def predict_svm():
global config
load_config('svm')
print('loading data...')
df = pd.read_csv(Config.getPath('data') + '/' + TRAINING_DATA)
df2 = df.sample(50000)
X = df2['question_text']
Y = df2['target']
Xtrain, Xtest, Ytrain, Ytest = train_test_split(X,
Y,
test_size=0.2,
random_state=42)
# Two classes - Fake=0, Reliable=1
config.set('num_target_tokens', 2)
classifier = ClassifierFactory.getSVM()
print('training size: ', len(Xtrain))
print('testing size: ', len(Xtest))
print('start fitting ...')
classifier.fit(Xtrain, Ytrain, Xtest, Ytest)
df = pd.read_csv(Config.getPath('data') + '/' + TESTING_DATA)
df = df.sample(100000)
X = df['question_text']
Y = df['target']
pred = classifier.predict(X)
score = metrics.accuracy_score(Y, pred)
f1score = metrics.f1_score(Y, pred)
print("accuracy: %0.3f" % score)
print("f1 score: %0.3f" % f1score)
cm = metrics.confusion_matrix(Ytest, pred, labels=[0, 1])
plot_confusion_matrix(cm, classes=[0, 1])
def main_svm():
load_config()
c = ClassifierFactory.getSVM()
train_vanilla(c)