def build_doc(pro_name, version):
input_doc_collection_path = PathUtil.doc(pro_name=pro_name,
version=version)
output_pre_doc_collection_path = PathUtil.pre_doc(pro_name=pro_name,
version=version,
pre_way="code-pre")
doc_collection: MultiFieldDocumentCollection = MultiFieldDocumentCollection.load(
input_doc_collection_path)
precess_doc_collection = PreprocessMultiFieldDocumentCollection.create_from_doc_collection(
preprocessor=CodeDocPreprocessor(), doc_collection=doc_collection)
precess_doc_collection.save(output_pre_doc_collection_path)
def train_avg_w2v_model(pro_name, version):
doc_path = PathUtil.doc(pro_name, version)
collection = MultiFieldDocumentCollection.load(str(doc_path))
processor = CodeDocPreprocessor()
pre_doc_collection = PreprocessMultiFieldDocumentCollection.create_from_doc_collection(
processor, collection)
pre_doc_path = PathUtil.pre_doc(pro_name, version, pre_way="code-pre")
pre_doc_collection.save(pre_doc_path)
word2vec_model_path = PathUtil.sim_model(pro_name=pro_name,
version=version,
model_type="avg_w2v")
AVGW2VFLModel.train(model_dir_path=word2vec_model_path,
doc_collection=pre_doc_collection)
return word2vec_model_path
def build_pre_doc(pro_name, version, preprocessor):
pre_way = "unknown-pre"
if isinstance(preprocessor, SimplePreprocessor):
pre_way = "sim-pre"
if isinstance(preprocessor, SpacyTextPreprocessor):
pre_way = "spacy-pre"
if isinstance(preprocessor, CodeDocPreprocessor):
pre_way = "code-pre"
if isinstance(preprocessor, PureCodePreprocessor):
pre_way = "pure-pre"
input_doc_collection_path = PathUtil.doc(pro_name=pro_name, version=version)
output_pre_doc_collection_path = PathUtil.pre_doc(pro_name=pro_name, version=version, pre_way=pre_way)
builder = CodeGraphBuilder()
builder.build_pre_doc(input_doc_collection_path, output_pre_doc_collection_path, preprocessor)
def build_extra_model_and_doc(pro_name, version_list):
for version in version_list:
preprocessors = [CodeDocPreprocessor()]
pre_way = "code-pre"
build_doc(pro_name=pro_name, version=version)
for preprocessor in preprocessors:
build_pre_doc(pro_name=pro_name, version=version, preprocessor=preprocessor)
train_name_searcher(pro_name=pro_name, version=version)
pre_doc_collection_path = PathUtil.pre_doc(pro_name=pro_name, version=version, pre_way=pre_way)
preprocess_doc_collection: PreprocessMultiFieldDocumentCollection = PreprocessMultiFieldDocumentCollection.load(
pre_doc_collection_path)
word2vec_model_path = PathUtil.sim_model(pro_name=pro_name, version=version, model_type="avg_w2v")
AVGW2VFLModel.train(model_dir_path=word2vec_model_path,
doc_collection=preprocess_doc_collection)
str(v) + ":" + str(k)
for k, v in self.end_related_relation_num.items()
])
if __name__ == "__main__":
domain_dir = PathUtil.domain_concept_dir("JabRef-2.6", version="v1")
domain_dir = Path(domain_dir)
term_save_path = str(domain_dir / "terms.txt")
operation_save_path = str(domain_dir / "operations.txt")
term_relation_save_path = str(domain_dir / "relations.json")
linkage_save_path = str(domain_dir / "linkages.json")
aliase_save_path = str(domain_dir / "aliases.json")
pre_doc_collection_out_path = PathUtil.pre_doc(pro_name="JabRef-2.6",
version="v2",
pre_way="code-pre")
reduce = ReduceDomainTerm(term_save_path, operation_save_path,
term_relation_save_path, linkage_save_path,
aliase_save_path, pre_doc_collection_out_path)
delete_based_on_name = reduce.delete_based_on_name()
print(delete_based_on_name)
print(len(delete_based_on_name))
delete_based_on_aliase_tf = reduce.delete_based_on_aliase_tf()
print(delete_based_on_aliase_tf)
print(len(delete_based_on_aliase_tf))
delete_based_on_name_length = reduce.delete_based_on_name_length()
print(delete_based_on_name_length)
print(len(delete_based_on_name_length))
