# creating testing and training labels
train_labels = np.array(train['bot'])
test_labels = np.array(test['bot'])
# creating index and columns for our final dataframe which contains results
index = [
'NaiveBayes - Gaussion', 'SVM', 'Decision Tree', 'Random Forest',
'Adaboost'
]
columns = ['Accuracy', 'Precision', 'Recall', 'F1_Score', 'AUC_Score']
# Initializing the dataframe
results = pd.DataFrame(index=index, columns=columns)
# Calling each of the ML methods and saving the corresponding returned accuracy
naiveb = NaiveBayes.TrainTest(features_train, train_labels, features_test,
test_labels)
results['Accuracy']['NaiveBayes - Gaussion'], results['Precision'][
'NaiveBayes - Gaussion'], results['Recall'][
'NaiveBayes - Gaussion'], results['F1_Score'][
'NaiveBayes - Gaussion'], results['AUC_Score'][
'NaiveBayes - Gaussion'] = naiveb
svm = SVM.TrainTest(features_train, train_labels, features_test, test_labels)
results['Accuracy']['SVM'], results['Precision']['SVM'], results['Recall'][
'SVM'], results['F1_Score']['SVM'], results['AUC_Score']['SVM'] = svm
dtree = DecisionTree.TrainTest(features_train, train_labels, features_test,
test_labels)
results['Accuracy']['Decision Tree'], results['Precision'][
'Decision Tree'], results['Recall']['Decision Tree'], results['F1_Score'][
'Decision Tree'], results['AUC_Score']['Decision Tree'] = dtree
