def svm_train_test(input_arg):
label_weights = None
best = input_arg[1]
testset = input_arg[0]
output_probabilities = True # Or False!
try:
# Create SVMClassifier with hyper-parameters
svm_best = SVMClassifier(shrinking=True,
kernel=best[0],
degree=best[1],
gamma=best[2],
coef0=best[3],
C=best[4],
label_weights=label_weights,
output_probabilities=output_probabilities)
except Exception as inst:
print "Error while instantiating SVMClassifier (required hyper-parameters are probably missing)"
print inst
sys.exit()
finaltrainset = datasets['finaltrainset']
svm_best.train(finaltrainset)
outputs, costs = svm_best.test(testset)
return (outputs, costs)
def find_best_model(hyperparams_grid,datasets):
best_val_error = np.inf
validset = datasets['validset']
trainset = datasets['trainset']
output_probabilities = True
label_weights = None
for params in hyperparams_grid:
try:
# Create SVMClassifier with hyper-parameters
svm = SVMClassifier(shrinking=True, kernel=params[0],degree=params[1],gamma=params[2],coef0=params[3],C=params[4],label_weights=label_weights, output_probabilities=output_probabilities)
except Exception as inst:
print "Error while instantiating SVMClassifier (required hyper-parameters are probably missing)"
print inst
sys.exit()
svm.train(trainset)
outputs, costs = svm.test(validset)
errors = compute_error_mean_and_sterror(costs)
error = errors[0]
if error < best_val_error:
best_val_error = error
best_hyperparams = params
return best_hyperparams
def svm_model(dataset_directory, dataset_name, params, datasets):
start_time = time.clock()
use_weights = False
output_probabilities = True
label_weights = None
if use_weights:
label_weights = finaltrainset.metadata['label_weights']
else:
label_weights = None
output_probabilities = True # Or False!
try:
# Create SVMClassifier with hyper-parameters
svm = SVMClassifier(shrinking=True,
kernel=params[0],
degree=params[1],
gamma=params[2],
coef0=params[3],
C=params[4],
label_weights=label_weights,
output_probabilities=output_probabilities)
except Exception as inst:
print "Error while instantiating SVMClassifier (required hyper-parameters are probably missing)"
print inst
sys.exit()
#finaltrainset = datasets['finaltrainset']
#svm.train(finaltrainset)
#testset = datasets['testset']
#outputs, costs = svm.test(testset)
dice_mean = train_and_test(svm, datasets)
end_time = time.clock()
processing_time = end_time - start_time
return [dice_mean, processing_time]
def svm_train_test(input_arg):
label_weights = None
best = input_arg[1]
testset = input_arg[0]
output_probabilities = True # Or False!
try:
# Create SVMClassifier with hyper-parameters
svm_best = SVMClassifier(shrinking=True, kernel=best[0],degree=best[1],gamma=best[2],coef0=best[3],C=best[4],label_weights=label_weights, output_probabilities=output_probabilities)
except Exception as inst:
print "Error while instantiating SVMClassifier (required hyper-parameters are probably missing)"
print inst
sys.exit()
finaltrainset = datasets['finaltrainset']
svm_best.train(finaltrainset)
outputs, costs = svm_best.test(testset)
return (outputs,costs)
for gamma in gammas:
for coef0 in coef0s:
hyperparams_grid.append(['sigmoid', 3, gamma, coef0, C])
if use_weights:
label_weights = finaltrainset.metadata['label_weights']
else:
label_weights = None
output_probabilities = True # Or False!
print "Pretraining..."
for params in hyperparams_grid:
try:
# Create SVMClassifier with hyper-parameters
svm = SVMClassifier(shrinking=True, kernel=params[0],degree=params[1],gamma=params[2],coef0=params[3],C=params[4],label_weights=label_weights, output_probabilities=output_probabilities)
except Exception as inst:
print "Error while instantiating SVMClassifier (required hyper-parameters are probably missing)"
print inst
sys.exit()
svm.train(trainset)
outputs, costs = svm.test(validset)
errors = compute_error_mean_and_sterror(costs)
error = errors[0]
if error < best_val_error:
best_val_error = error
best_hyperparams = params
"""
if use_weights:
label_weights = finaltrainset.metadata['label_weights']
else:
label_weights = None
output_probabilities = True # Or False!
print "Pretraining..."
for params in hyperparams_grid:
try:
# Create SVMClassifier with hyper-parameters
svm = SVMClassifier(shrinking=True,
kernel=params[0],
degree=params[1],
gamma=params[2],
coef0=params[3],
C=params[4],
label_weights=label_weights,
output_probabilities=output_probabilities)
except Exception as inst:
print "Error while instantiating SVMClassifier (required hyper-parameters are probably missing)"
print inst
sys.exit()
svm.train(trainset)
outputs, costs = svm.test(validset)
errors = compute_error_mean_and_sterror(costs)
error = errors[0]
if error < best_val_error:
def svm_model(datasets):
print "Setting hyperparameters gridsearch..."
best_hyperparams = None
best_val_error = np.inf
finaltrainset = datasets['finaltrainset']
trainset = datasets['trainset']
validset = datasets['validset']
testset = datasets['testset']
lbl = datasets['ground_truth']
output_probabilities = True # Or False!
kernels = ['rbf','sigmoid']
#degrees = [1,2,3,4,5,7,10,15]
gammas = [0.01,0.1,1,5,10,50,100,200,500,1000]
#coef0s = [-10,-1,-0.1,-0.01,0,0.001,0.01,0.1,1,2,5,10,20]
Cs = [1,5,10,25,50,75,100,200,500,1000,1500]
hyperparams_grid = []
# Rbf kernel parameters
start_time = time.clock()
for gamma in gammas:
for C in Cs:
hyperparams_grid.append(['rbf', 3, gamma, 0, C])
use_weights = None
if use_weights:
label_weights = finaltrainset.metadata['label_weights']
else:
label_weights = None
output_probabilities = False # Or False!
print "Pretraining..."
for params in hyperparams_grid:
try:
# Create SVMClassifier with hyper-parameters
svm = SVMClassifier(shrinking=True, kernel=params[0],degree=params[1],gamma=params[2],coef0=params[3],C=params[4],label_weights=label_weights, output_probabilities=output_probabilities)
except Exception as inst:
print "Error while instantiating SVMClassifier (required hyper-parameters are probably missing)"
print inst
sys.exit()
svm.train(trainset)
outputs, costs = svm.test(validset)
errors = compute_error_mean_and_sterror(costs)
error = errors[0]
if error < best_val_error:
best_val_error = error
best_hyperparams = params
print
print 'Classification error on valid set : ' + str(best_val_error)
print
print "Training..."
# Train SVM with best hyperparams on train + validset
#gamma = 5.0
#C = 1
#best_hyperparams = ['rbf',3,gamma,0,C]
best_svm = SVMClassifier(shrinking=True, kernel=best_hyperparams[0],degree=best_hyperparams[1],gamma=best_hyperparams[2],coef0=best_hyperparams[3],C=best_hyperparams[4],label_weights=label_weights, output_probabilities=output_probabilities)
best_svm.train(finaltrainset)
print 'Testing...'
outputs, costs = best_svm.test(testset)
end_time = time.clock()
processing_time = end_time - start_time
errors = compute_error_mean_and_sterror(costs)
error = errors[0]
print
print 'Classification error on test set : ' + str(error)
print "****************************************"
# Evaluation (compute_statistics.py)
id_to_class = {}
for label, id in testset.class_to_id.iteritems():
id_to_class[id] = label
auto_lbl = np.array([int(id_to_class[output[0]]) for output in outputs]) # Predicted labels
len_bg = testset.metadata['len_bg']
lbl = np.append(lbl, [0]*len_bg)
auto_lbl = np.append(auto_lbl, [0]*len_bg)
(dice, jaccard, precision, recall) = compute_statistics.compute_eval_multilabel_metrics(auto_lbl, lbl)
dice = dice[~np.isnan(dice)]
return [dice.mean(), processing_time]