def scalingTheData(): print '## Scaling the Data' reload(advancedclassify) numericalset=advancedclassify.loadnumerical( ) scaledset,scalef=advancedclassify.scaledata(numericalset) avgs=advancedclassify.lineartrain(scaledset) print 'numericalset[0].data',numericalset[0].data print 'numericalset[0].match', numericalset[0].match print advancedclassify.dpclassify(scalef(numericalset[0].data),avgs) print 'numericalset[11].match', numericalset[11].match print advancedclassify.dpclassify(scalef(numericalset[11].data),avgs)
def get_scaledset(numericalset):
scaledset, scalef = advancedclassify.scaledata(numericalset)
avgs = advancedclassify.lineartrain(scaledset)
print ">>> numericalset[0].match"
print numericalset[0].match
print ">>> advancedclassify.dpclassify(scalef(numericalset[0].data), avgs)"
print advancedclassify.dpclassify(scalef(numericalset[0].data), avgs)
print ">>> numericalset[11].match"
print numericalset[11].match
print ">>> advancedclassify.dpclassify(scalef(numericalset[11].data), avgs)"
print advancedclassify.dpclassify(scalef(numericalset[11].data), avgs)
return scaledset, scalef
def basicLinearClassification():
print '## Basic Linear Classification'
reload(advancedclassify)
avgs=advancedclassify.lineartrain(agesonly)
print avgs
for (k,v) in avgs.items():
if k==0:
p='b%s' % ('o')
if k==1:
p='b%s' % ('+')
plot(v[0],v[1],p)
show()
print '30,30',advancedclassify.dpclassify([30,30],avgs)
print '30,25',advancedclassify.dpclassify([30,25],avgs)
print '25,40',advancedclassify.dpclassify([25,40],avgs)
print '48,20',advancedclassify.dpclassify([48,20],avgs)
def get_linear_classification(agesonly):
avgs = advancedclassify.lineartrain(agesonly)
print ">>> advancedclassify.dpclassify([30, 30], avgs)"
print advancedclassify.dpclassify([30, 30], avgs)
print ">>> advancedclassify.dpclassify([30, 25], avgs)"
print advancedclassify.dpclassify([30, 25], avgs)
print ">>> advancedclassify.dpclassify([25, 40], avgs)"
print advancedclassify.dpclassify([25, 40], avgs)
print ">>> advancedclassify.dpclassify([48, 20], avgs)"
print advancedclassify.dpclassify([48, 20], avgs)
print "oops!!"
def classify_and_validate_dp(name, dataset):
avgs = advancedclassify.lineartrain(dataset)
correct_count = 0.0
for row in dataset:
res = advancedclassify.dpclassify(row.data, avgs)
if res == row.match:
correct_count += 1
accuracy = correct_count / len(dataset)
print "[%s] correct: %d/%d, accuracy: %f" % (name, correct_count,
len(dataset), accuracy)
def test_pg_197_to_214():
"""
Matchmaker Dataset
"""
import advancedclassify
agesonly = advancedclassify.loadmatch("agesonly.csv", allnum=True)
matchmaker = advancedclassify.loadmatch("matchmaker.csv")
"""
Difficulties with the data
"""
# Scatter plot of mans age vs womans age
# O is a match
# X is not a match
advancedclassify.plotagematches(agesonly)
"""
Basic linear classification
"""
avgs = advancedclassify.lineartrain(agesonly)
print advancedclassify.dpclassify([30,30], avgs)
print advancedclassify.dpclassify([30,25], avgs)
print advancedclassify.dpclassify([25,40], avgs)
print advancedclassify.dpclassify([48,20], avgs)
"""
Determing distances using Yahoo! maps
"""
print advancedclassify.milesdistance("cambride, ma", "new york, ny")
"""
Creating the new dataset
"""
numericalset = advancedclassify.loadnumerical()
print numericalset[0].data
"""
Scaling the dataset.
"""
scaledset, scalef = advancedclassify.scaledata(numericalset)
avgs = advancedclassify.lineartrain(scaledset)
print numericalset[0].data
print numericalset[0].match
print advancedclassify.dpclassify(scalef(numericalset[0].data), avgs)
print numericalset[11].match
print advancedclassify.dpclassify(scalef(numericalset[11].data), avgs)
"""
The kernel trick
"""
offset = advancedclassify.getoffset(agesonly)
print offset
print advancedclassify.nlclassify([30, 30], agesonly, offset)
print advancedclassify.nlclassify([30, 25], agesonly, offset)
print advancedclassify.nlclassify([25, 40], agesonly, offset)
# In contrast to linear classification now recognises that
# 48, 20 is not a good match
print advancedclassify.nlclassify([48, 20], agesonly, offset)
ssoffset = advancedclassify.getoffset(scaledset)
# 0
print numericalset[0].match
# 0
print advancedclassify.nlclassify(scalef(numericalset[0].data), scaledset, ssoffset)
# 1
print numericalset[1].match
# 1
print advancedclassify.nlclassify(scalef(numericalset[1].data), scaledset, ssoffset)
# 0
print numericalset[2].match
# 0
# print advancedclassify.nlclassify(scalef(numericalset[2].data), scaledset, ssoffset)
# man doesnt want children, women does, otherwise really gd match
newrow=[28.0, -1, -1, 26.0, -1, 1, 2, 0.8]
# 0
print advancedclassify.nlclassify(scalef(numericalset[0].data), scaledset, ssoffset)
# both want children
newrow=[28.0, -1, 1, 26.0, -1, 1, 2, 0.8]
# 0
print advancedclassify.nlclassify(scalef(numericalset[0].data), scaledset, ssoffset)
agesonly = ad.loadmatch('agesonly.csv', allnum=True)
matchmaker = ad.loadmatch('matchmaker.csv')
# ad.plotagematches(agesonly)
age = []
for line in file('agesonly.csv'):
l = []
for w in line.split(','):
l.append(int(w))
age.append(l)
tree = tr.buildtree(age)
tr.printtree(tree)
tr.drawtree(tree)
print tr.classify(tree, [65, 63])
avgs = ad.lineartrain(agesonly)
print avgs
print ad.dpclassify([30, 25], avgs.values())
print ad.dpclassify([25, 40], avgs.values())
print ad.dpclassify([48, 20], avgs.values())
print tr.classify(tree, [30, 25])
print tr.classify(tree, [25, 40])
print tr.classify(tree, [48, 20])
numericalset = ad.loadnumerical()
numericalset[0].data
import advancedclassify
agesonly = advancedclassify.loadmatch('agesonly.csv', allnum=True)
matchmaker = advancedclassify.loadmatch('matchmaker.csv')
# advancedclassify.plotagematches(agesonly)
avgs = advancedclassify.lineartrain(agesonly)
print advancedclassify.dpclassify([30,30], avgs)
print advancedclassify.dpclassify([30,25], avgs)
print advancedclassify.dpclassify([25,40], avgs)
print advancedclassify.dpclassify([48,20], avgs)
print advancedclassify.getlocation('1 alewife center, cambridge, ma')
import advancedclassify
agesonly = advancedclassify.loadmatch('agesonly.csv', allnum = True)
matchmaker = advancedclassify.loadmatch('matchmaker.csv')
reload(advancedclassify)
avgs = advancedclassify.lineartrain(agesonly)
reload(advancedclassify)
advancedclassify.dpclassify([30,30], avgs)
advancedclassify.dpclassify([48,32], avgs)
advancedclassify.dpclassify([25,40], avgs)
advancedclassify.dpclassify([48,20], avgs)
reload(advancedclassify)
numericalset = advancedclassify.loadnumerical()
numericalset[0].data
reload(advancedclassify)
scaledset, scalef = advancedclassify.scaledata(numericalset)
avgs = advancedclassify.lineartrain(scaledset)
numericalset[0].data
reload(advancedclassify)
offset = advancedclassify.getoffset(agesonly)
advancedclassify.nlclassify([30,30], agesonly, offset)
advancedclassify.nlclassify([48,32], agesonly, offset)
advancedclassify.nlclassify([25,40], agesonly, offset)
advancedclassify.nlclassify([48,20], agesonly, offset)
def test_pg_197_to_214():
"""
Matchmaker Dataset
"""
import advancedclassify
agesonly = advancedclassify.loadmatch("agesonly.csv", allnum=True)
matchmaker = advancedclassify.loadmatch("matchmaker.csv")
"""
Difficulties with the data
"""
# Scatter plot of mans age vs womans age
# O is a match
# X is not a match
advancedclassify.plotagematches(agesonly)
"""
Basic linear classification
"""
avgs = advancedclassify.lineartrain(agesonly)
print advancedclassify.dpclassify([30, 30], avgs)
print advancedclassify.dpclassify([30, 25], avgs)
print advancedclassify.dpclassify([25, 40], avgs)
print advancedclassify.dpclassify([48, 20], avgs)
"""
Determing distances using Yahoo! maps
"""
print advancedclassify.milesdistance("cambride, ma", "new york, ny")
"""
Creating the new dataset
"""
numericalset = advancedclassify.loadnumerical()
print numericalset[0].data
"""
Scaling the dataset.
"""
scaledset, scalef = advancedclassify.scaledata(numericalset)
avgs = advancedclassify.lineartrain(scaledset)
print numericalset[0].data
print numericalset[0].match
print advancedclassify.dpclassify(scalef(numericalset[0].data), avgs)
print numericalset[11].match
print advancedclassify.dpclassify(scalef(numericalset[11].data), avgs)
"""
The kernel trick
"""
offset = advancedclassify.getoffset(agesonly)
print offset
print advancedclassify.nlclassify([30, 30], agesonly, offset)
print advancedclassify.nlclassify([30, 25], agesonly, offset)
print advancedclassify.nlclassify([25, 40], agesonly, offset)
# In contrast to linear classification now recognises that
# 48, 20 is not a good match
print advancedclassify.nlclassify([48, 20], agesonly, offset)
ssoffset = advancedclassify.getoffset(scaledset)
# 0
print numericalset[0].match
# 0
print advancedclassify.nlclassify(scalef(numericalset[0].data), scaledset,
ssoffset)
# 1
print numericalset[1].match
# 1
print advancedclassify.nlclassify(scalef(numericalset[1].data), scaledset,
ssoffset)
# 0
print numericalset[2].match
# 0
# print advancedclassify.nlclassify(scalef(numericalset[2].data), scaledset, ssoffset)
# man doesnt want children, women does, otherwise really gd match
newrow = [28.0, -1, -1, 26.0, -1, 1, 2, 0.8]
# 0
print advancedclassify.nlclassify(scalef(numericalset[0].data), scaledset,
ssoffset)
# both want children
newrow = [28.0, -1, 1, 26.0, -1, 1, 2, 0.8]
# 0
print advancedclassify.nlclassify(scalef(numericalset[0].data), scaledset,
ssoffset)
