, log_ocel
+from pm4py.objects.ocel.util import attributes_names, extended_table, flattening, related_objects, related_events, filtering_utils, log_ocel, sampling

pm4py/objects/ocel/util/sampling.py

@@ -0,0 +1,50 @@
+from enum import Enum
+from pm4py.util import exec_utils
+from pm4py.objects.ocel import constants
+import random
+from pm4py.objects.ocel.util import filtering_utils
+from copy import copy
+from pm4py.objects.ocel.obj import OCEL
+from typing import Optional, Dict, Any
+
+
+class Parameters(Enum):
+    OBJECT_ID = constants.PARAM_OBJECT_ID
+    EVENT_ID = constants.PARAM_EVENT_ID
+    NUM_ENTITIES = "num_entities"
+
+
+def sample_ocel_events(ocel: OCEL, parameters: Optional[Dict[Any, Any]] = None) -> OCEL:
+    """
+    Keeps a sample of the events of an object-centric event log
+
+    Parameters
+    ------------------
+    ocel
+        Object-centric event log
+    parameters
+        Parameters of the algorithm, including:
+            - Parameters.EVENT_ID => event identifier
+            - Parameters.NUM_EVENTS => number of events
+
+    Returns
+    ------------------
+    sampled_ocel
+        Sampled object-centric event log
+    """
+    if parameters is None:
+        parameters = {}
+
+    event_id_column = exec_utils.get_param_value(Parameters.EVENT_ID, parameters, ocel.event_id_column)
+    num_entities = exec_utils.get_param_value(Parameters.NUM_ENTITIES, parameters, 100)
+
+    events = list(ocel.events[event_id_column].unique())
+    num_events = min(len(events), num_entities)
+
+    random.shuffle(events)
+    picked_events = events[:num_events]
+
+    ocel = copy(ocel)
+    ocel.events = ocel.events[ocel.events[event_id_column].isin(picked_events)]
+
+    return filtering_utils.propagate_event_filtering(ocel, parameters=parameters)

pm4py/utils.py

@@ -3,7 +3,7 @@
 
 import pandas as pd
 
-from pm4py.objects.log.obj import EventLog, Trace, Event
+from pm4py.objects.log.obj import EventLog, EventStream, Trace, Event
 from pm4py.objects.process_tree.obj import ProcessTree
 from pm4py.objects.ocel.obj import OCEL
 from pm4py.util import constants, xes_constants, pandas_utils
@@ -368,3 +368,53 @@ def general_checks_classical_event_log(log):
     if type(log) is OCEL:
         raise Exception("the method cannot be applied on object-centric event logs!")
     return True
+
+
+def sample_cases(log: Union[EventLog, pd.DataFrame], num_cases: int) -> Union[EventLog, pd.DataFrame]:
+    """
+    (Random) Sample a given number of cases from the event log.
+
+    Parameters
+    ---------------
+    log
+        Event log / Pandas dataframe
+    num_cases
+        Number of cases to sample
+
+    Returns
+    ---------------
+    sampled_log
+        Sampled event log (containing the specified amount of cases)
+    """
+    if isinstance(log, EventLog):
+        from pm4py.objects.log.util import sampling
+        return sampling.sample(log, num_cases)
+    elif isinstance(log, pd.DataFrame):
+        from pm4py.objects.log.util import dataframe_utils
+        return dataframe_utils.sample_dataframe(log, parameters={"max_no_cases": num_cases})
+
+
+def sample_events(log: Union[EventStream, OCEL], num_events: int) -> Union[EventStream, OCEL]:
+    """
+    (Random) Sample a given number of events from the event log.
+
+    Parameters
+    ---------------
+    log
+        Event stream / OCEL / Pandas dataframes
+    num_events
+        Number of events to sample
+
+    Returns
+    ---------------
+    sampled_log
+        Sampled event stream / OCEL / Pandas dataframes (containing the specified amount of events)
+    """
+    if isinstance(log, EventStream):
+        from pm4py.objects.log.util import sampling
+        return sampling.sample_stream(log, num_events)
+    elif isinstance(log, OCEL):
+        from pm4py.objects.ocel.util import sampling
+        return sampling.sample_ocel_events(log, parameters={"num_entities": num_events})
+    elif isinstance(log, pd.DataFrame):
+        return log.sample(n=num_events)