valid_set_y_org=numpy.loadtxt(filename,delimiter='\t',dtype=object)
prev,valid_set_y_org=cl.change_class_labels(valid_set_y_org)
# test set
filename=data_dir + "GM12878_200bp_Data_3Cl_l2normalized_TestSet.txt";
test_set_x_org=numpy.loadtxt(filename,delimiter='\t',dtype='float32')
filename=data_dir + "GM12878_200bp_Classes_3Cl_l2normalized_TestSet.txt";
test_set_y_org=numpy.loadtxt(filename,delimiter='\t',dtype=object)
prev,test_set_y_org=cl.change_class_labels(test_set_y_org)
filename=data_dir + "GM12878_Features_Unique.txt";
features=numpy.loadtxt(filename,delimiter='\t',dtype=object)
rng=numpy.random.RandomState(1000)
# train
classifier_trained,training_time=logistic_sgd.train_model(learning_rate=0.1, n_epochs=1000,
train_set_x_org=train_set_x_org,train_set_y_org=train_set_y_org,
valid_set_x_org=valid_set_x_org,valid_set_y_org=valid_set_y_org,
batch_size=200)
# test
test_set_y_pred,test_set_y_pred_prob,test_time=logistic_sgd.test_model(classifier_trained,test_set_x_org)
print test_set_y_pred
print test_set_y_pred_prob
print test_time
# evaluate classification performance
perf,conf_mat=cl.perform(test_set_y_org,test_set_y_pred,numpy.unique(train_set_y_org))
print perf
print conf_mat
gc_collect()
learning_rate=0.1,
corruption_level=0.1,
cost_measure="cross_entropy",
rng=rng) # cost_measure can be either "cross_entropy" or "euclidean"
# extract features from test set and validation set
test_set_x_extr = dA.test_model(model_trained, test_set_x_org)
valid_set_x_extr = dA.test_model(model_trained, valid_set_x_org)
# classification
# train classifier
logistic_trained, training_time_logistic = logistic_sgd.train_model(
learning_rate=0.1,
n_epochs=1000,
train_set_x_org=train_set_x_extr,
train_set_y_org=train_set_y_org,
valid_set_x_org=valid_set_x_extr,
valid_set_y_org=valid_set_y_org,
batch_size=200)
# test classifier
test_set_y_pred = logistic_sgd.test_model(logistic_trained, test_set_x_extr)
# evaluate classification performance
perf, conf_mat = cl.perform(test_set_y_org, test_set_y_pred,
numpy.unique(train_set_y_org))
print perf
print conf_mat
gc_collect()
# extract features from test set and validation set
test_set_x_extr = rbm.test_model(model_trained, test_set_x_org)
valid_set_x_extr =rbm.test_model(model_trained, valid_set_x_org)
# classification
# train classifier
learning_rate=0.1
n_epochs=100
batch_size=100
logistic_trained,training_time_logistic=logistic_sgd.train_model(learning_rate=learning_rate, n_epochs=n_epochs,
train_set_x_org=train_set_x_extr, train_set_y_org=train_set_y_org,
valid_set_x_org=valid_set_x_extr, valid_set_y_org=valid_set_y_org,
batch_size=batch_size)
# test classifier
test_set_y_pred,test_set_y_pred_prob,test_time=logistic_sgd.test_model(logistic_trained,test_set_x_extr)
# evaluate classification performance
perf_i,conf_mat_i=cl.perform(test_set_y_org,test_set_y_pred,numpy.unique(train_set_y_org))
print perf_i
print conf_mat_i
if i==0:
perf=perf_i
conf_mat=conf_mat_i
training_times=training_time
test_times=test_time
else:
perf=numpy.vstack((perf,perf_i))
conf_mat=conf_mat+conf_mat_i
training_times=training_times + training_time
test_times=test_times + test_time
# train, and extract features from training set
model_trained, train_set_x_extr, training_time = rbm.train_model(rng=rng,train_set_x_org=train_set_x_org,
training_epochs=10, batch_size=100,
n_hidden=93, learning_rate=0.1, persistent_chain_k=30)
# extract features from test set and validation set
test_set_x_extr = rbm.test_model(model_trained, test_set_x_org)
valid_set_x_extr =rbm.test_model(model_trained, valid_set_x_org)
# classification
# train classifier
logistic_trained,training_time_logistic=logistic_sgd.train_model(learning_rate=0.1, n_epochs=1000,
train_set_x_org=train_set_x_extr, train_set_y_org=train_set_y_org,
valid_set_x_org=valid_set_x_extr, valid_set_y_org=valid_set_y_org,
batch_size=200)
# test classifier
test_set_y_pred=logistic_sgd.test_model(logistic_trained,test_set_x_extr)
# evaluate classification performance
perf,conf_mat=cl.perform(test_set_y_org,test_set_y_pred,numpy.unique(train_set_y_org))
print perf
print conf_mat
# sample from RBM
samples_vis, samples_vis_mf=rbm.sample_model(rng, model_trained, test_set_x_org, n_chains=20,n_samples=10,sample_gap=1000)
# collect garbage
gc_collect()
# classification
# train classifier
learning_rate = 0.1
n_epochs = 100
batch_size = 100
logistic_trained, training_time_logistic = logistic_sgd.train_model(
learning_rate=learning_rate,
n_epochs=n_epochs,
train_set_x_org=train_set_x_extr,
train_set_y_org=train_set_y_org,
valid_set_x_org=valid_set_x_extr,
valid_set_y_org=valid_set_y_org,
batch_size=batch_size)
# test classifier
test_set_y_pred, test_set_y_pred_prob, test_time = logistic_sgd.test_model(
logistic_trained, test_set_x_extr)
# evaluate classification performance
perf_i, conf_mat_i = cl.perform(test_set_y_org, test_set_y_pred,
numpy.unique(train_set_y_org))
print perf_i
print conf_mat_i
if i == 0:
perf = perf_i
conf_mat = conf_mat_i
training_times = training_time
test_times = test_time
else:
perf = numpy.vstack((perf, perf_i))
conf_mat = conf_mat + conf_mat_i
training_times = training_times + training_time
