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)
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.")
