def _test_avg(self):
dataset = nc_rna_reader.toNumpy()
train_set_size = 200
X_train_full, y_train_full, X_test_full, y_test_full = dataset
X_train, y_train = self.get_sub_set_with_size([X_train_full, y_train_full], train_set_size)
X_test, y_test = self.get_sub_set_with_size([X_test_full, y_test_full], 10000)
train_set = (X_train, y_train)
test_set_original = (X_test, y_test)
clf_class = LinearSVC
for split_r in numpy.arange(0.1, 1.0, 0.1):
ra = RA(clf_class, ac_method="ac", subsample_count=200, split_r=split_r)
ra.fit(train_set)
err = self.compute_avg_error(ra, test_set_original)
print "%f\t%f" % (split_r, err)
def _test_avg(self):
dataset = rcv1_binary_reader.toNumpy()
train_set_size = 300
X_train_full, y_train_full, X_test_full, y_test_full = dataset
X_train, y_train = self.get_sub_set_with_size([X_train_full, y_train_full], train_set_size)
X_test, y_test = self.get_sub_set_with_size([X_test_full, y_test_full], 10000)
train_set = (X_train, y_train)
test_set_original = (X_test, y_test)
clf_class = LogisticRegression
for split_r in numpy.arange(0.1, 1.0, 0.1):
ra = RA(clf_class, ac_method = 'ac', subsample_count = 200, split_r=split_r)
ra.fit(train_set)
err = self.compute_avg_error(ra, test_set_original)
print split_r, err
