def bupa(self, dims=range(5), depth=4, width=2):
data = pods.datasets.bupa(dims=dims)
X, Y, XLabel = data["X"], data["Y"], data["XLabel"]
d = GPCData(X, Y, XLabel=XLabel, YLabel=["$\\leq 5$ drink units", "$> 5$ drink units"])
print "\n\nBUPA Liver Disorders dataset"
print "=====\nData size: D = %d, N = %d." % (d.getDim(), d.getNum())
search = GPCSearch(data=d, max_depth=depth, beam_width=width)
best, best1d = search.search()
constker = search.baseline()
report = GPCReport(name="BUPA", history=best, best1d=best1d, constkernel=constker)
report.export()
def cleveland(self, dims=[0, 3, 4, 7, 9, 11], depth=5, width=2):
data = pods.datasets.cleveland(dims=dims)
X, Y, XLabel = data["X"], data["Y"], data["XLabel"]
d = GPCData(X, Y, XLabel=XLabel, YLabel=["no heart disease", "with heart disease"])
print "\n\nCleveland Heart Disease dataset"
print "=====\nData size: D = %d, N = %d." % (d.getDim(), d.getNum())
search = GPCSearch(data=d, max_depth=4, beam_width=2)
best, best1d = search.search()
constker = search.baseline()
report = GPCReport(name="Cleveland", history=best, best1d=best1d, constkernel=constker)
report.export()
def wisconsin(self, dims=[0, 1, 4, 5, 7], depth=4, width=2):
data = pods.datasets.breastoriginal(dims=dims)
X, Y, XLabel = data["X"], data["Y"], data["XLabel"]
d = GPCData(X, Y, XLabel=XLabel, YLabel=["no breast cancer", "with breast cancer"])
print "\n\nWisconsin Breast Cancer dataset"
print "=====\nData size: D = %d, N = %d." % (d.getDim(), d.getNum())
search = GPCSearch(data=d, max_depth=depth, beam_width=width)
best, best1d = search.search()
constker = search.baseline()
report = GPCReport(name="Wisconsin", history=best, best1d=best1d, constkernel=constker)
report.export()
def pima(self, dims=[1, 5, 6, 7], depth=4, width=2):
data = pods.datasets.pima(dims=dims)
X, Y, XLabel = data["X"], data["Y"], data["XLabel"]
d = GPCData(X, Y, XLabel=XLabel, YLabel=["not diabetic", "diabetic"])
print "\n\nPima Indian Diabetes dataset"
print "=====\nData size: D = %d, N = %d." % (d.getDim(), d.getNum())
search = GPCSearch(data=d, max_depth=depth, beam_width=width)
best, best1d = search.search()
constker = search.baseline()
report = GPCReport(name="Pima", history=best, best1d=best1d, constkernel=constker)
report.export()
print ""
def pima(self, dims=[1, 5, 6, 7], depth=4, width=2):
data = pods.datasets.pima(dims=dims)
X, Y, XLabel = data['X'], data['Y'], data['XLabel']
d = GPCData(X, Y, XLabel=XLabel, YLabel=['not diabetic', 'diabetic'])
print "\n\nPima Indian Diabetes dataset"
print "=====\nData size: D = %d, N = %d." % (d.getDim(), d.getNum())
search = GPCSearch(data=d, max_depth=depth, beam_width=width)
best, best1d = search.search()
constker = search.baseline()
report = GPCReport(name='Pima',
history=best,
best1d=best1d,
constkernel=constker)
report.export()
print ""
def bupa(self, dims=range(5), depth=4, width=2):
data = pods.datasets.bupa(dims=dims)
X, Y, XLabel = data['X'], data['Y'], data['XLabel']
d = GPCData(X,
Y,
XLabel=XLabel,
YLabel=['$\\leq 5$ drink units', '$> 5$ drink units'])
print "\n\nBUPA Liver Disorders dataset"
print "=====\nData size: D = %d, N = %d." % (d.getDim(), d.getNum())
search = GPCSearch(data=d, max_depth=depth, beam_width=width)
best, best1d = search.search()
constker = search.baseline()
report = GPCReport(name='BUPA',
history=best,
best1d=best1d,
constkernel=constker)
report.export()
def wisconsin(self, dims=[0, 1, 4, 5, 7], depth=4, width=2):
data = pods.datasets.breastoriginal(dims=dims)
X, Y, XLabel = data['X'], data['Y'], data['XLabel']
d = GPCData(X,
Y,
XLabel=XLabel,
YLabel=['no breast cancer', 'with breast cancer'])
print "\n\nWisconsin Breast Cancer dataset"
print "=====\nData size: D = %d, N = %d." % (d.getDim(), d.getNum())
search = GPCSearch(data=d, max_depth=depth, beam_width=width)
best, best1d = search.search()
constker = search.baseline()
report = GPCReport(name='Wisconsin',
history=best,
best1d=best1d,
constkernel=constker)
report.export()
def cleveland(self, dims=[0, 3, 4, 7, 9, 11], depth=5, width=2):
data = pods.datasets.cleveland(dims=dims)
X, Y, XLabel = data['X'], data['Y'], data['XLabel']
d = GPCData(X,
Y,
XLabel=XLabel,
YLabel=['no heart disease', 'with heart disease'])
print "\n\nCleveland Heart Disease dataset"
print "=====\nData size: D = %d, N = %d." % (d.getDim(), d.getNum())
search = GPCSearch(data=d, max_depth=4, beam_width=2)
best, best1d = search.search()
constker = search.baseline()
report = GPCReport(name='Cleveland',
history=best,
best1d=best1d,
constkernel=constker)
report.export()
X = data['X'][:250,[1,5,6,7]]
Y = data['Y'][:250]
d = GPCData(X, Y, XLabel=['plasma glucose', 'BMI', 'pedigree function', 'age'])
print "\n=====\nData size: D = %d, N = %d." % (d.getDim(), d.getNum())
search = GPCSearch(data=d, max_depth=3, beam_width=1)
best, best1d = search.search()
print "\n=====\nBaseline:"
ck = search.baseline()
print ck
print "error = {}".format(ck.error())
report = GPCReport(name='Pima', history=best, best1d=best1d, constkernel=ck)
report.export()
# data = pods.datasets.iris()
# X = data['X']
# Y = data['Y']
# versi_ind = np.where(Y == 'Iris-versicolor')
# virgi_ind = np.where(Y == 'Iris-virginica')
# X = np.hstack((X[versi_ind,:], X[virgi_ind,:])).squeeze()
# Ynum = np.zeros(Y.size)
# Ynum[virgi_ind] = 1
# Ynum = np.hstack((Ynum[versi_ind], Ynum[virgi_ind])).reshape(X.shape[0], 1)
# d = GPCData(X, Ynum, XLabel=['Sepal Length', 'Sepal Width', 'Petal Length', 'Petal Width'], YLabel=['Versicolor', 'Virginica'])
# print "Data size = %d" % (d.getDim() * d.getNum())
# search = GPCSearch(data=d, max_depth=4, beam_width=2)
# best, best1d = search.search()