def __init__(self, _OD, _paramsets={'C':100,'gamma':0.1}, parallel = True, train=True):
self.OD = _OD
self.parallel = parallel
self.params = {}
for b in self.OD.bins:
if _paramsets.has_key(b):
self.params[b] = _paramsets[b]
else:
self.params[b] = _paramsets
self.ind = self.OD.indAttr()
self.dep = self.OD.observedContours()
self.indWeights = self.OD.indQuantities
self.svr = {}
if train:
self.train()
self.MU = MisclassUncert(self,self.OD)
class ExpectedDistribution:
def __init__(self, _OD, _paramsets={'C':100,'gamma':0.1}, parallel = True, train=True):
self.OD = _OD
self.parallel = parallel
self.params = {}
for b in self.OD.bins:
if _paramsets.has_key(b):
self.params[b] = _paramsets[b]
else:
self.params[b] = _paramsets
self.ind = self.OD.indAttr()
self.dep = self.OD.observedContours()
self.indWeights = self.OD.indQuantities
self.svr = {}
if train:
self.train()
self.MU = MisclassUncert(self,self.OD)
def train(self):
regressors = []
if self.parallel:
regressors = Parallel(n_jobs=-1)(delayed(trainBin)(self.params[b], np.atleast_2d(self.ind).T, self.dep[b],self.indWeights) for b in self.OD.bins)
else:
for b in self.OD.bins:
regressors.append(trainBin(self.params[b],np.atleast_2d(self.ind).T, self.dep[b],self.indWeights))
#self.svr[b] = SVR(cache_size=1000,kernel='rbf', C=self.params[b]['C'], gamma=self.params[b]['gamma'])
#self.svr[b].fit(np.array([self.ind]).T,self.dep[b])
for i,model in enumerate(regressors):
self.svr[self.OD.bins[i]] = model
def misclassUncertainty(self, values, ignore_eps=True):
return self.MU.misclassUncertainty(values, ignore_eps)
# Get the bin distribution predicted by the SVR model
def getExpectationsAt(self, vals, returnScaled=True, medianOnly=False):
if medianOnly:
results = self.svr[0.5].predict(vals)
if not returnScaled:
results = self.OD.unscalePoints(results)
return results
# get the result predicted for each input value
results = {}
if self.parallel and len(vals) > 1:
predlist = Parallel(n_jobs=-1)(delayed(predictBin)(self.svr[b],vals) for b in self.OD.bins)
for i,pred in enumerate(predlist):
results[self.OD.bins[i]] = pred
else:
for b in self.OD.bins:
results[b] = self.svr[b].predict(vals)
# Flatten lines which cross
# if b < 0.5 flatten b to its larger neighbor
reverse_bins = self.OD.bins[::-1]
for i,b in enumerate(reverse_bins):
if b < 0.5:
results[b] = np.minimum(results[b],results[reverse_bins[i-1]])
# if b > 0.5 flatten b to its smaller neighbor
for i,b in enumerate(self.OD.bins):
if b > 0.5:
results[b] = np.maximum(results[b],results[self.OD.bins[i-1]])
# undo scaling to display points corresponding to the original values
if not returnScaled:
for b in self.OD.bins:
results[b] = self.OD.unscalePoints(results[b])
return results
def getParams(self):
return self.svr[0.5].get_params()
'''SurpriseCalc has been moved to S.py and split up
