Hotfix release

CHANGELOG.md

@@ -1,5 +1,27 @@
 # PM4Py Changelog
 
+## PM4Py 2.2.19.1
+
+### Added
+* a193603e
+  * Event-Object Feature Extraction on OCEL
+* 8da05972
+  * Prefixes and Suffixes filters for Event Logs + Exposition in Simplified Interface
+
+### Changed
+
+### Deprecated
+
+### Fixed
+* cbf848ef
+  * Bug fix BPMN importer
+* ff0dfc4b
+  * Closed security issue within dependencies
+
+### Removed
+
+### Other
+
 ## PM4Py 2.2.19
 
 ### Added

Dockerfile

@@ -13,7 +13,7 @@ RUN apt-get -y install libtool flex bison pkg-config g++ libssl-dev automake
 RUN apt-get -y install libjemalloc-dev libboost-dev libboost-filesystem-dev libboost-system-dev libboost-regex-dev python3-dev autoconf flex bison cmake
 RUN apt-get -y install libxml2-dev libxslt-dev libfreetype6-dev libsuitesparse-dev
 RUN pip install -U wheel six pytest
-RUN pip install backcall==0.2.0 colorama==0.4.4 cycler==0.11.0 decorator==5.1.1 deprecation==2.1.0 fonttools==4.28.5 graphviz==0.19.1 intervaltree==3.1.0 ipython==8.0.1 jedi==0.18.1 jinja2==3.0.3 joblib==1.1.0 jsonpickle==2.1.0 kiwisolver==1.3.2 lxml==4.7.1 MarkupSafe==2.0.1 matplotlib==3.5.1 matplotlib-inline==0.1.3 mpmath==1.2.1 networkx==2.6.3 numpy==1.21.5 packaging==21.3 pandas==1.4.0 parso==0.8.3 pickleshare==0.7.5 pillow==9.0.0 prompt-toolkit==3.0.24 pydotplus==2.0.2 pygments==2.11.2 pyparsing==3.0.7 python-dateutil==2.8.2 pytz==2021.3 pyvis==0.1.9 scipy==1.7.3 setuptools==60.5.0 setuptools-scm==6.4.2 six==1.16.0 sortedcontainers==2.4.0 stringdist==1.0.9 sympy==1.9 threadpoolctl==3.0.0 tomli==2.0.0 tqdm==4.62.3 traitlets==5.1.1 wcwidth==0.2.5 
+RUN pip install backcall==0.2.0 colorama==0.4.4 cycler==0.11.0 decorator==5.1.1 deprecation==2.1.0 fonttools==4.29.1 graphviz==0.19.1 intervaltree==3.1.0 ipython==8.0.1 jedi==0.18.1 jinja2==3.0.3 jsonpickle==2.1.0 kiwisolver==1.3.2 lxml==4.7.1 MarkupSafe==2.0.1 matplotlib==3.5.1 matplotlib-inline==0.1.3 mpmath==1.2.1 networkx==2.6.3 numpy==1.22.2 packaging==21.3 pandas==1.4.0 parso==0.8.3 pickleshare==0.7.5 pillow==9.0.1 prompt-toolkit==3.0.27 pydotplus==2.0.2 pygments==2.11.2 pyparsing==3.0.7 python-dateutil==2.8.2 pytz==2021.3 pyvis==0.1.9 scipy==1.8.0 setuptools==60.8.2 six==1.16.0 sortedcontainers==2.4.0 stringdist==1.0.9 sympy==1.9 tqdm==4.62.3 traitlets==5.1.1 wcwidth==0.2.5 
 
 COPY . /app
 RUN cd /app && python setup.py install

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 = '2.2.19'
+release = '2.2.19.1'
 
 # -- General configuration ---------------------------------------------------
 

pm4py/__init__.py

@@ -38,7 +38,7 @@
     filter_between, filter_case_size, filter_case_performance, filter_activities_rework, filter_paths_performance, \
     filter_variants_by_coverage_percentage, filter_variants_top_k, filter_ocel_event_attribute, filter_ocel_object_attribute, \
     filter_ocel_object_types_allowed_activities, filter_ocel_object_per_type_count, filter_ocel_start_events_per_object_type, \
-    filter_ocel_end_events_per_object_type, filter_ocel_events_timestamp
+    filter_ocel_end_events_per_object_type, filter_ocel_events_timestamp, filter_prefixes, filter_suffixes
 from pm4py.hof import filter_log, filter_trace, sort_trace, sort_log
 from pm4py.meta import __name__, __version__, __doc__, __author__, __author_email__, \
     __maintainer__, __maintainer_email__

pm4py/algo/filtering/log/prefixes/__init__.py

@@ -0,0 +1 @@
+from pm4py.algo.filtering.log.prefixes import prefix_filter

pm4py/algo/filtering/log/prefixes/prefix_filter.py

@@ -0,0 +1,62 @@
+from enum import Enum
+from pm4py.util import exec_utils, xes_constants, constants
+from pm4py.objects.log.obj import EventLog, EventStream, Trace
+from typing import Dict, Optional, Any, Union
+from pm4py.objects.conversion.log import converter as log_converter
+
+
+class Parameters(Enum):
+    ACTIVITY_KEY = constants.PARAMETER_CONSTANT_ACTIVITY_KEY
+    STRICT = "strict"
+    FIRST_OR_LAST = "first_or_last"
+
+
+def apply(log: Union[EventLog, EventStream], activity: str, parameters: Optional[Dict[Any, Any]] = None) -> EventLog:
+    """
+    Filters the prefixes of an activity in the event log
+
+    Parameters
+    ----------------
+    log
+        Event log
+    activity
+        Target activity
+    parameters
+        Parameters of the algorithm, including:
+        - Parameters.ACTIVITY_KEY => the activity.
+        - Parameters.STRICT => applies the filter strictly (cuts the occurrences of the selected activity).
+        - Parameters.FIRST_OR_LAST => decides if the first or last occurrence of an activity should be selected.
+
+    Returns
+    ----------------
+    filtered_log
+        Filtered event log
+    """
+    if parameters is None:
+        parameters = {}
+
+    log = log_converter.apply(log, parameters=parameters)
+
+    activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes_constants.DEFAULT_NAME_KEY)
+    first_or_last = exec_utils.get_param_value(Parameters.FIRST_OR_LAST, parameters, "first")
+    strict = exec_utils.get_param_value(Parameters.STRICT, parameters, True)
+
+    filtered_log = EventLog(attributes=log.attributes, extensions=log.extensions, globals=log._omni,
+                       classifiers=log.classifiers, properties=log.properties)
+
+    for trace in log:
+        activities = [x[activity_key] if activity_key in x else None for x in trace]
+        if activity in activities:
+            if first_or_last == "first":
+                op = min
+            else:
+                op = max
+            idx_activity = op(i for i in range(len(activities)) if activities[i] == activity)
+            if not strict:
+                idx_activity = idx_activity + 1
+            filtered_trace = Trace(attributes=trace.attributes, properties=trace.properties)
+            for i in range(0, idx_activity):
+                filtered_trace.append(trace[i])
+            filtered_log.append(filtered_trace)
+
+    return filtered_log

pm4py/algo/filtering/log/suffixes/__init__.py

@@ -0,0 +1 @@
+from pm4py.algo.filtering.log.suffixes import suffix_filter

pm4py/algo/filtering/log/suffixes/suffix_filter.py

@@ -0,0 +1,62 @@
+from enum import Enum
+from pm4py.util import exec_utils, xes_constants, constants
+from pm4py.objects.log.obj import EventLog, EventStream, Trace
+from typing import Dict, Optional, Any, Union
+from pm4py.objects.conversion.log import converter as log_converter
+
+
+class Parameters(Enum):
+    ACTIVITY_KEY = constants.PARAMETER_CONSTANT_ACTIVITY_KEY
+    STRICT = "strict"
+    FIRST_OR_LAST = "first_or_last"
+
+
+def apply(log: Union[EventLog, EventStream], activity: str, parameters: Optional[Dict[Any, Any]] = None) -> EventLog:
+    """
+    Filters the suffixes of an activity in the event log
+
+    Parameters
+    ----------------
+    log
+        Event log
+    activity
+        Target activity
+    parameters
+        Parameters of the algorithm, including:
+        - Parameters.ACTIVITY_KEY => the activity.
+        - Parameters.STRICT => applies the filter strictly (cuts the occurrences of the selected activity).
+        - Parameters.FIRST_OR_LAST => decides if the first or last occurrence of an activity should be selected.
+
+    Returns
+    ----------------
+    filtered_log
+        Filtered event log
+    """
+    if parameters is None:
+        parameters = {}
+
+    log = log_converter.apply(log, parameters=parameters)
+
+    activity_key = exec_utils.get_param_value(Parameters.ACTIVITY_KEY, parameters, xes_constants.DEFAULT_NAME_KEY)
+    first_or_last = exec_utils.get_param_value(Parameters.FIRST_OR_LAST, parameters, "first")
+    strict = exec_utils.get_param_value(Parameters.STRICT, parameters, True)
+
+    filtered_log = EventLog(attributes=log.attributes, extensions=log.extensions, globals=log._omni,
+                       classifiers=log.classifiers, properties=log.properties)
+
+    for trace in log:
+        activities = [x[activity_key] if activity_key in x else None for x in trace]
+        if activity in activities:
+            if first_or_last == "first":
+                op = min
+            else:
+                op = max
+            idx_activity = op(i for i in range(len(activities)) if activities[i] == activity)
+            if strict:
+                idx_activity = idx_activity + 1
+            filtered_trace = Trace(attributes=trace.attributes, properties=trace.properties)
+            for i in range(idx_activity, len(trace)):
+                filtered_trace.append(trace[i])
+            filtered_log.append(filtered_trace)
+
+    return filtered_log

pm4py/algo/transformation/ocel/features/__init__.py

@@ -1,18 +1 @@
-'''
-    This file is part of PM4Py (More Info: https://pm4py.fit.fraunhofer.de).
-
-    PM4Py is free software: you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-
-    PM4Py is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with PM4Py.  If not, see <https://www.gnu.org/licenses/>.
-'''
-from pm4py.algo.transformation.ocel.features import objects, events
-
+from pm4py.algo.transformation.ocel.features import objects, events, events_objects

pm4py/algo/transformation/ocel/features/events/__init__.py

@@ -1,17 +1 @@
-'''
-    This file is part of PM4Py (More Info: https://pm4py.fit.fraunhofer.de).
-
-    PM4Py is free software: you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation, either version 3 of the License, or
-    (at your option) any later version.
-
-    PM4Py is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License
-    along with PM4Py.  If not, see <https://www.gnu.org/licenses/>.
-'''
-from pm4py.algo.transformation.ocel.features.events import algorithm, event_activity, event_timestamp, event_num_rel_objs_type, event_num_rel_objs, event_str_attributes, event_num_attributes, event_start_ot, event_end_ot, related_objects_features
+from pm4py.algo.transformation.ocel.features.events import algorithm, event_activity, event_timestamp, event_num_rel_objs_type, event_num_rel_objs, event_str_attributes, event_num_attributes, event_start_ot, event_end_ot, related_objects_features, new_interactions

pm4py/algo/transformation/ocel/features/events/algorithm.py

@@ -18,7 +18,7 @@
 from typing import Optional, Dict, Any, List
 from enum import Enum
 from pm4py.util import exec_utils
-from pm4py.algo.transformation.ocel.features.events import event_activity, event_num_rel_objs, event_num_rel_objs_type, event_timestamp, event_str_attributes, event_num_attributes, event_start_ot, event_end_ot, related_objects_features
+from pm4py.algo.transformation.ocel.features.events import event_activity, event_num_rel_objs, event_num_rel_objs_type, event_timestamp, event_str_attributes, event_num_attributes, event_start_ot, event_end_ot, related_objects_features, new_interactions
 
 
 class Parameters(Enum):
@@ -31,6 +31,7 @@ class Parameters(Enum):
     ENABLE_EVENT_NUM_ATTRIBUTES = "enable_event_num_attributes"
     ENABLE_EVENT_START_OT = "enable_event_start_ot"
     ENABLE_EVENT_END_OT = "enable_event_end_ot"
+    ENABLE_NEW_INTERACTIONS = "enable_new_interactions"
     ENABLE_RELATED_OBJECTS_FEATURES = "enable_related_objects_features"
 
 
@@ -57,6 +58,8 @@ def apply(ocel: OCEL, parameters: Optional[Dict[Any, Any]] = None):
                                                 lifecycle of some objects of a type.
         - Parameters.ENABLE_EVENT_END_OT => calculates some features which establish if the event completes the
                                                 lifecycle of some objects of a type.
+        - Parameters.ENABLE_NEW_INTERACTIONS => number of new interactions between the related objects which
+                                        appears in a given event.
         - Parameters.ENABLE_RELATED_OBJECTS_FEATURES => associates to the event some features calculated on the
                                                 related objects.
 
@@ -79,6 +82,8 @@ def apply(ocel: OCEL, parameters: Optional[Dict[Any, Any]] = None):
     enable_event_num_attributes = exec_utils.get_param_value(Parameters.ENABLE_EVENT_NUM_ATTRIBUTES, parameters, enable_all)
     enable_event_start_ot = exec_utils.get_param_value(Parameters.ENABLE_EVENT_START_OT, parameters, enable_all)
     enable_event_end_ot = exec_utils.get_param_value(Parameters.ENABLE_EVENT_END_OT, parameters, enable_all)
+    enable_new_interactions = exec_utils.get_param_value(Parameters.ENABLE_NEW_INTERACTIONS, parameters, enable_all)
+
     enable_related_objects_features = exec_utils.get_param_value(Parameters.ENABLE_RELATED_OBJECTS_FEATURES, parameters, False)
 
     ordered_events = list(ocel.events[ocel.event_id_column])
@@ -134,6 +139,12 @@ def apply(ocel: OCEL, parameters: Optional[Dict[Any, Any]] = None):
         for i in range(len(data)):
             datas[i] = datas[i] + data[i]
 
+    if enable_new_interactions:
+        data, feature_names = new_interactions.apply(ocel, parameters=parameters)
+        feature_namess = feature_namess + feature_names
+        for i in range(len(data)):
+            datas[i] = datas[i] + data[i]
+
     if enable_related_objects_features:
         data, feature_names = related_objects_features.apply(ocel, parameters=parameters)
         feature_namess = feature_namess + feature_names

pm4py/algo/transformation/ocel/features/events/new_interactions.py

@@ -0,0 +1,43 @@
+from pm4py.objects.ocel.obj import OCEL
+from typing import Optional, Dict, Any
+
+
+def apply(ocel: OCEL, parameters: Optional[Dict[Any, Any]] = None):
+    """
+    Discovers the number of new interactions between the related objects which appears in a given event.
+
+    Parameters
+    ---------------
+    ocel
+        OCEL
+    parameters
+        Parameters of the method
+
+    Returns
+    ----------------
+    data
+        Extracted feature values
+    feature_names
+        Feature names
+    """
+    if parameters is None:
+        parameters = {}
+
+    ordered_events = list(ocel.events[ocel.event_id_column])
+    rel_objs = ocel.relations.groupby(ocel.event_id_column)[ocel.object_id_column].agg(list).to_dict()
+
+    interactions = set()
+    data = []
+    feature_names = ["@@ev_new_interactions"]
+
+    for ev in ordered_events:
+        n = 0
+        if ev in rel_objs:
+            for o1 in rel_objs[ev]:
+                for o2 in rel_objs[ev]:
+                    if o1 < o2:
+                        if not (o1, o2) in interactions:
+                            n = n + 1
+        data.append([n])
+
+    return data, feature_names

pm4py/algo/transformation/ocel/features/events_objects/__init__.py

@@ -0,0 +1 @@
+from pm4py.algo.transformation.ocel.features.events_objects import algorithm, prefix_features

pm4py/algo/transformation/ocel/features/events_objects/algorithm.py

@@ -0,0 +1,74 @@
+from pm4py.objects.ocel.obj import OCEL
+from typing import Optional, Dict, Any
+from pm4py.algo.transformation.ocel.features.events import algorithm as event_feature_extraction
+from pm4py.algo.transformation.ocel.features.events_objects import prefix_features
+from pm4py.objects.ocel.util import explode
+from copy import copy
+from enum import Enum
+from pm4py.util import exec_utils
+
+
+class Parameters(Enum):
+    ENABLE_ALL_EO_FEATURES = "enable_all_eo_features"
+    ENABLE_EVENT_POINTWISE_FEATURES = "enable_event_pointwise_features"
+    ENABLE_PREFIX_FEATURES = "enable_prefix_features"
+
+
+def apply(ocel: OCEL, parameters: Optional[Dict[Any, Any]] = None):
+    """
+    Extract features that are related to the different combinations of events and objects of the OCEL.
+
+    Parameters
+    -----------------
+    ocel
+        Object-centric event log
+    parameters
+        Parameters of the algorithm, including:
+            - Parameters.ENABLE_ALL_EO_FEATURES => enables all the belowmentioned features
+            - Parameters.ENABLE_EVENT_POINTWISE_FEATURES => enables the calculation of pointwise features for the events
+            - Parameters.ENABLE_PREFIX_FEATURES => enables the prefix features
+
+    Returns
+    -----------------
+    data
+        Values of the features
+    feature_names
+        Names of the features
+    """
+    if parameters is None:
+        parameters = {}
+
+    enable_all = exec_utils.get_param_value(Parameters.ENABLE_ALL_EO_FEATURES, parameters, True)
+    enable_event_pointwise_features = exec_utils.get_param_value(Parameters.ENABLE_EVENT_POINTWISE_FEATURES, parameters, enable_all)
+    enable_prefix_features = exec_utils.get_param_value(Parameters.ENABLE_PREFIX_FEATURES, parameters, enable_all)
+
+    exploded_ocel = explode.apply(ocel)
+    ordered_events = list(exploded_ocel.events[exploded_ocel.event_id_column])
+
+    datas = []
+    features_namess = []
+    for i in range(len(ordered_events)):
+        datas.append([])
+
+    if enable_event_pointwise_features:
+        parameters_efe = copy(parameters)
+        parameters_efe["enable_all"] = False
+        parameters_efe["enable_related_objects_features"] = False
+        parameters_efe["enable_event_activity"] = True
+        parameters_efe["enable_event_timestamp"] = True
+        parameters_efe["enable_event_num_rel_objs_type"] = True
+        parameters_efe["enable_event_str_attributes"] = True
+        parameters_efe["enable_event_num_attributes"] = True
+        parameters_efe["enable_event_start_ot"] = True
+        data, feature_names = event_feature_extraction.apply(exploded_ocel, parameters=parameters_efe)
+        for i in range(len(data)):
+            datas[i] = datas[i] + data[i]
+        features_namess = features_namess + feature_names
+
+    if enable_prefix_features:
+        data, feature_names = prefix_features.apply(exploded_ocel, parameters=parameters)
+        for i in range(len(data)):
+            datas[i] = datas[i] + data[i]
+        features_namess = features_namess + feature_names
+
+    return datas, features_namess