def decompositionFromPool(self, rpool):
kernel = rpool['kernel_obj']
self.X = array_tools.as_2d_array(rpool['X'], True)
if 'basis_vectors' in rpool:
basis_vectors = array_tools.as_2d_array(rpool['basis_vectors'],
True)
if not self.X.shape[1] == basis_vectors.shape[1]:
raise Exception(
"X and basis_vectors have different number of columns")
else:
basis_vectors = None
if "bias" in rpool:
self.bias = float(rpool["bias"])
else:
self.bias = 1.
if basis_vectors is not None or self.X.shape[1] > self.X.shape[0]:
#First possibility: subset of regressors has been invoked
if basis_vectors is not None:
K_r = kernel.getKM(self.X).T
Krr = kernel.getKM(basis_vectors)
svals, evecs, U, Z = decomposeSubsetKM(K_r, Krr)
#Second possibility: dual mode if more attributes than examples
else:
K = kernel.getKM(self.X).T
svals, evecs = linalg.eig_psd(K)
U, Z = None, None
#Third possibility, primal decomposition
else:
#Invoking getPrimalDataMatrix adds the bias feature
X = getPrimalDataMatrix(self.X, self.bias)
evecs, svals, U = linalg.svd_economy_sized(X)
U, Z = None, None
return svals, evecs, U, Z
def accuracy(Y, P):
"""Binary classification accuracy.
A performance measure for binary classification problems.
Returns the fraction of correct class predictions. P[i]>0 is
considered a positive class prediction and P[i]<0 negative.
P[i]==0 is considered as classifier abstaining to make a decision,
which incurs 0.5 errors (in contrast to 0 error for correct and 1
error for incorrect prediction).
If 2-dimensional arrays are supplied as arguments, then accuracy
is separately computed for each column, after which the accuracies
are averaged.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels, must belong to set {-1,1}
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels, can be any real numbers.
Returns
-------
accuracy : float
number between 0 and 1
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(accuracy_multitask(Y, P))
def sqmprank(Y, P):
"""Squared magnitude preserving ranking error.
A performance measure for ranking problems. Computes the sum of (Y[i]-Y[j]-P[i]+P[j])**2
over all index pairs. normalized by the number of pairs. For query-structured data,
one would typically want to compute the error separately for each query, and average.
If 2-dimensional arrays are supplied as arguments, then error is separately computed for
each column, after which the errors are averaged.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct utility values, can be any real numbers
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted utility values, can be any real numbers.
Returns
-------
error : float
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(sqmprank_multitask(Y, P))
def cindex(Y, P):
"""Concordance, aka pairwise ranking accuracy. Computes the
relative fraction of concordant pairs, that is, Y[i] > Y[j]
and P[i] > P[j] (ties with P[i]=P[j] are assumed to be broken
randomly). Equivalent to area under ROC curve, if Y[i] belong
to {-1, 1}. An O(n*log(n)) implementation, based on order
statistic tree computations.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels, can be any real numbers.
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels, can be any real numbers.
Returns
-------
concordance index : float
number between 0 and 1, around 0.5 means random performance
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
perfs = cindex_multitask(Y,P)
perfs = np.array(perfs)
perfs = perfs[np.invert(np.isnan(perfs))]
if len(perfs) == 0:
raise UndefinedPerformance("No pairs, all the instances have the same output")
return np.mean(perfs)
def fscore(Y, P):
"""F1-Score.
A performance measure for binary classification problems.
F1 = 2*(Precision*Recall)/(Precision+Recall)
If 2-dimensional arrays are supplied as arguments, then macro-averaged
F-score is computed over the columns.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels, must belong to set {-1,1}
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels, can be any real numbers. P[i]>0 is treated
as a positive, and P[i]<=0 as a negative class prediction.
Returns
-------
fscore : float
number between 0 and 1
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(fscore_multitask(Y,P))
def auc(Y, P):
"""Area under the ROC curve (AUC).
A performance measure for binary classification problems.
Can be interpreted as an estimate of the probability, that
the classifier is able to discriminate between a randomly
drawn positive and negative training examples. An O(n*log(n))
time implementation, with correction for tied predictions.
If 2-dimensional arrays are supplied as arguments, then AUC
is separately computed for each column, after which the AUCs
are averaged.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels, must belong to set {-1,1}
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels, can be any real numbers.
Returns
-------
auc : float
number between 0 and 1
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(auc_multitask(Y,P))
def fscore(Y, P):
"""F1-Score.
A performance measure for binary classification problems.
F1 = 2*(Precision*Recall)/(Precision+Recall)
If 2-dimensional arrays are supplied as arguments, then macro-averaged
F-score is computed over the columns.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels, must belong to set {-1,1}
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels, can be any real numbers. P[i]>0 is treated
as a positive, and P[i]<=0 as a negative class prediction.
Returns
-------
fscore : float
number between 0 and 1
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(fscore_multitask(Y, P))
def accuracy(Y, P):
"""Binary classification accuracy.
A performance measure for binary classification problems.
Returns the fraction of correct class predictions. P[i]>0 is
considered a positive class prediction and P[i]<0 negative.
P[i]==0 is considered as classifier abstaining to make a decision,
which incurs 0.5 errors (in contrast to 0 error for correct and 1
error for incorrect prediction).
If 2-dimensional arrays are supplied as arguments, then accuracy
is separately computed for each column, after which the accuracies
are averaged.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels, must belong to set {-1,1}
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels, can be any real numbers.
Returns
-------
accuracy : float
number between 0 and 1
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(accuracy_multitask(Y, P))
def decompositionFromPool(self, rpool):
kernel = rpool['kernel_obj']
self.X = array_tools.as_2d_array(rpool['X'], True)
if 'basis_vectors' in rpool:
basis_vectors = array_tools.as_2d_array(rpool['basis_vectors'], True)
if not self.X.shape[1] == basis_vectors.shape[1]:
raise Exception("X and basis_vectors have different number of columns")
else:
basis_vectors = None
if "bias" in rpool:
self.bias = float(rpool["bias"])
else:
self.bias = 1.
if basis_vectors is not None or self.X.shape[1] > self.X.shape[0]:
#First possibility: subset of regressors has been invoked
if basis_vectors is not None:
K_r = kernel.getKM(self.X).T
Krr = kernel.getKM(basis_vectors)
svals, evecs, U, Z = decomposeSubsetKM(K_r, Krr)
#Second possibility: dual mode if more attributes than examples
else:
K = kernel.getKM(self.X).T
svals, evecs = linalg.eig_psd(K)
U, Z = None, None
#Third possibility, primal decomposition
else:
#Invoking getPrimalDataMatrix adds the bias feature
X = getPrimalDataMatrix(self.X, self.bias)
evecs, svals, U = linalg.svd_economy_sized(X)
U, Z = None, None
return svals, evecs, U, Z
def cv_old(self, regparam):
rls = self.rls
rls.solve(regparam)
Y = rls.Y
aucs = []
for k in range(Y.shape[1]):
pairs_start_inds, pairs_end_inds = [], []
for i in range(Y.shape[0] - 1):
for j in range(i + 1, Y.shape[0]):
if Y[i,k] > Y[j,k]:
pairs_start_inds.append(i)
pairs_end_inds.append(j)
elif Y[i,k] < Y[j,k]:
pairs_start_inds.append(j)
pairs_end_inds.append(i)
if len(pairs_start_inds) == 0:
raise UndefinedPerformance("Leave-pair-out undefined, all labels same for output %d" %k)
pred_start, pred_end = rls.leave_pair_out(np.array(pairs_start_inds), np.array(pairs_end_inds))
pred_start = array_tools.as_2d_array(pred_start)
pred_end = array_tools.as_2d_array(pred_end)
auc = 0.
for h in range(len(pred_start)):
if pred_start[h,k] > pred_end[h,k]:
auc += 1.
elif pred_start[h,k] == pred_end[h,k]:
auc += 0.5
auc /= len(pairs_start_inds)
aucs.append(auc)
auc = np.mean(aucs)
return auc, None
def sqerror(Y, P):
"""Mean squared error.
A performance measure for regression problems. Computes the sum of (Y[i]-P[i])**2
over all index pairs, normalized by the number of instances.
If 2-dimensional arrays are supplied as arguments, then error is separately computed for
each column, after which the errors are averaged.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_tasks]
Correct utility values, can be any real numbers
P : {array-like}, shape = [n_samples] or [n_samples, n_tasks]
Predicted utility values, can be any real numbers.
Returns
-------
error : float
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(sqerror_multitask(Y,P))
def cindex(Y, P):
"""Concordance, aka pairwise ranking accuracy. Computes the
relative fraction of concordant pairs, that is, Y[i] > Y[j]
and P[i] > P[j] (ties with P[i]=P[j] are assumed to be broken
randomly). Equivalent to area under ROC curve, if Y[i] belong
to {-1, 1}. An O(n*log(n)) implementation, based on order
statistic tree computations.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels, can be any real numbers.
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels, can be any real numbers.
Returns
-------
concordance index : float
number between 0 and 1, around 0.5 means random performance
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
perfs = cindex_multitask(Y, P)
perfs = np.array(perfs)
perfs = perfs[np.invert(np.isnan(perfs))]
if len(perfs) == 0:
raise UndefinedPerformance(
"No pairs, all the instances have the same output")
return np.mean(perfs)
def auc(Y, P):
"""Area under the ROC curve (AUC).
A performance measure for binary classification problems.
Can be interpreted as an estimate of the probability, that
the classifier is able to discriminate between a randomly
drawn positive and negative training examples. An O(n*log(n))
time implementation, with correction for tied predictions.
If 2-dimensional arrays are supplied as arguments, then AUC
is separately computed for each column, after which the AUCs
are averaged.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels, must belong to set {-1,1}
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels, can be any real numbers.
Returns
-------
auc : float
number between 0 and 1
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(auc_multitask(Y, P))
def cv_old(self, regparam):
rls = self.rls
rls.solve(regparam)
Y = rls.Y
aucs = []
for k in range(Y.shape[1]):
pairs_start_inds, pairs_end_inds = [], []
for i in range(Y.shape[0] - 1):
for j in range(i + 1, Y.shape[0]):
if Y[i,k] > Y[j,k]:
pairs_start_inds.append(i)
pairs_end_inds.append(j)
elif Y[i,k] < Y[j,k]:
pairs_start_inds.append(j)
pairs_end_inds.append(i)
if len(pairs_start_inds) == 0:
raise UndefinedPerformance("Leave-pair-out undefined, all labels same for output %d" %k)
pred_start, pred_end = rls.leave_pair_out(np.array(pairs_start_inds), np.array(pairs_end_inds))
pred_start = array_tools.as_2d_array(pred_start)
pred_end = array_tools.as_2d_array(pred_end)
auc = 0.
for h in range(len(pred_start)):
if pred_start[h,k] > pred_end[h,k]:
auc += 1.
elif pred_start[h,k] == pred_end[h,k]:
auc += 0.5
auc /= len(pairs_start_inds)
aucs.append(auc)
auc = np.mean(aucs)
return auc, None
def cv(self, regparam):
rls = self.rls
rls.solve(regparam)
Y = rls.Y
#Union of all pairs for which predictions are needed
all_pairs = set([])
for k in range(Y.shape[1]):
pairs = []
for i in range(Y.shape[0] - 1):
for j in range(i + 1, Y.shape[0]):
if Y[i, k] != Y[j, k]:
pairs.append((i, j))
#If all labels for some column are same, ranking accuracy is undefined
if len(pairs) == 0:
raise UndefinedPerformance(
"Leave-pair-out undefined, all labels same for output %d" %
k)
all_pairs.update(pairs)
all_start_inds = [x[0] for x in all_pairs]
all_end_inds = [x[1] for x in all_pairs]
#Compute leave-pair-out predictions for all pairs
all_start_inds = np.array(all_start_inds)
all_end_inds = np.array(all_end_inds)
pred_start, pred_end = rls.leave_pair_out(all_start_inds, all_end_inds)
pred_start = array_tools.as_2d_array(pred_start)
pred_end = array_tools.as_2d_array(pred_end)
pair_dict = dict(zip(all_pairs, range(pred_start.shape[0])))
aucs = []
#compute auc/ranking accuracy for each column of Y separately
for k in range(Y.shape[1]):
comparisons = []
#1 if the true and predicted agree, 0 if disagree, 0.5 if predictions tied
for i in range(Y.shape[0] - 1):
for j in range(i + 1, Y.shape[0]):
if Y[i, k] > Y[j, k]:
ind = pair_dict[(i, j)]
if pred_start[ind, k] > pred_end[ind, k]:
comparisons.append(1.)
elif pred_start[ind, k] == pred_end[ind, k]:
comparisons.append(0.5)
else:
comparisons.append(0.)
elif Y[i, k] < Y[j, k]:
ind = pair_dict[(i, j)]
if pred_start[ind, k] < pred_end[ind, k]:
comparisons.append(1.)
elif pred_start[ind, k] == pred_end[ind, k]:
comparisons.append(0.5)
else:
comparisons.append(0.)
auc = np.mean(comparisons)
aucs.append(auc)
#Take the mean of all columnwise aucs
auc = np.mean(aucs)
return auc, None
def cv(self, regparam):
rls = self.rls
rls.solve(regparam)
Y = rls.Y
#Union of all pairs for which predictions are needed
all_pairs = set([])
for k in range(Y.shape[1]):
pairs = []
for i in range(Y.shape[0] - 1):
for j in range(i + 1, Y.shape[0]):
if Y[i,k] != Y[j,k]:
pairs.append((i,j))
#If all labels for some column are same, ranking accuracy is undefined
if len(pairs) == 0:
raise UndefinedPerformance("Leave-pair-out undefined, all labels same for output %d" %k)
all_pairs.update(pairs)
all_start_inds = [x[0] for x in all_pairs]
all_end_inds = [x[1] for x in all_pairs]
#Compute leave-pair-out predictions for all pairs
all_start_inds = np.array(all_start_inds)
all_end_inds = np.array(all_end_inds)
pred_start, pred_end = rls.leave_pair_out(all_start_inds, all_end_inds)
pred_start = array_tools.as_2d_array(pred_start)
pred_end = array_tools.as_2d_array(pred_end)
pair_dict = dict(zip(all_pairs, range(pred_start.shape[0])))
aucs = []
#compute auc/ranking accuracy for each column of Y separately
for k in range(Y.shape[1]):
comparisons = []
#1 if the true and predicted agree, 0 if disagree, 0.5 if predictions tied
for i in range(Y.shape[0] - 1):
for j in range(i + 1, Y.shape[0]):
if Y[i,k] > Y[j,k]:
ind = pair_dict[(i,j)]
if pred_start[ind,k] > pred_end[ind,k]:
comparisons.append(1.)
elif pred_start[ind,k] == pred_end[ind,k]:
comparisons.append(0.5)
else:
comparisons.append(0.)
elif Y[i,k] < Y[j,k]:
ind = pair_dict[(i,j)]
if pred_start[ind,k] < pred_end[ind,k]:
comparisons.append(1.)
elif pred_start[ind,k] == pred_end[ind,k]:
comparisons.append(0.5)
else:
comparisons.append(0.)
auc = np.mean(comparisons)
aucs.append(auc)
#Take the mean of all columnwise aucs
auc = np.mean(aucs)
return auc, None
def __init__(self,
X,
Y,
regparam=1.0,
kernel='LinearKernel',
basis_vectors=None,
**kwargs):
Y = array_tools.as_2d_array(Y)
self.Y = np.mat(Y)
if X.shape[0] != Y.shape[0]:
raise Exception("First dimension of X and Y must be the same")
if basis_vectors != None:
if X.shape[1] != basis_vectors.shape[1]:
raise Exception(
"Number of columns for X and basis_vectors must be the same"
)
kwargs["bias"] = 0.
kwargs['kernel'] = kernel
kwargs['X'] = X
if basis_vectors != None:
kwargs['basis_vectors'] = basis_vectors
self.svdad = creators.createSVDAdapter(**kwargs)
self.regparam = regparam
self.svals = self.svdad.svals
self.svecs = self.svdad.rsvecs
self.size = self.Y.shape[0]
self.solve(self.regparam)
def getKM(self, X):
"""Returns the kernel matrix between the basis vectors and X.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
Returns
-------
K : array, shape = [n_samples, n_bvectors]
kernel matrix
"""
X = array_tools.as_2d_array(X, True)
test_X = X
if sp.issparse(test_X):
test_X = array_tools.spmat_resize(test_X, self.train_X.shape[1])
else:
test_X = array_tools.as_dense_matrix(test_X)
gamma = self.gamma
m = self.train_X.shape[0]
n = test_X.shape[0]
#The Gaussian kernel matrix is constructed from a linear kernel matrix
linkm = self.train_X * test_X.T
linkm = array_tools.as_dense_matrix(linkm)
if sp.issparse(test_X):
test_norms = ((test_X.T.multiply(test_X.T)).sum(axis=0)).T
else:
test_norms = (np.multiply(test_X.T, test_X.T).sum(axis=0)).T
K = mat(np.ones((m, 1), dtype=float64)) * test_norms.T
K = K + self.train_norms * mat(np.ones((1, n), dtype=float64))
K = K - 2 * linkm
K = -gamma * K
K = np.exp(K)
return K.A.T
def __init__(self, X, Y, subsetsize, regparam = 1.0, bias=1.0, measure=None, callbackfun=None, **kwargs):
self.callbackfun = callbackfun
self.regparam = regparam
if isinstance(X, sp.base.spmatrix):
self.X = X.todense()
else:
self.X = X
self.X = self.X.T
self.Y = array_tools.as_2d_array(Y)
#Number of training examples
self.size = self.Y.shape[0]
#if not self.Y.shape[1] == 1:
# raise Exception('GreedyRLS currently supports only one output at a time. The output matrix is now of shape ' + str(self.Y.shape) + '.')
self.bias = bias
self.measure = measure
fsize = X.shape[1]
self.desiredfcount = subsetsize
if not fsize >= self.desiredfcount:
raise Exception('The overall number of features ' + str(fsize) + ' is smaller than the desired number ' + str(self.desiredfcount) + ' of features to be selected.')
self.results = {}
##The current version works only with the squared error measure
#self.measure = None
#self.solve_bu(self.regparam)
#return
#if not self.Y.shape[1] == 1:
self.solve_weak(self.regparam)
def __init__(self,
X,
Y,
subsetsize,
regparam=1.0,
bias=1.0,
callbackfun=None,
**kwargs):
self.callbackfun = callbackfun
self.regparam = regparam
if isinstance(X, sp.base.spmatrix):
self.X = X.todense()
else:
self.X = X
self.X = self.X.T
self.X = self.X.astype("float64", copy=False)
self.Y = np.mat(array_tools.as_2d_array(Y))
#Number of training examples
self.size = self.Y.shape[0]
self.bias = bias
self.measure = None
fsize = X.shape[1]
self.desiredfcount = subsetsize
if not fsize >= self.desiredfcount:
raise Exception('The overall number of features ' + str(fsize) +
' is smaller than the desired number ' +
str(self.desiredfcount) +
' of features to be selected.')
self.results = {}
if 'use_default_callback' in kwargs and bool(
kwargs['use_default_callback']):
self.callbackfun = DefaultCallback(**kwargs)
#The current version works only with the squared error measure
self._solve_cython(self.regparam)
def getKM(self, X):
"""Returns the kernel matrix between the basis vectors and X.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
Returns
-------
K : array, shape = [n_samples, n_bvectors]
kernel matrix
"""
X = array_tools.as_2d_array(X, True)
test_X = X
if sp.issparse(test_X):
test_X = array_tools.spmat_resize(test_X, self.train_X.shape[1])
else:
test_X = array_tools.as_dense_matrix(test_X)
gamma = self.gamma
m = self.train_X.shape[0]
n = test_X.shape[0]
#The Gaussian kernel matrix is constructed from a linear kernel matrix
linkm = self.train_X * test_X.T
linkm = array_tools.as_dense_matrix(linkm)
if sp.issparse(test_X):
test_norms = ((test_X.T.multiply(test_X.T)).sum(axis=0)).T
else:
test_norms = (np.multiply(test_X.T, test_X.T).sum(axis=0)).T
K = mat(np.ones((m, 1), dtype = float64)) * test_norms.T
K = K + self.train_norms * mat(np.ones((1, n), dtype = float64))
K = K - 2 * linkm
K = - gamma * K
K = np.exp(K)
return K.A.T
def getKM(self, X):
"""Returns the kernel matrix between the basis vectors and X.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
Returns
-------
K : array, shape = [n_samples, n_bvectors]
kernel matrix
"""
X = array_tools.as_2d_array(X, True)
test_X = X
degree, coef0, gamma = self.degree, self.coef0, self.gamma
if sp.issparse(test_X):
test_X = array_tools.spmat_resize(test_X, self.train_X.shape[1])
else:
test_X = array_tools.as_dense_matrix(test_X)
train_X = self.train_X
K = array_tools.as_array(train_X * test_X.T)
K *= gamma
K += coef0
K = K ** degree
return K.T
def __init__(self, X_valid, Y_valid, measure=sqerror, maxiter=10):
self.X_valid = array_tools.as_matrix(X_valid)
self.Y_valid = array_tools.as_2d_array(Y_valid)
self.measure = measure
self.bestperf = None
self.bestA = None
self.iter = 0
self.last_update = 0
self.maxiter = maxiter
def __init__(self, X_valid, Y_valid, measure=sqerror, maxiter=10):
self.X_valid = array_tools.as_matrix(X_valid)
self.Y_valid = array_tools.as_2d_array(Y_valid)
self.measure = measure
self.bestperf = None
self.bestA = None
self.iter = 0
self.last_update = 0
self.maxiter = maxiter
def __init__(self, X, gamma=1.0):
X = array_tools.as_2d_array(X, True)
if gamma <= 0.:
raise Exception('ERROR: nonpositive kernel parameter for Gaussian kernel\n')
self.train_X = X
if sp.issparse(self.train_X):
self.train_norms = ((self.train_X.T.multiply(self.train_X.T)).sum(axis=0)).T
else:
self.train_norms = np.mat((np.multiply(self.train_X.T, self.train_X.T).sum(axis=0))).T
self.gamma = gamma
def __init__(self, X, gamma=1.0):
X = array_tools.as_2d_array(X, True)
if gamma <= 0.:
raise Exception('ERROR: nonpositive kernel parameter for Gaussian kernel\n')
self.train_X = X
if sp.issparse(self.train_X):
self.train_norms = ((self.train_X.T.multiply(self.train_X.T)).sum(axis=0)).T
else:
self.train_norms = np.mat((np.multiply(self.train_X.T, self.train_X.T).sum(axis=0))).T
self.gamma = gamma
def __init__(self, X_valid, Y_valid, qids_valid = None, measure=sqmprank, maxiter=10):
self.X_valid = array_tools.as_matrix(X_valid)
self.Y_valid = array_tools.as_2d_array(Y_valid)
self.qids_valid = qids_to_splits(qids_valid)
self.measure = measure
self.bestperf = None
self.bestA = None
self.iter = 0
self.last_update = 0
self.maxiter = maxiter
def spearman(Y, P):
"""Spearman correlation.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels
Returns
-------
correlation : float
number between -1 and 1
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(spearman_multitask(Y, P))
def spearman(Y, P):
"""Spearman correlation.
Parameters
----------
Y : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Correct labels
P : {array-like}, shape = [n_samples] or [n_samples, n_labels]
Predicted labels
Returns
-------
correlation : float
number between -1 and 1
"""
Y = array_tools.as_2d_array(Y)
P = array_tools.as_2d_array(P)
if not Y.shape == P.shape:
raise UndefinedPerformance("Y and P must be of same shape")
return np.mean(spearman_multitask(Y, P))
def __init__(self, X, Y, regparam = 1.0, qids = None, callbackfun=None, **kwargs):
self.regparam = regparam
self.callbackfun = None
self.Y = array_tools.as_2d_array(Y)
#Number of training examples
self.size = Y.shape[0]
if self.Y.shape[1] > 1:
raise Exception('CGRankRLS does not currently work in multi-label mode')
self.learn_from_labels = True
self.callbackfun = callbackfun
self.X = csc_matrix(X.T)
if qids is not None:
self.qids = map_qids(qids)
self.splits = qids_to_splits(self.qids)
else:
self.qids = None
regparam = self.regparam
qids = self.qids
if qids is not None:
P = sp.lil_matrix((self.size, len(set(qids))))
for qidind in range(len(self.splits)):
inds = self.splits[qidind]
qsize = len(inds)
for i in inds:
P[i, qidind] = 1. / sqrt(qsize)
P = P.tocsr()
PT = P.tocsc().T
else:
P = 1./sqrt(self.size)*(np.mat(np.ones((self.size,1), dtype=np.float64)))
PT = P.T
X = self.X.tocsc()
X_csr = X.tocsr()
def mv(v):
v = np.mat(v).T
return X_csr*(X.T*v)-X_csr*(P*(PT*(X.T*v)))+regparam*v
G = LinearOperator((X.shape[0],X.shape[0]), matvec=mv, dtype=np.float64)
Y = self.Y
if not self.callbackfun is None:
def cb(v):
self.A = np.mat(v).T
self.b = np.mat(np.zeros((1,1)))
self.callbackfun.callback(self)
else:
cb = None
XLY = X_csr*Y-X_csr*(P*(PT*Y))
try:
self.A = np.mat(cg(G, XLY, callback=cb)[0]).T
except Finished:
pass
self.b = np.mat(np.zeros((1,1)))
self.predictor = predictor.LinearPredictor(self.A, self.b)
def __init__(self,
X,
Y,
regparam=1.0,
bias=1.0,
callbackfun=None,
**kwargs):
self.Y = array_tools.as_2d_array(Y)
self.X = csc_matrix(X.T)
self.bias = bias
self.regparam = regparam
if self.bias != 0.:
bias_slice = sqrt(self.bias) * np.mat(
ones((1, self.X.shape[1]), dtype=np.float64))
self.X = sparse.vstack([self.X, bias_slice]).tocsc()
self.X_csr = self.X.tocsr()
self.callbackfun = callbackfun
self.results = {}
regparam = self.regparam
Y = self.Y
X = self.X
X_csr = self.X_csr
def mv(v):
return X.T * (X_csr * v) + regparam * v
G = LinearOperator((X.shape[1], X.shape[1]),
matvec=mv,
dtype=np.float64)
self.AA = []
if not self.callbackfun == None:
def cb(v):
self.A = np.mat(v).T
self.callbackfun.callback(self)
else:
cb = None
try:
self.A = np.mat(cg(G, Y, callback=cb)[0]).T
except Finished:
pass
if self.callbackfun != None:
self.callbackfun.finished(self)
self.A = X_csr * self.A
if self.bias == 0.:
self.b = np.mat(np.zeros((1, 1)))
else:
self.b = sqrt(self.bias) * self.A[-1]
self.A = self.A[:-1]
#self.results['predictor'] = self.getModel()
self.predictor = predictor.LinearPredictor(self.A, self.b)
def __init__(self,
X_valid,
Y_valid,
qids_valid=None,
measure=sqmprank,
maxiter=10):
self.X_valid = array_tools.as_matrix(X_valid)
self.Y_valid = array_tools.as_2d_array(Y_valid)
self.qids_valid = qids_to_splits(qids_valid)
self.measure = measure
self.bestperf = None
self.bestA = None
self.iter = 0
self.last_update = 0
self.maxiter = maxiter
def __init__(self, X, Y, qids, regparam = 1.0, kernel='LinearKernel', basis_vectors = None, **kwargs):
kwargs["bias"] = 0.
kwargs['kernel'] = kernel
kwargs['X'] = X
if basis_vectors is not None:
kwargs['basis_vectors'] = basis_vectors
self.svdad = adapter.createSVDAdapter(**kwargs)
self.Y = np.mat(array_tools.as_2d_array(Y))
self.regparam = regparam
self.svals = np.mat(self.svdad.svals)
self.svecs = self.svdad.rsvecs
self.size = self.Y.shape[0]
self.size = self.Y.shape[0]
self.qids = map_qids(qids)
self.qidlist = qids_to_splits(self.qids)
self.solve(self.regparam)
def __init__(self, X, Y, regparam = 1.0, kernel='LinearKernel', basis_vectors = None, **kwargs):
self.Y = array_tools.as_2d_array(Y)
if X.shape[0] != Y.shape[0]:
raise Exception("First dimension of X and Y must be the same")
if basis_vectors is not None:
if X.shape[1] != basis_vectors.shape[1]:
raise Exception("Number of columns for X and basis_vectors must be the same")
kwargs['X'] = X
kwargs['kernel'] = kernel
if basis_vectors is not None:
kwargs['basis_vectors'] = basis_vectors
self.svdad = adapter.createSVDAdapter(**kwargs)
self.regparam = regparam
self.svals = np.mat(self.svdad.svals)
self.svecs = np.mat(self.svdad.rsvecs)
self.size = self.Y.shape[0]
self.solve(self.regparam)
def __init__(self, **kwargs):
Y = kwargs["Y"]
Y = np.mat(array_tools.as_2d_array(Y))
if kwargs.has_key('K1'):
K1 = np.mat(kwargs['K1'])
K2 = np.mat(kwargs['K2'])
Y = Y.reshape((K1.shape[0], K2.shape[0]), order = 'F')
self.K1, self.K2 = K1, K2
self.kernelmode = True
else:
X1 = np.mat(kwargs['X1'])
X2 = np.mat(kwargs['X2'])
Y = Y.reshape((X1.shape[0], X2.shape[0]), order = 'F')
self.X1, self.X2 = X1, X2
self.kernelmode = False
self.Y = Y
self.regparam1 = kwargs["regparam1"]
self.regparam2 = kwargs["regparam2"]
self.trained = False
self.solve(self.regparam1, self.regparam2)
def __init__(self, **kwargs):
Y = kwargs["Y"]
Y = np.mat(array_tools.as_2d_array(Y))
if kwargs.has_key('K1'):
K1 = np.mat(kwargs['K1'])
K2 = np.mat(kwargs['K2'])
Y = Y.reshape((K1.shape[0], K2.shape[0]), order = 'F')
self.K1, self.K2 = K1, K2
self.kernelmode = True
else:
X1 = np.mat(kwargs['X1'])
X2 = np.mat(kwargs['X2'])
Y = Y.reshape((X1.shape[0], X2.shape[0]), order = 'F')
self.X1, self.X2 = X1, X2
self.kernelmode = False
self.Y = Y
self.regparam1 = kwargs["regparam1"]
self.regparam2 = kwargs["regparam2"]
self.trained = False
self.solve(self.regparam1, self.regparam2)
def __init__(self, X, Y, regparam = 1.0, bias = 1.0, callbackfun = None, **kwargs):
self.Y = array_tools.as_2d_array(Y)
self.X = csc_matrix(X.T)
self.bias = bias
self.regparam = regparam
if self.bias != 0.:
bias_slice = sqrt(self.bias)*np.mat(ones((1,self.X.shape[1]),dtype=np.float64))
self.X = sparse.vstack([self.X,bias_slice]).tocsc()
self.X_csr = self.X.tocsr()
self.callbackfun = callbackfun
self.results = {}
regparam = self.regparam
Y = self.Y
X = self.X
X_csr = self.X_csr
def mv(v):
return X.T*(X_csr*v)+regparam*v
G = LinearOperator((X.shape[1],X.shape[1]), matvec=mv, dtype=np.float64)
self.AA = []
if not self.callbackfun is None:
def cb(v):
self.A = np.mat(v).T
self.callbackfun.callback(self)
else:
cb = None
try:
self.A = np.mat(cg(G, Y, callback=cb)[0]).T
except Finished:
pass
if self.callbackfun is not None:
self.callbackfun.finished(self)
self.A = X_csr*self.A
if self.bias == 0.:
self.b = np.mat(np.zeros((1,1)))
else:
self.b = sqrt(self.bias)*self.A[-1]
self.A = self.A[:-1]
#self.results['predictor'] = self.getModel()
self.predictor = predictor.LinearPredictor(self.A, self.b)
def __init__(self, **kwargs):
Y = kwargs["Y"]
Y = array_tools.as_2d_array(Y)
Y = np.mat(Y)
if 'K1' in kwargs:
K1 = np.mat(kwargs['K1'])
K2 = np.mat(kwargs['K2'])
Y = Y.reshape((K1.shape[0], K2.shape[0]), order='F')
self.K1, self.K2 = K1, K2
self.kernelmode = True
else:
X1 = np.mat(kwargs['X1'])
X2 = np.mat(kwargs['X2'])
Y = Y.reshape((X1.shape[0], X2.shape[0]), order='F')
self.X1, self.X2 = X1, X2
self.kernelmode = False
self.Y = Y
if "regparam" in kwargs:
self.regparam = kwargs["regparam"]
else:
self.regparam = 1.
self.trained = False
self.solve(self.regparam)
def __init__(self, **kwargs):
Y = kwargs["Y"]
Y = array_tools.as_2d_array(Y)
Y = np.mat(Y)
if kwargs.has_key("K1"):
K1 = np.mat(kwargs["K1"])
K2 = np.mat(kwargs["K2"])
Y = Y.reshape((K1.shape[0], K2.shape[0]), order="F")
self.K1, self.K2 = K1, K2
self.kernelmode = True
else:
X1 = np.mat(kwargs["X1"])
X2 = np.mat(kwargs["X2"])
Y = Y.reshape((X1.shape[0], X2.shape[0]), order="F")
self.X1, self.X2 = X1, X2
self.kernelmode = False
self.Y = Y
if kwargs.has_key("regparam"):
self.regparam = kwargs["regparam"]
else:
self.regparam = 1.0
self.trained = False
self.solve(self.regparam)
def __init__(self,
X,
Y,
qids,
regparam=1.0,
kernel='LinearKernel',
basis_vectors=None,
**kwargs):
kwargs["bias"] = 0.
kwargs['kernel'] = kernel
kwargs['X'] = X
if basis_vectors is not None:
kwargs['basis_vectors'] = basis_vectors
self.svdad = adapter.createSVDAdapter(**kwargs)
self.Y = np.mat(array_tools.as_2d_array(Y))
self.regparam = regparam
self.svals = np.mat(self.svdad.svals)
self.svecs = self.svdad.rsvecs
self.size = self.Y.shape[0]
self.size = self.Y.shape[0]
self.qids = map_qids(qids)
self.qidlist = qids_to_splits(self.qids)
self.solve(self.regparam)
def __init__(self, X, Y, subsetsize, regparam = 1.0, bias=1.0, callbackfun=None, **kwargs):
self.callbackfun = callbackfun
self.regparam = regparam
if isinstance(X, sp.base.spmatrix):
self.X = X.todense()
else:
self.X = X
self.X = self.X.T
self.X = self.X.astype("float64", copy=False)
self.Y = np.mat(array_tools.as_2d_array(Y))
#Number of training examples
self.size = self.Y.shape[0]
self.bias = bias
self.measure = None
fsize = X.shape[1]
self.desiredfcount = subsetsize
if not fsize >= self.desiredfcount:
raise Exception('The overall number of features ' + str(fsize) + ' is smaller than the desired number ' + str(self.desiredfcount) + ' of features to be selected.')
self.results = {}
if 'use_default_callback' in kwargs and bool(kwargs['use_default_callback']):
self.callbackfun = DefaultCallback(**kwargs)
#The current version works only with the squared error measure
self._solve_cython(self.regparam)
def __init__(self,
X,
Y,
subsetsize,
regparam=1.0,
bias=1.0,
measure=None,
callbackfun=None,
**kwargs):
self.callbackfun = callbackfun
self.regparam = regparam
if isinstance(X, sp.base.spmatrix):
self.X = X.todense()
else:
self.X = X
self.X = self.X.T
self.Y = array_tools.as_2d_array(Y)
#Number of training examples
self.size = self.Y.shape[0]
#if not self.Y.shape[1] == 1:
# raise Exception('GreedyRLS currently supports only one output at a time. The output matrix is now of shape ' + str(self.Y.shape) + '.')
self.bias = bias
self.measure = measure
fsize = X.shape[1]
self.desiredfcount = subsetsize
if not fsize >= self.desiredfcount:
raise Exception('The overall number of features ' + str(fsize) +
' is smaller than the desired number ' +
str(self.desiredfcount) +
' of features to be selected.')
self.results = {}
##The current version works only with the squared error measure
#self.measure = None
#self.solve_bu(self.regparam)
#return
#if not self.Y.shape[1] == 1:
self.solve_weak(self.regparam)
def getKM(self, X):
"""Returns the kernel matrix between the basis vectors and X.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
Returns
-------
K : array, shape = [n_samples, n_bvectors]
kernel matrix
"""
X = array_tools.as_2d_array(X, True)
test_X = X
if sp.issparse(test_X):
test_X = array_tools.spmat_resize(test_X, self.train_X.shape[1])
else:
test_X = array_tools.as_dense_matrix(test_X)
train_X = self.train_X
K = train_X * test_X.T
K = array_tools.as_array(K)
if self.bias != 0:
K += self.bias
return K.T
def getKM(self, X):
"""Returns the kernel matrix between the basis vectors and X.
Parameters
----------
X : {array-like, sparse matrix}, shape = [n_samples, n_features]
Returns
-------
K : array, shape = [n_samples, n_bvectors]
kernel matrix
"""
X = array_tools.as_2d_array(X, True)
test_X = X
if sp.issparse(test_X):
test_X = array_tools.spmat_resize(test_X, self.train_X.shape[1])
else:
test_X = array_tools.as_dense_matrix(test_X)
train_X = self.train_X
K = train_X * test_X.T
K = array_tools.as_array(K)
if self.bias != 0:
K += self.bias
return K.T
def __init__(self, **kwargs):
Y = kwargs["Y"]
self.input1_inds = np.array(kwargs["label_row_inds"], dtype=np.int32)
self.input2_inds = np.array(kwargs["label_col_inds"], dtype=np.int32)
Y = array_tools.as_2d_array(Y)
self.Y = np.mat(Y)
self.trained = False
if "regparam" in kwargs:
self.regparam = kwargs["regparam"]
else:
self.regparam = 0.
if CALLBACK_FUNCTION in kwargs:
self.callbackfun = kwargs[CALLBACK_FUNCTION]
else:
self.callbackfun = None
if "compute_risk" in kwargs:
self.compute_risk = kwargs["compute_risk"]
else:
self.compute_risk = False
regparam = self.regparam
if 'K1' in kwargs:
K1 = kwargs['K1']
K2 = kwargs['K2']
if 'maxiter' in kwargs: maxiter = int(kwargs['maxiter'])
else: maxiter = None
Y = np.array(self.Y).ravel(order='F')
self.bestloss = float("inf")
def mv(v):
return sampled_kronecker_products.sampled_vec_trick(
v, K2, K1, self.input2_inds, self.input1_inds,
self.input2_inds, self.input1_inds) + regparam * v
def mv_mk(v):
vsum = regparam * v
for i in range(len(K1)):
K1i = K1[i]
K2i = K2[i]
inds2 = self.input2_inds[i]
inds1 = self.input1_inds[i]
vsum += weights[
i] * sampled_kronecker_products.sampled_vec_trick(
v, K2i, K1i, inds2, inds1, inds2, inds1)
return vsum
def mvr(v):
raise Exception('You should not be here!')
def cgcb(v):
if self.compute_risk:
P = sampled_kronecker_products.sampled_vec_trick(
v, K2, K1, self.input2_inds, self.input1_inds,
self.input2_inds, self.input1_inds)
z = (Y - P)
Ka = sampled_kronecker_products.sampled_vec_trick(
v, K2, K1, self.input2_inds, self.input1_inds,
self.input2_inds, self.input1_inds)
loss = (np.dot(z, z) + regparam * np.dot(v, Ka))
print("loss", 0.5 * loss)
if loss < self.bestloss:
self.A = v.copy()
self.bestloss = loss
else:
self.A = v
if not self.callbackfun is None:
self.predictor = KernelPairwisePredictor(
self.A, self.input1_inds, self.input2_inds)
self.callbackfun.callback(self)
if isinstance(K1, (list, tuple)):
if 'weights' in kwargs: weights = kwargs['weights']
else: weights = np.ones((len(K1)))
G = LinearOperator(
(len(self.input1_inds[0]), len(self.input1_inds[0])),
matvec=mv_mk,
rmatvec=mvr,
dtype=np.float64)
else:
weights = None
G = LinearOperator(
(len(self.input1_inds), len(self.input1_inds)),
matvec=mv,
rmatvec=mvr,
dtype=np.float64)
self.A = minres(G,
self.Y,
maxiter=maxiter,
callback=cgcb,
tol=1e-20)[0]
self.predictor = KernelPairwisePredictor(self.A, self.input1_inds,
self.input2_inds, weights)
else:
X1 = kwargs['X1']
X2 = kwargs['X2']
self.X1, self.X2 = X1, X2
if 'maxiter' in kwargs: maxiter = int(kwargs['maxiter'])
else: maxiter = None
if isinstance(X1, (list, tuple)):
raise NotImplementedError(
"Got list or tuple as X1 but multiple kernel learning has not been implemented for the proal case yet."
)
x1tsize, x1fsize = X1[0].shape #m, d
x2tsize, x2fsize = X2[0].shape #q, r
else:
x1tsize, x1fsize = X1.shape #m, d
x2tsize, x2fsize = X2.shape #q, r
kronfcount = x1fsize * x2fsize
Y = np.array(self.Y).ravel(order='F')
self.bestloss = float("inf")
def mv(v):
v_after = sampled_kronecker_products.sampled_vec_trick(
v, X2, X1, self.input2_inds, self.input1_inds)
v_after = sampled_kronecker_products.sampled_vec_trick(
v_after, X2.T, X1.T, None, None, self.input2_inds,
self.input1_inds) + regparam * v
return v_after
def mv_mk(v):
vsum = regparam * v
for i in range(len(X1)):
X1i = X1[i]
X2i = X2[i]
v_after = sampled_kronecker_products.sampled_vec_trick(
v, X2i, X1i, self.input2_inds, self.input1_inds)
v_after = sampled_kronecker_products.sampled_vec_trick(
v_after, X2i.T, X1i.T, None, None, self.input2_inds,
self.input1_inds)
vsum = vsum + v_after
return vsum
def mvr(v):
raise Exception('You should not be here!')
return None
def cgcb(v):
if self.compute_risk:
P = sampled_kronecker_products.sampled_vec_trick(
v, X2, X1, self.input2_inds, self.input1_inds)
z = (Y - P)
loss = (np.dot(z, z) + regparam * np.dot(v, v))
if loss < self.bestloss:
self.W = v.copy().reshape((x1fsize, x2fsize),
order='F')
self.bestloss = loss
else:
self.W = v.reshape((x1fsize, x2fsize), order='F')
if not self.callbackfun is None:
self.predictor = LinearPairwisePredictor(self.W)
self.callbackfun.callback(self)
if isinstance(X1, (list, tuple)):
G = LinearOperator((kronfcount, kronfcount),
matvec=mv_mk,
rmatvec=mvr,
dtype=np.float64)
vsum = np.zeros(kronfcount)
v_init = np.array(self.Y).reshape(self.Y.shape[0])
for i in range(len(X1)):
X1i = X1[i]
X2i = X2[i]
vsum += sampled_kronecker_products.sampled_vec_trick(
v_init, X2i.T, X1i.T, None, None, self.input2_inds,
self.input1_inds)
v_init = vsum
else:
G = LinearOperator((kronfcount, kronfcount),
matvec=mv,
rmatvec=mvr,
dtype=np.float64)
v_init = np.array(self.Y).reshape(self.Y.shape[0])
v_init = sampled_kronecker_products.sampled_vec_trick(
v_init, X2.T, X1.T, None, None, self.input2_inds,
self.input1_inds)
v_init = np.array(v_init).reshape(kronfcount)
if 'warm_start' in kwargs:
x0 = np.array(kwargs['warm_start']).reshape(kronfcount,
order='F')
else:
x0 = None
minres(G, v_init, x0=x0, maxiter=maxiter, callback=cgcb,
tol=1e-20)[0].reshape((x1fsize, x2fsize), order='F')
self.predictor = LinearPairwisePredictor(self.W)
if not self.callbackfun is None:
self.callbackfun.finished(self)
def __init__(self,
X,
Y,
regparam=1.0,
qids=None,
callbackfun=None,
**kwargs):
self.regparam = regparam
self.callbackfun = None
self.Y = array_tools.as_2d_array(Y)
#Number of training examples
self.size = Y.shape[0]
if self.Y.shape[1] > 1:
raise Exception(
'CGRankRLS does not currently work in multi-label mode')
self.learn_from_labels = True
self.callbackfun = callbackfun
self.X = csc_matrix(X.T)
if qids is not None:
self.qids = map_qids(qids)
self.splits = qids_to_splits(self.qids)
else:
self.qids = None
regparam = self.regparam
qids = self.qids
if qids is not None:
P = sp.lil_matrix((self.size, len(set(qids))))
for qidind in range(len(self.splits)):
inds = self.splits[qidind]
qsize = len(inds)
for i in inds:
P[i, qidind] = 1. / sqrt(qsize)
P = P.tocsr()
PT = P.tocsc().T
else:
P = 1. / sqrt(self.size) * (np.mat(
np.ones((self.size, 1), dtype=np.float64)))
PT = P.T
X = self.X.tocsc()
X_csr = X.tocsr()
def mv(v):
v = np.mat(v).T
return X_csr * (X.T * v) - X_csr * (P * (PT *
(X.T * v))) + regparam * v
G = LinearOperator((X.shape[0], X.shape[0]),
matvec=mv,
dtype=np.float64)
Y = self.Y
if not self.callbackfun is None:
def cb(v):
self.A = np.mat(v).T
self.b = np.mat(np.zeros((1, 1)))
self.callbackfun.callback(self)
else:
cb = None
XLY = X_csr * Y - X_csr * (P * (PT * Y))
try:
self.A = np.mat(cg(G, XLY, callback=cb)[0]).T
except Finished:
pass
self.b = np.mat(np.zeros((1, 1)))
self.predictor = predictor.LinearPredictor(self.A, self.b)
def __init__(self, **kwargs):
self.resource_pool = kwargs
Y = kwargs["Y"]
self.input1_inds = np.array(kwargs["label_row_inds"], dtype=np.int32)
self.input2_inds = np.array(kwargs["label_col_inds"], dtype=np.int32)
Y = array_tools.as_2d_array(Y)
self.Y = np.mat(Y)
self.trained = False
if kwargs.has_key("regparam"):
self.regparam = kwargs["regparam"]
else:
self.regparam = 0.0
if kwargs.has_key(CALLBACK_FUNCTION):
self.callbackfun = kwargs[CALLBACK_FUNCTION]
else:
self.callbackfun = None
if kwargs.has_key("compute_risk"):
self.compute_risk = kwargs["compute_risk"]
else:
self.compute_risk = False
regparam = self.regparam
if self.resource_pool.has_key("K1"):
K1 = self.resource_pool["K1"]
K2 = self.resource_pool["K2"]
if "maxiter" in self.resource_pool:
maxiter = int(self.resource_pool["maxiter"])
else:
maxiter = None
Y = np.array(self.Y).ravel(order="F")
self.bestloss = float("inf")
def mv(v):
return (
sampled_kronecker_products.sampled_vec_trick(
v, K2, K1, self.input2_inds, self.input1_inds, self.input2_inds, self.input1_inds
)
+ regparam * v
)
def mvr(v):
raise Exception("You should not be here!")
def cgcb(v):
if self.compute_risk:
P = sampled_kronecker_products.sampled_vec_trick(
v, K2, K1, self.input2_inds, self.input1_inds, self.input2_inds, self.input1_inds
)
z = Y - P
Ka = sampled_kronecker_products.sampled_vec_trick(
v, K2, K1, self.input2_inds, self.input1_inds, self.input2_inds, self.input1_inds
)
loss = np.dot(z, z) + regparam * np.dot(v, Ka)
print "loss", 0.5 * loss
if loss < self.bestloss:
self.A = v.copy()
self.bestloss = loss
else:
self.A = v
if not self.callbackfun is None:
self.predictor = KernelPairwisePredictor(self.A, self.input1_inds, self.input2_inds)
self.callbackfun.callback(self)
G = LinearOperator((len(self.input1_inds), len(self.input1_inds)), matvec=mv, rmatvec=mvr, dtype=np.float64)
self.A = minres(G, self.Y, maxiter=maxiter, callback=cgcb, tol=1e-20)[0]
self.predictor = KernelPairwisePredictor(self.A, self.input1_inds, self.input2_inds)
else:
X1 = self.resource_pool["X1"]
X2 = self.resource_pool["X2"]
self.X1, self.X2 = X1, X2
if "maxiter" in self.resource_pool:
maxiter = int(self.resource_pool["maxiter"])
else:
maxiter = None
x1tsize, x1fsize = X1.shape # m, d
x2tsize, x2fsize = X2.shape # q, r
kronfcount = x1fsize * x2fsize
Y = np.array(self.Y).ravel(order="F")
self.bestloss = float("inf")
def mv(v):
v_after = sampled_kronecker_products.sampled_vec_trick(v, X2, X1, self.input2_inds, self.input1_inds)
v_after = (
sampled_kronecker_products.sampled_vec_trick(
v_after, X2.T, X1.T, None, None, self.input2_inds, self.input1_inds
)
+ regparam * v
)
return v_after
def mvr(v):
raise Exception("You should not be here!")
return None
def cgcb(v):
if self.compute_risk:
P = sampled_kronecker_products.sampled_vec_trick(v, X2, X1, self.input2_inds, self.input1_inds)
z = Y - P
loss = np.dot(z, z) + regparam * np.dot(v, v)
if loss < self.bestloss:
self.W = v.copy().reshape((x1fsize, x2fsize), order="F")
self.bestloss = loss
else:
self.W = v.reshape((x1fsize, x2fsize), order="F")
if not self.callbackfun is None:
self.predictor = LinearPairwisePredictor(self.W)
self.callbackfun.callback(self)
G = LinearOperator((kronfcount, kronfcount), matvec=mv, rmatvec=mvr, dtype=np.float64)
v_init = np.array(self.Y).reshape(self.Y.shape[0])
v_init = sampled_kronecker_products.sampled_vec_trick(
v_init, X2.T, X1.T, None, None, self.input2_inds, self.input1_inds
)
v_init = np.array(v_init).reshape(kronfcount)
if self.resource_pool.has_key("warm_start"):
x0 = np.array(self.resource_pool["warm_start"]).reshape(kronfcount, order="F")
else:
x0 = None
minres(G, v_init, x0=x0, maxiter=maxiter, callback=cgcb, tol=1e-20)[0].reshape(
(x1fsize, x2fsize), order="F"
)
self.predictor = LinearPairwisePredictor(self.W)
if not self.callbackfun is None:
self.callbackfun.finished(self)
def __init__(self, **kwargs):
self.resource_pool = kwargs
Y = kwargs["Y"]
self.input1_inds = np.array(kwargs["label_row_inds"], dtype = np.int32)
self.input2_inds = np.array(kwargs["label_col_inds"], dtype = np.int32)
Y = array_tools.as_2d_array(Y)
self.Y = np.mat(Y)
self.trained = False
if kwargs.has_key("regparam"):
self.regparam = kwargs["regparam"]
else:
self.regparam = 0.
if kwargs.has_key(CALLBACK_FUNCTION):
self.callbackfun = kwargs[CALLBACK_FUNCTION]
else:
self.callbackfun = None
if kwargs.has_key("compute_risk"):
self.compute_risk = kwargs["compute_risk"]
else:
self.compute_risk = False
regparam = self.regparam
if self.resource_pool.has_key('K1'):
K1 = self.resource_pool['K1']
K2 = self.resource_pool['K2']
if 'maxiter' in self.resource_pool: maxiter = int(self.resource_pool['maxiter'])
else: maxiter = None
Y = np.array(self.Y).ravel(order = 'F')
self.bestloss = float("inf")
def mv(v):
return sampled_kronecker_products.sampled_vec_trick(v, K2, K1, self.input2_inds, self.input1_inds, self.input2_inds, self.input1_inds) + regparam * v
def mvr(v):
raise Exception('You should not be here!')
def cgcb(v):
if self.compute_risk:
P = sampled_kronecker_products.sampled_vec_trick(v, K2, K1, self.input2_inds, self.input1_inds, self.input2_inds, self.input1_inds)
z = (Y - P)
Ka = sampled_kronecker_products.sampled_vec_trick(v, K2, K1, self.input2_inds, self.input1_inds, self.input2_inds, self.input1_inds)
loss = (np.dot(z,z)+regparam*np.dot(v,Ka))
print "loss", 0.5*loss
if loss < self.bestloss:
self.A = v.copy()
self.bestloss = loss
else:
self.A = v
if not self.callbackfun == None:
self.predictor = KernelPairwisePredictor(self.A, self.input1_inds, self.input2_inds)
self.callbackfun.callback(self)
G = LinearOperator((len(self.input1_inds), len(self.input1_inds)), matvec = mv, rmatvec = mvr, dtype = np.float64)
minres(G, self.Y, maxiter = maxiter, callback = cgcb, tol=1e-20)[0]
self.predictor = KernelPairwisePredictor(self.A, self.input1_inds, self.input2_inds)
else:
X1 = self.resource_pool['X1']
X2 = self.resource_pool['X2']
self.X1, self.X2 = X1, X2
if 'maxiter' in self.resource_pool: maxiter = int(self.resource_pool['maxiter'])
else: maxiter = None
x1tsize, x1fsize = X1.shape #m, d
x2tsize, x2fsize = X2.shape #q, r
kronfcount = x1fsize * x2fsize
Y = np.array(self.Y).ravel(order = 'F')
self.bestloss = float("inf")
def mv(v):
#v_after = sampled_kronecker_products.x_gets_subset_of_A_kron_B_times_v(v, X1, X2.T, label_row_inds, label_col_inds)
v_after = sampled_kronecker_products.sampled_vec_trick(v, X2, X1, self.input2_inds, self.input1_inds)
#v_after = sampled_kronecker_products.x_gets_A_kron_B_times_sparse_v(v_after, X1.T, X2, label_row_inds, label_col_inds) + regparam * v
v_after = sampled_kronecker_products.sampled_vec_trick(v_after, X2.T, X1.T, None, None, self.input2_inds, self.input1_inds) + regparam * v
return v_after
def mvr(v):
raise Exception('You should not be here!')
return None
def cgcb(v):
#self.W = v.reshape((x1fsize, x2fsize), order = 'F')
if self.compute_risk:
#P = sampled_kronecker_products.x_gets_subset_of_A_kron_B_times_v(v, X1, X2.T, label_row_inds, label_col_inds)
P = sampled_kronecker_products.sampled_vec_trick(v, X2, X1, self.input2_inds, self.input1_inds)
z = (Y - P)
loss = (np.dot(z,z)+regparam*np.dot(v,v))
if loss < self.bestloss:
self.W = v.copy().reshape((x1fsize, x2fsize), order = 'F')
self.bestloss = loss
else:
self.W = v.reshape((x1fsize, x2fsize), order = 'F')
if not self.callbackfun == None:
self.predictor = LinearPairwisePredictor(self.W)
self.callbackfun.callback(self)
G = LinearOperator((kronfcount, kronfcount), matvec = mv, rmatvec = mvr, dtype = np.float64)
v_init = np.array(self.Y).reshape(self.Y.shape[0])
#v_init = sampled_kronecker_products.x_gets_A_kron_B_times_sparse_v(v_init, X1.T, X2, label_row_inds, label_col_inds)
v_init = sampled_kronecker_products.sampled_vec_trick(v_init, X2.T, X1.T, None, None, self.input2_inds, self.input1_inds)
v_init = np.array(v_init).reshape(kronfcount)
if self.resource_pool.has_key('warm_start'):
x0 = np.array(self.resource_pool['warm_start']).reshape(kronfcount, order = 'F')
else:
x0 = None
#self.W = bicgstab(G, v_init, x0 = x0, maxiter = maxiter, callback = cgcb)[0].reshape((x1fsize, x2fsize), order='F')
minres(G, v_init, x0 = x0, maxiter = maxiter, callback = cgcb, tol=1e-20)[0].reshape((x1fsize, x2fsize), order='F')
self.predictor = LinearPairwisePredictor(self.W)
if not self.callbackfun == None:
self.callbackfun.finished(self)
def __init__(self, X, bias=1.0):
X = array_tools.as_2d_array(X, True)
self.train_X = X
self.bias = bias
def __init__(self, X, degree=2, gamma=1.0, coef0=0):
X = array_tools.as_2d_array(X, True)
self.train_X = X
self.degree = degree
self.gamma = gamma
self.coef0 = coef0
def __init__(self, X, bias=1.0):
X = array_tools.as_2d_array(X, True)
self.train_X = X
self.bias = bias
