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 + '/Keyphrases/TopicRank/' + self.__dataset_name
self.__algorithmName = "TopicRank"
def __init__(self, numOfKeywords, pathData, dataset_name, normalization):
self.__normalization = normalization
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 + '/Keyphrases/PositionRank/' + self.__dataset_name
self.__algorithmName = "PositionRank"
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 + '/Keyphrases/TopicalPageRank/' + self.__dataset_name
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/dfs/" + self.__dataset_name + '_dfs.gz'
self.__pathToDatasetName = self.__pathData + "/Datasets/" + self.__dataset_name
self.__keywordsPath = self.__pathData + '/Keyphrases/TFIDF/' + self.__dataset_name
self.__algorithmName = "TFIDF"
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 + '/Keyphrases/KEA/' + self.__dataset_name
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 + '/Keyphrases/Rake/' + self.__dataset_name
self.__algorithmName = "RAKE"