def loadnumerical():
oldrows = advancedclassify.loadmatch('matchmaker.csv')
newrows = []
out = open('numerical.txt', 'w+')
for row in oldrows:
d = row.data
data = [float(d[0]), advancedclassify.yesno(d[1]), advancedclassify.yesno(d[2]), advancedclassify.yesno(d[5]),
advancedclassify.yesno(d[6]), advancedclassify.yesno(d[7]), advancedclassify.matchcount(d[3], d[8]),
milesdistance(d[4], d[9]), row.match]
newrows.append(advancedclassify.matchrow(data))
print(advancedclassify.matchrow(data).__str__())
out.write("%s\n" % data)
out.close()
return newrows
def loadnumerical():
oldrows = advancedclassify.loadmatch('matchmaker.csv')
newrows = []
out = open('numerical.txt', 'w+')
for row in oldrows:
d = row.data
data = [
float(d[0]),
advancedclassify.yesno(d[1]),
advancedclassify.yesno(d[2]),
advancedclassify.yesno(d[5]),
advancedclassify.yesno(d[6]),
advancedclassify.yesno(d[7]),
advancedclassify.matchcount(d[3], d[8]),
milesdistance(d[4], d[9]), row.match
]
newrows.append(advancedclassify.matchrow(data))
print(advancedclassify.matchrow(data).__str__())
out.write("%s\n" % data)
out.close()
return newrows
import advancedclassify
ageonly = advancedclassify.loadmatch('agesonly.csv', allnum = True)
advancedclassify.plotagematches(ageonly)
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)
import advancedclassify as ad
import treepredict as tr
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])
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')
def makerDataset():
print '## Matchmaker Dataset'
import advancedclassify
agesonly=advancedclassify.loadmatch('agesonly.csv',allnum=True)
matchmaker=advancedclassify.loadmatch('matchmaker.csv')
print ', '.join(['%s:%s' % item for item in matchmaker[0].__dict__.items()])
import advancedclassify
ageonly = advancedclassify.loadmatch('agesonly.csv', allnum=True)
advancedclassify.plotagematches(ageonly)
def get_dataset():
print "getting data..."
agesonly = advancedclassify.loadmatch('agesonly.csv', allnum=True)
matchmaker = advancedclassify.loadmatch('matchmaker.csv')
return (agesonly, matchmaker)
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)
# advancedclassifytest.py
import advancedclassify
agesonly = advancedclassify.loadmatch('agesonly.csv', allnum=True)
matchmaker = advancedclassify.loadmatch('matchmaker.csv')
numericalset = advancedclassify.loadnumerical()
scaledset, scalef = advancedclassify.scaledata(numericalset)
avgs = advancedclassify.lineartrain(scaledset)
ssoffset = advancedclassify.getoffset(scaledset)
print('classify numericalset[0] : ')
print(numericalset[0].match)
print(advancedclassify.nlclassify(scalef(numericalset[0].data), scaledset, ssoffset))
print('------------------------------')
print('classify numericalset[1] : ')
print(numericalset[1].match)
print(advancedclassify.nlclassify(scalef(numericalset[1].data), scaledset, ssoffset))
print('------------------------------')
print('classify numericalset[2] : ')
print(numericalset[2].match)
print(advancedclassify.nlclassify(scalef(numericalset[2].data), scaledset, ssoffset))
print('------------------------------')
print('classify newrow0 : ')
newrow0 = [28.0, -1, -1, 26.0, -1, 1, 2, 0.8]
