def cross(file='data/housingD.csv',rseed=1):
def klass(test):
return test.cells[train.klass[0].col]
seed(rseed)
tbl = discreteTable(file)
n=0
abcd=Abcd()
nLeaves=Num()
nNodes=Num()
for tests, train in xval(tbl):
tree = tdiv(train)
for node in dtnodes(tree):
print node.branch
nLeaves + len([n for n in dtleaves(tree)])
nNodes + len([n for n in dtnodes(tree)])
for test in tests:
want = klass(test)
got = classify(test,tree)
abcd(want,got)
exit()
nl()
abcd.header()
abcd.report()
print ":nodes",sorted(nNodes.some.all())
print ":leaves",sorted(nLeaves.some.all())
def cross(file='data/housingD.csv', rseed=1):
def klass(test):
return test.cells[train.klass[0].col]
seed(rseed)
tbl = discreteTable(file)
n = 0
abcd = Abcd()
nLeaves = Num()
nNodes = Num()
for tests, train in xval(tbl):
tree = tdiv(train)
for node in dtnodes(tree):
print node.branch
nLeaves + len([n for n in dtleaves(tree)])
nNodes + len([n for n in dtnodes(tree)])
for test in tests:
want = klass(test)
got = classify(test, tree)
abcd(want, got)
exit()
nl()
abcd.header()
abcd.report()
print ":nodes", sorted(nNodes.some.all())
print ":leaves", sorted(nLeaves.some.all())
def _Abcd(testleaf, train=[], test=[]):
abcd = Abcd(db='Traing', rx='Testing')
def isDef(x):
return "Defective" if x > 0.5 else "Non-Defective"
for leaf in testleaf:
try:
test += [isDef(leaf.score)]
except Exception, e: # go to middle points
# give the median of all rows in this point
# test += [isDef(leafscore(leaf))]
continue
def learns(tests,trains,indep=lambda x: x[:-1],
dep = lambda x: x[-1],
rf = Abcd(),
lg = Abcd(),
dt = Abcd(),
nb = Abcd()):
x1,y1,x2,y2= trainTest(tests,trains,indep,dep)
forest = RandomForestClassifier(n_estimators = 50)
forest = forest.fit(x1,y1)
for n,got in enumerate(forest.predict(x2)):
rf(predicted = got, actual = y2[n])
logreg = linear_model.LogisticRegression(C=1e5)
logreg.fit(x1, y1)
for n,got in enumerate(logreg.predict(x2)):
lg(predicted = got, actual = y2[n])
bayes = GaussianNB()
bayes.fit(x1,y1)
for n,got in enumerate(bayes.predict(x2)):
nb(predicted = got, actual = y2[n])
dectree = DecisionTreeClassifier(criterion="entropy",
random_state=1)
dectree.fit(x1,y1)
for n,got in enumerate(dectree.predict(x2)):
dt(predicted = got, actual = y2[n])
def _Abcd(predicted, actual):
predicted_txt = []
abcd = Abcd(db='Traing', rx='Testing')
def isDef(x):
return "Defective" if x > 0 else "Non-Defective"
for data in predicted:
predicted_txt +=[isDef(data)]
for act, pre in zip(actual, predicted_txt):
abcd.tell(act, pre)
abcd.header()
score = abcd.ask()
# pdb.set_trace()
return score
def _Abcd(testleaf, testdata, train):
# train=[]
test = []
abcd = Abcd(db='Traing', rx='Testing')
def isDef(x):
return "Defective" if x > The.option.threshold else "Non-Defective"
for leaf, data in zip(testleaf, testdata):
try:
test += [isDef(leaf.score)]
# test +=[isDef(majorityscore(data,leaf))]
except Exception: # go to middle points
# give the median of all rows in this point
# pdb.set_trace()
test += [isDef(leafscore(leaf))]
continue
for actual, predicted in zip(train, test):
abcd.tell(actual, predicted)
abcd.header()
score = abcd.ask()
return score
def _Abcd(testleaf, testdata, train):
# train=[]
test = []
abcd = Abcd(db='Traing', rx='Testing')
def isDef(x):
return "Defective" if x > The.option.threshold else "Non-Defective"
for leaf, data in zip(testleaf, testdata):
try:
test += [isDef(leaf.score)]
# test +=[isDef(majorityscore(data,leaf))]
except Exception: # go to middle points
# give the median of all rows in this point
# pdb.set_trace()
test += [isDef(leafscore(leaf))]
continue
for actual, predicted in zip(train, test):
abcd.tell(actual, predicted)
abcd.header()
score = abcd.ask()
return score
def snl(file='data/poi-1.5D.csv', rseed=1, w=dict(_1=0, _0=1)):
def klass(x):
return x.cells[train.klass[0].col]
def val((x, y)):
return y if x == ninf else x
seed(rseed)
nl()
print "#", file
tbl = discreteTable(file)
tree0 = tdiv(tbl)
showTdiv(tree0)
nl()
old, better, worse = Sym(), Sym(), Sym()
abcd1, abcd2 = Abcd(db=file, rx="where"), Abcd(db=file, rx="ranfor")
abcd3 = Abcd(db=file, rx="logref")
abcd4 = Abcd(db=file, rx="dt")
abcd5 = Abcd(db=file, rx="nb")
for tests, train in xval(tbl):
learns(tests,
train._rows,
indep=lambda row: map(val, row.cells[:-2]),
dep=lambda row: row.cells[-1],
rf=abcd2,
lg=abcd3,
dt=abcd4,
nb=abcd5),
tree = tdiv(train)
snakesAndLadders(tree, train, w)
for test in tests:
abcd1(actual=klass(test), predicted=classify(test, tree))
a, b = improve(test, tree)
old + a
better + b
_, c = degrade(test, tree)
worse + c
print "\n:asIs", old.counts
print ":plan", better.counts
print ":warn", worse.counts
abcd1.header()
abcd1.report()
abcd2.report()
abcd3.report()
abcd4.report()
abcd5.report()
def snl(file='data/poi-1.5D.csv',rseed=1,w=dict(_1=0,_0=1)):
def klass(x): return x.cells[train.klass[0].col]
def val((x,y)):
return y if x == ninf else x
seed(rseed)
nl(); print "#",file
tbl = discreteTable(file)
tree0 = tdiv(tbl)
showTdiv(tree0); nl()
old, better, worse = Sym(), Sym(), Sym()
abcd1, abcd2 = Abcd(db=file,rx="where"), Abcd(db=file,rx="ranfor")
abcd3 = Abcd(db=file, rx="logref")
abcd4 = Abcd(db=file, rx="dt")
abcd5 = Abcd(db=file, rx="nb")
for tests, train in xval(tbl):
learns(tests,train._rows,
indep=lambda row: map(val,row.cells[:-2]),
dep = lambda row: row.cells[-1],
rf = abcd2,
lg = abcd3,
dt = abcd4,
nb = abcd5),
tree = tdiv(train)
snakesAndLadders(tree,train,w)
for test in tests:
abcd1(actual = klass(test),
predicted = classify(test,tree))
a,b = improve(test,tree); old + a; better + b
_,c = degrade(test,tree); worse + c
print "\n:asIs",old.counts
print ":plan",better.counts
print ":warn",worse.counts
abcd1.header()
abcd1.report()
abcd2.report()
abcd3.report()
abcd4.report()
abcd5.report()
