def __init__(self, numOfKeywords, pathData, dataset_name): self.__lan = getlanguage(pathData + "/Datasets/" + dataset_name) self.__numOfKeywords = numOfKeywords self.__dataset_name = dataset_name self.__pathData = pathData self.__pathToDatasetName = pathData + "/Datasets/" + dataset_name self.__keywordsPath = self.__pathData + '/Keywords/TopicRank/' + self.__dataset_name self.__outputPath = self.__pathData + "/conversor/output/" self.__algorithmName = "TopicRank"
def __init__(self, numOfKeywords, pathData, dataset_name, normalization): self.__normalization = normalization self.__pathToLDAFolder = pathData + "/Models/Unsupervised/lda/" self.__lan = getlanguage(pathData + "/Datasets/" + dataset_name) self.__numOfKeywords = numOfKeywords self.__dataset_name = dataset_name self.__pathData = pathData self.__pathToDatasetName = pathData + "/Datasets/" + dataset_name self.__keywordsPath = self.__pathData + '/Keywords/TopicalPageRank/' + self.__dataset_name self.__outputPath = self.__pathData + "/conversor/output/" self.__algorithmName = "TopicalPageRank"
def __init__(self, numOfKeywords, pathData, dataset_name, normalization): self.__lan = getlanguage(pathData + "/Datasets/" + dataset_name) self.__numOfKeywords = numOfKeywords self.__dataset_name = dataset_name self.__normalization = normalization self.__pathData = pathData self.__pathToDFFile = self.__pathData + "/Models/Unsupervised/dfs/" + self.__dataset_name + '_dfs.gz' self.__pathToDatasetName = self.__pathData + "/Datasets/" + self.__dataset_name self.__keywordsPath = self.__pathData + '/Keywords/EmbedRank/' + self.__dataset_name self.__outputPath = self.__pathData + "/conversor/output/" self.__algorithmName = "EmbedRank"
def __init__(self, numOfKeywords, pathData, dataset_name, normalization): self.__lan = getlanguage(pathData + "/Datasets/" + dataset_name) self.__numOfKeywords = numOfKeywords self.__dataset_name = dataset_name self.__normalization = normalization self.__pathData = pathData self.__pathToDFFile = self.__pathData + "/Models/Unsupervised/dfs/" + self.__dataset_name + '_dfs.gz' self.__pathToDatasetName = self.__pathData + "/Datasets/" + self.__dataset_name self.__keywordsPath = self.__pathData + '/Keywords/SIFRankPlus/' + self.__dataset_name self.__outputPath = self.__pathData + "/conversor/output/" self.__algorithmName = "SIFRankPlus" self.__url = "http://0.0.0.0:5001/sifrankplus"
def __init__(self, numOfKeywords, pathData, dataset_name, normalization): self.__lan = getlanguage(pathData + "/Datasets/" + dataset_name) self.__numOfKeywords = numOfKeywords self.__dataset_name = dataset_name self.__normalization = normalization self.__pathData = pathData self.__pathToKeaModelsFolder = "" self.__pathToKEAFile = "" self.__pathToDFFile = "" self.__pathToCollectionOfDocs = "" self.__pathToDatasetName = self.__pathData + "/Datasets/" + self.__dataset_name self.__algorithmName = "KEA" self.__keywordsPath = self.__pathData + '/Keywords/KEA/' + self.__dataset_name self.__outputPath = self.__pathData + "/conversor/output/"
def __init__(self, numOfKeywords, pathData, dataset_name, normalization): super().__init__() self.__lan = getlanguage(pathData + "/Datasets/" + dataset_name) self.__numOfKeywords = numOfKeywords self.__dataset_name = dataset_name self.__normalization = normalization self.__pathData = pathData self.__pathToDFFile = self.__pathData + "/Models/Unsupervised/dfs/" + self.__dataset_name + '_dfs.gz' self.__pathToDatasetName = self.__pathData + "/Datasets/" + self.__dataset_name self.__keywordsPath = f"{self.__pathData}/Keywords/{self.__class__.__name__}/{self.__dataset_name}" self.__outputPath = self.__pathData + "/conversor/output/" self.__algorithmName = f"{self.__class__.__name__}" self.model = init_keyword_extractor( read_json('evaluation/config/embedrank_bert_as_a_service.json'))
def __init__(self, numOfKeywords, pathData, dataset_name, min_char_length=1, max_words_length=3, min_keyword_frequency=1): self.__lan = getlanguage(pathData + "/Datasets/" + dataset_name) self.__stop_words_pattern = build_stop_word_regex(self.__lan) self.__min_char_length = min_char_length self.__max_words_length = max_words_length self.__min_keyword_frequency = min_keyword_frequency self.__numOfKeywords = numOfKeywords self.__dataset_name = dataset_name self.__pathData = pathData self.__pathToDatasetName = pathData + "/Datasets/" + dataset_name self.__keywordsPath = self.__pathData + '/Keywords/Rake/' + self.__dataset_name self.__outputPath = self.__pathData + "/conversor/output/" self.__algorithmName = "RAKE"