Merge remote-tracking branch 'upstream/hotfixes' into release

Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.12.2
+FROM python:3.12.3
 
 RUN apt-get update
 RUN apt-get -y upgrade

pm4py/algo/filtering/pandas/cases/case_filter.py

@@ -81,7 +81,7 @@ def filter_on_case_size(df0: pd.DataFrame, case_id_glue: str = "case:concept:nam
         Filtered dataframe
     """
     df = df0.copy()
-    element_group_size = df[case_id_glue].groupby(df[case_id_glue]).transform('size')
+    element_group_size = df[[case_id_glue]].groupby(case_id_glue).transform('size')
     df = df[element_group_size >= min_case_size]
     if max_case_size is not None:
         df = df[element_group_size <= max_case_size]
@@ -114,7 +114,7 @@ def filter_on_case_performance(df: pd.DataFrame, case_id_glue: str = constants.C
     df
         Filtered dataframe
     """
-    grouped_df = df[[case_id_glue, timestamp_key]].groupby(df[case_id_glue])
+    grouped_df = df[[case_id_glue, timestamp_key]].groupby(case_id_glue)
     start_events = grouped_df.first()
     end_events = grouped_df.last()
     end_events.columns = [str(col) + '_2' for col in end_events.columns]
@@ -128,7 +128,7 @@ def filter_on_case_performance(df: pd.DataFrame, case_id_glue: str = constants.C
     stacked_df = stacked_df[stacked_df['caseDuration'] <= max_case_performance]
     stacked_df = stacked_df[stacked_df['caseDuration'] >= min_case_performance]
     i1 = df.set_index(case_id_glue).index
-    i2 = stacked_df.set_index(case_id_glue).index
+    i2 = stacked_df.index
     ret = df[i1.isin(i2)]
     ret.attrs = copy(df.attrs) if hasattr(df, 'attrs') else {}
     return ret

pm4py/algo/filtering/pandas/timestamp/timestamp_filter.py

@@ -60,15 +60,15 @@ def filter_traces_contained(df: pd.DataFrame, dt1: Union[str, datetime.datetime]
     dt1 = get_dt_from_string(dt1)
     dt2 = get_dt_from_string(dt2)
 
-    grouped_df = df[[case_id_glue, timestamp_key]].groupby(df[case_id_glue])
+    grouped_df = df[[case_id_glue, timestamp_key]].groupby(case_id_glue)
     first = grouped_df.first()
     last = grouped_df.last()
     last.columns = [str(col) + '_2' for col in last.columns]
     stacked = pandas_utils.concat([first, last], axis=1)
     stacked = stacked[stacked[timestamp_key] >= dt1]
     stacked = stacked[stacked[timestamp_key + "_2"] <= dt2]
     i1 = df.set_index(case_id_glue).index
-    i2 = stacked.set_index(case_id_glue).index
+    i2 = stacked.index
     ret = df[i1.isin(i2)]
 
     ret.attrs = copy(df.attrs) if hasattr(df, 'attrs') else {}
@@ -103,7 +103,7 @@ def filter_traces_intersecting(df: pd.DataFrame, dt1: Union[str, datetime.dateti
     case_id_glue = exec_utils.get_param_value(Parameters.CASE_ID_KEY, parameters, CASE_CONCEPT_NAME)
     dt1 = get_dt_from_string(dt1)
     dt2 = get_dt_from_string(dt2)
-    grouped_df = df[[case_id_glue, timestamp_key]].groupby(df[case_id_glue])
+    grouped_df = df[[case_id_glue, timestamp_key]].groupby(case_id_glue)
     first = grouped_df.first()
     last = grouped_df.last()
     last.columns = [str(col) + '_2' for col in last.columns]
@@ -116,7 +116,7 @@ def filter_traces_intersecting(df: pd.DataFrame, dt1: Union[str, datetime.dateti
     stacked3 = stacked3[stacked3[timestamp_key + "_2"] > dt2]
     stacked = pandas_utils.concat([stacked1, stacked2, stacked3], axis=0)
     i1 = df.set_index(case_id_glue).index
-    i2 = stacked.set_index(case_id_glue).index
+    i2 = stacked.index
     ret = df[i1.isin(i2)]
 
     ret.attrs = copy(df.attrs) if hasattr(df, 'attrs') else {}

pm4py/meta.py

@@ -16,7 +16,7 @@
 '''
 
 __name__ = 'pm4py'
-VERSION = '2.7.11.5'
+VERSION = '2.7.11.6'
 __version__ = VERSION
 __doc__ = 'Process mining for Python'
 __author__ = 'Fraunhofer Institute for Applied Information Technology FIT'

pm4py/statistics/traces/generic/pandas/case_statistics.py

@@ -172,17 +172,19 @@ def get_cases_description(df: pd.DataFrame, parameters: Optional[Dict[Union[str,
     business_hours_slots = exec_utils.get_param_value(Parameters.BUSINESS_HOUR_SLOTS, parameters, constants.DEFAULT_BUSINESS_HOUR_SLOTS)
     workcalendar = exec_utils.get_param_value(Parameters.WORKCALENDAR, parameters, constants.DEFAULT_BUSINESS_HOURS_WORKCALENDAR)
 
-    grouped_df = df[[case_id_glue, timestamp_key]].groupby(df[case_id_glue])
-    # grouped_df = df[[case_id_glue, timestamp_key]].groupby(df[case_id_glue])
+    grouped_df = df[[case_id_glue, timestamp_key]].groupby(case_id_glue)
+    # grouped_df = df[[case_id_glue, timestamp_key]].groupby(case_id_glue)
     first_eve_df = grouped_df.first()
     last_eve_df = grouped_df.last()
     del grouped_df
     last_eve_df.columns = [str(col) + '_2' for col in first_eve_df.columns]
     stacked_df = pandas_utils.concat([first_eve_df, last_eve_df], axis=1)
     del first_eve_df
     del last_eve_df
-    del stacked_df[case_id_glue]
-    del stacked_df[case_id_glue + "_2"]
+    if case_id_glue in stacked_df.columns:
+        del stacked_df[case_id_glue]
+    if case_id_glue + "_2" in stacked_df.columns:
+        del stacked_df[case_id_glue + "_2"]
 
     if business_hours:
         stacked_df['caseDuration'] = stacked_df.apply(
@@ -266,7 +268,7 @@ def get_variants_df_with_case_duration(df, parameters=None):
 
     workcalendar = exec_utils.get_param_value(Parameters.WORKCALENDAR, parameters, constants.DEFAULT_BUSINESS_HOURS_WORKCALENDAR)
 
-    grouped_df = df[[case_id_glue, timestamp_key, activity_key]].groupby(df[case_id_glue])
+    grouped_df = df[[case_id_glue, timestamp_key, activity_key]].groupby(case_id_glue)
 
     df1 = grouped_df[activity_key].agg(tuple).to_frame()
     new_cols = list(df1.columns)
@@ -279,8 +281,10 @@ def get_variants_df_with_case_duration(df, parameters=None):
     stacked_df = pandas_utils.concat([first_eve_df, last_eve_df], axis=1)
     del first_eve_df
     del last_eve_df
-    del stacked_df[case_id_glue]
-    del stacked_df[case_id_glue + "_2"]
+    if case_id_glue in stacked_df.columns:
+        del stacked_df[case_id_glue]
+    if case_id_glue + "_2" in stacked_df.columns:
+        del stacked_df[case_id_glue + "_2"]
     stacked_df['caseDuration'] = stacked_df[timestamp_key + "_2"] - stacked_df[timestamp_key]
     stacked_df['caseDuration'] = pandas_utils.get_total_seconds(stacked_df['caseDuration'])
     if business_hours:

pm4py/util/constants.py

@@ -136,6 +136,7 @@ def get_default_is_aware_enabled():
 
 OPENAI_EXEC_RESULT = True if get_param_from_env("PM4PY_OPENAI_EXEC_RESULT", "False").lower() == "true" else False
 DEFAULT_GVIZ_VIEW = get_param_from_env("PM4PY_DEFAULT_GVIZ_VIEW", None)
+DEFAULT_ENABLE_VISUALIZATIONS_VIEW = get_param_from_env("PM4PY_DEFAULT_ENABLE_VISUALIZATIONS_VIEW", True)
 
 JQUERY_LINK = "https://code.jquery.com/jquery-3.6.3.min.js"
 GRAPHVIZJS_LINK = "https://github.com/mdaines/viz-js/releases/download/v1.8.2/viz.js"

pm4py/visualization/bpmn/variants/classic.py

@@ -150,7 +150,8 @@ def view(gviz: graphviz.Digraph, parameters=None):
     gviz
         GraphViz diagram
     """
-    return gview.view(gviz, parameters=parameters)
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        return gview.view(gviz, parameters=parameters)
 
 
 def matplotlib_view(gviz: graphviz.Digraph, parameters=None):
@@ -162,5 +163,5 @@ def matplotlib_view(gviz: graphviz.Digraph, parameters=None):
     gviz
         Graphviz
     """
-
-    return gview.matplotlib_view(gviz, parameters=parameters)
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        return gview.matplotlib_view(gviz, parameters=parameters)

pm4py/visualization/bpmn/variants/dagrejs.py

@@ -88,18 +88,19 @@ def view(temp_file_name, parameters=None):
     if parameters is None:
         parameters = {}
 
-    iframe_width = exec_utils.get_param_value(Parameters.IFRAME_WIDTH, parameters, 900)
-    iframe_height = exec_utils.get_param_value(Parameters.IFRAME_HEIGHT, parameters, 600)
-    local_jupyter_file_name = exec_utils.get_param_value(Parameters.LOCAL_JUPYTER_FILE_NAME, parameters, "jupyter_bpmn_vis.html")
-
-    if vis_utils.check_visualization_inside_jupyter():
-        from IPython.display import IFrame
-        shutil.copyfile(temp_file_name, local_jupyter_file_name)
-        iframe = IFrame(local_jupyter_file_name, width=iframe_width, height=iframe_height)
-        from IPython.display import display
-        return display(iframe)
-    else:
-        vis_utils.open_opsystem_image_viewer(temp_file_name)
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        iframe_width = exec_utils.get_param_value(Parameters.IFRAME_WIDTH, parameters, 900)
+        iframe_height = exec_utils.get_param_value(Parameters.IFRAME_HEIGHT, parameters, 600)
+        local_jupyter_file_name = exec_utils.get_param_value(Parameters.LOCAL_JUPYTER_FILE_NAME, parameters, "jupyter_bpmn_vis.html")
+
+        if vis_utils.check_visualization_inside_jupyter():
+            from IPython.display import IFrame
+            shutil.copyfile(temp_file_name, local_jupyter_file_name)
+            iframe = IFrame(local_jupyter_file_name, width=iframe_width, height=iframe_height)
+            from IPython.display import display
+            return display(iframe)
+        else:
+            vis_utils.open_opsystem_image_viewer(temp_file_name)
 
 
 def save(temp_file_name, dest_file, parameters=None):

pm4py/visualization/common/gview.py

@@ -31,19 +31,20 @@ def view(gviz, parameters=None):
     gviz
         GraphViz diagram
     """
-    if constants.DEFAULT_GVIZ_VIEW == "matplotlib_view":
-        return matplotlib_view(gviz, parameters=parameters)
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        if constants.DEFAULT_GVIZ_VIEW == "matplotlib_view":
+            return matplotlib_view(gviz, parameters=parameters)
 
-    format = str(gviz.format).lower().replace("plain-ext", "html")
+        format = str(gviz.format).lower().replace("plain-ext", "html")
 
-    is_dot_installed = dot_util.check_dot_installed()
+        is_dot_installed = dot_util.check_dot_installed()
 
-    if format.startswith("html"):
-        html.view(gviz, parameters=parameters)
-    elif vis_utils.check_visualization_inside_jupyter():
-        vis_utils.view_image_in_jupyter(gviz.render())
-    else:
-        return gviz.view(cleanup=True)
+        if format.startswith("html"):
+            html.view(gviz, parameters=parameters)
+        elif vis_utils.check_visualization_inside_jupyter():
+            vis_utils.view_image_in_jupyter(gviz.render())
+        else:
+            return gviz.view(cleanup=True)
 
 
 def matplotlib_view(gviz, parameters=None):
@@ -55,23 +56,24 @@ def matplotlib_view(gviz, parameters=None):
     gviz
         Graphviz
     """
-    format = str(gviz.format).lower()
-    is_dot_installed = dot_util.check_dot_installed()
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        format = str(gviz.format).lower()
+        is_dot_installed = dot_util.check_dot_installed()
 
-    from pm4py.visualization.common import save
-    import matplotlib.pyplot as plt
-    import matplotlib.image as mpimg
+        from pm4py.visualization.common import save
+        import matplotlib.pyplot as plt
+        import matplotlib.image as mpimg
 
-    file_name = tempfile.NamedTemporaryFile(suffix='.'+format)
-    file_name.close()
+        file_name = tempfile.NamedTemporaryFile(suffix='.'+format)
+        file_name.close()
 
-    save.save(gviz, file_name.name)
+        save.save(gviz, file_name.name)
 
-    img = mpimg.imread(file_name.name)
-    plt.axis('off')
-    plt.tight_layout(pad=0, w_pad=0, h_pad=0)
-    plt.imshow(img)
-    plt.show()
+        img = mpimg.imread(file_name.name)
+        plt.axis('off')
+        plt.tight_layout(pad=0, w_pad=0, h_pad=0)
+        plt.imshow(img)
+        plt.show()
 
 
 def serialize_dot(gviz: Digraph, parameters=None) -> bytes:

pm4py/visualization/dotted_chart/visualizer.py

@@ -72,20 +72,21 @@ def view(figure: str):
     figure
         Path to the dotted chart
     """
-    if constants.DEFAULT_GVIZ_VIEW == "matplotlib_view":
-        import matplotlib.pyplot as plt
-        import matplotlib.image as mpimg
-        img = mpimg.imread(figure)
-        plt.axis('off')
-        plt.tight_layout(pad=0, w_pad=0, h_pad=0)
-        plt.imshow(img)
-        plt.show()
-        return
-
-    if vis_utils.check_visualization_inside_jupyter():
-        vis_utils.view_image_in_jupyter(figure)
-    else:
-        vis_utils.open_opsystem_image_viewer(figure)
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        if constants.DEFAULT_GVIZ_VIEW == "matplotlib_view":
+            import matplotlib.pyplot as plt
+            import matplotlib.image as mpimg
+            img = mpimg.imread(figure)
+            plt.axis('off')
+            plt.tight_layout(pad=0, w_pad=0, h_pad=0)
+            plt.imshow(img)
+            plt.show()
+            return
+
+        if vis_utils.check_visualization_inside_jupyter():
+            vis_utils.view_image_in_jupyter(figure)
+        else:
+            vis_utils.open_opsystem_image_viewer(figure)
 
 
 def save(figure: str, output_file_path: str):
@@ -125,9 +126,10 @@ def matplotlib_view(figure: str):
     figure
         Path to the dotted chart
     """
-    import matplotlib.pyplot as plt
-    import matplotlib.image as mpimg
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        import matplotlib.pyplot as plt
+        import matplotlib.image as mpimg
 
-    img = mpimg.imread(figure)
-    plt.imshow(img)
-    plt.show()
+        img = mpimg.imread(figure)
+        plt.imshow(img)
+        plt.show()

pm4py/visualization/footprints/visualizer.py

@@ -16,7 +16,7 @@
 '''
 from pm4py.visualization.footprints.variants import comparison, single, comparison_symmetric
 from enum import Enum
-from pm4py.util import exec_utils
+from pm4py.util import exec_utils, constants
 from pm4py.visualization.common import gview
 from pm4py.visualization.common import save as gsave
 from pm4py.visualization.common.gview import serialize, serialize_dot
@@ -90,7 +90,8 @@ def view(gviz, parameters=None):
     gviz
         GraphViz diagram
     """
-    return gview.view(gviz, parameters=parameters)
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        return gview.view(gviz, parameters=parameters)
 
 
 def matplotlib_view(gviz, parameters=None):
@@ -102,5 +103,5 @@ def matplotlib_view(gviz, parameters=None):
     gviz
         Graphviz
     """
-
-    return gview.matplotlib_view(gviz, parameters=parameters)
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        return gview.matplotlib_view(gviz, parameters=parameters)

pm4py/visualization/graphs/util/common.py

@@ -62,19 +62,20 @@ def view(temp_file_name):
     temp_file_name
         Path to the temporary file hosting the graph
     """
-    if constants.DEFAULT_GVIZ_VIEW == "matplotlib_view":
-        import matplotlib.pyplot as plt
-        import matplotlib.image as mpimg
-        img = mpimg.imread(temp_file_name)
-        plt.axis('off')
-        plt.tight_layout(pad=0, w_pad=0, h_pad=0)
-        plt.imshow(img)
-        plt.show()
-        return
-    if vis_utils.check_visualization_inside_jupyter():
-        vis_utils.view_image_in_jupyter(temp_file_name)
-    else:
-        vis_utils.open_opsystem_image_viewer(temp_file_name)
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        if constants.DEFAULT_GVIZ_VIEW == "matplotlib_view":
+            import matplotlib.pyplot as plt
+            import matplotlib.image as mpimg
+            img = mpimg.imread(temp_file_name)
+            plt.axis('off')
+            plt.tight_layout(pad=0, w_pad=0, h_pad=0)
+            plt.imshow(img)
+            plt.show()
+            return
+        if vis_utils.check_visualization_inside_jupyter():
+            vis_utils.view_image_in_jupyter(temp_file_name)
+        else:
+            vis_utils.open_opsystem_image_viewer(temp_file_name)
 
 
 def matplotlib_view(temp_file_name):
@@ -86,12 +87,13 @@ def matplotlib_view(temp_file_name):
     temp_file_name
         Path to the temporary file hosting the graph
     """
-    import matplotlib.pyplot as plt
-    import matplotlib.image as mpimg
+    if constants.DEFAULT_ENABLE_VISUALIZATIONS_VIEW:
+        import matplotlib.pyplot as plt
+        import matplotlib.image as mpimg
 
-    img = mpimg.imread(temp_file_name)
-    plt.imshow(img)
-    plt.show()
+        img = mpimg.imread(temp_file_name)
+        plt.imshow(img)
+        plt.show()
 
 
 def serialize(temp_file_name: str) -> bytes: