def run_test(sampler_type, X_train, y_train, X_test, y_test):
# Samplers
sampler = None
if sampler_type == 'rs':
sampler = RandomSampler(X_train, y_train, X_unlabeled, y_unlabeled)
elif sampler_type == 'ms':
sampler = MarginSampler(X_train, y_train, X_unlabeled, y_unlabeled)
elif sampler_type == 'hs':
sampler = HierarchicalSampler(X_train, y_train, X_unlabeled,
y_unlabeled)
else:
raise ValueError
print("Finish constructing sampler class " + sampler_type)
errors = []
X_train, y_train = sampler.X_train, sampler.y_train
i = 0
while i < max_unlabeled_size:
x_samples, y_samples = np.empty((batch_size, X_train.shape[1]),
float), np.empty((batch_size, ), int)
for b in range(batch_size):
x_sample, y_sample = sampler.sample()
# hack
if sampler_type != 'hs':
x_sample = x_sample.toarray()
x_samples[b] = x_sample
y_samples[b] = y_sample
X_train = vstack([X_train, x_samples])
y_train = np.append(y_train, y_samples)
model = LogisticRegression(multi_class="multinomial",
solver="lbfgs",
max_iter=200)
model.fit(X_train, y_train)
#y_pred = model.predict(X_test)
error = 1 - model.score(X_test, y_test)
print(sampler_type + ' number of labels: ' + str(training_size + i) +
' error=' + str(error))
errors.append(error)
i += batch_size
output.put((sampler_type, errors))
X_test = test_dataset.data
X_test = vstack([X_test, X_train_base[2000:, :]]).toarray()
y_test = test_dataset.target
y_test = np.append(y_test, y_train_base[2000:])
X_train_base = X_train_base[:2000, :]
y_train_base = y_train_base[:2000]
X_train, y_train = X_train_base[:
training_size], y_train_base[:
training_size]
X_unlabeled, y_unlabeled = X_train_base[training_size:], y_train_base[
training_size:]
rs = RandomSampler(X_train, y_train, X_unlabeled, y_unlabeled)
ms = MarginSampler(X_train, y_train, X_unlabeled, y_unlabeled)
hs = HierarchicalSampler(X_train, y_train, X_unlabeled, y_unlabeled)
x_train_random = X_train
y_train_random = y_train
x_train_margin = X_train
y_train_margin = y_train
x_train_Hierarchical = X_train
y_train_Hierarchical = y_train
print(
'Successfully loaded the Newsgroups dataset into train and test set.')
for num_samples in range(max_unlabeled_size):
#Add data, random
x_sample, y_sample = rs.sample()