def __init__(self, config, distance_metric):
self.config = config
self.distance_metric = distance_metric
self.clustring_results = []
self.log = logging.getLogger(__name__ + "." + __class__.__name__)
self.log = logger.add_log_file(self.log,
config.get("GENERAL", "logfile"))
def __init__(self, config, documents, external_vec):
self.config = config
self.documents = (documents)
self.num_of_words_per_doc = int(config.get("TF-IDF", "num_of_words_per_doc"))
self.external_vec = external_vec
self.stage = 1
self.log = logging.getLogger(__name__ + "." + __class__.__name__)
self.log = logger.add_log_file(self.log, config.get("GENERAL", "logfile"))
self.build_chunks = build_chunks
def __init__(self, filepath, config, id):
self.log = logging.getLogger(__name__ + "." + __class__.__name__)
self.log = logger.add_log_file(self.log,
config.get("GENERAL", "logfile"))
self.docID = id
self.docPath = filepath
self.basename = os.path.basename(filepath)
self.docText = self.getText(self.docPath)
self.chunks = []
self.chunkSize = int(config.get("CHUNKS", "size"))
self.DelayPar = int(config.get("CHUNKS", "delay"))
self.cluster = None
def __init__(self, config, documents, number_of_clusters, silhouette_width,
max_chunks_in_doc):
self.config = config
self.documents = documents
self.max_chunks_in_doc = max_chunks_in_doc
self.number_of_chunks_styles = number_of_clusters
self.silhouette_width = round(silhouette_width, 6)
self.max_docs_in_style = None
self.min_docs_in_style = None
self.number_of_documents_styles = 0
self.log = logging.getLogger(__name__ + "." + __class__.__name__)
self.log = logger.add_log_file(self.log,
config.get("GENERAL", "logfile"))
def __init__(self, config, documents):
self.config = config
self.distance_metric = []
self.documents = documents
self.comparable_chunks = []
self.chunks_index = {}
self.transferred_vectors = []
self.chebyshev_mat = []
Distance_Matric.vectors_dict = {}
Distance_Matric.corr_matrix = None
self.log = logging.getLogger(__name__ + "." + __class__.__name__)
self.log = logger.add_log_file(self.log,
config.get("GENERAL", "logfile"))
def __init__(self, config, text, docID, chunkID, model, preChunks=[]):
self.chunk_size = config.get("CHUNKS", "size")
self.delay = config.get("CHUNKS", "delay")
self.log = logging.getLogger(__name__ + "." + __class__.__name__)
self.log = logger.add_log_file(self.log,
config.get("GENERAL", "logfile"))
self.chunkID = chunkID
self.chunkVec = None
self.Doc = text
self.docID = docID
self.model = model
self.cluster = None
self.preChunks = preChunks
self.ranked_vec = {}
Chunk.createVec(self)
def __init__(self, config, filepath=None, documents=[]):
self.architecture = 1 if (config.get("Word2Vec", "arch")
== "Skip-Gram") else 0
self.training_model = 1 if (config.get("Word2Vec", "training_model")
== "Softmax") else 0
self.window = int(config.get("Word2Vec", "context_window"))
self.dimension = int(config.get("Word2Vec", "dimension"))
self.delimiter = config.get("Word2Vec", "text_delimiter")
self.file_path = filepath
self.sentences = []
self.vectors = None
self.log = logging.getLogger(__name__ + "." + __class__.__name__)
self.log = logger.add_log_file(self.log,
config.get("GENERAL", "logfile"))
if (documents):
self.set_sentences(documents)