Hands-On Machine Learning for Cybersecurity

Bagging

These are bootstrap aggregators where equal voting rights have been assigned to every model. The variance of these aggregators is maintained by drawing a random subset when making a decision.

Random forests are extensions of the bagging method. A random forest is a collection of decision trees that help in classification, regression, and decisions. The following shows the code for importing RandomForestClassifier:

import pandasfrom sklearn import model_selectionfrom sklearn.ensemble import RandomForestClassifierget_values = new_count_df.valuesA =get_values[:,0:8]B =get_values[:,8]seed = 7number_of_trees = 50max_num_features = 2kfold_crossval = model_selection.KFold(n_splits=10, random_state=seed)model = RandomForestClassifier(n_estimators=num_trees, ...