It is paradoxical, yet it works

Added graphics user interface, changed packet capturing so it works. It works only with rule based part now

added import_data method for importing data, now using the given KDDTest+ and KDDTrain+ data for training instead of only KDDTrain+, a lot of refactoring

added import_data method for importing data, now using the given KDDTest+ and KDDTrain+ data for training instead of only KDDTrain+, a lot of refactoring

added read_csv boolean, normalized data before feeding it to the model, removed regression curve plot (impractical for higher dimensional X), increased dimension of X, refactored a lot of code, added confusion matrix plot, accuracy now is being displayed with the confusion matrix plot, slightly improved the prediction method, now plotting logistic regression feature importances (here: coefficients), can now extract high confidence samples (ergo samples of >90% landing in class 1)

now normalizing data before feeding to model, refactored a lot of code like in logistic_regression.py

added read_csv boolean, normalized data before feeding it to the model, removed regression curve plot (impractical for higher dimensional X), increased dimension of X, refactored a lot of code, added confusion matrix plot, accuracy now is being displayed with the confusion matrix plot, slightly improved the prediction method, now plotting logistic regression feature importances (here: coefficients), can now extract high confidence samples (ergo samples of >90% landing in class 1)