def createModel(self, svdlearner):
A = svdlearner.A
A = self.reducedSetTransformation(A)
fs = self.X
if self.basis_vectors != None:
fs = self.X[self.basis_vectors]
bias = self.bias
X = getPrimalDataMatrix(fs, bias)
#The hyperplane is a linear combination of the feature vectors of the basis examples
W = X.T * A
if bias != 0:
W_biaz = W[W.shape[0] - 1] * math.sqrt(bias)
W_features = W[range(W.shape[0] - 1)]
mod = model.LinearModel(W_features, W_biaz)
else:
mod = model.LinearModel(W, 0.)
return mod
def getModel(self):
"""Returns the trained model, call this only after training.
Returns
-------
model : LinearModel
prediction function
"""
return model.LinearModel(self.A, self.b)
def getModel(self):
"""Returns the trained model, call this only after training.
Returns
-------
model : LinearModel
prediction function (model.W contains at most "subsetsize" number of non-zero coefficients)
"""
return model.LinearModel(self.A, self.b)
def callback(self, learner):
m = model.LinearModel(learner.A, learner.b)
P = m.predict(self.X_valid)
if self.qids_valid:
perfs = []
for query in self.qids_valid:
try:
perf = self.measure(self.Y_valid[query], P[query])
perfs.append(perf)
except UndefinedPerformance, e:
pass
perf = np.mean(perfs)
def createModel(self, svdlearner):
A = svdlearner.A
A = self.reducedSetTransformation(A)
#fs = svdlearner.resource_pool[data_sources.TRAIN_FEATURES]
fs = self.X
if self.bvectors != None:
fs = self.X[self.bvectors]
bias = self.bias
#if "bias" in svdlearner.resource_pool:
# bias = float(svdlearner.resource_pool["bias"])
#else:
# bias = 0.
X = getPrimalDataMatrix(fs, bias)
#The hyperplane is a linear combination of the feature vectors of the basis examples
W = X.T * A
if bias != 0:
W_biaz = W[W.shape[0] - 1] * math.sqrt(bias)
W_features = W[range(W.shape[0] - 1)]
mod = model.LinearModel(W_features, W_biaz)
else:
mod = model.LinearModel(W, 0.)
return mod
def testModel(self):
train_labels = np.random.random((10))
test_labels = np.random.random((10))
train_features = np.random.random((10,100))
test_features = np.random.random((10,100))
kwargs = {}
kwargs["train_labels"] = train_labels
kwargs["train_features"] = train_features
kwargs["regparam"] = 1
learner = RLS.createLearner(**kwargs)
learner.train()
model = learner.getModel()
print
#print 'Ten data points, single label '
model = mod.LinearModel(np.random.random((100)))
self.all_pred_cases(model)
model = mod.LinearModel(np.random.random((100, 2)))
self.all_pred_cases(model)
#model = mod.LinearModel(np.random.random((1, 2)))
#self.all_pred_cases(model)
kwargs["kernel"] = "GaussianKernel"
train_labels = np.random.random((10))
kwargs["train_labels"] = train_labels
learner = RLS.createLearner(**kwargs)
learner.train()
model = learner.getModel()
self.all_pred_cases(model)
kwargs["kernel"] = "GaussianKernel"
train_labels = np.random.random((10,2))
kwargs["train_labels"] = train_labels
learner = RLS.createLearner(**kwargs)
learner.train()
model = learner.getModel()
self.all_pred_cases(model)
def callback(self, learner):
A = learner.A
b = learner.bias
A = learner.X_csr*A
if b == 0:
b = np.mat(np.zeros((1,1)))
else:
b = sqrt(b)*A[-1]
A = A[:-1]
m = model.LinearModel(A,b)
P = m.predict(self.X_valid)
perf = self.measure(self.Y_valid,P)
if self.bestperf == None or (self.measure.iserror == (perf < self.bestperf)):
self.bestperf = perf
self.bestA = learner.A
self.last_update = 0
else:
self.iter += 1
self.last_update += 1
#print self.iter, self.last_update, perf
if self.last_update == self.maxiter:
learner.A = np.mat(self.bestA)
raise Finished("Done")
def createModel(self, svdlearner):
A = svdlearner.A
A = self.reducedSetTransformation(A)
mod = model.LinearModel(A, 0.)
return mod
def getModel(self):
return model.LinearModel(self.A, self.b)
