def __init__(
self,
preprocessor=Preprocessor(),
wordemb_creator=MockWordEmbeddingCreator(),
tokenizer=JavaCodeASTTokenizer(None, None),
preprocessed_token_output_directory=PREPROCESSED_CODE_OUTPUT_DIR):
super(IdentifierEmbeddingOnlyMethods,
self).__init__(preprocessor, wordemb_creator, tokenizer,
preprocessed_token_output_directory)
self._with_class_name = False
def __init__(
self,
preprocessor=Preprocessor(),
wordemb_creator=MockWordEmbeddingCreator(),
tokenizer=JavaCodeASTTokenizer(None, None),
preprocessed_token_output_directory=PREPROCESSED_CODE_OUTPUT_DIR):
super(MethodNameSentenceEmbeddingCreator,
self).__init__(preprocessor, wordemb_creator, tokenizer,
preprocessed_token_output_directory)
def __init__(
self,
preprocessor=Preprocessor(),
wordemb_creator=MockWordEmbeddingCreator(),
tokenizer=JavaCodeASTTokenizer(None, None),
preprocessed_token_output_directory=PREPROCESSED_CODE_OUTPUT_DIR):
super(IdentifierEmbeddingWithAttribute,
self).__init__(preprocessor, wordemb_creator, tokenizer,
preprocessed_token_output_directory)
self._with_attribute = True
def __init__(
self,
preprocessor=Preprocessor(),
wordemb_creator=MockWordEmbeddingCreator(),
tokenizer=JavaCodeASTTokenizer(None, None),
preprocessed_token_output_directory=PREPROCESSED_CODE_OUTPUT_DIR):
super(IdentifierEmbeddingCreatorWithMethodCommentToClass,
self).__init__(preprocessor, wordemb_creator, tokenizer,
preprocessed_token_output_directory)
self._with_class_name = True
self._with_method = True
self._with_method_comment_to_class = True
self._with_class_name_to_method = True
def __init__(
self,
preprocessor=Preprocessor(),
wordemb_creator=MockWordEmbeddingCreator(),
tokenizer=JavaCodeASTTokenizer(None, None),
preprocessed_token_output_directory=PREPROCESSED_CODE_OUTPUT_DIR):
super(CodeEmbeddingCreator,
self).__init__(preprocessor, wordemb_creator, tokenizer,
preprocessed_token_output_directory)
self._is_ital_identifier = False
self._is_ital_comm = False
if isinstance(wordemb_creator, FastTextAlignedEngItalEmbeddingCreator):
self._is_ital_comm = True
def __init__(
self,
precalculated_weights_file,
preprocessor=Preprocessor(),
wordemb_creator=MockWordEmbeddingCreator(),
tokenizer=JavaCodeASTTokenizer(None, None),
preprocessed_token_output_directory=PREPROCESSED_CODE_OUTPUT_DIR):
super(TFIDFIdentifierEmbeddingCreator,
self).__init__(preprocessor, wordemb_creator, tokenizer,
preprocessed_token_output_directory)
if not precalculated_weights_file:
log.info("No precalculated weights file read")
else:
self._tf_idf_data = TFIDFData(precalculated_weights_file)
def __init__(
self,
preprocessor=Preprocessor(),
wordemb_creator=MockWordEmbeddingCreator(),
tokenizer=JavaCodeASTTokenizer(None, None),
preprocessed_token_output_directory=PREPROCESSED_CODE_OUTPUT_DIR):
super(IdentifierEmbeddingOnlyClassNameAndComment,
self).__init__(preprocessor, wordemb_creator, tokenizer,
preprocessed_token_output_directory)
self._with_class_comment = True
self._with_method = False
self._with_class_name_to_method = False
self._with_attribute = False
self._with_attribute_comment_to_attr = False
self._with_attribute_comment_to_class = False
def __init__(
self,
preprocessor=Preprocessor(),
wordemb_creator=MockWordEmbeddingCreator(),
tokenizer=JavaCodeASTTokenizer(None, None),
preprocessed_token_output_directory=PREPROCESSED_CODE_OUTPUT_DIR):
self._with_class_name = True
self._with_super_classifier = False
self._with_class_comment = False
self._with_attribute = False
self._with_attribute_comment_to_attr = False
self._with_attribute_comment_to_class = False
self._with_method = True
self._with_method_comment_to_method = False
self._with_method_comment_to_class = False
self._with_method_body_to_method = False
self._with_method_body_to_class = False
self._with_class_name_to_method = True
self._with_inner_classifier = False
self._average_function = Util.create_averaged_vector # function that maps multiple vectors to one
super(IdentifierEmbeddingCreator,
self).__init__(preprocessor, wordemb_creator, tokenizer,
preprocessed_token_output_directory)