"""
Read data model 1
"""
# final_path = "Final_Experiment\\DividedData\\" + "cert_data_model\\"
# final_path = "/home/frenky/PycharmProjects/HTTPSDetector/MachineLearning/data_model/"
data_path = "data/"
X_train, X_test, Y_train, Y_test = get_all_data(data_path)
"""
Define model
"""
# model = RandomForestClassifier()
model = RandomForestClassifier(n_estimators=800, oob_score='TRUE')
"""
Crossvalidation
"""
detect_with_cross_validation(model, X_train, Y_train)
"""
Detecting
"""
model.fit(X_train, Y_train)
detect(model, X_test, Y_test)
# param = {
# 'n_estimators': [500, 600, 700, 800, 900, 1000, 1100, 1200, 1300, 1400]
# }
# kflod = StratifiedKFold(n_splits=10)
# grid_search = GridSearchCV(estimator=model, param_grid=param, scoring='accuracy', cv=kflod)
# grid_result = grid_search.fit(X_train, Y_train)
# print("Best: %f using %s" % (grid_result.best_score_, grid_search.best_params_))
#
# means = grid_result.cv_results_['mean_test_score']
""" Read data model 1 """ X_train, X_test, y_train, y_test = get_all_data(data_path) clf = MLPClassifier(solver='adam', alpha=1e-05, random_state=1) """ Crossvalidation """ detect_with_cross_validation(clf, X_train, y_train) """ Learning """ clf.fit(X_train, y_train) """ Detect """ detect(clf, X_test, y_test) # score = clf.score(X_test, y_test) # print score
# model = XGBClassifier(
# learning_rate=0.1,
# n_estimators=1000,
# max_depth=3,
# min_child_weight=5,
# gamma=0.1,
# subsample=0.8,
# colsample_bytree=0.8,
# objective='binary:logistic',
# nthread=4,
# scale_pos_weight=1,
# seed=27)
"""
Crossvalidation
"""
detect_with_cross_validation(model, np_X_train, np_y_train)
"""
Detect model
"""
model.fit(np_X_train, np_y_train)
detect(model, np_X_test, np_y_test)
# pyplot.bar(range(len(model.feature_importances_)), model.feature_importances_)
# pyplot.show()
# param = {
# 'n_estimators': [1300, 1400, 1500, 1600, 1700, 1800], #[600, 700, 800, 900, 950, 1000, 1050, 1100, 1150, 1200],
# 'learning_rate': [0.1],
# 'max_depth': [10],
# 'min_child_weight': [1],