def testComputGenderBucket(self):
fileutil = FileUtil()
data = fileutil.readFile("../resource/dataset.xls")
statistics = Statistics()
genderRating = statistics.computeGenderBucket(data)
for i in genderRating:
print i
pass
def testComputeNDBucketEnglish4(self):
fileutil = FileUtil()
data = fileutil.readFile("../resource/dataset.xls")
statistics = Statistics()
mat = numpy.array(data[2:len(data)]);
ndBucket = statistics.computeNDBuckets(mat[:,18])
print "-------------------ENGLISH 4--------------------------"
for idx,val in enumerate(ndBucket):
print "bucket#" + str(idx) + " total: " + str(len(val)) + " min: " + str(min(val)) + " max: " + str(max(val))
print "-----------------------------------------------------"
pass
def testComputeNDBucket(self):
fileutil = FileUtil()
data = fileutil.readFile("../resource/dataset.xls")
statistics = Statistics()
mat = numpy.array(data[2:len(data)]);
ndBucket = statistics.computeNDBuckets(mat[:,7])
for idx,val in enumerate(ndBucket):
print "bucket#" + str(idx) + " total: " + str(len(val))
pass
def testComputeND(self):
fileutil = FileUtil()
data = fileutil.readFile("../resource/dataset.xls")
statistics = Statistics()
mat = numpy.array(data[2:len(data)]);
marksSD = statistics.computeNormalDistribution(mat[:,7])
for idx,val in enumerate(mat[:,7]):
print str(val) + " ** " + str(marksSD[idx])
pass
def testComputeNDBucket(self):
fileutil = FileUtil()
data = fileutil.readFile("../resource/dataset.xls")
statistics = Statistics()
mat = numpy.array(data[2:len(data)]);
ndBucket = statistics.computeNDBuckets(mat[:,13])
print "-------------------Marks obtained by students in college--------------------------"
for idx,val in enumerate(ndBucket):
print "bucket#" + str(idx) + " total: " + str(len(val)) + " min: " + str(min(val)) + " max: " + str(max(val))
pass
def testComputNameLength(self):
fileutil = FileUtil()
data = fileutil.readFile("../resource/dataset.xls")
statistics = Statistics()
mat = numpy.array(data[2:len(data)]);
averages = statistics.computeNameLengthBucket(mat);
print "----------Average length of names-------------"
for idx, val in enumerate(averages):
print str(idx) + " " + str(val)
pass
def testCompareWithPerformance(self):
fileutil = FileUtil()
data = fileutil.readFile("../resource/dataset.xls")
statistics = Statistics()
mat = numpy.array(data[2:len(data)]);
ndBucket = statistics.computeNDBucketsWrtPrediction(mat[:,8], mat[:,30])
for idx,val in enumerate(ndBucket):
total = 0
for yval in val:
total = total + len(yval) # waste of n cycles
print "$performer:" + str(idx)
for fdx, yval in enumerate(val):
print "probability#" + str(len(yval) / float(total)) + "-- P(" + str(idx) + "|" + str(fdx) + ")"
print "grade#" + str(fdx) + " total: " + str(len(yval)) + " min: " + str(min(yval)) + " max: " + str(max(yval))
pass
def computeFullDataGrades(self):
fileutil = FileUtil()
data = fileutil.readFile("../resource/dataset.xls")
statistics = Statistics()
mat = numpy.array(data[2:len(data)]);
rmat = numpy.zeros((len(mat),19))
tuple = [0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18]
gradingCritera = numpy.zeros((19,4))
gradingTuple = [0,1,2,3] #we can fit 5 values in this range
#for i in range(0,18):
# gradingCritera.insert(i, gradingTuple)
#for j in range(0,18):
#gradingCritera[i].insert(j)
#fetch all the values from data
for i in range(0,18):
bucket = statistics.computeNDBuckets(mat[:,self.atMap(i)])
for j in range(0,4):
gradingCritera[i][j] = max(bucket[j])
for i in range(rmat.shape[0]):
for j in range(rmat.shape[1]):
try:
x = decimal.Decimal(mat[i][self.atMap(j)])
except InvalidOperation, ex:
x = gradingCritera[j][1] # passing it average value
#print "i:" + str(i) + " j:" + str(j)
if (x>=gradingCritera[j][3]):
rmat[i][j] = 4
elif (x>=gradingCritera[j][2]):
rmat[i][j] = 3
elif (x>=gradingCritera[j][1]):
rmat[i][j] = 2
elif (x>=gradingCritera[j][0]):
rmat[i][j] = 1
else:
rmat[i][j] = 0
