From 079d0988cdd3fe5770436b5bffafa95fad3eeeaf Mon Sep 17 00:00:00 2001 From: maicius Date: Thu, 28 Feb 2019 13:16:07 +0800 Subject: [PATCH 1/6] compare node and structure similarity between two diagram or two directory --- bpmn_python/bpmn_compare_similarity.py | 261 +++++++++++++++++++++++++ 1 file changed, 261 insertions(+) create mode 100644 bpmn_python/bpmn_compare_similarity.py diff --git a/bpmn_python/bpmn_compare_similarity.py b/bpmn_python/bpmn_compare_similarity.py new file mode 100644 index 0000000..6808ff4 --- /dev/null +++ b/bpmn_python/bpmn_compare_similarity.py @@ -0,0 +1,261 @@ +""" +比较两个BPMN模型的相似性 +""" + +from Levenshtein import distance +from bpmn_python.bpmn_diagram_rep import BpmnDiagramGraph +import os +import pandas as pd + + +class CompareBPMN(object): + def __init__(self, export_csv=False): + + self.export_csv = export_csv + self.result_list = [] + + + def get_bpmn_nodes(self, bpmn): + """ + :param bpmn: + :return: + """ + start_end_node = set() + nodes = bpmn.get_nodes() + # for node in nodes: + # # 去除开始节点和结束节点 + # if (node[1]['type'] == 'startEvent' or node[1]['type'] == 'endEvent'): + # start_end_node.add(node[0]) + # nodes.remove(node) + return nodes, start_end_node + + def get_bpmn_file_list(self, bpmn_file_path): + file_list = os.listdir(bpmn_file_path) + for file in file_list: + if file.find('.xml') == -1 and file.find('.bpmn') == -1: + file_list.remove(file) + return file_list + + def get_bpmn_flows(self, bpmn, start_end_node): + edges = bpmn.get_flows() + # edges = list(filter(lambda x: x[0] not in start_end_node and x[1] not in start_end_node, edges)) + return edges + + def calculate_similarity(self, file_name1, file_name2): + try: + raw_bpmn = BpmnDiagramGraph() + raw_bpmn.load_diagram_from_xml_file(file_name1) + raw_nodes, start_end_node = self.get_bpmn_nodes(raw_bpmn) + raw_edges = self.get_bpmn_flows(raw_bpmn, start_end_node) + + bpmn = BpmnDiagramGraph() + bpmn.load_diagram_from_xml_file(file_name2) + nodes, start_end_node = self.get_bpmn_nodes(bpmn) + edges = self.get_bpmn_flows(bpmn, start_end_node) + print(nodes) + print(raw_nodes) + if len(nodes) > 0 and len(raw_nodes) > 0: + # 计算节点内容相似性 + node_matching_sim, equivalence_mapping = self.calculate_node_matching_similarity(raw_nodes, + nodes) + print("node matching similarity: between", file_name1, "and", file_name2, ":", + round(node_matching_sim, 3)) + + structure_sim = self.calculate_structure_similarity(raw_edges, raw_nodes, edges, nodes, + equivalence_mapping) + return node_matching_sim, structure_sim + else: + return 0, 0 + except BaseException as e: + print("error in calculate similarity: ", e) + return 0, 0 + + def calculate_batch_similarity(self, bpmn_file_path1, bpmn_file_path2): + self.__raw_bpmn_file_path = bpmn_file_path1 + self.__bpmn_file_path = bpmn_file_path2 + raw_bpmn_file_list = self.get_bpmn_file_list(self.__raw_bpmn_file_path) + for bpmn_file in raw_bpmn_file_list: + try: + + raw_file_name = self.__raw_bpmn_file_path + bpmn_file + file_name = self.__bpmn_file_path + bpmn_file + + node_matching_sim, structure_sim = self.calculate_similarity(raw_file_name, file_name) + + self.result_list.append((bpmn_file, node_matching_sim, structure_sim)) + except BaseException as e: + print(e, bpmn_file) + df = pd.DataFrame(self.result_list) + df.sort_values(by=1, inplace=True, ascending=False) + df.reset_index() + if self.export_csv: + df.to_csv("result_sim.csv") + print(df.iloc[:, 1].mean(), df.iloc[:, 2].mean()) + + + def calculate_node_matching_similarity(self, raw_nodes, nodes): + """ + 比较传入的两个节点列表的相似性 + 首先找到列表中每个节点的相等映射 + :param raw_nodes: + :param nodes: + :return: + """ + col = list(map(lambda x: x[0], nodes)) + + edit_distance_df = pd.DataFrame(columns=col) + for raw_node in raw_nodes: + edit_distance_list = [0] * len(nodes) + edit_distance_list_df = pd.DataFrame([edit_distance_list], columns=col, index=[raw_node[0]]) + edit_distance_df = edit_distance_df.append(edit_distance_list_df) + for node in nodes: + # 计算句法相似度 + syn_sim = self.get_syn_sim(raw_node, node) + # 计算类型相似度 + type_sim = self.get_type_sim(raw_node, node) + node_sim = syn_sim * type_sim + edit_distance_df.loc[raw_node[0], node[0]] = node_sim + + equivalence_mapping = self.calculate_equivalence_mapping(sim_data_frame=edit_distance_df) + node_matching_sim = self.calculate_node_matching(equivalence_mapping, len(raw_nodes), len(nodes)) + + return node_matching_sim, equivalence_mapping + + def get_syn_sim(self, node1, node2): + """ + 根据传入的节点返回句法相似性 + :param node1: + :param node2: + :return: + """ + node1 = node1[1]['node_name'] + node2 = node2[1]['node_name'] + distance_val = distance(node1, node2) + if len(node1) == 0 and len(node2) == 0: + return 1 + else: + syn_sim = 1 - distance_val / max(len(node1), len(node2)) + return syn_sim + + def get_type_sim(self, node1, node2): + """ + 计算类型相似性 + :param node1: + :param node2: + :return: + """ + node_type1 = node1[1]['type'] + node_type2 = node2[1]['type'] + + if node_type1 == 'exclusiveGateway': + node_type1 = "parallelGateway" + if node_type2 == 'exclusiveGateway': + node_type2 = 'parallelGateway' + return 1 if node_type1 == node_type2 else 0 + + def calculate_equivalence_mapping(self, sim_data_frame): + """ + 根据传入的相似性矩阵计算最佳相等映射 + :param sim_data_frame: + :return: + """ + df_shape = sim_data_frame.shape + cols = list(sim_data_frame.columns.values) + equivalence_mapping = [] + while df_shape[0] > 0 and df_shape[1] > 0: + for col in cols: + mapping_tupple = self.find_best_mapping(col, sim_data_frame) + df_shape = sim_data_frame.shape + if mapping_tupple[2] > 0: + equivalence_mapping.append(mapping_tupple) + if mapping_tupple != (0, 0, 0): + cols.remove(mapping_tupple[0]) + return equivalence_mapping + + def calculate_node_matching(self, equivalence_mapping, raw_node_num, node_num): + """ + 计算节点相似度 + :param equivalence_mapping: + :param raw_node_num: + :param node_num: + :return: + """ + sum_sim = sum(map(lambda x: x[2], equivalence_mapping)) + return 2 * sum_sim / (raw_node_num + node_num) + + def find_best_mapping(self, col, sim_data_frame): + """ + 根据传入的节点名称和DataFrame寻找最佳映射 + :param col: + :param sim_data_frame: + :return: + """ + column_data = sim_data_frame.loc[:, col] + if len(column_data) > 0: + max_index = column_data[column_data == column_data.max()].index.values[0] + row_data = sim_data_frame.loc[max_index, :] + max_column = row_data[row_data == row_data.max()].index.values[0] + if max_column == col: + print('best mapping:', col, max_index) + sim_data_frame.drop([col], axis=1, inplace=True) + sim_data_frame.drop([max_index], axis=0, inplace=True) + return (col, max_index, row_data.max()) + else: + return self.find_best_mapping(max_column, sim_data_frame) + return (0, 0, 0) + + def calculate_structure_similarity(self, raw_edges, raw_nodes, edges, nodes, equivalence_mapping): + sn = self.calculate_sn(raw_nodes, nodes, equivalence_mapping) + se = self.calculate_se(raw_edges, edges, equivalence_mapping) + sim_sum = self.calculate_graph_edit_distance(equivalence_mapping) + graph_edit_distance = len(sn) + len(se) + 2 * sim_sum + print("图编辑距离：", graph_edit_distance) + snv = len(sn) / (len(raw_nodes) + len(nodes)) + sev = len(se) / (len(raw_edges) + len(edges)) + sbv = 2 * sim_sum / (len(raw_nodes) + len(nodes) - len(sn)) + simged = 1 - (snv + sev + sbv) / 3 + print("图编辑相似度:", round(simged, 3)) + return simged + + def calculate_graph_edit_distance(self, equivalence_mapping): + sim_sum = sum(map(lambda x: 1 - x[2], equivalence_mapping)) + return sim_sum + + def calculate_sn(self, raw_nodes, nodes, equivalence_mapping): + mapped_nodes = set(map(lambda x: x[0], equivalence_mapping)) + nodes = set(map(lambda x: x[0], nodes)) + delete_nodes = list(nodes - mapped_nodes) + + mapped_nodes2 = set(map(lambda x: x[1], equivalence_mapping)) + nodes2 = set(map(lambda x: x[0], raw_nodes)) + insert_nodes = list(nodes2 - mapped_nodes2) + sn = delete_nodes + insert_nodes + return sn + + def calculate_se(self, raw_edges, edges, equivalence_mapping): + equivalence_mapping_dict = {} + for item in equivalence_mapping: + equivalence_mapping_dict[item[0]] = item[1] + + raw_edges_set = set(map(lambda x: (x[0], x[1]), raw_edges)) + se_list = [] + for edge in edges: + if edge[0] in equivalence_mapping_dict and edge[1] in equivalence_mapping_dict: + new_edge_x = equivalence_mapping_dict[edge[0]] + new_edge_y = equivalence_mapping_dict[edge[1]] + if (new_edge_x, new_edge_y) not in raw_edges_set: + se_list.append((edge[0], edge[1])) + else: + new_set = set() + new_set.add((new_edge_x, new_edge_y)) + raw_edges_set = raw_edges_set - new_set + else: + se_list.append((edge[0], edge[1])) + raw_edges_list = list(raw_edges_set) + return se_list + raw_edges_list + + +if __name__ == '__main__': + cb = CompareBPMN() + # cb.calculate_batch_similarity("/Users/maicius/code/cpws_judge/data/", "/Users/maicius/code/CPWSSystem/resource/output/bpmn/") + cb.calculate_similarity(file_name1="/Users/maicius/code/cpws_judge/data/1431680.xml", file_name2="/Users/maicius/code/CPWSSystem/validate/bpmn_file/1431680.xml") From 2905982500e9cf42f19e26db43b19afb0a47676b Mon Sep 17 00:00:00 2001 From: maicius Date: Thu, 28 Feb 2019 13:42:21 +0800 Subject: [PATCH 2/6] change annotation from chinese to english --- bpmn_python/bpmn_compare_similarity.py | 90 +++++++++++++++----------- 1 file changed, 52 insertions(+), 38 deletions(-) diff --git a/bpmn_python/bpmn_compare_similarity.py b/bpmn_python/bpmn_compare_similarity.py index 6808ff4..8ccd15a 100644 --- a/bpmn_python/bpmn_compare_similarity.py +++ b/bpmn_python/bpmn_compare_similarity.py @@ -1,5 +1,7 @@ """ -比较两个BPMN模型的相似性 +Comparing the Similarity of Two BPMN Graphs +Implementation for Paper: +Similarity of business process models: Metrics and evaluation """ from Levenshtein import distance @@ -7,36 +9,42 @@ import os import pandas as pd - class CompareBPMN(object): - def __init__(self, export_csv=False): + def __init__(self, export_csv=False, export_excel=True): + """ + Comparing the Similarity of Two BPMN Graphs + Implementation for Paper: + 《Similarity of business process models: Metrics and evaluation》 + Address: https://kodu.ut.ee/~dumas/pubs/BetaWPSimilarity.pdf + + :param export_csv: If true, export export csv file as final result + :param export_excel: If true, export export excel file as final result + """ self.export_csv = export_csv + self.export_excel = export_excel self.result_list = [] - def get_bpmn_nodes(self, bpmn): """ :param bpmn: :return: """ - start_end_node = set() nodes = bpmn.get_nodes() - # for node in nodes: - # # 去除开始节点和结束节点 - # if (node[1]['type'] == 'startEvent' or node[1]['type'] == 'endEvent'): - # start_end_node.add(node[0]) - # nodes.remove(node) - return nodes, start_end_node + return nodes def get_bpmn_file_list(self, bpmn_file_path): + """ + :param bpmn_file_path: + :return: + """ file_list = os.listdir(bpmn_file_path) for file in file_list: if file.find('.xml') == -1 and file.find('.bpmn') == -1: file_list.remove(file) return file_list - def get_bpmn_flows(self, bpmn, start_end_node): + def get_bpmn_flows(self, bpmn): edges = bpmn.get_flows() # edges = list(filter(lambda x: x[0] not in start_end_node and x[1] not in start_end_node, edges)) return edges @@ -45,24 +53,25 @@ def calculate_similarity(self, file_name1, file_name2): try: raw_bpmn = BpmnDiagramGraph() raw_bpmn.load_diagram_from_xml_file(file_name1) - raw_nodes, start_end_node = self.get_bpmn_nodes(raw_bpmn) - raw_edges = self.get_bpmn_flows(raw_bpmn, start_end_node) + raw_nodes = self.get_bpmn_nodes(raw_bpmn) + raw_edges = self.get_bpmn_flows(raw_bpmn) bpmn = BpmnDiagramGraph() bpmn.load_diagram_from_xml_file(file_name2) - nodes, start_end_node = self.get_bpmn_nodes(bpmn) - edges = self.get_bpmn_flows(bpmn, start_end_node) - print(nodes) - print(raw_nodes) + nodes = self.get_bpmn_nodes(bpmn) + edges = self.get_bpmn_flows(bpmn) + if len(nodes) > 0 and len(raw_nodes) > 0: - # 计算节点内容相似性 + # calculate node matching similarity node_matching_sim, equivalence_mapping = self.calculate_node_matching_similarity(raw_nodes, nodes) print("node matching similarity: between", file_name1, "and", file_name2, ":", round(node_matching_sim, 3)) - + # calculate structure similarity structure_sim = self.calculate_structure_similarity(raw_edges, raw_nodes, edges, nodes, equivalence_mapping) + print("structure similarity: between", file_name1, "and", file_name2, ":", + round(structure_sim, 3)) return node_matching_sim, structure_sim else: return 0, 0 @@ -71,6 +80,12 @@ def calculate_similarity(self, file_name1, file_name2): return 0, 0 def calculate_batch_similarity(self, bpmn_file_path1, bpmn_file_path2): + """ + Compute the similarity of all BPMN graphs under two folders + :param bpmn_file_path1: + :param bpmn_file_path2: + :return: + """ self.__raw_bpmn_file_path = bpmn_file_path1 self.__bpmn_file_path = bpmn_file_path2 raw_bpmn_file_list = self.get_bpmn_file_list(self.__raw_bpmn_file_path) @@ -90,13 +105,16 @@ def calculate_batch_similarity(self, bpmn_file_path1, bpmn_file_path2): df.reset_index() if self.export_csv: df.to_csv("result_sim.csv") + + if self.export_excel: + df.to_excel("resulit_sim.excel") print(df.iloc[:, 1].mean(), df.iloc[:, 2].mean()) def calculate_node_matching_similarity(self, raw_nodes, nodes): """ - 比较传入的两个节点列表的相似性 - 首先找到列表中每个节点的相等映射 + compare similarity of two nodes + Similarity is measured by text editing distance (Levenshtein Distance) and node type :param raw_nodes: :param nodes: :return: @@ -109,13 +127,13 @@ def calculate_node_matching_similarity(self, raw_nodes, nodes): edit_distance_list_df = pd.DataFrame([edit_distance_list], columns=col, index=[raw_node[0]]) edit_distance_df = edit_distance_df.append(edit_distance_list_df) for node in nodes: - # 计算句法相似度 + # Syntactic Similarity syn_sim = self.get_syn_sim(raw_node, node) - # 计算类型相似度 + # Type Similarity type_sim = self.get_type_sim(raw_node, node) node_sim = syn_sim * type_sim edit_distance_df.loc[raw_node[0], node[0]] = node_sim - + # find best mapping for each node equivalence_mapping = self.calculate_equivalence_mapping(sim_data_frame=edit_distance_df) node_matching_sim = self.calculate_node_matching(equivalence_mapping, len(raw_nodes), len(nodes)) @@ -139,7 +157,7 @@ def get_syn_sim(self, node1, node2): def get_type_sim(self, node1, node2): """ - 计算类型相似性 + Calculate type similarity :param node1: :param node2: :return: @@ -147,17 +165,13 @@ def get_type_sim(self, node1, node2): node_type1 = node1[1]['type'] node_type2 = node2[1]['type'] - if node_type1 == 'exclusiveGateway': - node_type1 = "parallelGateway" - if node_type2 == 'exclusiveGateway': - node_type2 = 'parallelGateway' return 1 if node_type1 == node_type2 else 0 def calculate_equivalence_mapping(self, sim_data_frame): """ - 根据传入的相似性矩阵计算最佳相等映射 + Computing the Best Equivalent Mapping Based on the Input Similarity Matrix :param sim_data_frame: - :return: + :return: Best Equivalent Mapping List of Nodes """ df_shape = sim_data_frame.shape cols = list(sim_data_frame.columns.values) @@ -174,8 +188,8 @@ def calculate_equivalence_mapping(self, sim_data_frame): def calculate_node_matching(self, equivalence_mapping, raw_node_num, node_num): """ - 计算节点相似度 - :param equivalence_mapping: + Computing the final similarity of nodes according to the formulas in the paper + :param equivalence_mapping: Best Equivalent Mapping List of Nodes :param raw_node_num: :param node_num: :return: @@ -185,7 +199,7 @@ def calculate_node_matching(self, equivalence_mapping, raw_node_num, node_num): def find_best_mapping(self, col, sim_data_frame): """ - 根据传入的节点名称和DataFrame寻找最佳映射 + Find the best equivalence mapping for incoming nodes :param col: :param sim_data_frame: :return: @@ -196,7 +210,7 @@ def find_best_mapping(self, col, sim_data_frame): row_data = sim_data_frame.loc[max_index, :] max_column = row_data[row_data == row_data.max()].index.values[0] if max_column == col: - print('best mapping:', col, max_index) + # print('best mapping:', col, max_index) sim_data_frame.drop([col], axis=1, inplace=True) sim_data_frame.drop([max_index], axis=0, inplace=True) return (col, max_index, row_data.max()) @@ -209,12 +223,12 @@ def calculate_structure_similarity(self, raw_edges, raw_nodes, edges, nodes, equ se = self.calculate_se(raw_edges, edges, equivalence_mapping) sim_sum = self.calculate_graph_edit_distance(equivalence_mapping) graph_edit_distance = len(sn) + len(se) + 2 * sim_sum - print("图编辑距离：", graph_edit_distance) + print("graph edit distance：", graph_edit_distance) snv = len(sn) / (len(raw_nodes) + len(nodes)) sev = len(se) / (len(raw_edges) + len(edges)) sbv = 2 * sim_sum / (len(raw_nodes) + len(nodes) - len(sn)) simged = 1 - (snv + sev + sbv) / 3 - print("图编辑相似度:", round(simged, 3)) + print("graph edit similarity:", round(simged, 3)) return simged def calculate_graph_edit_distance(self, equivalence_mapping): From 382335ae817f2e9b06ce0dcf254e8a3a6b575ac1 Mon Sep 17 00:00:00 2001 From: maicius Date: Thu, 28 Feb 2019 13:42:38 +0800 Subject: [PATCH 3/6] add requirements --- requirements.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/requirements.txt b/requirements.txt index 272ec11..fcd3561 100644 --- a/requirements.txt +++ b/requirements.txt @@ -2,4 +2,5 @@ six pandas networkx matplotlib -pydotplus \ No newline at end of file +pydotplus +python-Levenshtein \ No newline at end of file From acfb3ff233be269fbca3513f2ae1da80e1abe413 Mon Sep 17 00:00:00 2001 From: maicius Date: Thu, 28 Feb 2019 14:27:18 +0800 Subject: [PATCH 4/6] add unit test --- bpmn_python/bpmn_compare_similarity.py | 29 +- tests/compare/CompareBPMNTest.py | 25 + .../compare/compare_resource/bpmn_file/1.xml | 167 ++++++ .../compare_resource/bpmn_file/1431680.xml | 490 ++++++++++++++++++ .../compare_resource/bpmn_file/152802.xml | 167 ++++++ .../compare_resource/bpmn_file/1955.xml | 152 ++++++ .../compare_resource/bpmn_file/8385.xml | 239 +++++++++ .../compare_resource/output/result_sim.csv | 6 + .../compare_resource/raw_bpmn_file/1.xml | 152 ++++++ .../raw_bpmn_file/1431680.xml | 298 +++++++++++ .../compare_resource/raw_bpmn_file/152802.xml | 191 +++++++ .../compare_resource/raw_bpmn_file/1955.xml | 152 ++++++ .../compare_resource/raw_bpmn_file/8385.xml | 239 +++++++++ 13 files changed, 2297 insertions(+), 10 deletions(-) create mode 100644 tests/compare/CompareBPMNTest.py create mode 100644 tests/compare/compare_resource/bpmn_file/1.xml create mode 100644 tests/compare/compare_resource/bpmn_file/1431680.xml create mode 100644 tests/compare/compare_resource/bpmn_file/152802.xml create mode 100644 tests/compare/compare_resource/bpmn_file/1955.xml create mode 100644 tests/compare/compare_resource/bpmn_file/8385.xml create mode 100644 tests/compare/compare_resource/output/result_sim.csv create mode 100644 tests/compare/compare_resource/raw_bpmn_file/1.xml create mode 100644 tests/compare/compare_resource/raw_bpmn_file/1431680.xml create mode 100644 tests/compare/compare_resource/raw_bpmn_file/152802.xml create mode 100644 tests/compare/compare_resource/raw_bpmn_file/1955.xml create mode 100644 tests/compare/compare_resource/raw_bpmn_file/8385.xml diff --git a/bpmn_python/bpmn_compare_similarity.py b/bpmn_python/bpmn_compare_similarity.py index 8ccd15a..b6feb41 100644 --- a/bpmn_python/bpmn_compare_similarity.py +++ b/bpmn_python/bpmn_compare_similarity.py @@ -77,39 +77,48 @@ def calculate_similarity(self, file_name1, file_name2): return 0, 0 except BaseException as e: print("error in calculate similarity: ", e) - return 0, 0 + raise e - def calculate_batch_similarity(self, bpmn_file_path1, bpmn_file_path2): + def calculate_batch_similarity(self, bpmn_file_path1, bpmn_file_path2, output_dir = ""): """ Compute the similarity of all BPMN graphs under two folders + Two files to compare are placed in different folders, + but they must have [[[the same file name]]] + :param bpmn_file_path1: :param bpmn_file_path2: :return: """ - self.__raw_bpmn_file_path = bpmn_file_path1 - self.__bpmn_file_path = bpmn_file_path2 + + self.__raw_bpmn_file_path = self.check_file_name(bpmn_file_path1) + self.__bpmn_file_path = self.check_file_name(bpmn_file_path2) raw_bpmn_file_list = self.get_bpmn_file_list(self.__raw_bpmn_file_path) for bpmn_file in raw_bpmn_file_list: try: - - raw_file_name = self.__raw_bpmn_file_path + bpmn_file + # file name must be same!! + raw_file_name = os.path.join(self.__raw_bpmn_file_path + bpmn_file) file_name = self.__bpmn_file_path + bpmn_file - node_matching_sim, structure_sim = self.calculate_similarity(raw_file_name, file_name) self.result_list.append((bpmn_file, node_matching_sim, structure_sim)) except BaseException as e: print(e, bpmn_file) + df = pd.DataFrame(self.result_list) df.sort_values(by=1, inplace=True, ascending=False) df.reset_index() if self.export_csv: - df.to_csv("result_sim.csv") + df.to_csv(os.path.join(output_dir, "result_sim.csv")) if self.export_excel: - df.to_excel("resulit_sim.excel") + df.to_excel(os.path.join(output_dir + "result_sim.excel")) print(df.iloc[:, 1].mean(), df.iloc[:, 2].mean()) + def check_file_name(self, file_name): + if file_name[-1] != '/': + return file_name + '/' + else: + return file_name def calculate_node_matching_similarity(self, raw_nodes, nodes): """ @@ -271,5 +280,5 @@ def calculate_se(self, raw_edges, edges, equivalence_mapping): if __name__ == '__main__': cb = CompareBPMN() - # cb.calculate_batch_similarity("/Users/maicius/code/cpws_judge/data/", "/Users/maicius/code/CPWSSystem/resource/output/bpmn/") + cb.calculate_batch_similarity("/Users/maicius/code/cpws_judge/data/", "/Users/maicius/code/CPWSSystem/resource/output/bpmn/") cb.calculate_similarity(file_name1="/Users/maicius/code/cpws_judge/data/1431680.xml", file_name2="/Users/maicius/code/CPWSSystem/validate/bpmn_file/1431680.xml") diff --git a/tests/compare/CompareBPMNTest.py b/tests/compare/CompareBPMNTest.py new file mode 100644 index 0000000..885f0c6 --- /dev/null +++ b/tests/compare/CompareBPMNTest.py @@ -0,0 +1,25 @@ +import unittest +import os + +from bpmn_python.bpmn_compare_similarity import CompareBPMN + + +class CompareBPMNTest(unittest.TestCase): + """ + Test compare bpmn similarity + """ + output_directory = "../compare_resource/output/" + example_directory_1 = "../compare_resource/bpmn_file/" + example_directory_2 = "../compare_resource/raw_bpmn_file/" + + def test_similarity_between_two_diagram(self): + cb = CompareBPMN() + cb.calculate_similarity(file_name1=os.path.abspath(self.example_directory_1 + "1.xml"), + file_name2=os.path.abspath(self.example_directory_2 + "1.xml")) + + def test_similarity_between_two_directory(self): + cb = CompareBPMN(export_csv=True, export_excel=False) + cb.calculate_batch_similarity(bpmn_file_path1=os.path.abspath(self.example_directory_1), + bpmn_file_path2=os.path.abspath(self.example_directory_2), + output_dir=os.path.abspath(self.output_directory) + ) diff --git a/tests/compare/compare_resource/bpmn_file/1.xml b/tests/compare/compare_resource/bpmn_file/1.xml new file mode 100644 index 0000000..621d4d9 --- /dev/null +++ b/tests/compare/compare_resource/bpmn_file/1.xml @@ -0,0 +1,167 @@ + + + + + SequenceFlow_1ho9gbz + + + SequenceFlow_1ho9gbz + SequenceFlow_1uwzf74 + + + + SequenceFlow_1aqkvvq + SequenceFlow_0q2txr2 + + + SequenceFlow_0e2yk4y + SequenceFlow_10mlqsr + + + SequenceFlow_1uwzf74 + SequenceFlow_1aqkvvq + SequenceFlow_0e2yk4y + + + + + + + + SequenceFlow_0gl1g92 + SequenceFlow_1qr340o + + + + SequenceFlow_0q2txr2 + SequenceFlow_10mlqsr + SequenceFlow_0gl1g92 + + + SequenceFlow_1qr340o + SequenceFlow_1wyvnyi + + + SequenceFlow_1wyvnyi + SequenceFlow_1ik2319 + + + + + SequenceFlow_1ik2319 + SequenceFlow_0huedwg + + + SequenceFlow_0huedwg + SequenceFlow_104eeb8 + + + + + + SequenceFlow_104eeb8 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tests/compare/compare_resource/bpmn_file/1431680.xml b/tests/compare/compare_resource/bpmn_file/1431680.xml new file mode 100644 index 0000000..0f99400 --- /dev/null +++ b/tests/compare/compare_resource/bpmn_file/1431680.xml @@ -0,0 +1,490 @@ + + + + + SequenceFlow_0s2hm7k + + + SequenceFlow_1rx93d9 + SequenceFlow_0tu8mxs + + + SequenceFlow_1mbt0ou + SequenceFlow_13x8n8m + + + SequenceFlow_1s87xqn + SequenceFlow_1rx93d9 + SequenceFlow_1mbt0ou + + + + + + SequenceFlow_0tu8mxs + SequenceFlow_13x8n8m + SequenceFlow_1y9iw52 + + + SequenceFlow_1y9iw52 + SequenceFlow_18am8b7 + + + + + + SequenceFlow_18am8b7 + SequenceFlow_06q3qq5 + SequenceFlow_1kmdnjf + SequenceFlow_1t9adhh + + + SequenceFlow_06q3qq5 + SequenceFlow_1cq8lhh + + + SequenceFlow_1kmdnjf + SequenceFlow_1o3aiep + + + SequenceFlow_1t9adhh + SequenceFlow_0wvwzxb + + + + + + + SequenceFlow_1wvyd9l + SequenceFlow_0d6jc3p + + + SequenceFlow_0rte4s6 + SequenceFlow_0q6xv6c + SequenceFlow_0z9h434 + + + SequenceFlow_0q6xv6c + SequenceFlow_044dqix + + + SequenceFlow_0z9h434 + SequenceFlow_0dt6fsk + + + + + SequenceFlow_044dqix + SequenceFlow_0dt6fsk + SequenceFlow_0a2saim + + + SequenceFlow_1jwr6tc + SequenceFlow_0qlcgjk + + + SequenceFlow_0a2saim + SequenceFlow_1jwr6tc + SequenceFlow_1955q5w + + + SequenceFlow_1955q5w + SequenceFlow_1gmv6b1 + + + + SequenceFlow_0qlcgjk + SequenceFlow_1gmv6b1 + SequenceFlow_1il9n1f + + + + + SequenceFlow_1il9n1f + SequenceFlow_0khw9zo + + + + SequenceFlow_0khw9zo + SequenceFlow_183vz9h + + + SequenceFlow_1t3jg9u + SequenceFlow_0l8m3dg + + + SequenceFlow_0fwrd36 + SequenceFlow_0ff4j04 + + + + SequenceFlow_183vz9h + SequenceFlow_1t3jg9u + SequenceFlow_0fwrd36 + + + + + + + + SequenceFlow_0ua5swk + + + + SequenceFlow_0d6jc3p + SequenceFlow_091nkqc + + + + + + + + + SequenceFlow_0l8m3dg + SequenceFlow_0ff4j04 + SequenceFlow_0ua5swk + + + + + SequenceFlow_1o3aiep + SequenceFlow_1cq8lhh + SequenceFlow_0wvwzxb + SequenceFlow_1wvyd9l + + + SequenceFlow_0s2hm7k + SequenceFlow_1s87xqn + + + + + SequenceFlow_0de47py + SequenceFlow_07bwfnn + + + + SequenceFlow_091nkqc + SequenceFlow_0de47py + SequenceFlow_1jp7ln7 + + + + SequenceFlow_1jp7ln7 + SequenceFlow_066q1z3 + + + + SequenceFlow_07bwfnn + SequenceFlow_066q1z3 + SequenceFlow_0rte4s6 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tests/compare/compare_resource/bpmn_file/152802.xml b/tests/compare/compare_resource/bpmn_file/152802.xml new file mode 100644 index 0000000..621d4d9 --- /dev/null +++ b/tests/compare/compare_resource/bpmn_file/152802.xml @@ -0,0 +1,167 @@ + + + + + SequenceFlow_1ho9gbz + + + SequenceFlow_1ho9gbz + SequenceFlow_1uwzf74 + + + + SequenceFlow_1aqkvvq + SequenceFlow_0q2txr2 + + + SequenceFlow_0e2yk4y + SequenceFlow_10mlqsr + + + SequenceFlow_1uwzf74 + SequenceFlow_1aqkvvq + SequenceFlow_0e2yk4y + + + + + + + + SequenceFlow_0gl1g92 + SequenceFlow_1qr340o + + + + SequenceFlow_0q2txr2 + SequenceFlow_10mlqsr + SequenceFlow_0gl1g92 + + + SequenceFlow_1qr340o + SequenceFlow_1wyvnyi + + + SequenceFlow_1wyvnyi + SequenceFlow_1ik2319 + + + + + SequenceFlow_1ik2319 + SequenceFlow_0huedwg + + + SequenceFlow_0huedwg + SequenceFlow_104eeb8 + + + + + + SequenceFlow_104eeb8 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tests/compare/compare_resource/bpmn_file/1955.xml b/tests/compare/compare_resource/bpmn_file/1955.xml new file mode 100644 index 0000000..4903214 --- /dev/null +++ b/tests/compare/compare_resource/bpmn_file/1955.xml @@ -0,0 +1,152 @@ + + + + + SequenceFlow_06t6f0w + + + SequenceFlow_06t6f0w + SequenceFlow_1kvi19q + + + + SequenceFlow_1kvi19q + SequenceFlow_1e13rm9 + + + + SequenceFlow_1e13rm9 + SequenceFlow_1jlefl9 + + + + SequenceFlow_1jlefl9 + SequenceFlow_15sdhno + + + + SequenceFlow_15sdhno + SequenceFlow_06f7v8a + + + + SequenceFlow_06f7v8a + SequenceFlow_0ol8amm + + + + SequenceFlow_0ol8amm + SequenceFlow_1vsp81t + + + + SequenceFlow_1vsp81t + SequenceFlow_1nua1nq + + + + SequenceFlow_1nua1nq + SequenceFlow_02w6rry + + + + SequenceFlow_02w6rry + SequenceFlow_0waw7p0 + + + + SequenceFlow_0waw7p0 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tests/compare/compare_resource/bpmn_file/8385.xml b/tests/compare/compare_resource/bpmn_file/8385.xml new file mode 100644 index 0000000..2d84ef8 --- /dev/null +++ b/tests/compare/compare_resource/bpmn_file/8385.xml @@ -0,0 +1,239 @@ + + + + + SequenceFlow_0mim1oh + + + SequenceFlow_0mim1oh + SequenceFlow_00wpsie + + + + SequenceFlow_00wpsie + SequenceFlow_16e90kf + + + + SequenceFlow_16e90kf + SequenceFlow_0a9y3x7 + + + + SequenceFlow_0a9y3x7 + SequenceFlow_0dqbxjo + + + + + SequenceFlow_0dqbxjo + SequenceFlow_0alwayy + SequenceFlow_14aawtr + + + SequenceFlow_0alwayy + SequenceFlow_1ntzza4 + + + + SequenceFlow_14aawtr + SequenceFlow_0gwcr7h + + + + + SequenceFlow_1ntzza4 + SequenceFlow_0gwcr7h + SequenceFlow_1tj9dbf + + + + SequenceFlow_1tj9dbf + SequenceFlow_11forgx + + + + + SequenceFlow_11forgx + SequenceFlow_1nknf8k + SequenceFlow_1tby6su + SequenceFlow_128kymz + + + SequenceFlow_1nknf8k + SequenceFlow_0v1ggx7 + + + + SequenceFlow_1tby6su + SequenceFlow_1n591yr + + + + SequenceFlow_128kymz + SequenceFlow_0uxd16h + + + + + SequenceFlow_0v1ggx7 + SequenceFlow_1n591yr + SequenceFlow_0uxd16h + SequenceFlow_1k8nv9n + + + + + SequenceFlow_1k8nv9n + SequenceFlow_1mxzq5s + + + + SequenceFlow_1mxzq5s + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tests/compare/compare_resource/output/result_sim.csv b/tests/compare/compare_resource/output/result_sim.csv new file mode 100644 index 0000000..6c76e2d --- /dev/null +++ b/tests/compare/compare_resource/output/result_sim.csv @@ -0,0 +1,6 @@ +,0,1,2 +2,8385.xml,1.0,1.0 +1,1955.xml,0.9444444444444445,0.8905723905723906 +4,152802.xml,0.9230769230769231,0.9230769230769231 +3,1431680.xml,0.431150741679648,0.4493900103718692 +0,1.xml,0.2606705161279959,0.3658535627235536 diff --git a/tests/compare/compare_resource/raw_bpmn_file/1.xml b/tests/compare/compare_resource/raw_bpmn_file/1.xml new file mode 100644 index 0000000..4903214 --- /dev/null +++ b/tests/compare/compare_resource/raw_bpmn_file/1.xml @@ -0,0 +1,152 @@ + + + + + SequenceFlow_06t6f0w + + + SequenceFlow_06t6f0w + SequenceFlow_1kvi19q + + + + SequenceFlow_1kvi19q + SequenceFlow_1e13rm9 + + + + SequenceFlow_1e13rm9 + SequenceFlow_1jlefl9 + + + + SequenceFlow_1jlefl9 + SequenceFlow_15sdhno + + + + SequenceFlow_15sdhno + SequenceFlow_06f7v8a + + + + SequenceFlow_06f7v8a + SequenceFlow_0ol8amm + + + + SequenceFlow_0ol8amm + SequenceFlow_1vsp81t + + + + SequenceFlow_1vsp81t + SequenceFlow_1nua1nq + + + + SequenceFlow_1nua1nq + SequenceFlow_02w6rry + + + + SequenceFlow_02w6rry + SequenceFlow_0waw7p0 + + + + SequenceFlow_0waw7p0 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tests/compare/compare_resource/raw_bpmn_file/1431680.xml b/tests/compare/compare_resource/raw_bpmn_file/1431680.xml new file mode 100644 index 0000000..849f351 --- /dev/null +++ b/tests/compare/compare_resource/raw_bpmn_file/1431680.xml @@ -0,0 +1,298 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + 0__1 + + + 0__1 + 1__2 + + + 1__2 + 2__3 + + + 2__3 + 3__3_split + + + 3_split__4a + 4a__5_join + + + 3_split__4b + 4b__5_join + + + 3_split__4d + 4d__5_join + + + 5_join__5 + 5__5_split + + + 5_split__6a + 6a__7_join + + + 5_split__6b + 6b__7_join + + + 5_split__6c + 6c__7_join + + + 5_split__6d + 6d__7_join + + + 5_split__6e + 6e__7_join + + + 5_split__6f + 6f__7_join + + + 5_split__6g + 6g__7_join + + + 7_join__7 + + + 3__3_split + 3_split__4a + 3_split__4b + 3_split__4d + + + 4a__5_join + 4b__5_join + 4d__5_join + 5_join__5 + + + 5__5_split + 5_split__6a + 5_split__6b + 5_split__6c + 5_split__6d + 5_split__6e + 5_split__6f + 5_split__6g + + + 6a__7_join + 6b__7_join + 6c__7_join + 6d__7_join + 6e__7_join + 6f__7_join + 6g__7_join + 7_join__7 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tests/compare/compare_resource/raw_bpmn_file/152802.xml b/tests/compare/compare_resource/raw_bpmn_file/152802.xml new file mode 100644 index 0000000..df31cc9 --- /dev/null +++ b/tests/compare/compare_resource/raw_bpmn_file/152802.xml @@ -0,0 +1,191 @@ + + + + + SequenceFlow_1ho9gbz + + + SequenceFlow_1ho9gbz + SequenceFlow_1uwzf74 + + + + SequenceFlow_1aqkvvq + SequenceFlow_0q2txr2 + + + SequenceFlow_0e2yk4y + SequenceFlow_10mlqsr + + + SequenceFlow_1uwzf74 + SequenceFlow_1aqkvvq + SequenceFlow_0e2yk4y + + + + + + + + SequenceFlow_0gl1g92 + SequenceFlow_1qr340o + + + + SequenceFlow_0q2txr2 + SequenceFlow_10mlqsr + SequenceFlow_0gl1g92 + + + SequenceFlow_1qr340o + SequenceFlow_1wyvnyi + + + SequenceFlow_1wyvnyi + SequenceFlow_1ik2319 + + + + + SequenceFlow_1ik2319 + SequenceFlow_0huedwg + + + SequenceFlow_0huedwg + SequenceFlow_104eeb8 + + + SequenceFlow_104eeb8 + SequenceFlow_075z9f1 + + + + + + SequenceFlow_075z9f1 + SequenceFlow_0cr4rl4 + + + SequenceFlow_0cr4rl4 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tests/compare/compare_resource/raw_bpmn_file/1955.xml b/tests/compare/compare_resource/raw_bpmn_file/1955.xml new file mode 100644 index 0000000..0f2ad22 --- /dev/null +++ b/tests/compare/compare_resource/raw_bpmn_file/1955.xml @@ -0,0 +1,152 @@ + + + + + SequenceFlow_06t6f0w + + + SequenceFlow_06t6f0w + SequenceFlow_1kvi19q + + + + SequenceFlow_1kvi19q + SequenceFlow_1e13rm9 + + + + SequenceFlow_1e13rm9 + SequenceFlow_1jlefl9 + + + + SequenceFlow_1jlefl9 + SequenceFlow_15sdhno + + + + SequenceFlow_15sdhno + SequenceFlow_06f7v8a + + + + SequenceFlow_06f7v8a + SequenceFlow_0ol8amm + + + + SequenceFlow_0ol8amm + SequenceFlow_1vsp81t + + + + SequenceFlow_1vsp81t + SequenceFlow_1nua1nq + + + + SequenceFlow_1nua1nq + SequenceFlow_02w6rry + + + + SequenceFlow_02w6rry + SequenceFlow_0waw7p0 + + + + SequenceFlow_0waw7p0 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/tests/compare/compare_resource/raw_bpmn_file/8385.xml b/tests/compare/compare_resource/raw_bpmn_file/8385.xml new file mode 100644 index 0000000..2d84ef8 --- /dev/null +++ b/tests/compare/compare_resource/raw_bpmn_file/8385.xml @@ -0,0 +1,239 @@ + + + + + SequenceFlow_0mim1oh + + + SequenceFlow_0mim1oh + SequenceFlow_00wpsie + + + + SequenceFlow_00wpsie + SequenceFlow_16e90kf + + + + SequenceFlow_16e90kf + SequenceFlow_0a9y3x7 + + + + SequenceFlow_0a9y3x7 + SequenceFlow_0dqbxjo + + + + + SequenceFlow_0dqbxjo + SequenceFlow_0alwayy + SequenceFlow_14aawtr + + + SequenceFlow_0alwayy + SequenceFlow_1ntzza4 + + + + SequenceFlow_14aawtr + SequenceFlow_0gwcr7h + + + + + SequenceFlow_1ntzza4 + SequenceFlow_0gwcr7h + SequenceFlow_1tj9dbf + + + + SequenceFlow_1tj9dbf + SequenceFlow_11forgx + + + + + SequenceFlow_11forgx + SequenceFlow_1nknf8k + SequenceFlow_1tby6su + SequenceFlow_128kymz + + + SequenceFlow_1nknf8k + SequenceFlow_0v1ggx7 + + + + SequenceFlow_1tby6su + SequenceFlow_1n591yr + + + + SequenceFlow_128kymz + SequenceFlow_0uxd16h + + + + + SequenceFlow_0v1ggx7 + SequenceFlow_1n591yr + SequenceFlow_0uxd16h + SequenceFlow_1k8nv9n + + + + + SequenceFlow_1k8nv9n + SequenceFlow_1mxzq5s + + + + SequenceFlow_1mxzq5s + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + From 02e31f4e12fb2ab29c2bfb02e16b3ce6a3022913 Mon Sep 17 00:00:00 2001 From: maicius Date: Thu, 28 Feb 2019 14:32:14 +0800 Subject: [PATCH 5/6] rename column name for output --- bpmn_python/bpmn_compare_similarity.py | 7 ++++++- tests/compare/compare_resource/output/result_sim.csv | 2 +- 2 files changed, 7 insertions(+), 2 deletions(-) diff --git a/bpmn_python/bpmn_compare_similarity.py b/bpmn_python/bpmn_compare_similarity.py index b6feb41..0497c67 100644 --- a/bpmn_python/bpmn_compare_similarity.py +++ b/bpmn_python/bpmn_compare_similarity.py @@ -106,13 +106,18 @@ def calculate_batch_similarity(self, bpmn_file_path1, bpmn_file_path2, output_di df = pd.DataFrame(self.result_list) df.sort_values(by=1, inplace=True, ascending=False) + + print("avg node matching similarity: ", df.iloc[:, 1].mean()) + print("avg structure similarity: ", df.iloc[:, 2].mean()) + + df.columns = ['file_name', 'node_sim', 'structure_sim'] df.reset_index() if self.export_csv: df.to_csv(os.path.join(output_dir, "result_sim.csv")) if self.export_excel: df.to_excel(os.path.join(output_dir + "result_sim.excel")) - print(df.iloc[:, 1].mean(), df.iloc[:, 2].mean()) + def check_file_name(self, file_name): if file_name[-1] != '/': diff --git a/tests/compare/compare_resource/output/result_sim.csv b/tests/compare/compare_resource/output/result_sim.csv index 6c76e2d..d2135e4 100644 --- a/tests/compare/compare_resource/output/result_sim.csv +++ b/tests/compare/compare_resource/output/result_sim.csv @@ -1,4 +1,4 @@ -,0,1,2 +,file_name,node_sim,structure_sim 2,8385.xml,1.0,1.0 1,1955.xml,0.9444444444444445,0.8905723905723906 4,152802.xml,0.9230769230769231,0.9230769230769231 From 0105f19dd6e84236df4265cfa3f59e749b173e95 Mon Sep 17 00:00:00 2001 From: maicius Date: Thu, 28 Feb 2019 14:36:09 +0800 Subject: [PATCH 6/6] remove __main__ module --- bpmn_python/bpmn_compare_similarity.py | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/bpmn_python/bpmn_compare_similarity.py b/bpmn_python/bpmn_compare_similarity.py index 0497c67..5e15dc3 100644 --- a/bpmn_python/bpmn_compare_similarity.py +++ b/bpmn_python/bpmn_compare_similarity.py @@ -280,10 +280,4 @@ def calculate_se(self, raw_edges, edges, equivalence_mapping): else: se_list.append((edge[0], edge[1])) raw_edges_list = list(raw_edges_set) - return se_list + raw_edges_list - - -if __name__ == '__main__': - cb = CompareBPMN() - cb.calculate_batch_similarity("/Users/maicius/code/cpws_judge/data/", "/Users/maicius/code/CPWSSystem/resource/output/bpmn/") - cb.calculate_similarity(file_name1="/Users/maicius/code/cpws_judge/data/1431680.xml", file_name2="/Users/maicius/code/CPWSSystem/validate/bpmn_file/1431680.xml") + return se_list + raw_edges_list \ No newline at end of file