def compareNormalRuns(normalFile, abnormalFile):
# Parameters
winSize = [100, 125, 150, 175, 200]
#winSize = range(200,400,20)
k = 5 # top-k abnormal correlations
d = 5 # top-d abnormal dimensions
printMessage("comparing normal file : " + normalFile)
printMessage("with abnormal file : " + abnormalFile)
normM = DataLoader.load(normalFile)
normM.diff()
normM.removeColumns([0])
n = normM.cols
abnormM = DataLoader.load(abnormalFile)
abnormM.diff()
abnormM.removeColumns([0])
# this will store the top correlations between normal and abnormal runs
top_corrs = []
for w in winSize:
print("win size = " + str(w))
normalCorrMatrix = normM.getCorrelationMatrix(w)
abnormalCorrMatrix = abnormM.getCorrelationMatrix(w)
print("rows = " + str(normalCorrMatrix.rows))
print("cols = " + str(abnormalCorrMatrix.cols))
corrList = getAbnormalCorrelations(normalCorrMatrix,
abnormalCorrMatrix,
k,
d,
values_only=True)
# is k the optimal number here
for i in range(0, k):
top_corrs.append(corrList[i].diss)
return top_corrs
def metricsAnalysis(normalFile, abnormalFile):
# Parameters
winSize = [100, 125, 150, 175, 200]
#winSize = range(200,400,20)
K = [3] # top-k abnormal correlations
D = [3] # top-d abnormal dimensions
printMessage('Loading data files...')
normM = DataLoader.load(normalFile)
normM.diff()
normM.removeColumns([0])
n = normM.cols
abnormM = DataLoader.load(abnormalFile)
abnormM.diff()
abnormM.removeColumns([0])
# Get features names
metrics = getFeaturesNames(normalFile)
del (metrics[0]) # remove ID metric
metricsRank = {}
for w in winSize:
printMessage('Calculating correlations for window-size: ' + str(w))
normalCorrMatrix = normM.getCorrelationMatrix(w)
abnormalCorrMatrix = abnormM.getCorrelationMatrix(w)
for k in K:
for d in D:
printMessage('Finding abnormal correlations...')
corrList = getAbnormalCorrelations(normalCorrMatrix,
abnormalCorrMatrix, k, d)
abnormalMetrics = findAbnormalMetrics(corrList, metrics, n)
for m in abnormalMetrics:
if m not in metricsRank.keys():
metricsRank[m] = 1
else:
metricsRank[m] = metricsRank[m] + 1
printResults(metricsRank)
def metricsAnalysis(normalFile, abnormalFile):
# Parameters
winSize = [100, 125, 150, 175, 200]
#winSize = range(200,400,20)
K = [3] # top-k abnormal correlations
D = [3] # top-d abnormal dimensions
printMessage('Loading data files...')
normM = DataLoader.load(normalFile)
normM.diff()
normM.removeColumns([0])
n = normM.cols
abnormM = DataLoader.load(abnormalFile)
abnormM.diff()
abnormM.removeColumns([0])
# Get features names
metrics = getFeaturesNames(normalFile)
del(metrics[0]) # remove ID metric
metricsRank = {}
for w in winSize:
printMessage('Calculating correlations for window-size: ' + str(w))
normalCorrMatrix = normM.getCorrelationMatrix(w)
abnormalCorrMatrix = abnormM.getCorrelationMatrix(w)
for k in K:
for d in D:
printMessage('Finding abnormal correlations...')
corrList = getAbnormalCorrelations(normalCorrMatrix, abnormalCorrMatrix, k, d)
abnormalMetrics = findAbnormalMetrics(corrList, metrics, n)
for m in abnormalMetrics:
if m not in metricsRank.keys():
metricsRank[m] = 1
else:
metricsRank[m] = metricsRank[m] + 1
printResults(metricsRank)
#!/usr/bin/env python
from localization import DataLoader, Column, Matrix
import sys
###############################################################################
# Main script
###############################################################################
fileA = sys.argv[1]
fileB = sys.argv[2]
fileAMatrix = DataLoader.load(fileA)
fileBMatrix = DataLoader.load(fileB)
print "File A:", "cols:", fileAMatrix.cols, "rows:", fileAMatrix.rows
print "File B:", "cols:", fileBMatrix.cols, "rows:", fileBMatrix.rows
for i in range(fileAMatrix.cols):
if i > 0:
print "Comparing col", i
colA = fileAMatrix.getCol(i)
colB = fileBMatrix.getCol(i)
for j in range(colA.size()):
diff = float(colA.at(j)) - float(colB.at(j))
if diff > 0.001:
print "\tDiff:", diff