ma_cisco_malware/models/__init__.py

import keras.backend as K

import dataset
from . import pauls_networks
from . import renes_networks


def get_models_by_params(params: dict):
    # decomposing param section
    # mainly embedding model
    network_type = params.get("type")
    vocab_size = len(dataset.get_character_dict()) + 1
    embedding_size = params.get("embedding_size")
    input_length = params.get("input_length")
    filter_embedding = params.get("filter_embedding")
    kernel_embedding = params.get("kernel_embedding")
    hidden_embedding = params.get("hidden_embedding")
    dropout = params.get("dropout")
    # mainly prediction model
    flow_features = params.get("flow_features")
    domain_features = params.get("domain_features")
    window_size = params.get("window_size")
    domain_length = params.get("domain_length")
    filter_main = params.get("filter_main")
    kernel_main = params.get("kernels_main")
    dense_dim = params.get("dense_main")
    # create models
    networks = renes_networks if network_type == "rene" else pauls_networks
    embedding_model = networks.get_embedding(vocab_size, embedding_size, input_length,
                                             filter_embedding, kernel_embedding, hidden_embedding, drop_out=dropout)

    predict_model = networks.get_model(dropout, flow_features, domain_features, window_size, domain_length,
                                       filter_main, kernel_main, dense_dim, embedding_model)

    new_model = networks.get_new_model(dropout, flow_features, domain_features, window_size, domain_length,
                                       filter_main, kernel_main, dense_dim, embedding_model)

    return embedding_model, predict_model, new_model


def get_metrics():
    return dict([
        ("precision", precision),
        ("recall", recall),
        ("f1_score", f1_score),
    ])


def get_metric_functions():
    return [precision, recall, f1_score]


def precision(y_true, y_pred):
    # Count positive samples.
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
    return true_positives / (predicted_positives + K.epsilon())


def recall(y_true, y_pred):
    # Count positive samples.
    true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
    possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
    return true_positives / (possible_positives + K.epsilon())


def f1_score(y_true, y_pred):
    return f_score(1)(y_true, y_pred)


def f05_score(y_true, y_pred):
    return f_score(0.5)(y_true, y_pred)


def f_score(beta):
    def _f(y_true, y_pred):
        p = precision(y_true, y_pred)
        r = recall(y_true, y_pred)

        bb = beta ** 2

        fbeta_score = (1 + bb) * (p * r) / (bb * p + r + K.epsilon())

        return fbeta_score

    return _f