def aggregate_statistics(statistics, measure="frequency", aggregation_measure=None):
"""
Gets aggregated statistics
Parameters
----------
statistics
Individual element statistics (including unaggregated performances)
measure
Desidered view on data (frequency or performance)
aggregation_measure
Aggregation measure (e.g. mean, min) to use
Returns
----------
aggregated_statistics
Aggregated statistics for arcs, transitions, places
"""
min_trans_frequency, max_trans_frequency = find_min_max_trans_frequency(statistics)
min_arc_frequency, max_arc_frequency = find_min_max_arc_frequency(statistics)
min_arc_performance, max_arc_performance = find_min_max_arc_performance(statistics, aggregation_measure)
aggregated_statistics = {}
for elem in statistics.keys():
if type(elem) is PetriNet.Arc:
if measure == "frequency":
freq = statistics[elem]["count"]
arc_penwidth = get_arc_penwidth(freq, min_arc_frequency, max_arc_frequency)
aggregated_statistics[elem] = {"label": str(freq), "penwidth": str(arc_penwidth)}
elif measure == "performance":
if statistics[elem]["performance"]:
aggr_stat = aggregate_stats(statistics, elem, aggregation_measure)
aggr_stat_hr = human_readable_stat(aggr_stat)
arc_penwidth = get_arc_penwidth(aggr_stat, min_arc_performance, max_arc_performance)
aggregated_statistics[elem] = {"label": aggr_stat_hr, "penwidth": str(arc_penwidth)}
elif type(elem) is PetriNet.Transition:
if measure == "frequency":
if elem.label is not None:
freq = statistics[elem]["count"]
color = get_trans_freq_color(freq, min_trans_frequency, max_trans_frequency)
aggregated_statistics[elem] = {"label": elem.label + " (" + str(freq) + ")", "color": color}
elif type(elem) is PetriNet.Place:
pass
return aggregated_statistics
def execute_script():
log = xes_importer.apply(
os.path.join("..", "tests", "input_data", "receipt.xes"))
throughput_time = case_statistics.get_median_caseduration(log)
variants, variants_times = variants_filter.get_variants_along_with_case_durations(
log)
dfg = dfg_discovery.apply(log)
filtered_log = variants_filter.apply_auto_filter(deepcopy(log))
# filtered_log = log
tree = inductive_miner.apply_tree(filtered_log)
fp_log = fp_discovery.apply(log,
variant=fp_discovery.Variants.ENTIRE_EVENT_LOG)
fp_model = fp_discovery.apply(tree)
conf = fp_conformance.apply(fp_log, fp_model)
conf_occ = sorted([(x, dfg[x]) for x in conf],
key=lambda y: (y[1], y[0][0], y[0][1]),
reverse=True)
print(
"source activity\t\ttarget activity\t\toccurrences\t\tthroughput time log\t\tthroughput time traces with path"
)
for i in range(min(10, len(conf_occ))):
path = conf_occ[i][0]
occ = conf_occ[i][1]
red_log = paths_filter.apply(log, [path])
red_throughput_time = case_statistics.get_median_caseduration(red_log)
print("%s\t\t%s\t\t%d\t\t%s\t\t%s" %
(path[0], path[1], occ, human_readable_stat(throughput_time),
human_readable_stat(red_throughput_time)))
variants_length = sorted([(x, len(variants[x])) for x in variants.keys()],
key=lambda y: (y[1], y[0]),
reverse=True)
print(
"\nvariant\t\toccurrences\t\tthroughput time log\t\tthroughput time traces with path"
)
for i in range(min(10, len(variants_length))):
var = variants_length[i][0]
vark = str(var)
if len(vark) > 10:
vark = vark[:10]
occ = variants_length[i][1]
fp_log_var = fp_discovery.apply(
variants[var], variant=fp_discovery.Variants.ENTIRE_EVENT_LOG)
conf_var = fp_conformance.apply(fp_log_var, fp_model)
is_fit = str(len(conf_var) == 0)
var_throughput = case_statistics.get_median_caseduration(variants[var])
print("%s\t\t%d\t\t%s\t\t%s\t\t%s" %
(vark, occ, is_fit, throughput_time,
human_readable_stat(var_throughput)))
# print(conf_occ)
conf_colors = tree_visualization.apply(tree, conf)
if True:
gviz = pt_visualizer.apply(
tree,
parameters={
"format":
"svg",
pt_visualizer.Variants.WO_DECORATION.value.Parameters.COLOR_MAP:
conf_colors,
pt_visualizer.Variants.WO_DECORATION.value.Parameters.ENABLE_DEEPCOPY:
False
})
pt_visualizer.view(gviz)
def apply(network_analysis_edges0: Dict[Tuple[str, str], Dict[str, Any]],
parameters: Optional[Dict[Any, Any]] = None) -> Digraph:
"""
Creates a visualization of the network analysis (performance view)
Parameters
-----------------
network_analysis_edges0
Edges of the network analysis
parameters
Parameters of the algorithm, including:
- Parameters.FORMAT => the format of the visualization
- Parameters.BGCOLOR => the background color
- Parameters.ACTIVITY_THRESHOLD => the minimum number of occurrences for an activity to be included (default: 1)
- Parameters.EDGE_THRESHOLD => the minimum number of occurrences for an edge to be included (default: 1)
- Parameters.AGGREGATION_MEASURE => the aggregation measure (default: mean)
Returns
------------------
digraph
Graphviz graph
"""
if parameters is None:
parameters = {}
image_format = exec_utils.get_param_value(Parameters.FORMAT, parameters,
"png")
bgcolor = exec_utils.get_param_value(Parameters.BGCOLOR, parameters,
"transparent")
activity_threshold = exec_utils.get_param_value(
Parameters.ACTIVITY_THRESHOLD, parameters, 1)
edge_threshold = exec_utils.get_param_value(Parameters.EDGE_THRESHOLD,
parameters, 1)
aggregation_measure = exec_utils.get_param_value(
Parameters.AGGREGATION_MEASURE, parameters, "mean")
aggregation_f = mean
if aggregation_measure == "median":
aggregation_f = median
elif aggregation_measure == "min":
aggregation_f = min
elif aggregation_measure == "max":
aggregation_f = max
elif aggregation_measure == "stdev":
aggregation_f = stdev
elif aggregation_measure == "sum":
aggregation_f = sum
filename = tempfile.NamedTemporaryFile(suffix='.gv')
viz = Digraph("pt",
filename=filename.name,
engine='dot',
graph_attr={'bgcolor': bgcolor})
viz.attr('node', shape='ellipse', fixedsize='false')
network_analysis_edges = {}
network_analysis_edges_agg_performance = {}
for x in network_analysis_edges0:
network_analysis_edges[x] = {}
network_analysis_edges_agg_performance[x] = {}
for y in network_analysis_edges0[x]:
network_analysis_edges[x][y] = len(network_analysis_edges0[x][y])
network_analysis_edges_agg_performance[x][y] = aggregation_f(
network_analysis_edges0[x][y])
nodes = set(x[0] for x in network_analysis_edges).union(
set(x[1] for x in network_analysis_edges))
nodes_in_degree = {x: 0 for x in nodes}
nodes_out_degree = {x: 0 for x in nodes}
for edge in network_analysis_edges:
for edge_value in network_analysis_edges[edge]:
if network_analysis_edges[edge][edge_value] >= edge_threshold:
nodes_in_degree[
edge[1]] += network_analysis_edges[edge][edge_value]
nodes_out_degree[
edge[0]] += network_analysis_edges[edge][edge_value]
nodes_max_degree = {
x: max(nodes_in_degree[x], nodes_out_degree[x])
for x in nodes
}
max_node_value = sys.maxsize
min_node_value = -sys.maxsize
nodes_dict = {}
for node in nodes_max_degree:
if nodes_max_degree[node] >= activity_threshold:
nodes_dict[node] = str(uuid.uuid4())
viz.node(nodes_dict[node],
node + "\n(in=" + str(nodes_in_degree[node]) + "; out=" +
str(nodes_out_degree[node]) + ")",
style="filled",
fillcolor=vis_utils.get_trans_freq_color(
nodes_max_degree[node], max_node_value,
max_node_value))
count = nodes_max_degree[node]
if count > max_node_value:
max_node_value = count
elif count < min_node_value:
min_node_value = count
min_edge_value = sys.maxsize
max_edge_value = -sys.maxsize
for edge in network_analysis_edges:
if edge[0] in nodes_dict and edge[1] in nodes_dict:
for edge_value in network_analysis_edges[edge]:
count = network_analysis_edges[edge][edge_value]
if count > max_edge_value:
max_edge_value = count
elif count < min_edge_value:
min_edge_value = count
for edge in network_analysis_edges:
if edge[0] in nodes_dict and edge[1] in nodes_dict:
for edge_value in network_analysis_edges[edge]:
if network_analysis_edges[edge][edge_value] >= edge_threshold:
viz.edge(nodes_dict[edge[0]],
nodes_dict[edge[1]],
label=edge_value + "\n" +
vis_utils.human_readable_stat(
network_analysis_edges_agg_performance[edge]
[edge_value]) + "",
penwidth=str(
vis_utils.get_arc_penwidth(
network_analysis_edges[edge][edge_value],
min_edge_value, max_edge_value)))
viz.format = image_format
return viz