def mrmrTest(cutMethod=1, method=0, runs=3):
#Artifial Datasets
files = ['data1000-f1.csv', 'data1000-f2.csv','data1000-f3.csv','data1000-f4.csv','data5000-f1.csv', 'data5000-f2.csv','data5000-f3.csv','data5000-f4.csv','data20000-f1.csv', 'data20000-f2.csv','data20000-f3.csv','data20000-f4.csv','data1000-f1-r500.csv','data5000-f1-r500.csv','data20000-f1-r500.csv']
buenos = [[0,1,2,3,4,5,6,13,14],[0,1,8,9],[0,1,6,7],[0,1,3,2],[0,1,2,3,4,5,6,13,14],[0,1,8,9],[0,1,6,7],[0,1,3,2],[0,1,2,3,4,5,6,13,14],[0,1,8,9],[0,1,6,7],[0,1,3,2],[0,1,2,3,4,5,6,13,14],[0,1,2,3,4,5,6,13,14],[0,1,2,3,4,5,6,13,14]]
modelsType = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
#Real Datasets
#files = ['real/sonar_scale.csv', 'real/splice_scale.csv', 'real/colon-cancer.csv', 'real/leu.csv', 'real/duke.csv', 'real/BH20000.csv', 'real/madelon-test.csv']
#buenos = [['?'],['?'],['?'],['?'],['?'],['?'],['?']]
#modelsType = [0,0,0,0,0,0,0]
i=0
verboseClassifiers = True
for f in files:
modelType = modelsType[i]
filepath = 'Data/'+f
filepath2 = 'Data2/'+f
data = read_csv(filepath)
X = np.array(data.ix[:,0:-1])
y = np.array(data.ix[:,-1])
print (filepath, buenos[i])
startTime = time.time()
if(modelType==0):
acc = ml.clasificationJudge(X=X,y=y, testPerc=0.5, runs=runs)
else:
acc = ml.regresionJudge(X=X,y=y, testPerc=0.5, runs=runs)
endTime = time.time()
print ("original:", acc, X.shape[1], str(round(endTime-startTime,3))+"s")
#try:
startTime = time.time()
[rank,featureImportance] = rankExtraction(filepath2,method)
if(cutMethod==0):
cutpos = cuts.greatestDiffCut(weights=featureImportance)
elif(cutMethod==1):
cutpos = cuts.monotonicValidationCut(X=X, y=y, modelType=modelType, rank=rank, consecutives=5, runs=runs)
rank = rank[0:cutpos]
endTime = time.time()
timefs = round(endTime-startTime,3)
X = np.array(data.ix[:,rank])
startTime = time.time()
if(modelType==0):
acc = ml.clasificationJudge(X=X,y=y, testPerc=0.5, runs=runs)
else:
acc = ml.regresionJudge(X=X,y=y, testPerc=0.5, runs=runs)
endTime = time.time()
timeml = round(endTime-startTime,3)
print ("result: ",acc, timefs, timeml, len(rank), rank[0:5])
print ()
def featureSelection(X,y, modelType=0, runs=3, processes=0, measure=1, binMethod=0, cutMethod=1, minRed=0, rrThreshold=0.9, debug=False): if(measure<=4): corrMethod = measure elif(measure==5): measure = [0,1] elif(measure==6): measure = [1,3,4] wlist = [] if(measure<=4): if(binMethod==0): weights = p.binStatic(X=X,y=y,processes=processes,measure=corrMethod) elif(binMethod==1): weights = p.binarySearchBins(X=X, y=y, processes=processes, measure=corrMethod, split=0, useSteps=2, normalizeResult=False, debug=False) else: for corrMethod in measure: if(binMethod==0): wlist.append(p.binStatic(X=X,y=y,processes=processes,measure=corrMethod)) elif(binMethod==1): wlist.append(p.binarySearchBins(X=X, y=y, processes=processes, measure=corrMethod, split=0, useSteps=2, normalizeResult=False, debug=False)) weights = (ut.sumMixedCorrelation(wlist)) #print weights rank = ut.getOrderRank(weights) orank = set(rank) if(cutMethod==-1): rank = rank [0:20] if(cutMethod==0): rank = rank[0:cuts.greatestDiffCut(weights=weights)] elif(cutMethod==1): rank = rank[0:cuts.monotonicValidationCut(X=X, y=y, modelType=modelType, rank=rank, consecutives=5, runs=runs)] elif(cutMethod==2): #rank = rank[0:cuts.monotonicValidationCut(X=X, y=y, modelType=modelType, rank=rank, consecutives=X.shape[1], runs=runs)] [rank,originalRankPositions] = cuts.searchValidationCut(X=X, y=y, modelType=modelType, rank=rank, consecutives=X.shape[1], runs=runs) elif(cutMethod==3): [rank,originalRankPositions] = cuts.searchValidationCut(X=X, y=y, modelType=modelType, rank=rank, consecutives=5, runs=runs) if(debug): print "cutted",rank if(minRed==1): rank = p.parallelRemoveRedundant(X=X, rank=rank, processes=processes, measure=measure, threshold=rrThreshold) if(debug): print "mrmr",rank #print "weights:", #for i in rank: # print weights[i], #print return rank
def artificialTest():
#Syntentic classification datasets
#files = ['data1000-f1.csv', 'data1000-f2.csv','data1000-f3.csv','data1000-f4.csv','data5000-f1.csv', 'data5000-f2.csv','data5000-f3.csv','data5000-f4.csv','data20000-f1.csv', 'data20000-f2.csv','data20000-f3.csv','data20000-f4.csv','data1000-f1-r500.csv','data5000-f1-r500.csv','data20000-f1-r500.csv']
#buenos = [[0,1,2,3,4,5,6,13,14],[0,1,8,9],[0,1,6,7],[0,1,3,2],[0,1,2,3,4,5,6,13,14],[0,1,8,9],[0,1,6,7],[0,1,3,2],[0,1,2,3,4,5,6,13,14],[0,1,8,9],[0,1,6,7],[0,1,3,2],[0,1,2,3,4,5,6,13,14],[0,1,2,3,4,5,6,13,14],[0,1,2,3,4,5,6,13,14]]
#modelsType = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
#Syntetic Regression datasets
#files = ['regression/reg1000-f1.csv']
#buenos = [[0,1,2,3,4,5]]
#modelsType = [1]
#Real Datasets
files = [
'real/sonar_scale.csv', 'real/splice_scale.csv',
'real/colon-cancer.csv', 'real/leu.csv', 'real/duke.csv',
'real/BH20000.csv', 'real/madelon-test.csv'
]
buenos = [['?'], ['?'], ['?'], ['?'], ['?'], ['?'], ['?']]
modelsType = [0, 0, 0, 0, 0, 0, 0]
i = 0
for f in files:
modelType = modelsType[i]
filename = 'Data/' + f
########### Separate Data ###########
print(filename, buenos[i])
data = read_csv(filename)
X = np.array(data.ix[:, 0:-1])
y = np.array(data.ix[:, -1])
########### Search ###########
#Static search
#'''
startTime = time.time()
weights = bs.binStatic(X, y, 2)
endTime = time.time()
print("Serial static " + str(round(endTime - startTime, 3)) +
" seconds.")
print("weights:", weights[0:20])
startTime = time.time()
weights = p.binStatic(X, y, 0, 2)
endTime = time.time()
print("Parallel static " + str(round(endTime - startTime, 3)) +
" seconds.")
print("weights:", weights[0:20])
weights = ut.sumMixedCorrelation(
[bs.binStatic(X, y, 0),
bs.binStatic(X, y, 1)])
print("Combined Static:", weights)
#'''
#Dynamic search
'''
startTime = time.time()
weights = bs.binarySearchBins(X,y,2,0,2)
endTime = time.time()
print "Serial dynamic " + str(round(endTime-startTime,3)) + " seconds."
print "weights:", weights[0:20]
startTime = time.time()
weights = p.binarySearchBins(X,y,0,2,0,2)
endTime = time.time()
print "Parallel dynamic " + str(round(endTime-startTime,3)) + " seconds."
print "weights:", weights[0:20]
weights = ut.sumMixedCorrelation([bs.binarySearchBins(X,y,0,0,2),bs.binarySearchBins(X,y,1,0,2)])
print "Combined Dyniamic:",weights
#'''
########### Cuts ###########
print("\nCuts:")
rank = ut.getOrderRank(weights)
print("rank:", rank[0:20])
#'''
startTime = time.time()
print("Full features Accurracy:",
ml.clasificationJudge(X=X, y=y, testPerc=0.5, runs=3))
endTime = time.time()
print("Full classification time: " +
str(round(endTime - startTime, 3)) + " seconds.")
startTime = time.time()
cutpos1 = cuts.greatestDiffCut(weights)
print(rank[0:cutpos1])
endTime = time.time()
print("\nCut greatestDiffCut time: " +
str(round(endTime - startTime, 3)) + " seconds.")
startTime = time.time()
print(
"greatestDiffCut Accurracy:",
ml.clasificationJudge(X=X[:, rank[0:cutpos1]],
y=y,
testPerc=0.5,
runs=3), " #features:", cutpos1)
endTime = time.time()
print("Classification greatestDiffCut time: " +
str(round(endTime - startTime, 3)) + " seconds.")
#'''
startTime = time.time()
cutpos2 = cuts.monotonicValidationCut(X=X,
y=y,
rank=rank,
modelType=modelType,
consecutives=5,
runs=3)
endTime = time.time()
print("\nCut MonotonicValidationCut time: " +
str(round(endTime - startTime, 3)) + " seconds.")
startTime = time.time()
print(
"MonotonicValidation Accurracy:",
ml.clasificationJudge(X=X[:, rank[0:cutpos2]],
y=y,
testPerc=0.5,
runs=3), " #features:", cutpos2)
endTime = time.time()
print("Classification MonotonicValidationCut time: " +
str(round(endTime - startTime, 3)) + " seconds.")
#'''
#'''
startTime = time.time()
cutpos3 = cuts.monotonicValidationCut(X=X,
y=y,
rank=rank,
modelType=modelType,
consecutives=X.shape[1],
runs=3)
endTime = time.time()
print("Cut FullValidationCut time: " +
str(round(endTime - startTime, 3)) + " seconds.")
startTime = time.time()
print(
"FullValidationCut Accurracy:",
ml.clasificationJudge(X=X[:, rank[0:cutpos3]],
y=y,
testPerc=0.5,
runs=3), " #features:", cutpos3)
endTime = time.time()
print("Classification FullValidationCut time: " +
str(round(endTime - startTime, 3)) + " seconds.")
#'''
#Removing redundant
originalRank = list(rank)
print("\nFinding redundant features:")
'''
startTime = time.time()
rank = set(bs.removeRedundant(X, rank))
print "Serial mode"
print "Original Rank:", originalRank
print "Not redundant:",rank
print "Redundant:",set(originalRank).difference(set(rank))
endTime = time.time()
print "Time finding redundant: " + str(round(endTime-startTime,3)) + " seconds."
#'''
#'''
startTime = time.time()
rank = list(originalRank)
rank = set(p.parallelRemoveRedundant(X, rank))
print("Parallel mode")
print("Original Rank:", originalRank)
print("Not redundant:", rank)
print("Redundant:", set(originalRank).difference(set(rank)))
endTime = time.time()
rank = list(rank)
print("Time finding redundant: " + str(round(endTime - startTime, 3)) +
" seconds.")
print("Final not redundant features Accurracy:",
ml.clasificationJudge(X=X[:, rank], y=y, testPerc=0.5, runs=3))
#'''
i = i + 1
print("-------------------------------------\n")