# trainD = rawData[:f]+rawData[t:]
# trainL = labels[:f]+labels[t:]
# testD = rawData[f:t]
# testL = labels[f:t]
#
# predictions = getKnnResults(trainD,trainL,testD,tol,mej)
# allPred += predictions
#
# avgf = avgFscore(testL,predictions)
# aaa += avgf
# print "%2d fscore : %.6f" % (i, avgf)
#
# print "povpreceno (%f,%d) : %.6f" % (tol,mej,aaa/k)
# allTests[mej+tol] = allPred
labels = data.getLabelsArray(True)
rawData = data.getDataArray(True)
stPrimerov = len(labels)
testData = data.getTestArray(True)
predictions = getPredictionsRows(rawData,labels,testData)
cPickle.dump(predictions,open("minidata/knn-sotedRes-straight-dist-%d.pickled" % time(),"w"))
f = file("result%d.csv" % time(),"w")
f.write("\n".join([",".join([str(x) for x in i]) for i in predictions ]))
f.flush()
f.close()
import data
import math
d = data.getDataArray()
t = data.getTestArray()
a10 = data.getBadAttributes(d,10)
d10 = data.filterArr(d,a10)
t10 = data.filterArr(t,a10)
binD = [[int(x>0) for x in i] for i in d10]
binT = [[int(x>0) for x in i] for i in t10]
logD = [[int(math.ceil(math.log(x) if x > 0 else 0)) for x in i] for i in d10]
logT = [[int(math.ceil(math.log(x) if x > 0 else 0)) for x in i] for i in t10]
newD = []
newT = []
for i in range(len(t10)):
newD.append(list(d10[i])+list(binD[i])+list(logD[i]))
newT.append(list(t10[i])+list(binT[i])+list(logT[i]))
f = file("plusBinLogTraingingData.csv","w")
f.write("\n".join(["\t".join([str(x).replace("c","") for x in i]) for i in newD ]))
f.flush()
f.close()
f = file("plusBinLogTestData.csv","w")
f.write("\n".join(["\t".join([str(x).replace("c","") for x in i]) for i in newT ]))
f.flush()
