Beispiel #1
0
    def __init__(self):
        self.debug = config['ainews.debug']
        self.today = date.today()
        self.earliest_date = self.today - timedelta(
            days=int(config['ainews.period']))
        self.db = AINewsDB()
        self.corpus = AINewsCorpus()
        self.duplicates = AINewsDuplicates()
        self.txtpro = AINewsTextProcessor()
        self.weka = AINewsWekaClassifier()

        self.articles = {}
        self.semiauto_email_output = ""
Beispiel #2
0
    def __init__(self):
        self.txtpro = AINewsTextProcessor()
        self.cache_urls = {}

        #: A dictionary of word=>word freq in corpus
        self.dftext = {}

        #: A dictionary of word=>wordid
        self.idwords = {}

        #: A dictionary of wordid=>word
        self.wordids = {}

        self.db = AINewsDB()

        self.categories = ["AIOverview","Agents", "Applications", \
                 "CognitiveScience", "Education", "Ethics", "Games", "History", \
                 "Interfaces", "MachineLearning", "NaturalLanguage", "Philosophy", \
                 "Reasoning", "Representation", "Robots", "ScienceFiction", \
                 "Speech", "Systems", "Vision"]

        self.retained_db_docs = None

        self.restore_corpus()
Beispiel #3
0
 def __init__(self):
     self.txtpro = AINewsTextProcessor()