def test_classifier(dataset, classifier):
print("-----TESTING CLASSIFIER-----")
if isinstance(classifier, keras.engine.training.Model):
x_test, y_test = dl.prepare_data_for_RNN(dataset)
print("-----TEST SET SIZE: " + str(x_test["sentence1"].shape) +
"-----")
scores = classifier.evaluate(x_test, y_test)
print("\n%s: %.2f%%" % (classifier.metrics_names[1], scores[1] * 100))
elif isinstance(classifier, keras.models.Sequential):
x_test, y_test = dl.prepare_data_for_NN(dataset)
print("-----TEST SET SIZE: " + str(len(x_test)) + "-----")
scores = classifier.evaluate(x_test, y_test)
print("\n%s: %.2f%%" % (classifier.metrics_names[1], scores[1] * 100))
elif isinstance(classifier,
sklearn.ensemble.forest.RandomForestClassifier):
x_test, y_test = dl.prepare_data_for_RF(dataset)
print("-----TEST SET SIZE: " + str(len(x_test)) + "-----")
else:
x_test, y_test = dl.prepare_data_for_ZeroR(dataset)
print("-----TEST SET SIZE: " + str(len(x_test)) + "-----")
prediction = classifier.predict(x_test)
numberOfClasses = y_test.shape[1]
position = np.argmax(prediction, axis=-1)
y_pred = np.identity(numberOfClasses)[position]
target_names = ['nonrelated', 'related']
print(classification_report(y_test, y_pred, target_names=target_names))
y_test = [np.where(r == 1)[0][0] for r in y_test]
y_pred = [np.where(r == 1)[0][0] for r in y_pred]
y_true = pd.Series(y_test)
y_pred = pd.Series(y_pred)
print(
pd.crosstab(y_true,
y_pred,
rownames=['True'],
colnames=['Predicted'],
margins=True))
def train_RF_classifier(dataset):
print("-----TRAIN CLASSIFIER-----")
x_train, y_train = dl.prepare_data_for_RF(dataset)
estimators = 200
randomForest = RandomForestClassifier(n_estimators=estimators)
randomForest.fit(x_train, y_train)
print("-----TRAINING COMPLETE-----")
return randomForest