def f():
s1 = regressionTreeBase.SampleSummary()
s2 = regressionTreeBase.SampleSummary(1.0)
s3 = regressionTreeBase.SampleSummary(2.0, 2.0, 2.0)
s = (s3 + s2) - s1
return (s.mean, s.stdev, s.variance, s.impurity())
def f():
hist = regressionTreeBase.SampleSummaryHistogram(
0.0, 1.0, 5.0, False)
s = regressionTreeBase.SampleSummary(3)
hist.observe(0.1, s)
hist.observe(1.2, regressionTreeBase.SampleSummary(2))
hist.observe(2.8, regressionTreeBase.SampleSummary(1))
hist.observe(3.9, regressionTreeBase.SampleSummary(2))
hist.observe(4.4, regressionTreeBase.SampleSummary(3))
return hist.bestSplitPointAndImpurityImprovement()
def f():
m = regressionTreeBase._MutableVector(sz, 0)
for ix in xrange(sz):
m.augmentItem(ix, sz + ix)
return [m[ix] for ix in range(len(m))]
def f():
m = regressionTreeBase._MutableVector(sz, 0)
for ix in xrange(sz):
m.setitem(ix, ix)
return [val for val in m]
def f():
m = regressionTreeBase._MutableVector(sz, 0)
for ix in xrange(sz):
m.augmentItem(ix, sz + ix)
return [m[ix] for ix in range(len(m))]
def f():
m = regressionTreeBase._MutableVector(sz, 0)
for ix in xrange(sz):
m.setitem(ix, ix)
return [val for val in m]
def f():
s = regressionTreeBase.SampleSummary()
return regressionTreeBase.SampleSummary.impurityImprovement(s, s)