def execute_script():
log_path = os.path.join("..", "tests", "input_data",
"roadtraffic50traces.xes")
# log_path = os.path.join("..", "tests", "input_data", "receipt.xes")
log = xes_importer.apply(log_path)
# now, it is possible to get a default representation of an event log
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 = tree.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: "svg"})
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 = tree.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: "svg"})
dt_vis.view(gviz)
def test_61(self):
import os
from pm4py.objects.log.importer.xes import importer as xes_importer
log = xes_importer.apply(os.path.join("input_data", "roadtraffic50traces.xes"))
from pm4py.objects.log.util import get_log_representation
str_trace_attributes = []
str_event_attributes = ["concept:name"]
num_trace_attributes = []
num_event_attributes = ["amount"]
data, feature_names = get_log_representation.get_representation(log, str_trace_attributes, str_event_attributes,
num_trace_attributes, num_event_attributes)
data, feature_names = get_log_representation.get_default_representation(log)
from pm4py.objects.log.util import get_class_representation
target, classes = get_class_representation.get_class_representation_by_trace_duration(log, 2 * 8640000)
from sklearn import tree
clf = tree.DecisionTreeClassifier()
clf.fit(data, target)
from pm4py.visualization.decisiontree import visualizer as dectree_visualizer
gviz = dectree_visualizer.apply(clf, feature_names, classes)
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"))
net, im, fm = inductive_miner.apply(log)
# 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: "svg"})
visualizer.view(gviz)
def test_decisiontree_traceduration(self):
# to avoid static method warnings in tests,
# that by construction of the unittest package have to be expressed in such way
self.dummy_variable = "dummy_value"
log_path = os.path.join("input_data", "roadtraffic50traces.xes")
log = xes_importer.apply(log_path)
data, feature_names = get_log_representation.get_representation(log, [], ["concept:name"], [], ["amount"])
target, classes = get_class_representation.get_class_representation_by_trace_duration(log, 2 * 8640000)
clf = tree.DecisionTreeClassifier(max_depth=7)
clf.fit(data, target)
gviz = dt_vis.apply(clf, feature_names, classes,
parameters={dt_vis.Variants.CLASSIC.value.Parameters.FORMAT: "svg"})
del gviz
def test_decisiontree_evattrvalue(self):
# to avoid static method warnings in tests,
# that by construction of the unittest package have to be expressed in such way
self.dummy_variable = "dummy_value"
log_path = os.path.join("input_data", "roadtraffic50traces.xes")
log = xes_importer.apply(log_path)
data, feature_names = log_to_features.apply(log, variant=log_to_features.Variants.TRACE_BASED,
parameters={"str_tr_attr": [], "str_ev_attr": ["concept:name"],
"num_tr_attr": [], "num_ev_attr": ["amount"]})
target, classes = get_class_representation.get_class_representation_by_str_ev_attr_value_value(log,
"concept:name")
clf = tree.DecisionTreeClassifier(max_depth=7)
clf.fit(data, target)
gviz = dt_vis.apply(clf, feature_names, classes,
parameters={dt_vis.Variants.CLASSIC.value.Parameters.FORMAT: "svg"})
del gviz
num_event_attributes = ["amount"]
data, feature_names = get_log_representation.get_representation(log, str_trace_attributes, str_event_attributes, num_trace_attributes, num_event_attributes) #error
data, feature_names = get_log_representation.get_default_representation(log)
import pandas as pd
dataframe = pd.DataFrame(data, columns=feature_names)
dataframe
dataframe.to_csv("features.csv", index=False)
from sklearn import tree
clf = tree.DecisionTreeClassifier()
clf.fit(data, target)
from pm4py.visualization.decisiontree import visualizer as dectree_visualizer
gviz = dectree_visualizer.apply(clf, feature_names, classes)
#-----
import os
from pm4py.objects.log.importer.xes import importer as xes_importer
log = xes_importer.apply(os.path.join("tests", "input_data", "roadtraffic50traces.xes"))
from pm4py.objects.log.util import get_log_representation
str_trace_attributes = []
str_event_attributes = ["concept:name"]
num_trace_attributes = []
num_event_attributes = ["amount"]
data, feature_names = get_log_representation.get_representation(log, str_trace_attributes, str_event_attributes, num_trace_attributes, num_event_attributes)