def _test_maxent_based(self):
dataset = news_20_reader.toNumpy()
n_feature = 'all'
print "Dataset: News20, Classifier: Maximum Entropy"
print
self.run_ratio(LogisticRegression, dataset, n_feature)
def test_class_ratio(self):
'''
Compare several competing methods changing the ratio of the positive
class in the dataset. We use binary class dataset for the easy of
interpretation.
'''
#X_train_full, y_train_full, X_test, y_test = nc_rna_reader.toNumpy()
X_train_full, y_train_full, X_test, y_test = news_20_reader.toNumpy()
set_size = 1000
X_train, y_train = self.get_sub_set_with_size([X_train_full, y_train_full], set_size)
train_set = (X_train, y_train)
test_set_original = (X_test, y_test)
ms = MSHI(LinearSVC)
ms.fit(train_set)
print 'Done training'
for r in numpy.arange(0.05, 1.0, 0.05):
#for r in [0.05]:
X_test_new, y_test_new = SetGen.with_pos_ratio(test_set_original, r, pos_label=1)
test_set = [X_test_new, y_test_new]
dist_true = DE.arrayToDist(y_test_new)
dist_est = ms.predict(X_test_new)
err = rms(dist_est, dist_true)
print "r: %f, pos: %f" % (r, dist_est[1])
def test(self):
X_train, y_train, X_test, y_test = news_20_reader.toNumpy()
X_test, y_test = SetGen.with_pos_ratio([X_test, y_test], 0.50, pos_label=1)
clf = LogisticRegression
it = Itr2(clf, 2)
it.fit([X_train, y_train])
dist = it.predict(X_test)
print dist
def test_ratio(self):
dataset = news_20_reader.toNumpy()
for set_size in numpy.arange(100, 210, 10):
self.run_ratio(dataset, set_size)
print
def _test_maxent_based(self):
dataset = news_20_reader.toNumpy()
n_feature = 'all'
print "News20 with Maxent"
self.run_test_with(dataset, LogisticRegression, n_feature)
def _test_svm_based3(self):
dataset = news_20_reader.toNumpy()
n_feature = 'all'
print "News20 with SVM"
self.run_test_with(dataset, LinearSVC, n_feature)
def _test_maxent_based(self):
print "Compare News20 with Maxent"
dataset = news_20_reader.toNumpy()
n_feature = 'all'
self.run_test_with(dataset, self.compare_maxent_based, n_feature)
