Bayes.py

# -*- code:utf-8 -*-

import pandas as pd
import numpy as np
from sklearn import *
from sklearn import naive_bayes
from sklearn import tree
from sklearn.ensemble import RandomForestClassifier
from xgboost import XGBClassifier
import random


def get_result(labels, predictions):
    TP, FN, TN, FP = 0, 0, 0, 0
    for i in range(len(labels)):
        if labels[i] == 0:
            if predictions[i] == 0:
                TP += 1
            else:
                FN += 1
        else:
            if predictions[i] == 1:
                TN += 1
            else:
                FP += 1
    accuracy = (TP + TN) / (TP + TN + FP + FN)
    precision = TP / (TP + FP)
    recall = TP / (TP + FN)
    F1 = 2 * precision * recall / (precision + recall)
    return accuracy, precision, recall, F1


def main():
    filename = 'android_traffic.csv'
    dataset = pd.read_csv(filename, sep=';')
    dataset = np.array(dataset)

    le = preprocessing.LabelEncoder()
    dataset[:, 0] = le.fit_transform(dataset[:, 0])
    dataset[:, -1] = le.fit_transform(dataset[:, -1])

    dataset = np.delete(dataset, [11, 12, 13], axis=1)

    features = dataset[:, :-1]
    labels = np.asarray(dataset[:, -1], dtype=np.float64)

    x_train, x_test, y_train, y_test = model_selection.train_test_split(features, labels, test_size=0.3,
                                                                        random_state=random.randint(0, 100))
    # model = naive_bayes.ComplementNB()
    # model = tree.DecisionTreeClassifier()
    # model = RandomForestClassifier(bootstrap = True, oob_score = True, criterion = 'gini')
    model = XGBClassifier() 
    model.fit(x_train, y_train)
    predicted = model.predict(x_test)

    accuracy = metrics.accuracy_score(y_test, predicted)
    precision = metrics.precision_score(y_test, predicted, pos_label=0)
    recall = metrics.recall_score(y_test, predicted, pos_label=0)
    F1 = metrics.f1_score(y_test, predicted, pos_label=0)
    print('Accuracy: ' + str(accuracy))
    print('Precision: ' + str(precision))
    print('Recall: ' + str(recall))
    print('F1 score: ' + str(F1))


if __name__ == '__main__':
    main()