def init(self, path="word2vec_api_software_wiki.txt", binary=True):
self.session = EngineFactory.create_session()
self.graphClient = DefaultGraphAccessor(GraphClient(server_number=4))
self.entity_vector_model = EntityVectorComputeModel()
self.entity_vector_model.init_word2vec_model(path=path, binary=binary)
print("init complete")
def get_all_nodes(self, step=5000, labels=None):
total_node_list = []
self.graph_accessor = DefaultGraphAccessor(self._graph)
if labels is None:
labels = []
if labels:
max_id = self.graph_accessor.get_max_id_for_labels(*labels)
min_id = self.graph_accessor.get_min_id_for_labels(*labels)
else:
max_id = self.graph_accessor.get_max_id_for_node()
min_id = 0
iteration = range(min_id, max_id, step)
for start_id in iteration:
try:
end_id = min(start_id + step, max_id)
nodes_in_scope = self.get_nodes_in_scope(start_id, end_id, labels)
_logger.info("start id=%s,end_id=%s", str(start_id), str(end_id))
if nodes_in_scope is not None:
_logger.info("get nodes in scope successfully")
total_node_list.extend(nodes_in_scope)
else:
_logger.info("get nodes in scope failed")
except Exception, error:
_logger.exception("")
def test_expand_nodes_with_filter_nodes(self):
graphClient = DefaultGraphAccessor(GraphClient())
# test_case = [(55730, True, 50, 50), (15555, True, 4, 4), (93008, True, 10, 11), (1708, True, 8, 7)]
test_case = [
(55730, True, 50, 50),
]
graphJsonParser = GraphJsonParser()
for node_id, is_valid, node_num, relation_num in test_case:
print("test case=", node_id, is_valid, node_num, relation_num)
subgraph = graphClient.expand_node_for_adjacent_nodes_to_subgraph(
node_id)
subgraph_json = graphJsonParser.parse_subgraph_to_public_json(
subgraph)
print(subgraph_json)
if is_valid:
self.assertNotEqual(subgraph_json, {
"nodes": [],
"relations": []
})
else:
self.assertEqual(subgraph_json, {"nodes": [], "relations": []})
continue
self.assertEqual(node_num, len(subgraph_json["nodes"]))
self.assertEqual(relation_num, len(subgraph_json["relations"]))
for n in subgraph_json["nodes"]:
print(n)
for r in subgraph_json["relations"]:
print(r)
def __init__(self):
self.question_preprossor = QuestionPreprossor()
self.question_analyzer = QuestionAnalyzer()
self.candidate_answer_generator = CandidateAnswerSetGenerator()
# self.answer_generator = AnswerGenerator()
self.answer_generator = None
self.client = DefaultGraphAccessor(GraphClient())
class TestNodeCleaner(TestCase):
def test_clean_labels(self):
self.graphClient = DefaultGraphAccessor(GraphClient(server_number=1))
node = self.graphClient.find_node_by_id(16)
self.assertEqual(NodeCleaner.clean_labels(node), [u'software', u'background knowledge', u'WikiData'])
node = self.graphClient.find_node_by_id(177777)
print node
self.assertEqual(NodeCleaner.clean_labels(node), [u'background knowledge', u'WikiData'])
def test_construct_property_set(self):
node_list = [{"aaa": 1, "ccc": 6}, {"aaa": 2, "bbb": 3, "ccc": 6}, {"ccc": 4, "ddd": 5}]
result = {"aaa", "ccc"}
self.assertEqual(construct_property_set(node_list), result)
print construct_property_set(node_list)
def test_rename_property(self):
self.graphClient = DefaultGraphAccessor(GraphClient(server_number=0))
node_list = self.graphClient.find_by_name_property("awesome item", "acl9")
result = rename_property(node_list)
print result
def test_public_labels_name(self):
t = PUBLIC_LABELS
self.assertIsNotNone(t)
print(t)
def test_clean_labels(self):
self.graphClient = DefaultGraphAccessor(GraphClient(server_number=1))
node = self.graphClient.find_node_by_id(16)
self.assertEqual(NodeCleaner.clean_labels(node), [u'software', u'background knowledge', u'WikiData'])
node = self.graphClient.find_node_by_id(177777)
print node
self.assertEqual(NodeCleaner.clean_labels(node), [u'background knowledge', u'WikiData'])
def test_sort_nodes_by_quality(self):
graphClient = DefaultGraphAccessor(GraphClient(server_number=1))
graphJson = GraphJsonParser()
keyword = "java"
top_number = 10
subgraph = graphClient.search_nodes_by_name_in_subgraph(
keyword, top_number)
print subgraph
nodes = graphJson.parse_nodes_in_subgraph_to_public_json(subgraph)
print nodes
def init(self, vector_dir_path="./model/"):
self.kg_models = KnowledgeGraphFeafureModels()
self.kg_models.init(vector_dir_path=vector_dir_path)
self._session = EngineFactory.create_session(echo=False)
self._entity_extractor = EntityExtractor()
# self._tf_idf_model = TFIDFModel()
# self._tf_idf_model.load(dict_type=2)
self.qa_searcher = QAEntitySearcher()
client = GraphClient(server_number=4)
self.semanticSearchAccessor = SemanticSearchAccessor(client)
self.defaultAccessor = DefaultGraphAccessor(client)
self._logger = Logger("QAResultSearch").get_log()
def build_aliases_for_domain_entity(self):
EntityForQA.delete_names_by_source(session=self.session, source="domain entity")
client = GraphClient(server_number=4)
accessor = DomainEntityAccessor(client)
default_accessor = DefaultGraphAccessor(client)
domain_entity_list = accessor.get_all_domain_entity()
for domain_entity in domain_entity_list:
entity = EntityForQA(kg_id=default_accessor.get_id_for_node(node=domain_entity),
entity_id=domain_entity['domain_entity_id'], source="domain entity",
attr='domain_entity_id', attr_value=domain_entity['domain_entity:name'])
self.session.add(entity)
self.session.commit()
class NodeCollection:
def __init__(self, graph):
'''
init with a Graph object
:param graph: ::GraphAccessor, ::GraphClient,::Graph
'''
if isinstance(graph, GraphAccessor):
self._graph = graph.graph
elif isinstance(graph, GraphClient):
self._graph = graph.graph
elif isinstance(graph, Graph):
self._graph = graph
else:
self._graph = None
self.graph_accessor = None
def get_all_nodes(self, step=5000, labels=None):
total_node_list = []
self.graph_accessor = DefaultGraphAccessor(self._graph)
if labels is None:
labels = []
if labels:
max_id = self.graph_accessor.get_max_id_for_labels(*labels)
min_id = self.graph_accessor.get_min_id_for_labels(*labels)
else:
max_id = self.graph_accessor.get_max_id_for_node()
min_id = 0
iteration = range(min_id, max_id, step)
for start_id in iteration:
try:
end_id = min(start_id + step, max_id)
nodes_in_scope = self.get_nodes_in_scope(start_id, end_id, labels)
_logger.info("start id=%s,end_id=%s", str(start_id), str(end_id))
if nodes_in_scope is not None:
_logger.info("get nodes in scope successfully")
total_node_list.extend(nodes_in_scope)
else:
_logger.info("get nodes in scope failed")
except Exception, error:
_logger.exception("")
return total_node_list
def walk(self):
'''
'''
file = open('log1.txt', 'w')
client = DefaultGraphAccessor()
iterator = 0
possibility_list = [0] * RandomWalk.max_id
adjacent_node_list = [0] * RandomWalk.max_id
file.writelines("begin: " + time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())) + '\n')
file.flush()
while iterator < self.generationNumber:
file.writelines("iteration: " + str(iterator) + " " + time.strftime('%Y-%m-%d %H:%M:%S',
time.localtime(time.time())) + '\n')
file.flush()
# print str(iterator) + " " + time.strftime('%Y-%m-%d %H:%M:%S',time.localtime(time.time()))
current_node_index = 1
step_length_list = [0] * RandomWalk.max_id
for i in range(0, self.stepNumber):
if (current_node_index > 0 and current_node_index < 7520) or current_node_index > 7524:
if adjacent_node_list[current_node_index - 1] == 0:
adjacent_node = client.get_adjacent_node_id_list(current_node_index)
adjacent_node_list[current_node_index - 1] = adjacent_node
else:
adjacent_node = adjacent_node_list[current_node_index - 1]
next_node_index = adjacent_node[random.randint(0, len(adjacent_node) - 1)]
# print str(iterator) + " " + str(i) + " " + str(len(adjacent_node)) + " " + str(
# next_node_index)
if (next_node_index > 1 and next_node_index < 7520) or next_node_index > 7524:
current_node_index = next_node_index
if step_length_list[next_node_index - 1] == 0 and next_node_index != 1:
step_length_list[next_node_index - 1] = i + 1
possibility_list[next_node_index - 1] += 1 - (
step_length_list[next_node_index - 1] / float(self.stepNumber))
iterator += 1
file.writelines("end: " + time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(time.time())) + '\n')
file.flush()
file.close()
for i in range(0, RandomWalk.max_id):
possibility_list[i] /= self.generationNumber
if possibility_list[i] > 0:
print str(i) + " " + str(possibility_list[i])
def init(self, vector_dir_path="./model/", ):
time_start = time.time()
print("start init the model=%d" % time_start)
client = GraphClient(server_number=4)
self.defaultAccessor = DefaultGraphAccessor(client)
self._api_wv = EntityVectorModel.load(vector_dir_path + self.WORD2VEC_FILE_LIST["api"], binary=True)
self._domain_entity_wv = EntityVectorModel.load(vector_dir_path + self.WORD2VEC_FILE_LIST["domain entity"],
binary=True)
self._wiki_wv = EntityVectorModel.load(vector_dir_path + self.WORD2VEC_FILE_LIST["wikidata"], binary=True)
self._sentence_wv = EntityVectorModel.load(vector_dir_path + self.WORD2VEC_FILE_LIST["sentence"], binary=True)
self._graph_wv = EntityVectorModel.load(vector_dir_path + self.WORD2VEC_FILE_LIST["graph"], binary=True)
self._entity_vector_compute_model = EntityVectorComputeModel()
self._entity_vector_compute_model.init_word2vec_model(vector_dir_path + self.WORD2VEC_FILE_LIST["word2vec"],
binary=True)
self.NP_VECTOR_NOT_EXIST = np.zeros(128)
self.NP_VECTOR_NOT_EXIST[1] = 1e-07
time_end = time.time()
print("init complete in %d" % (time_end - time_start))
def start_import_for_api_entity(self, linking_result_file):
graph_client = GraphClient(server_number=4)
default_graph_client = DefaultGraphAccessor(graph_client)
api_entity_graph_client = DomainEntityAccessor(graph_client)
api_entity_graph_client.delete_all_api_entity_to_wikipedia_relation()
print("delete all old may link relation complete")
with open(linking_result_file, 'r') as f:
link_relation_list = json.load(f)
for each in link_relation_list:
api_entity_id = each['api_entity_id']
wikipedia_entity_id = each['wikipedia_entity_id']
if api_entity_id is None or wikipedia_entity_id is None:
continue
api_entity = api_entity_graph_client.find_api_entity_node_by_id(api_entity_id)
if api_entity is None:
continue
wikipedia_entity = default_graph_client.find_node_by_id(wikipedia_entity_id)
if wikipedia_entity is None:
continue
api_entity_graph_client.create_entity_to_general_concept_relation(api_entity, wikipedia_entity)
from skgraph.graph.accessor.factory import NodeBuilder
# Mysql connect
from skgraph.graph.accessor.graph_accessor import DefaultGraphAccessor, GraphClient
from skgraph.util.code_text_process import clean_html_text
conn = MySQLdb.connect(host='10.141.221.73',
port=3306,
user='******',
passwd='root',
db='fdroid',
charset="utf8")
cur = conn.cursor()
# neo4j connect
connect_graph = DefaultGraphAccessor(GraphClient(server_number=1)).graph
# read from mysql
def mySQLReader(start, end):
node1lib = connect_graph.find_one(label="schema",
property_key="wd_item_id",
property_value="Q21127166")
# get all-version library
cur.execute(
"select * from jdk_library where library_id >= %s and library_id < %s",
(start, end))
lib_sql_data_list = cur.fetchall()
for lib_node_mysql_data_index in range(0, len(lib_sql_data_list)):
from py2neo import Node
from skgraph.graph.accessor.graph_accessor import DefaultGraphAccessor, GraphClient
from skgraph.graph.operation.generateDataPpi import DataCreateUtil
from skgraph.graph.operation.random_walk_restart import Walker
log_file = open('log.txt', 'w')
input_file_name = 'data.ppi'
max_id = 1665370
client_1 = DefaultGraphAccessor(GraphClient(server_number=1))
client_2 = DefaultGraphAccessor(GraphClient(server_number=2))
data_util = DataCreateUtil(client_1)
for id in range(23, max_id + 1):
log_file.writelines('begin %d\n' % (id))
if data_util.createData(id) == 1:
log_file.writelines('generate ppi end\n')
walker = Walker(input_file_name, client_2)
walker.run_exp(id, 0.15, log_file)
log_file.flush()
else:
node_1 = Node(link_id=id)
client_2.merge(node_1)
log_file.writelines('add node end\n')
log_file.flush()
log_file.close()
class SentenceLevelSemanticSearch:
SORT_FUNCTION_ENTITIES_BRIDGE = 3
SORT_FUNCTION_AVERAGE_ENTITY_GRAPH_SIMILAR = 4
SORT_FUNCTION_AVERAGE_VECTOR = 2
SORT_FUNCTION_NOT_AVERAGE_GRAPH_VECTOR = 1
SORT_FUNCTION_SELECT_PART_ENTITY_LINK = 5
def __init__(self, ):
self._session = None
self.kg_models = None
self._entity_extractor = None
# self._tf_idf_model = None
self.qa_searcher = None
self.semanticSearchAccessor = None
self.defaultAccessor = None
self._logger = None
def init(self, vector_dir_path="./model/"):
self.kg_models = KnowledgeGraphFeafureModels()
self.kg_models.init(vector_dir_path=vector_dir_path)
self._session = EngineFactory.create_session(echo=False)
self._entity_extractor = EntityExtractor()
# self._tf_idf_model = TFIDFModel()
# self._tf_idf_model.load(dict_type=2)
self.qa_searcher = QAEntitySearcher()
client = GraphClient(server_number=4)
self.semanticSearchAccessor = SemanticSearchAccessor(client)
self.defaultAccessor = DefaultGraphAccessor(client)
self._logger = Logger("QAResultSearch").get_log()
def semantic_search(self,
query_text,
each_np_candidate_entity_num=50,
sort_function=SORT_FUNCTION_SELECT_PART_ENTITY_LINK,
sentence_limit=20,
weight_context_sim=0.6,
weight_graph_sim=0.4,
):
try:
qa_info_manager = self.get_candidate_sentences(query_text,
each_np_candidate_entity_num=each_np_candidate_entity_num)
# sentence_list=qa_info_manager.get_candidate_sentence_list()
#
# entity_for_qa_set
# entity_for_qa_set.print_informat()
# entity_list = entity_for_qa_set.get_entity_node_list()
# chunk_to_related_entity_list_map = entity_for_qa_set.keyword_2_entitynodemap
self._logger.info("entity_list =%d sentence_list=%d" % (
qa_info_manager.get_entity_size(), qa_info_manager.get_sentence_size()))
# for n in entity_list:
# print("entity", n)
new_sentence_list = []
# if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_NOT_AVERAGE_GRAPH_VECTOR:
# new_sentence_list = self.sort_sentence_by_build_graph_vector_for_query_in_semantic_weight(query_text,
# sentence_list=sentence_list,
# entity_list=entity_list,
# weight_context_sim=weight_context_sim,
# weight_graph_sim=weight_graph_sim)
#
# if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_AVERAGE_VECTOR:
# new_sentence_list = self.sort_sentence_by_build_average_graph_vector_for_query(query_text,
# sentence_list=sentence_list,
# entity_list=entity_list,
# weight_context_sim=weight_context_sim,
# weight_graph_sim=weight_graph_sim
# )
#
# if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_ENTITIES_BRIDGE:
# new_sentence_list = self.sort_sentence_by_entities_as_bridge(query_text,
# sentence_list=sentence_list,
# entity_list=entity_list,
# weight_context_sim=weight_context_sim,
# weight_graph_sim=weight_graph_sim)
#
# if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_AVERAGE_ENTITY_GRAPH_SIMILAR:
# new_sentence_list = self.sort_sentence_by_entities_for_graph_similarity_as_bridge(query_text,
# sentence_list=sentence_list,
# entity_list=entity_list,
# weight_context_sim=weight_context_sim,
# weight_graph_sim=weight_graph_sim)
if sort_function == SentenceLevelSemanticSearch.SORT_FUNCTION_SELECT_PART_ENTITY_LINK:
new_sentence_list = self.sort_sentence_by_select_part_entity_as_bridge(query_text,
qa_info_manager=qa_info_manager,
weight_context_sim=weight_context_sim,
weight_graph_sim=weight_graph_sim,
)
result_list = qa_info_manager.fill_api_id_in_result_list(new_sentence_list[:sentence_limit])
self._logger.info("result_list =%d " % len(result_list))
return result_list
except Exception:
self._logger.exception("----qaexception----")
traceback.print_exc()
return []
def get_candidate_sentences(self, query_text, each_np_candidate_entity_num=20):
chunk_list = self.get_chunk_from_text(query_text)
print("chunk num=%d %s" % (len(chunk_list), ",".join(chunk_list)))
qa_info_manager = self.search_entity_by_fulltext(chunk_list, each_np_candidate_entity_num)
qa_info_manager.start_create_node_info_collection()
print("related entity for qa", qa_info_manager)
entity_for_qa_list = qa_info_manager.get_all_entity_for_qa_list()
print("entity_for_qa_list num=%d" % len(entity_for_qa_list))
sentence_list = self.search_sentence_by_entity_for_qa_list(entity_for_qa_list)
print("sentence_list num=%d" % len(sentence_list))
qa_info_manager.add_sentence_node_list(sentence_list)
return qa_info_manager
def expand_the_chunk_by_words(self, final_chunk_list):
final_set = []
for chunk in final_chunk_list:
final_set.append(chunk)
for word in chunk.split(" "):
final_set.append(word)
print("word set", final_set)
return list(set(final_set))
def get_chunk_from_text(self, text):
final_chunk_list = self._entity_extractor.get_all_possible_key_word_from_text(text)
return final_chunk_list
def search_entity_by_fulltext(self, chunk_list, each_np_candidate_entity_num=20):
qa_info_manager = QACacheInfoManager(semanticSearchAccessor=self.semanticSearchAccessor,
defaultSearchAccessor=self.defaultAccessor,
kg_models=self.kg_models)
for chunk in chunk_list:
related_entity_list = self.qa_searcher.search_related_entity(chunk, each_np_candidate_entity_num)
qa_info_manager.add(chunk, related_entity_list)
related_entity_for_api = self.qa_searcher.search_related_entity_for_api(chunk, each_np_candidate_entity_num)
qa_info_manager.add(chunk, related_entity_for_api)
return qa_info_manager
def search_all_entity_by_fulltext_by_half(self, chunk, each_np_candidate_entity_num=20):
qa_info_manager = QACacheInfoManager(semanticSearchAccessor=self.semanticSearchAccessor,
defaultSearchAccessor=self.defaultAccessor,
kg_models=self.kg_models)
related_entity_for_api = self.qa_searcher.search_related_entity_for_api(chunk, each_np_candidate_entity_num/2)
qa_info_manager.add(chunk, related_entity_for_api)
related_entity_list = self.qa_searcher.search_related_entity(chunk, each_np_candidate_entity_num/2)
qa_info_manager.add(chunk, related_entity_list)
return qa_info_manager
def search_sentence_by_entity_for_qa_list(self, entity_for_qa_list):
entity_id_string_list = [str(entity_for_qa.kg_id) for entity_for_qa in entity_for_qa_list]
entity_id_string_list = list(set(entity_id_string_list))
return self.semanticSearchAccessor.search_sentence_by_entity_list(entity_id_string_list=entity_id_string_list)
def get_relation_by_nodes(self, node_list):
return self.semanticSearchAccessor.get_nodes_relation(node_list)
def sort_sentence_by_entities_as_bridge(self, question,
sentence_list,
entity_list,
weight_context_sim=0.5,
weight_graph_sim=0.5
):
self._logger.info("run sort_sentence_by_entities_as_bridge get result=%d" % len(sentence_list))
question_vec = self.kg_models.get_question_entity_vector(question)
entity_vec_list, entity_graph_vec_list = self.kg_models.get_vectors_for_entity_list(entity_list)
sentence_vec_list, sentence_graph_vec_list = self.kg_models.get_vectors_for_entity_list(sentence_list)
qe_sim_np = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_vec, entity_vec_list)
qe_sim_np = qe_sim_np / qe_sim_np.sum()
kg_context_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(entity_vec_list,
sentence_vec_list)
kg_graph_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(entity_graph_vec_list,
sentence_graph_vec_list)
qs_context_sim = weight_context_sim * qe_sim_np * kg_context_sim
qs_graph_sim = weight_graph_sim * qe_sim_np * kg_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"sentence_type": sentence["sentence_type_code"],
"text": sentence["sentence_text"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info("run sort_sentence_by_entities_as_bridge get result num=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
return result
def sort_sentence_by_entities_for_graph_similarity_as_bridge(self, question,
sentence_list,
entity_list,
weight_context_sim=0.5,
weight_graph_sim=0.5
):
self._logger.info(
"run sort_sentence_by_entities_for_graph_similarity_as_bridge get result=%d" % len(sentence_list))
question_context_vec = self.kg_models.get_question_entity_vector(question)
entity_vec_list, entity_graph_vec_list = self.kg_models.get_vectors_for_entity_list(entity_list)
sentence_vec_list, sentence_graph_vec_list = self.kg_models.get_vectors_for_entity_list(sentence_list)
qe_sim_np = np.ones((1, len(entity_list)))
qe_sim_np = qe_sim_np / qe_sim_np.sum()
qs_context_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
sentence_vec_list)
kg_graph_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(entity_graph_vec_list,
sentence_graph_vec_list)
qs_context_sim = weight_context_sim * qs_context_sim
qs_graph_sim = weight_graph_sim * qe_sim_np * kg_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"sentence_type": sentence["sentence_type_code"],
"text": sentence["sentence_text"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info("run sort_sentence_by_entities_as_bridge get result num=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
print("sorted result")
for t in result:
print("test sort", t)
print(result[:100])
return result
def sort_sentence_by_build_average_graph_vector_for_query(self, question, sentence_list, entity_list,
weight_context_sim=0.5, weight_graph_sim=0.5
):
self._logger.info(
"run sort_sentence_by_build_average_graph_vector_for_query get sentence_list=%d" % len(sentence_list))
kg_models = self.kg_models
question_context_vec = kg_models.get_question_entity_vector(question)
entity_vec_list, entity_graph_vec_list = self.kg_models.get_vectors_for_entity_list(entity_list)
sentence_vec_list, sentence_graph_vec_list = self.kg_models.get_vectors_for_entity_list(sentence_list)
entity_list, entity_vec_list, entity_graph_vec_list = self.remove_the_not_related_entity(entity_graph_vec_list,
entity_list,
entity_vec_list,
question_context_vec)
query_graph_vector = kg_models.get_question_graph_vector_by_average_all_entities(
question=question,
entity_graph_vec_list=entity_graph_vec_list)
qs_context_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
sentence_vec_list)
qs_graph_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(query_graph_vector,
sentence_graph_vec_list)
qs_context_sim = weight_context_sim * qs_context_sim
qs_graph_sim = weight_graph_sim * qs_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"text": sentence["sentence_text"],
"sentence_type": sentence["sentence_type_code"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info("run sort_sentence_by_build_average_graph_vector_for_query get result num=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
return result
def sort_sentence_by_select_part_entity_as_bridge(self, question,
qa_info_manager,
# sentence_list,
# entity_list,
weight_context_sim=0.6,
weight_graph_sim=0.4,
# chunk_to_related_entity_list_map=None,
):
self._logger.info(
"run sort part entity result=%d" % qa_info_manager.get_sentence_size())
print("entity for node")
qa_info_manager.print_entities()
print("sentence for node")
# qa_info_manager.print_sentences()
entity_info_collection = qa_info_manager.get_entity_info_collection()
sentence_info_collection = qa_info_manager.get_sentence_info_collection()
entity_info_collection.init_vectors(self.kg_models)
sentence_info_collection.init_vectors(self.kg_models)
sentence_list = sentence_info_collection.get_entity_list()
entity_vec_list = entity_info_collection.get_entity_context_list()
entity_graph_vec_list = entity_info_collection.get_entity_graph_list()
entity_list = entity_info_collection.get_entity_list()
sentence_vec_list = sentence_info_collection.get_entity_context_list()
sentence_graph_vec_list = sentence_info_collection.get_entity_graph_list()
question_context_vec = self.kg_models.get_question_entity_vector(question)
entity_list, entity_vec_list, entity_graph_vec_list = self.get_top_related_entity_info_list(
question_context_vec=question_context_vec, qa_info_manager=qa_info_manager)
# entity_list, entity_vec_list, entity_graph_vec_list = self.remove_the_not_related_entity_by_only_save_one_for_each(
# entity_graph_vec_list=entity_graph_vec_list, entity_vec_list=entity_vec_list, entity_list=entity_list,
# question_context_vec=question_context_vec,
# qa_info_manager=qa_info_manager
#
# )
qs_context_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
sentence_vec_list)
# todo:change to the average graph similarity
# qs_graph_sim = self.get_graph_similarity_by_average_entity_graph_vector(entity_graph_vec_list, question,
# sentence_graph_vec_list)
qs_graph_sim = self.get_query_to_sentence_graph_sim_by_select_top_enttity(entity_graph_vec_list, entity_list,
entity_vec_list,
sentence_graph_vec_list,
sentence_vec_list)
qs_context_sim = weight_context_sim * qs_context_sim
qs_graph_sim = weight_graph_sim * qs_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"sentence_type": sentence["sentence_type_code"],
"text": sentence["sentence_text"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info("run sort_sentence_by_entities_as_bridge get result num=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
print(result[:100])
return result
def get_graph_similarity_by_average_entity_graph_vector(self, entity_graph_vec_list, question,
sentence_graph_vec_list):
query_graph_vector = self.kg_models.get_question_graph_vector_by_average_all_entities(
question=question,
entity_graph_vec_list=entity_graph_vec_list)
qs_graph_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(query_graph_vector,
sentence_graph_vec_list)
return qs_graph_sim
def get_graph_similarity_average_entity_graph_vector_similarity(self, entity_graph_vec_list, question,
sentence_graph_vec_list):
# query_graph_vector = self.kg_models.get_question_graph_vector_by_average_all_entities(
# question=question,
# entity_graph_vec_list=entity_graph_vec_list)
qs_graph_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(sentence_graph_vec_list,
entity_graph_vec_list)
return np.mean(qs_graph_sim, axis=1)
def get_query_to_sentence_graph_sim_by_select_top_enttity(self, entity_graph_vec_list, entity_list, entity_vec_list,
sentence_graph_vec_list, sentence_vec_list):
# kg_se_graph_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(sentence_graph_vec_list,
# entity_graph_vec_list,
# )
kg_se_context_sim = MatrixCalculation.compute_cossin_for_matrix_to_matrix_normalize(
sentence_vec_list,
entity_vec_list)
# TODO
# kg_se_sim = 0.5 * kg_se_graph_sim + 0.5 * kg_se_context_sim
kg_se_sim = kg_se_context_sim
print("final entity list", len(entity_list), entity_list)
select_linking_entity_num = min(5, len(entity_list))
onehot_maxsim_se_matrix = MatrixCalculation.get_most_similar_top_n_entity_as_matrix(
top_n=select_linking_entity_num, s_e_similarity_matrix=kg_se_sim)
s_query_graph_vec_matrix = onehot_maxsim_se_matrix * np.matrix(
entity_graph_vec_list) / select_linking_entity_num
qs_graph_sim = MatrixCalculation.compute_cossin_for_one_to_one_in_two_list_normalize(sentence_graph_vec_list,
s_query_graph_vec_matrix.getA())
return qs_graph_sim
def remove_the_not_related_entity_by_only_save_one_for_each(self, entity_graph_vec_list, entity_list,
entity_vec_list, question_context_vec,
qa_info_manager):
chunk_to_related_entity_list_map = qa_info_manager.keyword_2_entitynodemap
qe_sim_np = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
entity_vec_list)
entity_info_sumary_list = []
for (entity, sim, entity_vec, entity_graph_vec) in zip(entity_list, qe_sim_np.getA()[0], entity_vec_list,
entity_graph_vec_list):
print("after first removing sim=", sim, "entity=", entity)
entity_info_sumary_list.append({"entity": entity,
"sim": sim,
"entity_vec": entity_vec,
"entity_graph_vec": entity_graph_vec
})
entity_info_sumary_list.sort(key=lambda k: (k.get('sim', 0)), reverse=True)
valid_word_set = set([])
word_to_related_entity_list_map = {}
for chunk, related_entity_list in chunk_to_related_entity_list_map.items():
word = chunk
if word not in valid_word_set:
valid_word_set.add(word)
word_to_related_entity_list_map[word] = related_entity_list
else:
word_to_related_entity_list_map[word].extend(related_entity_list)
# clean_entity_info_list = self.get_clean_entity_for_each_word_by_max_similarity(entity_info_sumary_list,
# word_to_related_entity_list_map)
#
clean_entity_info_list = self.get_clean_entity_for_each_word_by_max_n_similarity(entity_info_sumary_list,
word_to_related_entity_list_map)
new_entity_list = []
new_entity_graph_vec_list = []
new_entity_vec_list = []
for entity_info_sumary in clean_entity_info_list:
new_entity_list.append(entity_info_sumary["entity"])
new_entity_graph_vec_list.append(entity_info_sumary["entity_graph_vec"])
new_entity_vec_list.append(entity_info_sumary["entity_vec"])
print("final save sim=", entity_info_sumary["sim"], "entity=", entity_info_sumary["entity"])
return new_entity_list, new_entity_vec_list, new_entity_graph_vec_list
def get_top_related_entity_info_list(self, question_context_vec,
qa_info_manager):
node_info_collection = qa_info_manager.get_node_info_collection()
node_info_collection.fill_each_entity_with_similary_to_question(question_context_vec)
node_info_collection.sort_by_qe_sim()
# selected_entity_info_list = qa_info_manager.get_top_node_info_by_each_keywords_three_different_type()
selected_entity_info_list = qa_info_manager.get_top_node_info_by_each_keywords()
new_entity_list = []
new_entity_vec_list = []
new_entity_graph_vec_list = []
for node_info in selected_entity_info_list:
new_entity_list.append(node_info.entity_node)
new_entity_vec_list.append(node_info.entity_context_vec)
new_entity_graph_vec_list.append(node_info.entity_graph_vec)
return new_entity_list, new_entity_vec_list, new_entity_graph_vec_list
def get_clean_entity_for_each_word_by_max_n_similarity(self, entity_info_sumary_list,
word_to_related_entity_list_map):
clean_entity_kg_id_list = set([])
print("start get_clean_entity_infi_sumary_list ")
word_name_entity_mark = {}
for valid_word, related_entity_list in word_to_related_entity_list_map.items():
print("valid word=", valid_word)
entity_info_list = self.get_first_from_entity_info_sumary_list_and_in_related_entity_list(
entity_info_sumary_list, related_entity_list, 3)
# for entity_info in entity_info_list:
print("get candidate for word=", valid_word, entity_info_list)
word_name_entity_mark[valid_word] = entity_info_list
clean_entity_info_list = []
clean_entity_kg_id_list = set([])
for word, entity_info_list in word_name_entity_mark.items():
for entity_info in entity_info_list:
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
if kg_id not in clean_entity_kg_id_list:
clean_entity_info_list.append(entity_info)
clean_entity_kg_id_list.add(kg_id)
print("valid word=", word, entity_info["entity"])
return clean_entity_info_list
def get_clean_entity_for_each_word_by_max_similarity(self, entity_info_sumary_list,
word_to_related_entity_list_map):
clean_entity_kg_id_list = set([])
print("start get_clean_entity_infi_sumary_list ")
word_name_entity_mark = {}
for valid_word, related_entity_list in word_to_related_entity_list_map.items():
print("valid word=", valid_word)
entity_info_list = self.get_first_from_entity_info_sumary_list_and_in_related_entity_list(
entity_info_sumary_list, related_entity_list)
for entity_info in entity_info_list:
print("get candidate for word=", valid_word, entity_info["entity"])
word_name_entity_mark[valid_word] = entity_info
clean_entity_info_list = []
clean_entity_kg_id_list = set([])
for word, entity_info in word_name_entity_mark.items():
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
if kg_id not in clean_entity_kg_id_list:
clean_entity_info_list.append(entity_info)
clean_entity_kg_id_list.add(kg_id)
print("valid word=", word, entity_info["entity"])
return clean_entity_info_list
def get_clean_entity_infi_sumary_list(self, entity_info_sumary_list, word_to_related_entity_list_map):
clean_entity_kg_id_list = set([])
print("start get_clean_entity_infi_sumary_list ")
word_name_entity_mark = {}
for valid_word, related_entity_list in word_to_related_entity_list_map.items():
print("valid word=", valid_word)
entity_info_list = self.get_first_from_entity_info_sumary_list_and_in_related_entity_list(
entity_info_sumary_list, related_entity_list)
for entity_info in entity_info_list:
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
print("get candidate for word=", valid_word, entity_info["entity"])
if kg_id not in clean_entity_kg_id_list:
if valid_word not in word_name_entity_mark.keys():
word_name_entity_mark[valid_word] = entity_info
else:
old_entity_info = word_name_entity_mark[valid_word]
if entity_info["sim"] > old_entity_info["sim"]:
word_name_entity_mark[valid_word] = entity_info
for seperate_name in valid_word.split(" "):
if seperate_name not in word_name_entity_mark.keys():
word_name_entity_mark[seperate_name] = entity_info
else:
old_entity_info = word_name_entity_mark[seperate_name]
if entity_info["sim"] > old_entity_info["sim"]:
word_name_entity_mark[seperate_name] = entity_info
clean_entity_kg_id_list.add(kg_id)
clean_entity_info_list = []
clean_entity_kg_id_list = set([])
for word, entity_info in word_name_entity_mark.items():
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
if kg_id not in clean_entity_kg_id_list:
clean_entity_info_list.append(entity_info)
clean_entity_kg_id_list.add(kg_id)
print("valid word=", word, entity_info["entity"])
return clean_entity_info_list
def remove_the_not_related_entity(self, entity_graph_vec_list, entity_list, entity_vec_list, question_context_vec):
qe_sim_np = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
entity_vec_list)
print("qeustion to entity similary")
new_entity_list = []
new_entity_vec_list = []
new_entity_graph_vec_list = []
qe_sim_clean = []
for (entity, sim, entity_vec, entity_graph_vec) in zip(entity_list, qe_sim_np.getA()[0], entity_vec_list,
entity_graph_vec_list):
print("sim=", sim, "entity=", entity)
if sim > MIN_RELATED_ENTITY_SIMILARITY:
print("adding ", entity)
new_entity_list.append(entity)
new_entity_vec_list.append(entity_vec)
new_entity_graph_vec_list.append(entity_graph_vec)
qe_sim_clean.append(sim)
entity_list = new_entity_list
entity_vec_list = new_entity_vec_list
entity_graph_vec_list = new_entity_graph_vec_list
new_entity_list = []
new_entity_vec_list = []
new_entity_graph_vec_list = []
entity_info_sumary_list = []
for (entity, sim, entity_vec, entity_graph_vec) in zip(entity_list, qe_sim_clean, entity_vec_list,
entity_graph_vec_list):
print("after first removing sim=", sim, "entity=", entity)
entity_info_sumary_list.append({"entity": entity,
"sim": sim,
"entity_vec": entity_vec,
"entity_graph_vec": entity_graph_vec
})
entity_info_sumary_list.sort(key=lambda k: (k.get('sim', 0)), reverse=True)
api_class_name_set = set([])
new_entity_info_sumary_list = []
for entity_info_sumary in entity_info_sumary_list:
if entity_info_sumary["entity"].has_label("api"):
qualified_name = entity_info_sumary["entity"]["qualified_name"]
if qualified_name in api_class_name_set:
continue
if "(" in qualified_name:
simple_name = qualified_name.split("(")[0]
class_name = ".".join(simple_name.split(".")[:-1])
if class_name in api_class_name_set:
continue
else:
api_class_name_set.add(class_name)
new_entity_info_sumary_list.append(entity_info_sumary)
else:
api_class_name_set.add(qualified_name)
new_entity_info_sumary_list.append(entity_info_sumary)
else:
new_entity_info_sumary_list.append(entity_info_sumary)
for entity_info_sumary in new_entity_info_sumary_list:
new_entity_list.append(entity_info_sumary["entity"])
new_entity_graph_vec_list.append(entity_info_sumary["entity_graph_vec"])
new_entity_vec_list.append(entity_info_sumary["entity_vec"])
print("final save sim=", entity_info_sumary["sim"], "entity=", entity_info_sumary["entity"])
return new_entity_list, new_entity_vec_list, new_entity_graph_vec_list
def sort_sentence_by_build_graph_vector_for_query_in_semantic_weight(self, question, sentence_list, entity_list,
weight_context_sim=0.5, weight_graph_sim=0.5
):
self._logger.info(
"run sort_sentence_by_build_graph_vector_for_query_in_semantic_weight get sentence_list=%d" % len(
sentence_list))
kg_models = self.kg_models
question_context_vec = kg_models.get_question_entity_vector(question)
entity_vec_list, entity_graph_vec_list = self.kg_models.get_vectors_for_entity_list(entity_list)
sentence_vec_list, sentence_graph_vec_list = self.kg_models.get_vectors_for_entity_list(sentence_list)
query_graph_vector = kg_models.get_question_graph_vector_by_semantic_weight_all_entities(
question_context_vec=question_context_vec,
entity_context_vec_list=entity_vec_list,
entity_graph_vec_list=entity_graph_vec_list)
qs_context_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(question_context_vec,
sentence_vec_list)
qs_graph_sim = MatrixCalculation.compute_cossin_for_vec_to_matrix_normalize(query_graph_vector,
sentence_graph_vec_list)
qs_context_sim = weight_context_sim * qs_context_sim
qs_graph_sim = weight_graph_sim * qs_graph_sim
qs_sim = qs_context_sim + qs_graph_sim
qs_sim = qs_sim.tolist()[0]
qs_context_sim = qs_context_sim.tolist()[0]
qs_graph_sim = qs_graph_sim.tolist()[0]
for sum_sim, sentence, context_sim, graph_sim in zip(qs_sim, sentence_list, qs_context_sim, qs_graph_sim):
sentence["qs_sim"] = sum_sim
sentence["qs_context_sim"] = context_sim
sentence["qs_graph_sim"] = graph_sim
result = []
for sentence in sentence_list:
result.append({
"kg_id": self.defaultAccessor.get_id_for_node(sentence),
"sentence_id": sentence["sentence_id"],
"text": sentence["sentence_text"],
"qs_sim": sentence["qs_sim"],
"qs_context_sim": sentence["qs_context_sim"],
"qs_graph_sim": sentence["qs_graph_sim"]
})
self._logger.info(
"run sort_sentence_by_build_graph_vector_for_query_in_semantic_weight get result=%d" % len(result))
result.sort(key=lambda k: (k.get('qs_sim', 0)), reverse=True)
return result
def get_all_entity(self, entity_for_qa_list):
entity_id_string_list = [str(entity_for_qa.kg_id) for entity_for_qa in entity_for_qa_list]
entity_id_string_list = list(set(entity_id_string_list))
return self.semanticSearchAccessor.get_all_entity(entity_id_string_list=entity_id_string_list)
def get_first_from_entity_info_sumary_list_and_in_related_entity_list(self, entity_info_sumary_list,
related_entity_list, top_relate_entity_num=1):
return_result_list = []
for entity_info in entity_info_sumary_list:
kg_id = self.defaultAccessor.get_id_for_node(entity_info["entity"])
entity = self.get_entity_from_entity_list_by_kgid(kg_id, related_entity_list)
if entity is not None:
return_result_list.append(entity_info)
if len(return_result_list) >= top_relate_entity_num:
return return_result_list
return []
def get_entity_from_entity_list_by_kgid(self, kg_id, related_entity_list):
for related_entity in related_entity_list:
if related_entity.kg_id == kg_id:
return related_entity
return None
from skgraph.graph.label_util import LabelUtil
from skgraph.graph.node_cleaner import GraphJsonParser
reload(sys)
sys.setdefaultencoding("utf-8")
app = Flask(__name__)
CORS(app)
db_handler = SQLAlchemyHandler()
db_handler.setLevel(logging.WARN) # Only serious messages
app.logger.addHandler(db_handler)
logger = Logger("neo4jServer").get_log()
logger.info("create logger")
graphClient = DefaultGraphAccessor(GraphClient(server_number=1))
logger.info("create graphClient")
api_entity_linker = APIEntityLinking()
logger.info("create api_entity_linker object")
questionAnswerSystem = QuestionAnswerSystem()
logger.info("create questionAnswerSystem")
dbSOPostSearcher = SOPostSearcher(EngineFactory.create_so_session(),
logger=app.logger)
logger.info("create SO POST Searcher")
api_entity_session = EngineFactory.create_session(autocommit=True)
apiSearcher = APISearcher(session=api_entity_session, logger=app.logger)
logger.info("create API Searcher")
from skgraph.graph.accessor.graph_accessor import DefaultGraphAccessor, GraphClient
client = DefaultGraphAccessor(GraphClient(server_number=1))
relation_type_list = client.get_all_relation_type()
for relation_name in relation_type_list:
client.create_relation_node(relation_name=relation_name)
label_list = client.get_all_label_list()
remove_lables = ["wall", "wikidata", "wd_property", "relation", "schema"]
for label in label_list:
if label not in remove_lables:
node = client.find_a_node_by_label(label)
if node is not None:
for property in node.keys():
client.create_relation_node(relation_name=property)
import codecs
import json
from py2neo import Relationship
from skgraph.graph.accessor.graph_accessor import GraphClient, DefaultGraphAccessor
from skgraph.graph.accessor.graph_client_for_awesome import AwesomeGraphAccessor
from skgraph.graph.accessor.graph_client_for_wikipedia import WikipediaGraphAccessor
from shared.logger_util import Logger
_logger = Logger("AwesomeImporter").get_log()
awesomeGraphAccessor = AwesomeGraphAccessor(GraphClient(server_number=0))
wikipediaGraphAccessor = WikipediaGraphAccessor(awesomeGraphAccessor)
defaultGraphAccessor = DefaultGraphAccessor(awesomeGraphAccessor)
baseGraphClient = awesomeGraphAccessor.graph
file_name = "awesome_item_category_related_to_wikipedia_relation_list.json"
with codecs.open(file_name, 'r', 'utf-8') as f:
relation_list = json.load(f)
for tag_relation in relation_list:
start_entity_name = tag_relation["start_entity_name"]
relation = tag_relation["relation"]
end_url = tag_relation["end_url"]
start_node = awesomeGraphAccessor.find_awesome_cate_by_name(
start_entity_name)
end_node = defaultGraphAccessor.get_node_by_wikipedia_link(end_url)
if end_node is None:
end_node = wikipediaGraphAccessor.create_wikipedia_item_entity_by_url(
end_url)
def setUp(self):
self.graphClient = DefaultGraphAccessor(GraphClient())
self.nodeCleaner = NodeCleaner()
class SearchUtil:
def __init__(self, graph_client, api_searcher):
self.graph_accessor = DefaultGraphAccessor(graph_client)
self.api_searcher = api_searcher
def search(self, keywords, top_number):
result_node_list = []
jobs = []
api_db_search_job = gevent.spawn(
self.api_searcher.search_api_entity_with_order, keywords,
top_number)
jobs.append(api_db_search_job)
graph_search_job = gevent.spawn(
self.graph_accessor.search_nodes_by_name_in_list, keywords,
top_number)
jobs.append(graph_search_job)
gevent.joinall(jobs, timeout=2000)
api_entity_list = api_db_search_job.value
api_id_list = []
for api_entity in api_entity_list:
api_id_list.append(api_entity.id)
api_node_list = self.graph_accessor.get_api_entity_map_to_node(
api_id_list)
for api_node in api_node_list:
if api_node not in result_node_list:
result_node_list.append(api_node)
graph_node_result_list = graph_search_job.value
for graph_node in graph_node_result_list:
if graph_node not in result_node_list:
result_node_list.append(graph_node)
## todo, change the node search to a more generate way, for example, a scorer is necessary
node_score = {}
for node in result_node_list:
node_id = self.graph_accessor.get_id_for_node(node)
node_score[node_id] = 0
for node in result_node_list:
node_id = self.graph_accessor.get_id_for_node(node)
if node in api_node_list and node in graph_node_result_list:
node_score[node_id] = node_score[node_id] + 10
if node.has_label("extended knowledge"):
node_score[node_id] = node_score[node_id] - 3
if node.has_label("java class") or node.has_label("wikidata"):
node_score[node_id] = node_score[node_id] + 1
if node.has_label("java constructor"):
node_score[node_id] = node_score[node_id] - 1
left_nodes = []
for node in result_node_list:
left_nodes.append(node)
sorted_node_list = []
while len(left_nodes) > 0:
max_score = -10000
max_node = None
for node in left_nodes:
node_id = self.graph_accessor.get_id_for_node(node)
if node_score[node_id] > max_score:
max_score = node_score[node_id]
max_node = node
sorted_node_list.append(max_node)
left_nodes.remove(max_node)
return sorted_node_list[:top_number]
# -*- coding:utf8 -*-
import sys
import nltk
from skgraph.graph.accessor.graph_accessor import GraphClient
from skgraph.graph.accessor.graph_accessor import DefaultGraphAccessor
reload(sys)
sys.setdefaultencoding('utf8')
graph_client = GraphClient(server_number=0)
graph_accessor = DefaultGraphAccessor(graph_client)
'''
merge node and relation belong to extended knowledge and entity which name
'''
class DuplicateCleaner:
def merge_node_with_same_name(self):
print 'begin merge node with same name'
query = "match(a:`extended knowledge`:entity) return id(a) as id,a.name as name"
try:
nodeList = []
result = graph_accessor.graph.run(query)
for n in result:
node = (n['id'], n['name'])
nodeList.append(node)
except Exception:
return []
nodeDict = {}
a = 1
for n in nodeList:
import threading
from Queue import Queue
from py2neo import Node
from skgraph.graph.accessor.graph_accessor import DefaultGraphAccessor, GraphClient
from skgraph.graph.accessor.graph_client_for_rwr import RandomWalkGraphAccessor
from skgraph.graph.operation.generateDataPpi import DataCreateUtil
from skgraph.graph.operation.random_walk_restart import Walker
log_file = open('log_single.txt', 'w')
input_file_name = 'data.ppi'
node_id = 53157
client_1 = DefaultGraphAccessor(GraphClient(server_number=1))
client_2 = DefaultGraphAccessor(GraphClient(server_number=2))
data_util = DataCreateUtil(client_1)
end_status = 0
class Producer(threading.Thread):
def __init__(self, queue):
threading.Thread.__init__(self)
self.data = queue
def run(self):
print 'begin produce'
log_file.writelines('begin %d\n' % (node_id))
log_file.flush()
if client_1.find_node_by_id(node_id) == None:
return 0
if data_util.createData(node_id) == 1:
def awesome_item_rename_duplicate(awesome_graph_accessor, node_collection):
node_list = node_collection.get_all_nodes(1000, ['awesome item'])
print len(node_list)
node_map = construct_key_count_map(node_list)
i = 0
for key in node_map.keys():
if len(node_map[key]) > 1:
print key, " ", len(node_map[key])
for each in node_map[key]:
print each
i += 1
print i
node_list_after_step1 = []
for key in node_map.keys():
if len(node_map[key]) > 1:
step1_node_list = node_map[key]
for node in step1_node_list:
if "url" in dict(node):
url = node["url"]
if "//github.com/" in url:
# print url, " ", type(url)
github_name = get_name_by_github_url(url)
if github_name != "" and github_name.lower() != key.lower():
node["name"] = github_name
node_list_after_step1.append(node)
else:
node_list_after_step1.append(node)
else:
node_list_after_step1.append(node)
for node in node_list_after_step1:
print node
awesome_graph_accessor.push_node(node)
node_map_after_step1 = construct_key_count_map(node_list_after_step1)
# i = 0
# for key in node_map_after_step1.keys():
# if len(node_map_after_step1[key]) > 1:
# print key, " ", len(node_map_after_step1[key]), " ", node_map_after_step1[key]
# i += 1
# print i
# with open("node_map_after_step1.txt", 'w') as f:
# for key in node_map_after_step1.keys():
# if len(node_map_after_step1[key]) > 1:
# nodes_str = key + " " + str(len(node_map_after_step1[key])) + " " + str(node_map_after_step1[key])
# f.write(nodes_str + "\n")z
node_list_after_step2 = []
for key in node_map_after_step1.keys():
step2_node_list = node_map_after_step1[key]
for i in range(0, len(step2_node_list) - 1):
for j in range(i + 1, len(step2_node_list)):
if "url" in step2_node_list[i]:
url1 = step2_node_list[i]["url"]
else:
url1 = ""
if "url" in step2_node_list[j]:
url2 = step2_node_list[j]["url"]
else:
url2 = ""
if "description" in step2_node_list[i]:
description1 = step2_node_list[i]["description"]
else:
description1 = ""
if "description" in step2_node_list[j]:
description2 = step2_node_list[j]["description"]
else:
description2 = ""
if description1 != "" and description2 != "":
desc_sim = description_similarity(description1, description2)
if desc_sim >= 0.7:
step2_node_list[i].setdefault("duplicate", 1)
step2_node_list[j].setdefault("duplicate", 1)
else:
url_sim = 0
if url1 != "" and url2 != "":
url_sim = url_similarity(url1, url2)
if url_sim >= 0.8:
step2_node_list[i].setdefault("duplicate", 2)
step2_node_list[j].setdefault("duplicate", 2)
else:
node1 = awesome_graph_accessor.find_start_by_relation_type_and_end_url("collect", url1)
node2 = awesome_graph_accessor.find_start_by_relation_type_and_end_url("collect", url2)
if node1 is not None and node2 is not None:
node_id1 = GraphAccessor.get_id_for_node(node1)
node_id2 = GraphAccessor.get_id_for_node(node2)
if node_id1 == node_id2:
step2_node_list[i].setdefault("duplicate", 3)
step2_node_list[j].setdefault("duplicate", 3)
for each in step2_node_list:
node_list_after_step2.append(each)
node_map_after_step2 = construct_key_count_map(node_list_after_step2)
# i = 0
# for key in node_map_after_step2.keys():
# if len(node_map_after_step2[key]) > 1 and property_in_dict_list("duplicate", node_map_after_step2[key]) is True:
# print key, " ", len(node_map_after_step2[key]), " ", node_map_after_step2[key]
# i += 1
# print i
pending_map = {}
duplicate_id_list = []
for key in node_map_after_step2.keys():
temp_list = []
temp_id_list = []
if len(node_map_after_step2[key]) > 1 and property_in_dict_list("duplicate", node_map_after_step2[key]) is True:
for each in node_map_after_step2[key]:
if "duplicate" in dict(each):
temp_list.append(each)
temp_id_list.append(DefaultGraphAccessor.get_id_for_node(each))
pending_map.setdefault(key, temp_list)
duplicate_id_list.append(temp_id_list)
for key in pending_map.keys():
pending_list = rename_property(pending_map[key])
for each in pending_list:
print each
awesome_graph_accessor.push_node(each)
print len(pending_map)
with open("duplicate_id_list.txt", 'w') as f:
f.write(str(duplicate_id_list))
def setUp(self):
self.graphClient = DefaultGraphAccessor(GraphClient())
self.filter = NodeRelationFilter()
import threading
import time
from Queue import Queue
from py2neo import Node
from skgraph.graph.accessor.graph_accessor import DefaultGraphAccessor, GraphClient
from skgraph.graph.accessor.graph_client_for_rwr import RandomWalkGraphAccessor
from skgraph.graph.operation.generateDataPpi import DataCreateUtil
from skgraph.graph.operation.random_walk_restart import Walker
log_file = open('log.txt', 'w')
exception_file = open('exception.txt', 'a+')
input_file_name = 'data.ppi'
begin_id = 92354
client_1 = DefaultGraphAccessor(GraphClient(server_number=1))
client_2 = DefaultGraphAccessor(GraphClient(server_number=2))
data_util = DataCreateUtil(client_1)
max_id = client_1.get_max_id_for_node()
end_status = 0
print_status = 0
class Producer(threading.Thread):
def __init__(self, queue, queue_length):
threading.Thread.__init__(self)
self.data = queue
self.queue_length = queue_length
def run(self):
print 'begin produce'
from py2neo import Relationship
from skgraph.graph.accessor.graph_accessor import DefaultGraphAccessor, GraphClient
from graph_operation import GraphOperation
graphClient = DefaultGraphAccessor(GraphClient(server_number=1))
class JavaReturnValueTypeLinkerOperation(GraphOperation):
name = 'JavaReturnValueTypeLinkerOperation'
def operate(self, node):
return_value_type = node["value type"]
if return_value_type:
type_node = graphClient.find_one_by_alias_name_property(
"java class", return_value_type)
if type_node is not None:
relation = Relationship(node, "type of", type_node)
graphClient.merge(relation)
return node, node
def test_rename_property(self):
self.graphClient = DefaultGraphAccessor(GraphClient(server_number=0))
node_list = self.graphClient.find_by_name_property("awesome item", "acl9")
result = rename_property(node_list)
print result
def __init__(self, graph_client, api_searcher, api_semantic_search):
self.graph_accessor = DefaultGraphAccessor(graph_client)
self.api_searcher = api_searcher
self.api_semantic_search = api_semantic_search
class TestGraphClient(TestCase):
graphClient = None
def setUp(self):
self.graphClient = DefaultGraphAccessor(GraphClient())
self.nodeCleaner = NodeCleaner()
def test_get_max_id_for_node(self):
self.assertEqual(self.graphClient.get_max_id_for_node(), 697753)
def test_get_adjacent_node_id_list(self):
self.assertEqual(self.graphClient.get_adjacent_node_id_list(66666666),
[])
correct = [64289, 52628, 62565]
self.assertEqual(self.graphClient.get_adjacent_node_id_list(7899),
correct)
def test_get_node_name_by_id(self):
self.assertEqual(self.graphClient.get_node_name_by_id(66666666), None)
self.assertEqual(self.graphClient.get_node_name_by_id(3444),
"Adobe Device Central")
def test_expand_node_for_directly_adjacent_nodes_to_subgraph(self):
# self.assertEqual(self.graphClient.expand_node_for_adjacent_nodes_to_subgraph(3444),
# "Adobe Device Central")
pass
def test_find_by_alias_name_property_exactly_match_from_label_limit_one(
self):
self.assertEqual(
self.graphClient.find_one_by_alias_name_property(
"entity", "Adobe Device Central"), None)
interface = self.graphClient.find_one_by_alias_name_property(
"api", "Interface PrintGraphics")
self.assertEqual(93008, self.graphClient.get_id_for_node(interface))
def test_find_by_alias_name_property(self):
self.assertEqual(
self.graphClient.find_by_alias_name_property(
"entity", "Adobe Device Central"), [])
interfaces = self.graphClient.find_by_alias_name_property(
"api", "Interface PrintGraphics")
self.assertEqual(len(interfaces), 1)
self.assertEqual(93008,
self.graphClient.get_id_for_node(interfaces[0]))
def test_get_relation_by_relation_id(self):
relation = self.graphClient.get_relation_by_relation_id(470129)
self.assertIsNone(relation)
relation = self.graphClient.get_relation_by_relation_id(122211)
self.assertEqual(122211, self.graphClient.get_id_for_node(relation))
self.assertEqual(
91, self.graphClient.get_id_for_node(relation.start_node()))
self.assertEqual(29390,
self.graphClient.get_id_for_node(relation.end_node()))
subgraph = self.graphClient.get_relations_between_two_nodes_in_subgraph(
246029, 246030)
relations_json = []
for r in subgraph.relationships():
r = {
"id": self.graphClient.get_id_for_node(relation),
"name": relation.type(),
"start_id":
self.graphClient.get_start_id_for_relation(relation),
"end_id": self.graphClient.get_end_id_for_relation(relation)
}
print r
subgraph = self.graphClient.get_relations_between_two_nodes_in_subgraph(
246029, 246033)
self.assertEqual(subgraph, None)
def test_find_node_by_id(self):
node = self.graphClient.find_node_by_id(5444)
self.assertEqual(5444, self.graphClient.get_id_for_node(node))
def test_search_nodes_by_name(self):
nodes = self.graphClient.search_nodes_by_name("java")
count = 0
for n in nodes:
count = count + 1
self.assertEqual(10, count)
nodes = self.graphClient.search_nodes_by_name("String buffer()")
count = 0
for n in nodes:
count = count + 1
self.assertEqual(10, count)
def test_search_nodes_by_name_in_subgraph(self):
subgraph = self.graphClient.search_nodes_by_name_in_subgraph("java")
count = 0
for n in subgraph.nodes():
count = count + 1
self.assertEqual(10, count)
subgraph = self.graphClient.search_nodes_by_name_in_subgraph(
"String buffer()")
count = 0
if subgraph is not None:
for n in subgraph.nodes():
count = count + 1
self.assertEqual(10, count)
def test_get_relations_between_two_nodes_in_subgraph(self):
subgraph = self.graphClient.get_relations_between_two_nodes_in_subgraph(
48, 3600)
self.assertEqual(None, subgraph)
subgraph = self.graphClient.get_relations_between_two_nodes_in_subgraph(
48, 3643)
self.assertEqual(2, len(subgraph.nodes()))
self.assertEqual(1, len(subgraph.relationships()))
def test_get_relations_between_two_nodes(self):
record_list = self.graphClient.get_relations_between_two_nodes(
48, 3600)
count = 0
for n in record_list:
count = count + 1
self.assertEqual(0, count)
record_list = self.graphClient.get_relations_between_two_nodes_in_subgraph(
48, 3643)
count = 0
for n in record_list:
count = count + 1
self.assertEqual(1, count)
def test_cleaner(self):
node = self.graphClient.find_node_by_id(444)
self.assertEqual(self.nodeCleaner.get_clean_node_name(node),
"fake news")
node = self.graphClient.find_node_by_id(4444)
self.assertEqual(self.nodeCleaner.get_clean_node_name(node), "")
self.assertEqual(self.graphClient.get_id_for_node(Node("lll", a=3)),
-1)
self.assertEqual(self.graphClient.get_id_for_node(node), 4444)
def test_get_shortest_path_to_name(self):
name = self.graphClient.get_node_name_by_id(8000)
subraph = self.graphClient.get_shortest_path_to_name_in_subgraph(
444, name)
print subraph
def test_get_shortest_path(self):
record_list = self.graphClient.get_shortest_path(444,
8000,
max_degree=2)
self.assertEqual(0, count_record_list(record_list))
record_list = self.graphClient.get_shortest_path(444, 8000)
self.assertNotEqual(None, record_list)
self.assertEqual(1, count_record_list(record_list))
subgraph = self.graphClient.get_shortest_path_in_subgraph(444,
8000,
max_degree=2)
self.assertEqual(None, subgraph)
subgraph = self.graphClient.get_shortest_path_in_subgraph(444,
8000,
max_degree=6)
self.assertNotEqual(None, subgraph)
self.assertEqual(len(subgraph.nodes()), 7)
self.assertEqual(len(subgraph.relationships()), 6)
print subgraph
def test_get_newest_nodes(self):
node_list = self.graphClient.get_newest_nodes(10)
self.assertEqual(10, len(node_list))
print(node_list)
graphJsonParser = GraphJsonParser()
returns = graphJsonParser.parse_node_list_to_json(node_list)
print(returns)
