Пример #1
0
	def __init__(self, *args, **kwargs):
		"""
		Initialization assumes that SENTTREE_PATH environment is set. 
		"""
		DocumentReader.__init__(self, *args, **kwargs)
		self.dbstring = os.environ["SENTTREE_DBSTRING"]
		self.postgres_recorder = PostgresDataRecorder(self.dbstring)
		self.folderPath = os.environ['SENTTREE_PATH']
Пример #2
0
	def __init__(self,*args, **kwargs):
		"""
		Initialization assumes that IMDB_PATH environment is set. 
		To set in linux or mac: export IMDB_PATH=/some_directory_containing_IMDB_data
		"""
		DocumentReader.__init__(self, *args, **kwargs)
		self.dbstring = os.environ["IMDB_DBSTRING"]
		self.postgres_recorder = PostgresDataRecorder(self.dbstring)
		self.folderPath = os.environ['IMDB_PATH']
Пример #3
0
    def __init__(self, *args, **kwargs):
        """
		It reads he environment variable and initializes the 
		base class. 
		"""
        DocumentReader.__init__(self, *args, **kwargs)
        self.dbstring = os.environ["REUTERS_DBSTRING"]
        self.postgres_recorder = PostgresDataRecorder(self.dbstring)
        self.folderPath = os.environ['REUTERS_PATH']
        self.validationDict = {}
Пример #4
0
    def __init__(self, *args, **kwargs):
        """
		Initialization assumes that NEWSGROUP_PATH environment is set. 
		To set in linux or mac: export NEWSGROUP_PATH=/some_directory_containing_newsgroup_data
		"""
        DocumentReader.__init__(self, *args, **kwargs)
        self.dbstring = os.environ["NEWSGROUP_DBSTRING"]
        self.postgres_recorder = PostgresDataRecorder(self.dbstring)
        self.folderPath = os.environ['NEWSGROUP_PATH']
        self.validationDict = {}
        self.topic_names = []
Пример #5
0
	def __init__(self,*args, **kwargs):
		"""
		It reads he environment variable and initializes the 
		base class. 
		"""
		DocumentReader.__init__(self, *args, **kwargs)
		self.dbstring = os.environ["DUC_DBSTRING"]
		self.postgres_recorder = PostgresDataRecorder(self.dbstring)
		self.folderPath = os.environ['DUC_PATH']
		self.processed_filenames = []
		self.processed_summaries = []
		self.lambda_val = os.environ['DUC_LAMBDA']
		self.diversity = os.environ['DUC_DIVERSITY']
		self.duc_topic = os.environ['DUC_TOPIC']
		self.document_id = 0