def _evaluate(indata):
prefix = 'distribution_'
# what is sg('likelihood')?
likelihood = abs(sg('hmm_likelihood') - indata[prefix + 'likelihood'])
return util.check_accuracy(indata[prefix + 'accuracy'],
likelihood=likelihood)
# best path? which? no_b_trans? trans? trans_deriv?
if indata['name'] == 'HMM':
best_path = 0
best_path_state = 0
for i in xrange(indata[prefix + 'num_examples']):
best_path += distribution.best_path(i)
for j in xrange(indata[prefix + 'N']):
best_path_state += distribution.get_best_path_state(i, j)
best_path = abs(best_path - indata[prefix + 'best_path'])
best_path_state=abs(best_path_state-\
indata[prefix+'best_path_state'])
return util.check_accuracy(indata[prefix + 'accuracy'],
derivatives=derivatives,
likelihood=likelihood,
best_path=best_path,
best_path_state=best_path_state)
else:
return util.check_accuracy(indata[prefix + 'accuracy'],
derivatives=derivatives,
likelihood=likelihood)
def _evaluate(indata):
if indata.has_key('clustering_k'):
first_arg = indata['clustering_k']
elif indata.has_key('clustering_merges'):
first_arg = indata['clustering_merges']
else:
return False
feats = util.get_features(indata, 'distance_')
dfun = eval(indata['distance_name'])
distance = dfun(feats['train'], feats['train'])
cfun = eval(indata['clustering_name'])
clustering = cfun(first_arg, distance)
clustering.train()
if indata.has_key('clustering_radi'):
radi = max(abs(clustering.get_radiuses() - indata['clustering_radi']))
centers=max(abs(clustering.get_cluster_centers().flatten() - \
indata['clustering_centers'].flat))
return util.check_accuracy(indata['clustering_accuracy'],
radi=radi,
centers=centers)
elif indata.has_key('clustering_merge_distance'):
merge_distance=max(abs(clustering.get_merge_distances()- \
indata['clustering_merge_distance']))
pairs=max(abs(clustering.get_cluster_pairs()- \
indata['clustering_pairs']).flat)
return util.check_accuracy(indata['clustering_accuracy'],
merge_distance=merge_distance,
pairs=pairs)
else:
return util.check_accuracy(indata['clustering_accuracy'])
def _evaluate (indata):
prefix='distribution_'
# what is sg('likelihood')?
likelihood=abs(sg('hmm_likelihood')-indata[prefix+'likelihood'])
return util.check_accuracy(indata[prefix+'accuracy'],
likelihood=likelihood)
# best path? which? no_b_trans? trans? trans_deriv?
if indata['name']=='HMM':
best_path=0
best_path_state=0
for i in xrange(indata[prefix+'num_examples']):
best_path+=distribution.best_path(i)
for j in xrange(indata[prefix+'N']):
best_path_state+=distribution.get_best_path_state(i, j)
best_path=abs(best_path-indata[prefix+'best_path'])
best_path_state=abs(best_path_state-\
indata[prefix+'best_path_state'])
return util.check_accuracy(indata[prefix+'accuracy'],
derivatives=derivatives, likelihood=likelihood,
best_path=best_path, best_path_state=best_path_state)
else:
return util.check_accuracy(indata[prefix+'accuracy'],
derivatives=derivatives, likelihood=likelihood)
def _evaluate (indata): if 'clustering_k' in indata: first_arg=indata['clustering_k'] elif 'clustering_merges' in indata: first_arg=indata['clustering_merges'] else: return False feats=util.get_features(indata, 'distance_') dfun=eval(indata['distance_name']) distance=dfun(feats['train'], feats['train']) cfun=eval(indata['clustering_name']) clustering=cfun(first_arg, distance) clustering.train() if 'clustering_radi' in indata: radi=max(abs(clustering.get_radiuses()-indata['clustering_radi'])) centers=max(abs(clustering.get_cluster_centers().flatten() - \ indata['clustering_centers'].flat)) return util.check_accuracy(indata['clustering_accuracy'], radi=radi, centers=centers) elif 'clustering_merge_distance' in indata: merge_distance=max(abs(clustering.get_merge_distances()- \ indata['clustering_merge_distance'])) pairs=max(abs(clustering.get_cluster_pairs()- \ indata['clustering_pairs']).flat) return util.check_accuracy(indata['clustering_accuracy'], merge_distance=merge_distance, pairs=pairs) else: return util.check_accuracy(indata['clustering_accuracy'])
def _evaluate(indata):
prefix = 'distribution_'
feats = util.get_features(indata, prefix)
if indata[prefix + 'name'] == 'HMM':
distribution = HMM(feats['train'], indata[prefix + 'N'],
indata[prefix + 'M'], indata[prefix + 'pseudo'])
distribution.train()
distribution.baum_welch_viterbi_train(BW_NORMAL)
else:
dfun = eval(indata[prefix + 'name'])
distribution = dfun(feats['train'])
distribution.train()
likelihood = distribution.get_log_likelihood_sample()
num_examples = feats['train'].get_num_vectors()
num_param = distribution.get_num_model_parameters()
derivatives = 0
for i in xrange(num_param):
for j in xrange(num_examples):
val = distribution.get_log_derivative(i, j)
if val != -inf and val != nan: # only consider sparse matrix!
derivatives += val
derivatives = abs(derivatives - indata[prefix + 'derivatives'])
likelihood = abs(likelihood - indata[prefix + 'likelihood'])
if indata[prefix + 'name'] == 'HMM':
best_path = 0
best_path_state = 0
for i in xrange(indata[prefix + 'num_examples']):
best_path += distribution.best_path(i)
for j in xrange(indata[prefix + 'N']):
best_path_state += distribution.get_best_path_state(i, j)
best_path = abs(best_path - indata[prefix + 'best_path'])
best_path_state=abs(best_path_state-\
indata[prefix+'best_path_state'])
return util.check_accuracy(indata[prefix + 'accuracy'],
derivatives=derivatives,
likelihood=likelihood,
best_path=best_path,
best_path_state=best_path_state)
else:
return util.check_accuracy(indata[prefix + 'accuracy'],
derivatives=derivatives,
likelihood=likelihood)
def _evaluate_custom(indata, prefix):
feats = {
'train': RealFeatures(indata[prefix + 'data']),
'test': RealFeatures(indata[prefix + 'data'])
}
symdata = indata[prefix + 'symdata']
lowertriangle = array([
symdata[(x, y)] for x in xrange(symdata.shape[1])
for y in xrange(symdata.shape[0]) if y <= x
])
kernel = CustomKernel()
kernel.set_triangle_kernel_matrix_from_triangle(lowertriangle)
triangletriangle = max(
abs(indata[prefix + 'matrix_triangletriangle'] -
kernel.get_kernel_matrix()).flat)
kernel.set_triangle_kernel_matrix_from_full(indata[prefix + 'symdata'])
fulltriangle = max(
abs(indata[prefix + 'matrix_fulltriangle'] -
kernel.get_kernel_matrix()).flat)
kernel.set_full_kernel_matrix_from_full(indata[prefix + 'data'])
fullfull = max(
abs(indata[prefix + 'matrix_fullfull'] -
kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix + 'accuracy'],
triangletriangle=triangletriangle,
fulltriangle=fulltriangle,
fullfull=fullfull)
def _evaluate_custom (indata, prefix):
raise NotImplementedError, 'Custom kernel not yet implemented in static interfaces.'
symdata=indata[prefix+'symdata']
lowertriangle=array([symdata[(x,y)] for x in xrange(symdata.shape[1])
for y in xrange(symdata.shape[0]) if y<=x])
sg('set_kernel', 'CUSTOM')
sg('set_triangle_kernel_matrix_from_triangle', lowertriangle)
triangletriangle=max(abs(
indata[prefix+'matrix_triangletriangle']-sg('get_kernel_matrix')).flat)
sg('set_triangle_kernel_matrix_from_full', indata[prefix+'symdata'])
fulltriangle=max(abs(
indata[prefix+'matrix_fulltriangle']-sg('get_kernel_matrix')).flat)
sg('set_full_kernel_matrix_from_full', indata[prefix+'data'])
fullfull=max(abs(
indata[prefix+'matrix_fullfull']-sg('get_kernel_matrix')).flat)
return util.check_accuracy(
indata[prefix+'accuracy'],
triangletriangle=triangletriangle,
fulltriangle=fulltriangle,
fullfull=fullfull
)
def _evaluate(indata):
prefix = 'kernel_'
feats = util.get_features(indata, prefix)
kargs = util.get_args(indata, prefix)
fun = eval(indata[prefix + 'name'] + 'Kernel')
kernel = fun(feats['train'], feats['train'], *kargs)
prefix = 'regression_'
kernel.parallel.set_num_threads(indata[prefix + 'num_threads'])
try:
name = indata[prefix + 'name']
if (name == 'KERNELRIDGEREGRESSION'):
name = 'KernelRidgeRegression'
rfun = eval(name)
except NameError as e:
print("%s is disabled/unavailable!" % indata[prefix + 'name'])
return False
labels = RegressionLabels(double(indata[prefix + 'labels']))
if indata[prefix + 'type'] == 'svm':
regression = rfun(indata[prefix + 'C'], indata[prefix + 'epsilon'],
kernel, labels)
elif indata[prefix + 'type'] == 'kernelmachine':
regression = rfun(indata[prefix + 'tau'], kernel, labels)
else:
return False
regression.parallel.set_num_threads(indata[prefix + 'num_threads'])
if prefix + 'tube_epsilon' in indata:
regression.set_tube_epsilon(indata[prefix + 'tube_epsilon'])
regression.train()
alphas = 0
bias = 0
sv = 0
if prefix + 'bias' in indata:
bias = abs(regression.get_bias() - indata[prefix + 'bias'])
if prefix + 'alphas' in indata:
for item in regression.get_alphas().tolist():
alphas += item
alphas = abs(alphas - indata[prefix + 'alphas'])
if prefix + 'support_vectors' in indata:
for item in inregression.get_support_vectors().tolist():
sv += item
sv = abs(sv - indata[prefix + 'support_vectors'])
kernel.init(feats['train'], feats['test'])
classified = max(
abs(regression.apply().get_labels() - indata[prefix + 'classified']))
return util.check_accuracy(indata[prefix + 'accuracy'],
alphas=alphas,
bias=bias,
support_vectors=sv,
classified=classified)
def _evaluate (indata): prefix='distribution_' feats=util.get_features(indata, prefix) if indata[prefix+'name']=='HMM': distribution=HMM(feats['train'], indata[prefix+'N'], indata[prefix+'M'], indata[prefix+'pseudo']) distribution.train() distribution.baum_welch_viterbi_train(BW_NORMAL) else: dfun=eval(indata[prefix+'name']) distribution=dfun(feats['train']) distribution.train() likelihood=distribution.get_log_likelihood_sample() num_examples=feats['train'].get_num_vectors() num_param=distribution.get_num_model_parameters() derivatives=0 for i in xrange(num_param): for j in xrange(num_examples): val=distribution.get_log_derivative(i, j) if val!=-inf and val!=nan: # only consider sparse matrix! derivatives+=val derivatives=abs(derivatives-indata[prefix+'derivatives']) likelihood=abs(likelihood-indata[prefix+'likelihood']) if indata[prefix+'name']=='HMM': best_path=0 best_path_state=0 for i in xrange(indata[prefix+'num_examples']): best_path+=distribution.best_path(i) for j in xrange(indata[prefix+'N']): best_path_state+=distribution.get_best_path_state(i, j) best_path=abs(best_path-indata[prefix+'best_path']) best_path_state=abs(best_path_state-\ indata[prefix+'best_path_state']) return util.check_accuracy(indata[prefix+'accuracy'], derivatives=derivatives, likelihood=likelihood, best_path=best_path, best_path_state=best_path_state) else: return util.check_accuracy(indata[prefix+'accuracy'], derivatives=derivatives, likelihood=likelihood)
def _evaluate (indata, prefix):
dmatrix=sg('get_distance_matrix', 'TRAIN')
dm_train=max(abs(indata['distance_matrix_train']-dmatrix).flat)
dmatrix=sg('get_distance_matrix', 'TEST')
dm_test=max(abs(indata['distance_matrix_test']-dmatrix).flat)
return util.check_accuracy(
indata[prefix+'accuracy'], dm_train=dm_train, dm_test=dm_test)
def _evaluate (indata):
prefix='kernel_'
feats=util.get_features(indata, prefix)
kargs=util.get_args(indata, prefix)
fun=eval(indata[prefix+'name']+'Kernel')
kernel=fun(feats['train'], feats['train'], *kargs)
prefix='regression_'
kernel.parallel.set_num_threads(indata[prefix+'num_threads'])
try:
name = indata[prefix+'name']
if (name=='KERNELRIDGEREGRESSION'):
name = 'KernelRidgeRegression'
rfun=eval(name)
except NameError as e:
print("%s is disabled/unavailable!"%indata[prefix+'name'])
return False
labels=RegressionLabels(double(indata[prefix+'labels']))
if indata[prefix+'type']=='svm':
regression=rfun(
indata[prefix+'C'], indata[prefix+'epsilon'], kernel, labels)
elif indata[prefix+'type']=='kernelmachine':
regression=rfun(indata[prefix+'tau'], kernel, labels)
else:
return False
regression.parallel.set_num_threads(indata[prefix+'num_threads'])
if prefix+'tube_epsilon' in indata:
regression.set_tube_epsilon(indata[prefix+'tube_epsilon'])
regression.train()
alphas=0
bias=0
sv=0
if prefix+'bias' in indata:
bias=abs(regression.get_bias()-indata[prefix+'bias'])
if prefix+'alphas' in indata:
for item in regression.get_alphas().tolist():
alphas+=item
alphas=abs(alphas-indata[prefix+'alphas'])
if prefix+'support_vectors' in indata:
for item in inregression.get_support_vectors().tolist():
sv+=item
sv=abs(sv-indata[prefix+'support_vectors'])
kernel.init(feats['train'], feats['test'])
classified=max(abs(
regression.apply().get_labels()-indata[prefix+'classified']))
return util.check_accuracy(indata[prefix+'accuracy'], alphas=alphas,
bias=bias, support_vectors=sv, classified=classified)
def _evaluate (indata, prefix):
if indata.has_key(prefix+'radi'):
[radi, centers]=sg('get_clustering')
radi=max(abs(radi.T[0]-indata[prefix+'radi']))
centers=max(abs(centers-indata[prefix+'centers']).flat)
return util.check_accuracy(indata[prefix+'accuracy'],
radi=radi, centers=centers)
elif indata.has_key(prefix+'merge_distance'):
[merge_distances, pairs]=sg('get_clustering')
merge_distances=max(abs(merge_distances.T[0]- \
indata[prefix+'merge_distance']))
pairs=max(abs(pairs-indata[prefix+'pairs']).flat)
return util.check_accuracy(indata[prefix+'accuracy'],
merge_distances=merge_distances, pairs=pairs)
else:
raise StandardError, 'Incomplete clustering data.'
def _evaluate (indata, prefix):
util.set_and_train_kernel(indata)
kmatrix=sg('get_kernel_matrix', 'TRAIN')
km_train=max(abs(indata['kernel_matrix_train']-kmatrix).flat)
kmatrix=sg('get_kernel_matrix', 'TEST')
km_test=max(abs(indata['kernel_matrix_test']-kmatrix).flat)
return util.check_accuracy(
indata[prefix+'accuracy'], km_train=km_train, km_test=km_test)
def _evaluate(indata, prefix):
if indata.has_key(prefix + 'radi'):
[radi, centers] = sg('get_clustering')
radi = max(abs(radi.T[0] - indata[prefix + 'radi']))
centers = max(abs(centers - indata[prefix + 'centers']).flat)
return util.check_accuracy(indata[prefix + 'accuracy'],
radi=radi,
centers=centers)
elif indata.has_key(prefix + 'merge_distance'):
[merge_distances, pairs] = sg('get_clustering')
merge_distances=max(abs(merge_distances.T[0]- \
indata[prefix+'merge_distance']))
pairs = max(abs(pairs - indata[prefix + 'pairs']).flat)
return util.check_accuracy(indata[prefix + 'accuracy'],
merge_distances=merge_distances,
pairs=pairs)
else:
raise StandardError, 'Incomplete clustering data.'
def _evaluate (indata): prefix='distance_' feats=util.get_features(indata, prefix) dfun=eval(indata[prefix+'name']) dargs=util.get_args(indata, prefix) distance=dfun(feats['train'], feats['train'], *dargs) dm_train=max(abs( indata[prefix+'matrix_train']-distance.get_distance_matrix()).flat) distance.init(feats['train'], feats['test']) dm_test=max(abs( indata[prefix+'matrix_test']-distance.get_distance_matrix()).flat) return util.check_accuracy( indata[prefix+'accuracy'], dm_train=dm_train, dm_test=dm_test)
def _evaluate(indata):
prefix = "kernel_"
feats = util.get_features(indata, prefix)
kfun = eval(indata[prefix + "name"] + "Kernel")
kargs = util.get_args(indata, prefix)
prefix = "preproc_"
pargs = util.get_args(indata, prefix)
feats = util.add_preproc(indata[prefix + "name"], feats, *pargs)
prefix = "kernel_"
kernel = kfun(feats["train"], feats["train"], *kargs)
km_train = max(abs(indata[prefix + "matrix_train"] - kernel.get_kernel_matrix()).flat)
kernel.init(feats["train"], feats["test"])
km_test = max(abs(indata[prefix + "matrix_test"] - kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix + "accuracy"], km_train=km_train, km_test=km_test)
def _evaluate (indata, prefix): feats=util.get_features(indata, prefix) kfun=eval(indata[prefix+'name']+'Kernel') kargs=util.get_args(indata, prefix) kernel=kfun(*kargs) if indata.has_key(prefix+'normalizer'): kernel.set_normalizer(eval(indata[prefix+'normalizer']+'()')) kernel.init(feats['train'], feats['train']) km_train=max(abs( indata[prefix+'matrix_train']-kernel.get_kernel_matrix()).flat) kernel.init(feats['train'], feats['test']) km_test=max(abs( indata[prefix+'matrix_test']-kernel.get_kernel_matrix()).flat) return util.check_accuracy( indata[prefix+'accuracy'], km_train=km_train, km_test=km_test)
def _evaluate(indata, prefix):
feats = util.get_features(indata, prefix)
kfun = eval(indata[prefix + 'name'] + 'Kernel')
kargs = util.get_args(indata, prefix)
kernel = kfun(*kargs)
if indata.has_key(prefix + 'normalizer'):
kernel.set_normalizer(eval(indata[prefix + 'normalizer'] + '()'))
kernel.init(feats['train'], feats['train'])
km_train = max(
abs(indata[prefix + 'matrix_train'] - kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
km_test = max(
abs(indata[prefix + 'matrix_test'] - kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix + 'accuracy'],
km_train=km_train,
km_test=km_test)
def _evaluate(indata):
prefix = 'distance_'
feats = util.get_features(indata, prefix)
dfun = eval(indata[prefix + 'name'])
dargs = util.get_args(indata, prefix)
distance = dfun(feats['train'], feats['train'], *dargs)
dm_train = max(
abs(indata[prefix + 'matrix_train'] -
distance.get_distance_matrix()).flat)
distance.init(feats['train'], feats['test'])
dm_test = max(
abs(indata[prefix + 'matrix_test'] -
distance.get_distance_matrix()).flat)
return util.check_accuracy(indata[prefix + 'accuracy'],
dm_train=dm_train,
dm_test=dm_test)
def _evaluate (indata): prefix='kernel_' feats=util.get_features(indata, prefix) kfun=eval(indata[prefix+'name']+'Kernel') kargs=util.get_args(indata, prefix) prefix='preprocessor_' pargs=util.get_args(indata, prefix) feats=util.add_preprocessor(indata[prefix+'name'], feats, *pargs) prefix='kernel_' kernel=kfun(feats['train'], feats['train'], *kargs) km_train=max(abs( indata[prefix+'matrix_train']-kernel.get_kernel_matrix()).flat) kernel.init(feats['train'], feats['test']) km_test=max(abs( indata[prefix+'matrix_test']-kernel.get_kernel_matrix()).flat) return util.check_accuracy( indata[prefix+'accuracy'], km_train=km_train, km_test=km_test)
def _evaluate (indata):
alphas=0
bias=0
sv=0
if indata.has_key('regression_bias'):
[bias, weights]=sg('get_svm')
weights=weights.T
bias=abs(bias-indata['regression_bias'])
for item in weights[0].tolist():
alphas+=item
alphas=abs(alphas-indata['regression_alpha_sum'])
for item in weights[1].tolist():
sv+=item
sv=abs(sv-indata['regression_sv_sum'])
classified=max(abs(sg('classify')-indata['regression_classified']))
return util.check_accuracy(indata['regression_accuracy'],
alphas=alphas, bias=bias, support_vectors=sv, classified=classified)
def _evaluate_auc (indata, prefix):
subk=_get_subkernels(indata, prefix)['0']
feats_subk=util.get_features(subk, '')
subk['kernel'].init(feats_subk['train'], feats_subk['test'])
feats={
'train': WordFeatures(indata[prefix+'data_train'].astype(ushort)),
'test': WordFeatures(indata[prefix+'data_test'].astype(ushort))
}
kernel=AUCKernel(10, subk['kernel'])
kernel.init(feats['train'], feats['train'])
km_train=max(abs(
indata[prefix+'matrix_train']-kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
km_test=max(abs(
indata[prefix+'matrix_test']-kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix+'accuracy'],
km_train=km_train, km_test=km_test)
def _evaluate_combined (indata, prefix):
kernel=CombinedKernel()
feats={'train':CombinedFeatures(), 'test':CombinedFeatures()}
subkernels=_get_subkernels(indata, prefix)
for subk in subkernels.itervalues():
feats_subk=util.get_features(subk, '')
feats['train'].append_feature_obj(feats_subk['train'])
feats['test'].append_feature_obj(feats_subk['test'])
kernel.append_kernel(subk['kernel'])
kernel.init(feats['train'], feats['train'])
km_train=max(abs(
indata['kernel_matrix_train']-kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
km_test=max(abs(
indata['kernel_matrix_test']-kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix+'accuracy'],
km_train=km_train, km_test=km_test)
def _evaluate_top_fisher(indata, prefix):
feats = {}
wordfeats = util.get_features(indata, prefix)
pos_train = HMM(wordfeats['train'], indata[prefix + 'N'],
indata[prefix + 'M'], indata[prefix + 'pseudo'])
pos_train.train()
pos_train.baum_welch_viterbi_train(BW_NORMAL)
neg_train = HMM(wordfeats['train'], indata[prefix + 'N'],
indata[prefix + 'M'], indata[prefix + 'pseudo'])
neg_train.train()
neg_train.baum_welch_viterbi_train(BW_NORMAL)
pos_test = HMM(pos_train)
pos_test.set_observations(wordfeats['test'])
neg_test = HMM(neg_train)
neg_test.set_observations(wordfeats['test'])
if indata[prefix + 'name'] == 'TOP':
feats['train'] = TOPFeatures(10, pos_train, neg_train, False, False)
feats['test'] = TOPFeatures(10, pos_test, neg_test, False, False)
else:
feats['train'] = FKFeatures(10, pos_train, neg_train)
feats['train'].set_opt_a(-1) #estimate prior
feats['test'] = FKFeatures(10, pos_test, neg_test)
feats['test'].set_a(
feats['train'].get_a()) #use prior from training data
prefix = 'kernel_'
args = util.get_args(indata, prefix)
kernel = PolyKernel(feats['train'], feats['train'], *args)
# kernel=PolyKernel(*args)
# kernel.init(feats['train'], feats['train'])
km_train = max(
abs(indata[prefix + 'matrix_train'] - kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
km_test = max(
abs(indata[prefix + 'matrix_test'] - kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix + 'accuracy'],
km_train=km_train,
km_test=km_test)
def _evaluate_auc(indata, prefix):
subk = _get_subkernels(indata, prefix)['0']
feats_subk = util.get_features(subk, '')
subk['kernel'].init(feats_subk['train'], feats_subk['test'])
feats = {
'train': WordFeatures(indata[prefix + 'data_train'].astype(ushort)),
'test': WordFeatures(indata[prefix + 'data_test'].astype(ushort))
}
kernel = AUCKernel(10, subk['kernel'])
kernel.init(feats['train'], feats['train'])
km_train = max(
abs(indata[prefix + 'matrix_train'] - kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
km_test = max(
abs(indata[prefix + 'matrix_test'] - kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix + 'accuracy'],
km_train=km_train,
km_test=km_test)
def _evaluate(indata):
prefix = 'kernel_'
feats = util.get_features(indata, prefix)
kfun = eval(indata[prefix + 'name'] + 'Kernel')
kargs = util.get_args(indata, prefix)
prefix = 'preproc_'
pargs = util.get_args(indata, prefix)
feats = util.add_preproc(indata[prefix + 'name'], feats, *pargs)
prefix = 'kernel_'
kernel = kfun(feats['train'], feats['train'], *kargs)
km_train = max(
abs(indata[prefix + 'matrix_train'] - kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
km_test = max(
abs(indata[prefix + 'matrix_test'] - kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix + 'accuracy'],
km_train=km_train,
km_test=km_test)
def _evaluate_combined(indata, prefix):
kernel = CombinedKernel()
feats = {'train': CombinedFeatures(), 'test': CombinedFeatures()}
subkernels = _get_subkernels(indata, prefix)
for subk in subkernels.itervalues():
feats_subk = util.get_features(subk, '')
feats['train'].append_feature_obj(feats_subk['train'])
feats['test'].append_feature_obj(feats_subk['test'])
kernel.append_kernel(subk['kernel'])
kernel.init(feats['train'], feats['train'])
km_train = max(
abs(indata['kernel_matrix_train'] - kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
km_test = max(
abs(indata['kernel_matrix_test'] - kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix + 'accuracy'],
km_train=km_train,
km_test=km_test)
def _evaluate (indata, prefix):
alphas=0
bias=0
sv=0
if indata[prefix+'type']=='lda':
pass
else:
if indata.has_key(prefix+'label_type') and \
indata[prefix+'label_type'] != 'series' and \
indata.has_key(prefix+'bias'):
[b, weights]=sg('get_svm')
weights=weights.T
bias=abs(b-indata[prefix+'bias'])
alphas, sv=_get_alpha_and_sv(indata, prefix)
classified=max(abs(sg('classify')-indata[prefix+'classified']))
return util.check_accuracy(indata[prefix+'accuracy'],
alphas=alphas, bias=bias, support_vectors=sv, classified=classified)
def _evaluate_top_fisher (indata, prefix):
feats={}
wordfeats=util.get_features(indata, prefix)
pos_train=HMM(wordfeats['train'], indata[prefix+'N'], indata[prefix+'M'],
indata[prefix+'pseudo'])
pos_train.train()
pos_train.baum_welch_viterbi_train(BW_NORMAL)
neg_train=HMM(wordfeats['train'], indata[prefix+'N'], indata[prefix+'M'],
indata[prefix+'pseudo'])
neg_train.train()
neg_train.baum_welch_viterbi_train(BW_NORMAL)
pos_test=HMM(pos_train)
pos_test.set_observations(wordfeats['test'])
neg_test=HMM(neg_train)
neg_test.set_observations(wordfeats['test'])
if indata[prefix+'name']=='TOP':
feats['train']=TOPFeatures(10, pos_train, neg_train, False, False)
feats['test']=TOPFeatures(10, pos_test, neg_test, False, False)
else:
feats['train']=FKFeatures(10, pos_train, neg_train)
feats['train'].set_opt_a(-1) #estimate prior
feats['test']=FKFeatures(10, pos_test, neg_test)
feats['test'].set_a(feats['train'].get_a()) #use prior from training data
prefix='kernel_'
args=util.get_args(indata, prefix)
kernel=PolyKernel(feats['train'], feats['train'], *args)
# kernel=PolyKernel(*args)
# kernel.init(feats['train'], feats['train'])
km_train=max(abs(
indata[prefix+'matrix_train']-kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
km_test=max(abs(
indata[prefix+'matrix_test']-kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix+'accuracy'],
km_train=km_train, km_test=km_test)
def _evaluate_pie (indata, prefix): pie=PluginEstimate() feats=util.get_features(indata, prefix) labels=BinaryLabels(double(indata['classifier_labels'])) pie.set_labels(labels) pie.set_features(feats['train']) pie.train() fun=eval(indata[prefix+'name']+'Kernel') kernel=fun(feats['train'], feats['train'], pie) km_train=max(abs( indata[prefix+'matrix_train']-kernel.get_kernel_matrix()).flat) kernel.init(feats['train'], feats['test']) pie.set_features(feats['test']) km_test=max(abs( indata[prefix+'matrix_test']-kernel.get_kernel_matrix()).flat) classified=max(abs( pie.apply().get_values()-indata['classifier_classified'])) return util.check_accuracy(indata[prefix+'accuracy'], km_train=km_train, km_test=km_test, classified=classified)
def _evaluate(indata):
alphas = 0
bias = 0
sv = 0
if indata.has_key('regression_bias'):
[bias, weights] = sg('get_svm')
weights = weights.T
bias = abs(bias - indata['regression_bias'])
for item in weights[0].tolist():
alphas += item
alphas = abs(alphas - indata['regression_alpha_sum'])
for item in weights[1].tolist():
sv += item
sv = abs(sv - indata['regression_sv_sum'])
classified = max(abs(sg('classify') - indata['regression_classified']))
return util.check_accuracy(indata['regression_accuracy'],
alphas=alphas,
bias=bias,
support_vectors=sv,
classified=classified)
def _evaluate_custom (indata, prefix):
feats={
'train': RealFeatures(indata[prefix+'data']),
'test': RealFeatures(indata[prefix+'data'])
}
symdata=indata[prefix+'symdata']
lowertriangle=array([symdata[(x,y)] for x in xrange(symdata.shape[1])
for y in xrange(symdata.shape[0]) if y<=x])
kernel=CustomKernel()
kernel.set_triangle_kernel_matrix_from_triangle(lowertriangle)
triangletriangle=max(abs(
indata[prefix+'matrix_triangletriangle']-kernel.get_kernel_matrix()).flat)
kernel.set_triangle_kernel_matrix_from_full(indata[prefix+'symdata'])
fulltriangle=max(abs(
indata[prefix+'matrix_fulltriangle']-kernel.get_kernel_matrix()).flat)
kernel.set_full_kernel_matrix_from_full(indata[prefix+'data'])
fullfull=max(abs(
indata[prefix+'matrix_fullfull']-kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix+'accuracy'],
triangletriangle=triangletriangle, fulltriangle=fulltriangle,
fullfull=fullfull)
def _evaluate_top_fisher (indata, prefix):
raise NotImplementedError, 'TOP/Fisher not yet supported in static interfaces.'
sg('new_hmm', indata[prefix+'N'], indata[prefix+'M'])
pos=HMM(wordfeats['train'], indata[prefix+'N'], indata[prefix+'M'],
indata[prefix+'pseudo'])
pos.train()
pos.baum_welch_viterbi_train(BW_NORMAL)
neg=HMM(wordfeats['train'], indata[prefix+'N'], indata[prefix+'M'],
indata[prefix+'pseudo'])
neg.train()
neg.baum_welch_viterbi_train(BW_NORMAL)
pos_clone=HMM(pos)
neg_clone=HMM(neg)
pos_clone.set_observations(wordfeats['test'])
neg_clone.set_observations(wordfeats['test'])
if indata[prefix+'type']=='TOP':
feats['train']=TOPFeatures(10, pos, neg, False, False)
feats['test']=TOPFeatures(10, pos_clone, neg_clone, False, False)
else:
feats['train']=FKFeatures(10, pos, neg)
feats['train'].set_opt_a(-1) #estimate prior
feats['test']=FKFeatures(10, pos_clone, neg_clone)
feats['test'].set_a(feats['train'].get_a()) #use prior from training data
prefix='kernel_'
args=util.get_args(indata, prefix)
kernel=PolyKernel(feats['train'], feats['train'], *args)
km_train=max(abs(
indata[prefix+'matrix_train']-kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
km_test=max(abs(
indata[prefix+'matrix_test']-kernel.get_kernel_matrix()).flat)
return util.check_accuracy(indata[prefix+'accuracy'],
km_train=km_train, km_test=km_test)
def _evaluate_pie(indata, prefix):
pie = PluginEstimate()
feats = util.get_features(indata, prefix)
labels = BinaryLabels(double(indata['classifier_labels']))
pie.set_labels(labels)
pie.set_features(feats['train'])
pie.train()
fun = eval(indata[prefix + 'name'] + 'Kernel')
kernel = fun(feats['train'], feats['train'], pie)
km_train = max(
abs(indata[prefix + 'matrix_train'] - kernel.get_kernel_matrix()).flat)
kernel.init(feats['train'], feats['test'])
pie.set_features(feats['test'])
km_test = max(
abs(indata[prefix + 'matrix_test'] - kernel.get_kernel_matrix()).flat)
classified = max(
abs(pie.apply().get_confidences() - indata['classifier_classified']))
return util.check_accuracy(indata[prefix + 'accuracy'],
km_train=km_train,
km_test=km_test,
classified=classified)
alphas = 0
bias = 0
sv = 0
if indata.has_key(prefix + "bias"):
bias = abs(regression.get_bias() - indata[prefix + "bias"])
if indata.has_key(prefix + "alphas"):
for item in regression.get_alphas().tolist():
alphas += item
alphas = abs(alphas - indata[prefix + "alphas"])
if indata.has_key(prefix + "support_vectors"):
for item in inregression.get_support_vectors().tolist():
sv += item
sv = abs(sv - indata[prefix + "support_vectors"])
kernel.init(feats["train"], feats["test"])
classified = max(abs(regression.apply().get_labels() - indata[prefix + "classified"]))
return util.check_accuracy(
indata[prefix + "accuracy"], alphas=alphas, bias=bias, support_vectors=sv, classified=classified
)
########################################################################
# public
########################################################################
def test(indata):
return _evaluate(indata)
def _evaluate (indata):
prefix='classifier_'
ctype=indata[prefix+'type']
if indata[prefix+'name']=='KNN':
feats=util.get_features(indata, 'distance_')
elif ctype=='kernel':
feats=util.get_features(indata, 'kernel_')
else:
feats=util.get_features(indata, prefix)
machine=_get_machine(indata, prefix, feats)
try:
fun=eval(indata[prefix+'name'])
except NameError as e:
print("%s is disabled/unavailable!"%indata[prefix+'name'])
return False
# cannot refactor into function, because labels is unrefed otherwise
if prefix+'labels' in indata:
labels=BinaryLabels(double(indata[prefix+'labels']))
if ctype=='kernel':
classifier=fun(indata[prefix+'C'], machine, labels)
elif ctype=='linear':
classifier=fun(indata[prefix+'C'], feats['train'], labels)
elif ctype=='knn':
classifier=fun(indata[prefix+'k'], machine, labels)
elif ctype=='lda':
classifier=fun(indata[prefix+'gamma'], feats['train'], labels)
elif ctype=='perceptron':
classifier=fun(feats['train'], labels)
elif ctype=='wdsvmocas':
classifier=fun(indata[prefix+'C'], indata[prefix+'degree'],
indata[prefix+'degree'], feats['train'], labels)
else:
return False
else:
classifier=fun(indata[prefix+'C'], machine)
if classifier.get_name() == 'LibLinear':
print(classifier.get_name(), "yes")
classifier.set_liblinear_solver_type(L2R_LR)
classifier.parallel.set_num_threads(indata[prefix+'num_threads'])
if ctype=='linear':
if prefix+'bias' in indata:
classifier.set_bias_enabled(True)
else:
classifier.set_bias_enabled(False)
if ctype=='perceptron':
classifier.set_learn_rate=indata[prefix+'learn_rate']
classifier.set_max_iter=indata[prefix+'max_iter']
if prefix+'epsilon' in indata:
try:
classifier.set_epsilon(indata[prefix+'epsilon'])
except AttributeError:
pass
if prefix+'max_train_time' in indata:
classifier.set_max_train_time(indata[prefix+'max_train_time'])
if prefix+'linadd_enabled' in indata:
classifier.set_linadd_enabled(indata[prefix+'linadd_enabled'])
if prefix+'batch_enabled' in indata:
classifier.set_batch_computation_enabled(indata[prefix+'batch_enabled'])
classifier.train()
res=_get_results(indata, prefix, classifier, machine, feats)
return util.check_accuracy(res['accuracy'],
alphas=res['alphas'], bias=res['bias'], sv=res['sv'],
classified=res['classified'])
if ctype=='perceptron': classifier.set_learn_rate=indata[prefix+'learn_rate'] classifier.set_max_iter=indata[prefix+'max_iter'] if indata.has_key(prefix+'epsilon'): try: classifier.set_epsilon(indata[prefix+'epsilon']) except AttributeError: pass if indata.has_key(prefix+'max_train_time'): classifier.set_max_train_time(indata[prefix+'max_train_time']) if indata.has_key(prefix+'linadd_enabled'): classifier.set_linadd_enabled(indata[prefix+'linadd_enabled']) if indata.has_key(prefix+'batch_enabled'): classifier.set_batch_computation_enabled(indata[prefix+'batch_enabled']) classifier.train() res=_get_results(indata, prefix, classifier, machine, feats) return util.check_accuracy(res['accuracy'], alphas=res['alphas'], bias=res['bias'], sv=res['sv'], classified=res['classified']) ######################################################################## # public ######################################################################## def test (indata): return _evaluate(indata)
if indata.has_key(prefix + 'epsilon'):
try:
classifier.set_epsilon(indata[prefix + 'epsilon'])
except AttributeError:
pass
if indata.has_key(prefix + 'max_train_time'):
classifier.set_max_train_time(indata[prefix + 'max_train_time'])
if indata.has_key(prefix + 'linadd_enabled'):
classifier.set_linadd_enabled(indata[prefix + 'linadd_enabled'])
if indata.has_key(prefix + 'batch_enabled'):
classifier.set_batch_computation_enabled(indata[prefix +
'batch_enabled'])
classifier.train()
res = _get_results(indata, prefix, classifier, machine, feats)
return util.check_accuracy(res['accuracy'],
alphas=res['alphas'],
bias=res['bias'],
sv=res['sv'],
classified=res['classified'])
########################################################################
# public
########################################################################
def test(indata):
return _evaluate(indata)
if ctype == "perceptron":
classifier.set_learn_rate = indata[prefix + "learn_rate"]
classifier.set_max_iter = indata[prefix + "max_iter"]
if indata.has_key(prefix + "epsilon"):
try:
classifier.set_epsilon(indata[prefix + "epsilon"])
except AttributeError:
pass
if indata.has_key(prefix + "max_train_time"):
classifier.set_max_train_time(indata[prefix + "max_train_time"])
if indata.has_key(prefix + "linadd_enabled"):
classifier.set_linadd_enabled(indata[prefix + "linadd_enabled"])
if indata.has_key(prefix + "batch_enabled"):
classifier.set_batch_computation_enabled(indata[prefix + "batch_enabled"])
classifier.train()
res = _get_results(indata, prefix, classifier, machine, feats)
return util.check_accuracy(
res["accuracy"], alphas=res["alphas"], bias=res["bias"], sv=res["sv"], classified=res["classified"]
)
########################################################################
# public
########################################################################
def test(indata):
return _evaluate(indata)
sv = 0
if indata.has_key(prefix + 'bias'):
bias = abs(regression.get_bias() - indata[prefix + 'bias'])
if indata.has_key(prefix + 'alphas'):
for item in regression.get_alphas().tolist():
alphas += item
alphas = abs(alphas - indata[prefix + 'alphas'])
if indata.has_key(prefix + 'support_vectors'):
for item in inregression.get_support_vectors().tolist():
sv += item
sv = abs(sv - indata[prefix + 'support_vectors'])
kernel.init(feats['train'], feats['test'])
classified = max(
abs(regression.apply().get_labels() - indata[prefix + 'classified']))
return util.check_accuracy(indata[prefix + 'accuracy'],
alphas=alphas,
bias=bias,
support_vectors=sv,
classified=classified)
########################################################################
# public
########################################################################
def test(indata):
return _evaluate(indata)
def _evaluate(indata):
prefix = 'classifier_'
ctype = indata[prefix + 'type']
if indata[prefix + 'name'] == 'KNN':
feats = util.get_features(indata, 'distance_')
elif ctype == 'kernel':
feats = util.get_features(indata, 'kernel_')
else:
feats = util.get_features(indata, prefix)
machine = _get_machine(indata, prefix, feats)
try:
fun = eval(indata[prefix + 'name'])
except NameError as e:
print("%s is disabled/unavailable!" % indata[prefix + 'name'])
return False
# cannot refactor into function, because labels is unrefed otherwise
if prefix + 'labels' in indata:
labels = BinaryLabels(double(indata[prefix + 'labels']))
if ctype == 'kernel':
classifier = fun(indata[prefix + 'C'], machine, labels)
elif ctype == 'linear':
classifier = fun(indata[prefix + 'C'], feats['train'], labels)
elif ctype == 'knn':
classifier = fun(indata[prefix + 'k'], machine, labels)
elif ctype == 'lda':
classifier = fun(indata[prefix + 'gamma'], feats['train'], labels)
elif ctype == 'perceptron':
classifier = fun(feats['train'], labels)
elif ctype == 'wdsvmocas':
classifier = fun(indata[prefix + 'C'], indata[prefix + 'degree'],
indata[prefix + 'degree'], feats['train'], labels)
else:
return False
else:
classifier = fun(indata[prefix + 'C'], machine)
if classifier.get_name() == 'LibLinear':
print(classifier.get_name(), "yes")
classifier.set_liblinear_solver_type(L2R_LR)
classifier.parallel.set_num_threads(indata[prefix + 'num_threads'])
if ctype == 'linear':
if prefix + 'bias' in indata:
classifier.set_bias_enabled(True)
else:
classifier.set_bias_enabled(False)
if ctype == 'perceptron':
classifier.set_learn_rate = indata[prefix + 'learn_rate']
classifier.set_max_iter = indata[prefix + 'max_iter']
if prefix + 'epsilon' in indata:
try:
classifier.set_epsilon(indata[prefix + 'epsilon'])
except AttributeError:
pass
if prefix + 'max_train_time' in indata:
classifier.set_max_train_time(indata[prefix + 'max_train_time'])
if prefix + 'linadd_enabled' in indata:
classifier.set_linadd_enabled(indata[prefix + 'linadd_enabled'])
if prefix + 'batch_enabled' in indata:
classifier.set_batch_computation_enabled(indata[prefix +
'batch_enabled'])
classifier.train()
res = _get_results(indata, prefix, classifier, machine, feats)
return util.check_accuracy(res['accuracy'],
alphas=res['alphas'],
bias=res['bias'],
sv=res['sv'],
classified=res['classified'])