def test_svm_based3(self):
print "Compare Sentiment with SVM"
dataset = sentiment_reader.toNumpy()
X_train, y_train, X_test, y_test = dataset
X_test = X_test[:1000]
y_test = y_test[:1000]
#n_feature = 'all'
acc_matrix, f1_matrix, auc_matrix = self.compare_svm_based(dataset)
def test_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.
'''
#dataset = rcv1_binary_reader.toNumpy()
#dataset = snippet_reader.toNumpy()
dataset = sentiment_reader.toNumpy()
#set_size = 200
#X_train_full, y_train_full, X_test, y_test = dataset
#X_train, y_train = self.get_sub_set_with_size([X_train_full, y_train_full], set_size)
#assert(len(y_train) == set_size)
X_train, y_train, X_test, y_test = dataset
X_test = X_test[:1000]
y_test = y_test[:1000]
train_set = (X_train, y_train)
test_set_original = (X_test, y_test)
clf = SVMLight()
#clf = LinearSVC()
clf.fit(X_train, y_train)
mla = MLA(clf, verbose=1)
for r in np.arange(0.05, 1.0, 0.05):
#r = 0.1
# Generate a new test set with desired positive proportions.
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_dict = DE.arrayToDistDict(y_test_new)
mla.fit(X_train, y_train, dist_dict)
y_pred = mla.predict(X_test_new)
cm = confusion_matrix(y_test_new, y_pred)
acc = self.accuracy(cm)
print r, acc
from data_io import sentiment_reader from data_io import domain_reader from data_io import snippet_reader from sklearn.svm import LinearSVC X_train, y_train, X_test, y_test = sentiment_reader.toNumpy() clf = LinearSVC() clf.fit(X_train, y_train) print clf.score(X_test, y_test)
def _test_svm_based4(self):
print "Compare Domain with SVM"
dataset = sentiment_reader.toNumpy()
#n_feature = 'all'
acc_matrix, f1_matrix, auc_matrix = self.compare_svm_based(dataset)