featNo = chosenFeatures[j]
file.write(str(j+1)+":")
file.write(str(matrix[i][featNo])+" ")
file.write("\n")
return 0
result = loadPredict('predictions')
[labelEval, searchID] = loadTest('test.dat')
# print predict
# print labels
# print ids
ourRank = []
results = hh.splitColumnsForEachID(searchID, result)
labels = hh.splitColumnsForEachID(searchID, labelEval)
for i in range(len(results)):
rank = []
for j in range(len(results[i])):
rank.append((results[i][j], labels[i][j]))
rank = sorted(rank, key=itemgetter(0))
ourRank.append(rank)
# for each in ourRank:
# for eeach in each:
# print eeach
# print "\n"
time = (time.split())[0]
month = int(time[5:7])
day = int(time[-11:-9])
dictMonth = {1:31,2:59,3:90,4:120,5:151,6:181,7:212,8:243,9:273,10:304,11:334,12:365}
num_week = (dictMonth[month] + day+ int(booking[i]) )
if num_week>=365:
num_week = num_week%365
num_week = num_week//7
if num_week > 51:
num_week = num_week%51
allData[i][1] = num_week
#24 normalizing distance
dis = hh.replaceNullwithMedian(allData,25)
dis = hh.getColumn(allData,25)
dis = hh.splitColumnsForEachID(searchIDs, dis)
for i in range(len(dis)):
dis[i] = hh.normalizeOneZeroVec(dis[i])
normDis = []
for each in dis:
normEach = [i for i in each]
normDis += normEach
allData = hh.setColumn(allData,normDis,25)
#p27-50 - remove Nulls (24 features)
toFillNull = [4,5,13,18,19,20,21,22,24]
for i in toFillNull:
allData = hh.replaceNullwithMedian(allData,i)