def main(args):
point2centroid = defaultdict(list)
point2centroidfinal = defaultdict(list)
point2centroidreject = defaultdict(list)
point2centroid = args
for centroid in point2centroid:
# print 'centroid',centroid
centroidX, centroidY = centroid.split(',')
distlist = finallist = pdevlist = rejectlist = []
newX = newY = sumX = sumY = count = ctrrej = 0
for point in point2centroid[centroid]:
#print point
pointX, pointY = point.split(',')
#datapoint += pointX + ' ' + pointY +'\n'
dist = (((int(centroidX) - int(pointX))**2) +
((int(centroidY) - int(pointY))**2))**.5
distlist.append(dist)
pmed = stats.medianscore(distlist)
#print 'pmed',pmed
for p in distlist:
pdev = abs(p - pmed)
pdevlist.append(pdev)
med_pdev = stats.medianscore(pdevlist)
#print "med_pdev", med_pdev
for p in distlist:
if med_pdev > 0:
test_stat = abs(p - pmed) / med_pdev
#print test_stat
if test_stat < 2:
finallist.append(p)
else:
ctrrej += 1
rejectlist.append(p)
for point in point2centroid[centroid]:
# print point
pointX, pointY = point.split(',')
dist = (((int(centroidX) - int(pointX))**2) +
((int(centroidY) - int(pointY))**2))**.5
if dist in rejectlist and dist > 100:
point2centroidreject[centroid].append(point)
else:
point2centroidfinal[centroid].append(point)
sumX += int(pointX)
sumY += int(pointY)
count += 1
newX = sumX / count
newY = sumY / count
newCentroid = newX + ',' + newY
# print newCentroid
point2centroidfinal[newCentroid] = point2centroidfinal[
centroid]
del point2centroidfinal[centroid]
clustering.main(point2centroidfinal)
def test_medianscore(self):
"Testing medianscore"
# data of even lenghts
data1 = [self.L, self.LF, self.A, self.AF]
for d in data1:
self.EQ(stats.medianscore(d), 10.5)
# data with odd lenghts
L2 = self.L + [20]
A2 = num_array(L2)
data2 = [L2, A2]
for d in data2:
self.EQ(stats.medianscore(d), 11)
def test_medianscore(self):
"Testing medianscore"
# data of even lenghts
data1 = [ self.L, self.LF, self.A, self.AF ]
for d in data1 :
self.EQ( stats.medianscore( d ), 10.5 )
# data with odd lenghts
L2 = self.L + [ 20 ]
A2 = num_array( L2 )
data2 = [ L2, A2 ]
for d in data2:
self.EQ( stats.medianscore( d ), 11 )
def _format_ratings(self, output):
ratings = []
for result in self.data:
try:
ratings.append( float(result[0].toPython()) )
except ValueError:
pass
output['results'] = {}
if ratings:
output['results']['median'] = stats.medianscore(ratings)
output['results']['mode'] = stats.mode(ratings)
output['results']['mean'] = stats.mean(ratings)
output['results']['histogram'] = stats.histogram(ratings,6)
output['results']['cumfreq'] = stats.cumfreq(ratings,6)
output['results']['count'] = len(ratings)
return output
lf = list(range(1, 21))
lf[2] = 3.0
a = N.array(l)
af = N.array(lf)
ll = [l] * 5
aa = N.array(ll)
print('\nCENTRAL TENDENCY')
print('geometricmean:', stats.geometricmean(l), stats.geometricmean(lf),
stats.geometricmean(a), stats.geometricmean(af))
print('harmonicmean:', stats.harmonicmean(l), stats.harmonicmean(lf),
stats.harmonicmean(a), stats.harmonicmean(af))
print('mean:', stats.mean(l), stats.mean(lf), stats.mean(a), stats.mean(af))
print('median:', stats.median(l), stats.median(lf), stats.median(a),
stats.median(af))
print('medianscore:', stats.medianscore(l), stats.medianscore(lf),
stats.medianscore(a), stats.medianscore(af))
print('mode:', stats.mode(l), stats.mode(a))
print('\nMOMENTS')
print('moment:', stats.moment(l), stats.moment(lf), stats.moment(a),
stats.moment(af))
print('variation:', stats.variation(l), stats.variation(a),
stats.variation(lf), stats.variation(af))
print('skew:', stats.skew(l), stats.skew(lf), stats.skew(a), stats.skew(af))
print('kurtosis:', stats.kurtosis(l), stats.kurtosis(lf), stats.kurtosis(a),
stats.kurtosis(af))
print('tmean:', stats.tmean(a, (5, 17)), stats.tmean(af, (5, 17)))
print('tvar:', stats.tvar(a, (5, 17)), stats.tvar(af, (5, 17)))
print('tstdev:', stats.tstdev(a, (5, 17)), stats.tstdev(af, (5, 17)))
print('tsem:', stats.tsem(a, (5, 17)), stats.tsem(af, (5, 17)))
N=numpy l = range(1,21) lf = range(1,21) lf[2] = 3.0 a = N.array(l) af = N.array(lf) ll = [l]*5 aa = N.array(ll) print '\nCENTRAL TENDENCY' print 'geometricmean:',stats.geometricmean(l), stats.geometricmean(lf), stats.geometricmean(a), stats.geometricmean(af) print 'harmonicmean:',stats.harmonicmean(l), stats.harmonicmean(lf), stats.harmonicmean(a), stats.harmonicmean(af) print 'mean:',stats.mean(l), stats.mean(lf), stats.mean(a), stats.mean(af) print 'median:',stats.median(l),stats.median(lf),stats.median(a),stats.median(af) print 'medianscore:',stats.medianscore(l),stats.medianscore(lf),stats.medianscore(a),stats.medianscore(af) print 'mode:',stats.mode(l),stats.mode(a) print '\nMOMENTS' print 'moment:',stats.moment(l),stats.moment(lf),stats.moment(a),stats.moment(af) print 'variation:',stats.variation(l),stats.variation(a),stats.variation(lf),stats.variation(af) print 'skew:',stats.skew(l),stats.skew(lf),stats.skew(a),stats.skew(af) print 'kurtosis:',stats.kurtosis(l),stats.kurtosis(lf),stats.kurtosis(a),stats.kurtosis(af) print 'tmean:',stats.tmean(a,(5,17)),stats.tmean(af,(5,17)) print 'tvar:',stats.tvar(a,(5,17)),stats.tvar(af,(5,17)) print 'tstdev:',stats.tstdev(a,(5,17)),stats.tstdev(af,(5,17)) print 'tsem:',stats.tsem(a,(5,17)),stats.tsem(af,(5,17)) print 'describe:' print stats.describe(l) print stats.describe(lf) print stats.describe(a)
def main(args):
point2centroid = defaultdict(list)
point2centroidfinal = defaultdict(list)
point2centroidreject = defaultdict(list)
point2centroid = args
#point2centroid = [('278,728',['351,467','395,285','611,160','612,409','561,239']), ('778,258',['747,355','699,481','730,207','739,182','870,104','782,161'])]
for centroid in point2centroid:
# print 'centroid',centroid
centroidX, centroidY = centroid.split(',')
distlist=finallist=pdevlist=rejectlist=[]
newX =newY=sumX=sumY=count=ctrrej=0
for point in point2centroid[centroid]:
#print point
pointX, pointY = point.split(',')
#datapoint += pointX + ' ' + pointY +'\n'
dist = (((int(centroidX) - int(pointX))**2) + ((int(centroidY) - int(pointY))**2))**.5
distlist.append(dist)
pmed = stats.medianscore(distlist)
#print 'pmed',pmed
for p in distlist:
pdev = abs(p-pmed)
pdevlist.append(pdev)
med_pdev = stats.medianscore(pdevlist)
#print "med_pdev", med_pdev
for p in distlist:
if med_pdev >0:
test_stat = abs(p-pmed)/med_pdev
#print test_stat
if test_stat<2:
finallist.append(p)
else:
ctrrej +=1
rejectlist.append(p)
#print 'distlist', distlist
#print 'finallist', finallist
#print 'rejectlist', rejectlist
#print 'ctrrej', ctrrej
for point in point2centroid[centroid]:
#print point
pointX, pointY = point.split(',')
dist = (((int(centroidX) - int(pointX))**2) + ((int(centroidY) - int(pointY))**2))**.5
if dist in rejectlist and dist >100:
point2centroidreject[centroid].append(point)
else:
point2centroidfinal[centroid].append(point)
sumX += int(pointX)
sumY +=int(pointY)
count +=1
newX=sumX/count
newY=sumY/count
newCentroid = `newX`+','+`newY`
#print newCentroid
point2centroidfinal[newCentroid]=point2centroidfinal[centroid]
del point2centroidfinal[centroid]
#print 'final',point2centroidfinal
#print 'reject', point2centroidreject
clustering.main(point2centroidfinal)
lf = range(1, 21)
lf[2] = 3.0
a = N.array(l)
af = N.array(lf)
ll = [l] * 5
aa = N.array(ll)
print '\nCENTRAL TENDENCY'
print 'geometricmean:', stats.geometricmean(l), stats.geometricmean(
lf), stats.geometricmean(a), stats.geometricmean(af)
print 'harmonicmean:', stats.harmonicmean(l), stats.harmonicmean(
lf), stats.harmonicmean(a), stats.harmonicmean(af)
print 'mean:', stats.mean(l), stats.mean(lf), stats.mean(a), stats.mean(af)
print 'median:', stats.median(l), stats.median(lf), stats.median(
a), stats.median(af)
print 'medianscore:', stats.medianscore(l), stats.medianscore(
lf), stats.medianscore(a), stats.medianscore(af)
print 'mode:', stats.mode(l), stats.mode(a)
print '\nMOMENTS'
print 'moment:', stats.moment(l), stats.moment(lf), stats.moment(
a), stats.moment(af)
print 'variation:', stats.variation(l), stats.variation(a), stats.variation(
lf), stats.variation(af)
print 'skew:', stats.skew(l), stats.skew(lf), stats.skew(a), stats.skew(af)
print 'kurtosis:', stats.kurtosis(l), stats.kurtosis(lf), stats.kurtosis(
a), stats.kurtosis(af)
print 'tmean:', stats.tmean(a, (5, 17)), stats.tmean(af, (5, 17))
print 'tvar:', stats.tvar(a, (5, 17)), stats.tvar(af, (5, 17))
print 'tstdev:', stats.tstdev(a, (5, 17)), stats.tstdev(af, (5, 17))
print 'tsem:', stats.tsem(a, (5, 17)), stats.tsem(af, (5, 17))
def evaluate(self, *args, **params):
return _stats.medianscore(*args, **params)
