def train_search_user_defined_kernel():
"""
Funciton for training and applying grid search for linear+RBF kernel
"""
print('Start searching user-defined linear+RBF kernel...')
with open('%s_search1.txt' % 'udefined', 'w') as f:
cost_list = [1e-6, 1e-5, 1e-4, 1e-3, 1e-2]
gamma_list = [1e-3, 1e-6, 1e-9]
print('Cost: %s\ngamma: %s\n' % (cost_list, gamma_list), file=f)
for cost in cost_list:
for gamma in gamma_list:
try:
start = time.time()
prob = svm_problem(Y_train,
linear_RBF_kernel_train(gamma),
isKernel=True)
param = svm_parameter('-q -s 0 -t 4 -c %.14f' % cost)
model = svm_train(prob, param)
pred_label, pred_acc, pred_val = svm_predict(
Y_test, linear_RBF_kernel_test(gamma), model)
elapsed_time = time.time() - start
print('%f,%f,%f,%f' %
(cost, gamma, pred_acc[0], elapsed_time),
file=f)
print([cost, gamma, pred_acc[0], elapsed_time])
except:
print('%f,%f(FAIL)' % (cost, gamma), file=f)
f.flush()
def train_predict(y_train: np.array,
x_train: np.array,
y_test: np.array,
x_test: np.array,
degree: int = 3,
c: int = 2):
model = svmutil.svm_train(y_train, x_train,
f'-r 2 -t 1 -d {degree} -c {c} -q')
p_label, p_acc, p_val = svmutil.svm_predict(y_test, x_test, model, '-q')
acc, mse, _ = p_acc
sv_num = model.l
return acc, mse, sv_num
def train_svm(kernel, parameter_for_training=''):
"""
Train SVM with specific kernel (linear, polynomial, or RBF)
"""
kernel2int = {'linear': 0, 'polynomial': 1, 'RBF': 2}
start = time.time()
# set training arguments and training
model = svm_train(
Y_train, X_train,
parameter_for_training + ' -q -s 0 -t %d' % (kernel2int[kernel]))
# prediction
pred_label, pred_acc, pred_val = svm_predict(Y_test, X_test, model)
return pred_acc[0], time.time() - start
def libsvm(lb_tr, ins_tr, lb_te, ins_te):
"""
libsvm classifier, using libsvm
-------------------------------
read normalized libsvm format files from ./dataset
output:
accu --classification accuracy
co --confusion matrix
"""
rate, param = grid.find_parameters('dataset/YaleB.scale.tr', '-log2c -1,1,1 -log2g -1,1,1')
prob = svmutil.svm_problem(lb_tr, ins_tr)
param = svmutil.svm_parameter('-c %f -g %f' % (param['c'], param['g']))
m = svmutil.svm_train(prob, param)
p_label, p_acc, p_val = svmutil.svm_predict(lb_te, ins_te, m)
co = met.confusion_matrix(lb_te, p_label)
accu = p_acc[0]
return accu, co
def predict(self, X, y):
return svmutil.svm_predict(y.tolist(), X.tolist(), self.model)[1][0]
def predictByFile(test_file_name, model):
y, X = svmutil.svm_read_problem(test_file_name)
p_label, p_acc, p_val = svmutil.svm_predict(y, X, model)
print len(p_label)
def predict(f_vector, model):
X = [f_vector]
y = [0]
p_label, p_acc, p_val = svmutil.svm_predict(y, X, model)
return p_label
files = [el for el in files if '.npy' in el]
files = [el for el in files if 'Val' not in el]
dat_list = [np.load(base_dir + el, allow_pickle=True) for el in files]
k = 20
holdout = 0
y, x, y_test, x_test = form_svm_input(dat_list, k, holdout)
# train SVM
#y, x = scipy.asarray(Y), scipy.asarray(X)
#y_test, x_test = scipy.asarray(Y_test), scipy.asarray(X_test)
x = scipy.transpose(x)
#x_test = scipy.transpose(x_test)
prob = svmutil.svm_problem(y, x)
#param = svmutil.svm_parameter('-s 1 -t 1 -c 1 -n .05 -b 0 -m 10240') #1 works best, cost of 100 seems good (.000001 multiclass)
param = svmutil.svm_parameter('-t 1 -c .000001 -b 0')
m = svmutil.svm_train(prob, param)
#label = svmutil.svm_predict(y_test, x_test, m)
files = os.listdir(base_dir)
files = [el for el in files if '.npy' in el]
files = [el for el in files if 'Val' in el]
dat_list = [np.load(base_dir + el, allow_pickle=True) for el in files]
y_test, x_test, dc1, dc2 = form_svm_input(dat_list, k, 0)
x_test = scipy.transpose(x_test)
label = svmutil.svm_predict(y_test, x_test, m)
print(confusion_matrix(label[0], y_test))
train_prob = svm_problem(seed_docs_cls, seed_docs_theta)
seed_docs_svm_mdl = svm_train(train_prob, train_param)
# # SVM prediction for all the documents in the corpus
# num_corpus_docs = len(features)
# svm_labels, _, svm_decision_values = svm_predict([0]*num_corpus_docs,
# features, seed_docs_svm_mdl,
# '-b 0 -q')
# svm_prediction = [[doc_id, svm_label, svm_decision_values[doc_id][0]]
# for doc_id, svm_label in enumerate(svm_labels)]
# SVM prediction only for the test documents
num_test_docs = len(test_doc_ids)
svm_labels, _, svm_decision_values = svm_predict([0]*num_test_docs,
test_docs_features,
seed_docs_svm_mdl,
'-b 0 -q')
svm_prediction = [[doc_id, svm_labels[i], svm_decision_values[i][0]]
for i, doc_id in enumerate(test_doc_ids)]
return C_g_dict, svm_prediction # [doc_id, svm_class_label, svm_decision_value]
def eval_prediction(doc_true_class_ids, doc_prediction):
'''
doc_prediction: doc_id, predicted_class, prediction_score
'''
y1, x_test_precomputed = svmutil.svm_read_problem('test_precomputed.csv')
for kernel_type, opts in options.items():
print('\tkernel type: {0}\n\t'.format(kernel_type), end='')
tic()
if (train_flag):
m[kernel_type] = svmutil.svm_train(prob, opts)
svmutil.svm_save_model('model/' + kernel_type + '.model',
m[kernel_type])
else:
m[kernel_type] = svmutil.svm_load_model('model/' + kernel_type +
'.model')
train_time[kernel_type] = toc()
tic()
p_label[kernel_type], p_acc[kernel_type], p_val[kernel_type] = \
svmutil.svm_predict(y_test, x_test, m[kernel_type])
test_time[kernel_type] = toc()
print('\tresult(acc, mse, scc): {0}\n'.format(p_acc[kernel_type]))
for kernel_type, opts in options_precomputed.items():
print('\tkernel type: {0}\n\t'.format(kernel_type), end='')
tic()
if (train_flag):
m[kernel_type] = svmutil.svm_train(prob_precomputed, opts)
svmutil.svm_save_model('model/' + kernel_type + '.model',
m[kernel_type])
else:
m[kernel_type] = svmutil.svm_load_model('model/' + kernel_type +
'.model')
train_time[kernel_type] = toc()
tic()
def predictByFile( test_file_name, model ):
y, X = svmutil.svm_read_problem( test_file_name )
p_label, p_acc, p_val = svmutil.svm_predict(y, X, model)
print len(p_label)
def predict( f_vector, model ):
X = [ f_vector ]
y = [ 0 ]
p_label, p_acc, p_val = svmutil.svm_predict(y, X, model)
return p_label
