def __init__(self, documents = [], transforms = [TFIDF, LSA]):
self.vectors = []
self.parser = Parser()
if len(documents) > 0:
self._build(documents, transforms)
self.vector_to_doc = {}
self.jokes = documents #added this instance variable to contain actual jokes
def __init__(self, documents=[], transforms=[TFIDF, LSA]):
self.collection_of_document_term_vectors = []
self.transformed_matrix = []
self.parser = Parser()
if len(documents) > 0:
self._build(documents, transforms)
def __init__(self, documentsdict={}, transforms=[TFIDF, LSA]):
self.collection_of_document_term_vectors = []
self.documents = []
self.file_path_all = []
self.document_ID_file_info_mapping = {}
self.transformed_matrix = []
self.parser = Parser()
self._addToList(documentsdict)
if len(self.documents) > 0:
self._build(self.documents, transforms)
def create_parser(self): return Parser(ParserTest.FakeStopWords())
def create_parser_with_stopwords(self, words_string): return Parser(ParserTest.FakeStopWords(words_string))