Android_malware_classification.py

import tensorflow as tf

from keras.layers import Dense, Dropout, LSTM, Embedding, Activation
from keras.preprocessing.sequence import pad_sequences
from keras.models import Sequential
from keras.optimizers import SGD, Adam, Nadam
import pandas as pd
import numpy as np
from sklearn.metrics import confusion_matrix, precision_score, recall_score, f1_score, cohen_kappa_score
from keras.utils.vis_utils import plot_model
from sklearn.metrics import confusion_matrix
from keras.layers.normalization import BatchNormalization
import keras
import keras_metrics
from keras import backend as K
import time

input_file = 'input_5000.csv'

def load_data(test_split = 0.2):
    print ('Loading data...')
    df = pd.read_csv(input_file)
    df['sequence'] = df['sequence'].apply(lambda x: [int(e) for e in x.split()])
    df = df.reindex(np.random.permutation(df.index))

    train_size = int(len(df) * (1 - test_split))

    X_train = df['sequence'].values[:train_size]
    y_train = np.array(df['target'].values[:train_size])
    X_test = np.array(df['sequence'].values[train_size:])
    y_test = np.array(df['target'].values[train_size:])

    return pad_sequences(X_train), y_train, pad_sequences(X_test), y_test


def create_model(input_length):
    print ('Creating model...')
    model = Sequential()


    model.add(Dense(64, input_dim=132, init='uniform'))
    model.add(BatchNormalization())
    model.add(Activation('relu'))
    model.add(Dropout(0.5))
    model.add(Dense(32, init='uniform'))
    model.add(Activation('tanh'))
    model.add(BatchNormalization())
    model.add(Dropout(0.5))
    model.add(Dense(1, init='uniform'))
    model.add(Activation('sigmoid'))

    sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
    adam = Adam(lr=0.02)


    print ('Compiling...')
    model.compile(loss='binary_crossentropy',
                  optimizer=Adam(lr=0.002, beta_1=0.9, beta_2=0.999, epsilon=None, decay=0.0, amsgrad=False),
                  metrics=['accuracy',keras_metrics.precision(), keras_metrics.recall(),keras_metrics.false_positive(), keras_metrics.false_negative()])

                  #keras_metrics.false_positive(), keras_metrics.false_negative()
    return model





X_train, y_train, X_test, y_test = load_data()

print(X_train.shape)
start_time = time.time()

model = create_model(len(X_train[0]))

print ('Fitting model...')
history = model.fit(X_train, y_train, batch_size=10, nb_epoch=1000, validation_split = 0.1, verbose = 1)

print("---------------%s seconds----------" % (time.time() - start_time))


score, acc, prec, rec, false_positive, false_negative = model.evaluate(X_test, y_test, batch_size=50)
# print('Test score:', score)
# print("----------------------------------------------------------")
print("----------------------------------------------------------")
print("----------------------------------------------------------")
print('Test accuracy:', acc )
print("----------------------------------------------------------")
print("----------------------------------------------------------")

# labels = ['target']
# cm = confusion_matrix(y_test, score, labels)
# print(cm)
# fig = plt.figure()
# ax = fig.add_subplot(111)
# cax = ax.matshow(cm)
# plt.title('Confusion matrix of the classifier')
# fig.colorbar(cax)
# ax.set_xticklabels([''] + labels)
# ax.set_yticklabels([''] + labels)
# plt.xlabel('Predicted')
# plt.ylabel('True')
# plt.show()
# print(false_negative)





model.summary()