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

process-intelligence-solutions · Apr 12, 2024 · 0213b90 · 0213b90
2 parents 104d2db + 6687770
commit 0213b90
Show file tree

Hide file tree

Showing 69 changed files with 915 additions and 616 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -12,6 +12,7 @@ RUN apt-get -y install g++ libboost-all-dev libncurses5-dev wget
 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 apt-get -y install libclang-16-dev llvm-16-dev
 RUN pip install -U wheel six pytest
 RUN pip install -U meson-python>=0.13.1 Cython>=3.0.6 ninja spin==0.8 build
 RUN pip install deprecation==2.1.0 graphviz==0.20.3 intervaltree==3.1.0 networkx==3.3 packaging==24.0 python-dateutil==2.9.0.post0 pytz==2024.1 six==1.16.0 sortedcontainers==2.4.0 tzdata==2024.1 
@@ -24,6 +25,7 @@ RUN pip install contourpy==1.2.1 fonttools==4.51.0 kiwisolver==1.4.5 matplotlib=
 #RUN cd / && git clone https://github.com/scipy/scipy.git && cd /scipy && git submodule update --init && pip3 install .
 #RUN cd / && git clone https://github.com/lxml/lxml.git && cd /lxml && pip3 install .
 #RUN pip3 install matplotlib
+#RUN cd / && git clone https://github.com/duckdb/duckdb.git && cd /duckdb && make && cd /duckdb/tools/pythonpkg && python3 setup.py install
 
 COPY . /app
 RUN cd /app && python setup.py install
diff --git a/examples/align_approx_pt.py b/examples/align_approx_pt.py
@@ -1,7 +1,7 @@
 import os
+import importlib.util
 from pm4py.algo.discovery.inductive import algorithm as inductive
 from pm4py.objects.log.importer.xes import importer as xes_importer
-from pm4py.visualization.process_tree import visualizer as pt_vis
 from pm4py.algo.conformance.alignments.process_tree import algorithm as align_approx
 from pm4py.objects.petri_net.utils.align_utils import pretty_print_alignments
 from examples import examples_conf
@@ -12,8 +12,11 @@ def execute_script():
 
     log = xes_importer.apply(log_path)
     tree = inductive.apply(log)
-    gviz = pt_vis.apply(tree, parameters={pt_vis.Variants.WO_DECORATION.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
-    pt_vis.view(gviz)
+
+    if importlib.util.find_spec("graphviz"):
+        from pm4py.visualization.process_tree import visualizer as pt_vis
+        gviz = pt_vis.apply(tree, parameters={pt_vis.Variants.WO_DECORATION.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
+        pt_vis.view(gviz)
 
     print("start calculate approximated alignments")
     approx_alignments = align_approx.apply(log, tree)

diff --git a/examples/align_decomposition_ex_paper.py b/examples/align_decomposition_ex_paper.py
@@ -1,8 +1,8 @@
 from pm4py.objects.petri_net.obj import PetriNet, Marking
 from pm4py.objects.petri_net.utils.petri_utils import add_arc_from_to
-from pm4py.visualization.petri_net import visualizer
 from pm4py.objects.petri_net.utils import decomposition
 from examples import examples_conf
+import importlib.util
 
 
 def execute_script():
@@ -82,13 +82,17 @@ def execute_script():
     im[start] = 1
     fm = Marking()
     fm[end] = 1
-    gvizs = []
-    gvizs.append(visualizer.apply(net, im, final_marking=fm, parameters={"format": examples_conf.TARGET_IMG_FORMAT}))
-    visualizer.view(gvizs[len(gvizs) - 1])
     decomposed_net = decomposition.decompose(net, im, fm)
-    for snet, sim, sfm in decomposed_net:
-        gvizs.append(visualizer.apply(snet, sim, final_marking=sfm, parameters={"format": examples_conf.TARGET_IMG_FORMAT}))
+    gvizs = []
+
+    if importlib.util.find_spec("graphviz"):
+        from pm4py.visualization.petri_net import visualizer
+
+        gvizs.append(visualizer.apply(net, im, final_marking=fm, parameters={"format": examples_conf.TARGET_IMG_FORMAT}))
         visualizer.view(gvizs[len(gvizs) - 1])
+        for snet, sim, sfm in decomposed_net:
+            gvizs.append(visualizer.apply(snet, sim, final_marking=sfm, parameters={"format": examples_conf.TARGET_IMG_FORMAT}))
+            visualizer.view(gvizs[len(gvizs) - 1])
 
 
 if __name__ == "__main__":

diff --git a/examples/bpmn_from_pt_conversion.py b/examples/bpmn_from_pt_conversion.py
@@ -6,6 +6,7 @@
 from pm4py.objects.log.importer.xes import importer as xes_import
 from pm4py.objects.bpmn.exporter import exporter as bpmn_exporter
 from examples import examples_conf
+import importlib.util
 
 
 
@@ -14,10 +15,11 @@ def execute_script():
     log = xes_import.apply(log_path)
     ptree = inductive_miner.apply(log)
     bpmn = pt_converter.apply(ptree, variant=pt_converter.Variants.TO_BPMN)
-    #bpmn = bpmn_layouter.apply(bpmn)
-    bpmn_exporter.apply(bpmn, "stru.bpmn")
-    os.remove("stru.bpmn")
-    pm4py.view_bpmn(bpmn, format=examples_conf.TARGET_IMG_FORMAT)
+
+    if importlib.util.find_spec("graphviz"):
+        bpmn_exporter.apply(bpmn, "stru.bpmn")
+        os.remove("stru.bpmn")
+        pm4py.view_bpmn(bpmn, format=examples_conf.TARGET_IMG_FORMAT)
 
 
 if __name__ == "__main__":

diff --git a/examples/bpmn_js_visualization.py b/examples/bpmn_js_visualization.py
@@ -1,12 +1,14 @@
 import pm4py
+import importlib.util
 
 
 def execute_script():
     log = pm4py.read_xes("../tests/input_data/running-example.xes")
 
     bpmn_model = pm4py.discover_bpmn_inductive(log)
 
-    pm4py.view_bpmn(bpmn_model, variant_str="dagrejs")
+    if importlib.util.find_spec("graphviz"):
+        pm4py.view_bpmn(bpmn_model, variant_str="dagrejs")
 
 
 if __name__ == "__main__":

diff --git a/examples/corr_mining.py b/examples/corr_mining.py
@@ -6,8 +6,7 @@
 from pm4py.statistics.start_activities.pandas import get as sa_get
 from pm4py.statistics.end_activities.pandas import get as ea_get
 from examples import examples_conf
-
-from pm4py.visualization.dfg import visualizer as dfg_vis
+import importlib.util
 
 
 def execute_script():
@@ -25,13 +24,16 @@ def execute_script():
     soj_time = soj_time_get.apply(df, parameters=parameters)
     dfg, performance_dfg = correlation_miner.apply(df, variant=correlation_miner.Variants.CLASSIC,
                                                    parameters=parameters)
-    gviz_freq = dfg_vis.apply(dfg, activities_count=act_count, serv_time=soj_time, variant=dfg_vis.Variants.FREQUENCY,
-                              parameters=parameters)
-    dfg_vis.view(gviz_freq)
-    gviz_perf = dfg_vis.apply(performance_dfg, activities_count=act_count, serv_time=soj_time,
-                              variant=dfg_vis.Variants.PERFORMANCE,
-                              parameters=parameters)
-    dfg_vis.view(gviz_perf)
+
+    if importlib.util.find_spec("grapviz"):
+        from pm4py.visualization.dfg import visualizer as dfg_vis
+        gviz_freq = dfg_vis.apply(dfg, activities_count=act_count, serv_time=soj_time, variant=dfg_vis.Variants.FREQUENCY,
+                                  parameters=parameters)
+        dfg_vis.view(gviz_freq)
+        gviz_perf = dfg_vis.apply(performance_dfg, activities_count=act_count, serv_time=soj_time,
+                                  variant=dfg_vis.Variants.PERFORMANCE,
+                                  parameters=parameters)
+        dfg_vis.view(gviz_perf)
 
 
 if __name__ == "__main__":

diff --git a/examples/cost_based_dfg.py b/examples/cost_based_dfg.py
@@ -1,15 +1,18 @@
 import pm4py
 import os
 from pm4py.algo.discovery.dfg.adapters.pandas import df_statistics
-from pm4py.visualization.dfg import visualizer as dfg_visualizer
 from examples import examples_conf
+import importlib.util
 
 
 def execute_script():
     log = pm4py.read_xes(os.path.join("..", "tests", "input_data", "roadtraffic100traces.xes"), return_legacy_log_object=False)
     cost_based_dfg = df_statistics.get_dfg_graph(log, measure="cost", cost_attribute="amount")
-    gviz = dfg_visualizer.apply(cost_based_dfg, variant=dfg_visualizer.Variants.COST, parameters={"format": examples_conf.TARGET_IMG_FORMAT})
-    dfg_visualizer.view(gviz)
+
+    if importlib.util.find_spec("grapviz"):
+        from pm4py.visualization.dfg import visualizer as dfg_visualizer
+        gviz = dfg_visualizer.apply(cost_based_dfg, variant=dfg_visualizer.Variants.COST, parameters={"format": examples_conf.TARGET_IMG_FORMAT})
+        dfg_visualizer.view(gviz)
 
 
 if __name__ == "__main__":

diff --git a/examples/data_petri_nets.py b/examples/data_petri_nets.py
@@ -6,6 +6,7 @@
 from pm4py.objects.petri_net.data_petri_nets.data_marking import DataMarking
 from pm4py.objects.log.importer.xes import importer as xes_importer
 from examples import examples_conf
+import importlib.util
 
 
 def get_trans_by_name(net, name):
@@ -18,7 +19,10 @@ def get_trans_by_name(net, name):
 def execute_script():
     log = xes_importer.apply(os.path.join("..", "tests", "input_data", "roadtraffic100traces.xes"))
     net, im, fm = pm4py.read_pnml(os.path.join("..", "tests", "input_data", "data_petri_net.pnml"), auto_guess_final_marking=True)
-    pm4py.view_petri_net(net, im, fm, format=examples_conf.TARGET_IMG_FORMAT)
+
+    if importlib.util.find_spec("graphviz"):
+        pm4py.view_petri_net(net, im, fm, format=examples_conf.TARGET_IMG_FORMAT)
+
     aligned_traces = alignments.apply(log, net, im, fm, variant=alignments.Variants.VERSION_DIJKSTRA_LESS_MEMORY, parameters={"ret_tuple_as_trans_desc": True})
     for index, trace in enumerate(log):
         aligned_trace = aligned_traces[index]

diff --git a/examples/dec_treplay_imdf.py b/examples/dec_treplay_imdf.py
@@ -2,9 +2,9 @@
 
 from pm4py.algo.discovery.inductive import algorithm as inductive_miner
 from pm4py.objects.log.importer.xes import importer as xes_importer
-from pm4py.visualization.petri_net import visualizer as pn_vis
 from pm4py.objects.conversion.process_tree import converter as process_tree_converter
 from examples import examples_conf
+import importlib.util
 
 
 def execute_script():
@@ -14,18 +14,21 @@ def execute_script():
     # apply Inductive Miner
     process_tree = inductive_miner.apply(log)
     net, initial_marking, final_marking = process_tree_converter.apply(process_tree)
-    # get visualization
-    variant = pn_vis.Variants.PERFORMANCE
-    parameters_viz = {pn_vis.Variants.PERFORMANCE.value.Parameters.AGGREGATION_MEASURE: "mean", pn_vis.Variants.PERFORMANCE.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT}
-    gviz = pn_vis.apply(net, initial_marking, final_marking, log=log, variant=variant,
-                        parameters=parameters_viz)
-    pn_vis.view(gviz)
-    # do another visualization with frequency
-    variant = pn_vis.Variants.FREQUENCY
-    parameters_viz = {pn_vis.Variants.FREQUENCY.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT}
-    gviz = pn_vis.apply(net, initial_marking, final_marking, log=log, variant=variant,
-                        parameters=parameters_viz)
-    pn_vis.view(gviz)
+
+    if importlib.util.find_spec("graphviz"):
+        from pm4py.visualization.petri_net import visualizer as pn_vis
+        # get visualization
+        variant = pn_vis.Variants.PERFORMANCE
+        parameters_viz = {pn_vis.Variants.PERFORMANCE.value.Parameters.AGGREGATION_MEASURE: "mean", pn_vis.Variants.PERFORMANCE.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT}
+        gviz = pn_vis.apply(net, initial_marking, final_marking, log=log, variant=variant,
+                            parameters=parameters_viz)
+        pn_vis.view(gviz)
+        # do another visualization with frequency
+        variant = pn_vis.Variants.FREQUENCY
+        parameters_viz = {pn_vis.Variants.FREQUENCY.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT}
+        gviz = pn_vis.apply(net, initial_marking, final_marking, log=log, variant=variant,
+                            parameters=parameters_viz)
+        pn_vis.view(gviz)
 
 
 if __name__ == "__main__":

diff --git a/examples/decisiontree_align_example.py b/examples/decisiontree_align_example.py
@@ -1,23 +1,27 @@
 from pm4py.objects.log.importer.xes import importer as xes_importer
 from pm4py.algo.discovery.inductive import algorithm as inductive_miner
 from pm4py.algo.decision_mining import algorithm
-from pm4py.visualization.decisiontree import visualizer as visualizer
 from pm4py.objects.conversion.process_tree import converter as process_tree_converter
 from examples import examples_conf
 import os
+import importlib.util
 
 
 def execute_script():
     # in this case, we obtain a decision tree by alignments on a specific decision point
     log = xes_importer.apply(os.path.join("..", "tests", "input_data", "running-example.xes"))
     process_tree = inductive_miner.apply(log)
     net, im, fm = process_tree_converter.apply(process_tree)
-    # we need to specify a decision point. In this case, the place p_10 is a suitable decision point
-    clf, feature_names, classes = algorithm.get_decision_tree(log, net, im, fm, decision_point="p_10")
-    # we can visualize the decision tree
-    gviz = visualizer.apply(clf, feature_names, classes,
-                            parameters={visualizer.Variants.CLASSIC.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
-    visualizer.view(gviz)
+
+    if importlib.util.find_spec("sklearn") and importlib.util.find_spec("graphviz"):
+        # we need to specify a decision point. In this case, the place p_10 is a suitable decision point
+        clf, feature_names, classes = algorithm.get_decision_tree(log, net, im, fm, decision_point="p_10")
+
+        # we can visualize the decision tree
+        from pm4py.visualization.decisiontree import visualizer as visualizer
+        gviz = visualizer.apply(clf, feature_names, classes,
+                                parameters={visualizer.Variants.CLASSIC.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
+        visualizer.view(gviz)
 
 
 if __name__ == "__main__":

diff --git a/examples/decisiontree_trivial_example.py b/examples/decisiontree_trivial_example.py
@@ -4,8 +4,8 @@
 from pm4py.objects.log.importer.xes import importer as xes_importer
 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
 from examples import examples_conf
+import importlib.util
 
 
 def execute_script():
@@ -16,21 +16,29 @@ def execute_script():
     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'
-    clf = ml_utils.DecisionTreeClassifier(max_depth=7)
-    clf.fit(data, target)
-    # visualize the decision tree
-    gviz = dt_vis.apply(clf, feature_names, classes, parameters={dt_vis.Variants.CLASSIC.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
-    dt_vis.view(gviz)
+
+    if importlib.util.find_spec("sklearn") and importlib.util.find_spec("graphviz"):
+        # mine the decision tree given 'data' and 'target'
+        clf = ml_utils.DecisionTreeClassifier(max_depth=7)
+        clf.fit(data, target)
+
+        # visualize the decision tree
+        from pm4py.visualization.decisiontree import visualizer as dt_vis
+        gviz = dt_vis.apply(clf, feature_names, classes, parameters={dt_vis.Variants.CLASSIC.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
+        dt_vis.view(gviz)
 
     # gets classes representation by trace duration (threshold between the two classes = 200D)
     target, classes = get_class_representation.get_class_representation_by_trace_duration(log, 2 * 8640000)
-    # mine the decision tree given 'data' and 'target'
-    clf = ml_utils.DecisionTreeClassifier(max_depth=7)
-    clf.fit(data, target)
-    # visualize the decision tree
-    gviz = dt_vis.apply(clf, feature_names, classes, parameters={dt_vis.Variants.CLASSIC.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
-    dt_vis.view(gviz)
+
+    if importlib.util.find_spec("sklearn") and importlib.util.find_spec("graphviz"):
+        # mine the decision tree given 'data' and 'target'
+        clf = ml_utils.DecisionTreeClassifier(max_depth=7)
+        clf.fit(data, target)
+
+        # visualize the decision tree
+        from pm4py.visualization.decisiontree import visualizer as dt_vis
+        gviz = dt_vis.apply(clf, feature_names, classes, parameters={dt_vis.Variants.CLASSIC.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
+        dt_vis.view(gviz)
 
 
 if __name__ == "__main__":

diff --git a/examples/dfg_align_log.py b/examples/dfg_align_log.py
@@ -6,9 +6,9 @@
 from pm4py.algo.filtering.dfg import dfg_filtering
 from pm4py.algo.conformance.alignments.dfg import algorithm as dfg_alignment
 from pm4py.statistics.attributes.log import get
-from pm4py.visualization.dfg import visualizer
 from pm4py.objects.petri_net.utils import align_utils
 from examples import examples_conf
+import importlib.util
 
 
 def execute_script():
@@ -32,9 +32,13 @@ def execute_script():
     print(bb - aa)
     print(sum(x["visited_states"] for x in aligned_traces))
     print(sum(x["cost"] // align_utils.STD_MODEL_LOG_MOVE_COST for x in aligned_traces))
-    gviz = visualizer.apply(dfg, activities_count=ac, parameters={"start_activities": sa, "end_activities": ea,
-                                                                  "format": examples_conf.TARGET_IMG_FORMAT})
-    visualizer.view(gviz)
+
+    if importlib.util.find_spec("graphviz"):
+        from pm4py.visualization.dfg import visualizer
+        gviz = visualizer.apply(dfg, activities_count=ac, parameters={"start_activities": sa, "end_activities": ea,
+                                                                      "format": examples_conf.TARGET_IMG_FORMAT})
+        visualizer.view(gviz)
+
     cc = time.time()
     aligned_traces2 = petri_alignments.apply(log, net, im, fm,
                                              variant=petri_alignments.Variants.VERSION_DIJKSTRA_LESS_MEMORY)

diff --git a/examples/dfg_filt_act_paths_perc.py b/examples/dfg_filt_act_paths_perc.py
@@ -1,7 +1,7 @@
 import pm4py
-from pm4py.visualization.dfg import visualizer as dfg_visualizer
 from pm4py.algo.filtering.dfg import dfg_filtering
 from examples import examples_conf
+import importlib.util
 
 
 def execute_script():
@@ -12,11 +12,14 @@ def execute_script():
     dfg, sa, ea, act_count = dfg_filtering.filter_dfg_on_activities_percentage(dfg, sa, ea, act_count, 0.3)
     # keep the specified amount of paths
     dfg, sa, ea, act_count = dfg_filtering.filter_dfg_on_paths_percentage(dfg, sa, ea, act_count, 0.3)
-    # view the DFG
-    gviz = dfg_visualizer.apply(dfg, activities_count=act_count, parameters={dfg_visualizer.Variants.FREQUENCY.value.Parameters.START_ACTIVITIES: sa,
-                                                                             dfg_visualizer.Variants.FREQUENCY.value.Parameters.END_ACTIVITIES: ea,
-                                                                             dfg_visualizer.Variants.FREQUENCY.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
-    dfg_visualizer.view(gviz)
+
+    if importlib.util.find_spec("graphviz"):
+        # view the DFG
+        from pm4py.visualization.dfg import visualizer as dfg_visualizer
+        gviz = dfg_visualizer.apply(dfg, activities_count=act_count, parameters={dfg_visualizer.Variants.FREQUENCY.value.Parameters.START_ACTIVITIES: sa,
+                                                                                 dfg_visualizer.Variants.FREQUENCY.value.Parameters.END_ACTIVITIES: ea,
+                                                                                 dfg_visualizer.Variants.FREQUENCY.value.Parameters.FORMAT: examples_conf.TARGET_IMG_FORMAT})
+        dfg_visualizer.view(gviz)
 
 
 if __name__ == "__main__":