def __init__(self, args):
# create logger
self.logger = logging.getLogger(__name__)
self.logger.setLevel(logging.DEBUG)
# create console handler and set level to debug
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
# create formatter
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
# add formatter to ch
ch.setFormatter(formatter)
# add ch to logger
self.logger.addHandler(ch)
self.logger.debug("Starting Collector process in %s" % os.getcwd())
self.logger.debug("Gevent Version %s" % gevent.__version__)
#TODO: move output file name to config
#fname = "./NetFlow.%s.bin"%str(time.time()*100000)
#WARN: might want to remove this after testing
#self.out = open(fname,"wb")
#create tool instances
self.interface = Interface()
self.parse = Parse()
self.describe = Describe()
self.standardize = Standardize()
self.transform = Transform()
self.partition = Partition()
self.q = Queue()
self.inWindow = False
self.score = Score()
#TODO: move csv name to config
self.csv = CSV("output.csv")
return super(Collector, self).__init__(args)
def __init__(self,args):
# create logger
self.logger = logging.getLogger(__name__)
self.logger.setLevel(logging.DEBUG)
# create console handler and set level to debug
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
# create formatter
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
# add formatter to ch
ch.setFormatter(formatter)
# add ch to logger
self.logger.addHandler(ch)
self.logger.debug( "Starting Collector process in %s"%os.getcwd())
#self.logger.debug( "Gevent Version %s"%gevent.__version__)
#TODO: move output file name to config
fname = "./NetFlow.%d.bin"%int(time.time())
#WARN: might want to remove this after testing
self.out = open(fname,"wb")
#create tool instances
self.interface = Interface()
self.parse = Parse()
self.context = Context()
self.describe = Describe()
self.standardize = Standardize()
self.transform = Transform()
self.partition = Partition()
self.q = Queue()
self.inWindow = settings.SETTINGS.get("collector","inWindow")
self.score = Score()
#TODO: move csv name to config
#self.csv = CSV("output.csv")
self.output = Output()
return super(Collector,self).__init__(args)
from loader import FileLoader
from describe import Describe
class Pair_Plot():
def pair_plot(self, data, desc):
try:
data.drop("Index", axis=1, inplace=True)
sns.pairplot(data, hue="Hogwarts House", markers=".")
plt.show()
except Exception as e:
print("Histogram failed : {}".format(e))
exit()
if (__name__ == '__main__'):
file = "datasets/dataset_train.csv"
result = 0
if (len(sys.argv) < 3):
if (len(sys.argv) == 2):
file = sys.argv[1]
loader = FileLoader()
path = sys.path[0] + '/' + file
data = loader.load(path)
describer = Describe()
result = describer.describe(data)
pair_plotter = Pair_Plot()
pair_plotter.pair_plot(data, result)
else:
print("There is too much arguments.")
class Collector(DatagramServer):
x = 0
def __init__(self,args):
# create logger
self.logger = logging.getLogger(__name__)
self.logger.setLevel(logging.DEBUG)
# create console handler and set level to debug
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
# create formatter
formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
# add formatter to ch
ch.setFormatter(formatter)
# add ch to logger
self.logger.addHandler(ch)
self.logger.debug( "Starting Collector process in %s"%os.getcwd())
#self.logger.debug( "Gevent Version %s"%gevent.__version__)
#TODO: move output file name to config
fname = "./NetFlow.%d.bin"%int(time.time())
#WARN: might want to remove this after testing
self.out = open(fname,"wb")
#create tool instances
self.interface = Interface()
self.parse = Parse()
self.context = Context()
self.describe = Describe()
self.standardize = Standardize()
self.transform = Transform()
self.partition = Partition()
self.q = Queue()
self.inWindow = settings.SETTINGS.get("collector","inWindow")
self.score = Score()
#TODO: move csv name to config
#self.csv = CSV("output.csv")
self.output = Output()
return super(Collector,self).__init__(args)
def done(self):
#pass
self.out.close()
#really important to call del on the csv obj to ensure it closes correctly
#del self.csv
def handle(self, rawData, address):
Collector.x += 1
#print '%s %s: got %r' % (Collector.x, address[0], rawData)
self.out.write(rawData)
interfacedData = self.interface.run(rawData)
#self.logger.debug("Interface: %s"%(repr(interfacedData)))
#once the rawData is "interfaced" we are passing it around by reference
# interfaced data must be iterable
try:
for record in interfacedData:
self.parse.run(record)
#self.logger.debug("Parse: %s"%(repr(record)))
self.context.run(record)
#self.logger.debug("Context: %s"%(repr(record)))
self.describe.run(record)
#self.logger.debug("Describe: %s"%(repr(record)))
#push the record onto the queue until window
if not (self.inWindow):
self.q.put(record)
#self.logger.debug("adding record to queue %s"%(repr(record)))
if (self.q.qsize() == int(settings.SETTINGS.get("collector","describeWindow"))):
#self.logger.debug("Describe Window of %s records met, Begin Processing queue"%settings.SETTINGS.get("collector","describeWindow"))
self.inWindow = True
while not self.q.empty():
item = self.q.get()
#self.logger.debug("processing record from queue %s"%(repr(item)))
self.standardize.run(item)
self.transform.run(item)
self.partition.run(item)
#self.csv.writeRow(self.csv.format(item))
self.output.run(item)
self.q.task_done()
else:
self.standardize.run(record)
#self.logger.debug("Standardize: %s"%(repr(record)))
self.transform.run(record)
#self.logger.debug("Transform: %s"%(repr(record)))
self.partition.run(record)
#self.logger.debug("Partition: %s"%(repr(record)))
#self.csv.writeRow(self.csv.format(record))
self.output.run(record)
#self.score.run(record)
except Exception as e:
self.logger.error("Interfaced data is not iterable %s"%(str(e)))
class Collector(DatagramServer):
x = 0
def __init__(self, args):
# create logger
self.logger = logging.getLogger(__name__)
self.logger.setLevel(logging.DEBUG)
# create console handler and set level to debug
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
# create formatter
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
# add formatter to ch
ch.setFormatter(formatter)
# add ch to logger
self.logger.addHandler(ch)
self.logger.debug("Starting Collector process in %s" % os.getcwd())
self.logger.debug("Gevent Version %s" % gevent.__version__)
#TODO: move output file name to config
#fname = "./NetFlow.%s.bin"%str(time.time()*100000)
#WARN: might want to remove this after testing
#self.out = open(fname,"wb")
#create tool instances
self.interface = Interface()
self.parse = Parse()
self.describe = Describe()
self.standardize = Standardize()
self.transform = Transform()
self.partition = Partition()
self.q = Queue()
self.inWindow = False
self.score = Score()
#TODO: move csv name to config
self.csv = CSV("output.csv")
return super(Collector, self).__init__(args)
def done(self):
#self.out.close()
#really important to call del on the csv obj to ensure it closes correctly
del self.csv
def handle(self, rawData, address):
Collector.x += 1
#print '%s %s: got %r' % (Collector.x, address[0], data)
#self.out.write(rawData)
interfacedData = self.interface.run(rawData)
#once the rawData is "interfaced" we are passing it around by reference
# interfaced data must be iterable
try:
for record in interfacedData:
self.parse.run(record)
self.describe.run(record)
#push the record onto the queue until window
if not (self.inWindow):
self.q.put(record)
#self.logger.debug("adding record to queue %s"%(repr(record)))
if (self.q.qsize() == int(
settings.SETTINGS.get("collector",
"describeWindow"))):
self.logger.debug(
"Describe Window of %s records met, Begin Processing queue"
% settings.SETTINGS.get("collector",
"describeWindow"))
self.inWindow = True
while not self.q.empty():
item = self.q.get()
#self.logger.debug("processing record from queue %s"%(repr(item)))
self.standardize.run(item)
self.transform.run(item)
self.partition.run(item)
self.csv.writeRow(self.csv.format(item))
self.q.task_done()
else:
self.standardize.run(record)
self.transform.run(record)
self.partition.run(record)
self.csv.writeRow(self.csv.format(record))
self.score.run(record)
except Exception as e:
self.logger.error("Interfaced data is not iterable %s" % (str(e)))