def main():
pd.set_option('display.expand_frame_repr', False)
pathFolder = input("Insert dataset path folder (tips: dataset):")
pathDataset = input("Insert dataset path folder (tips: KDD99.csv):")
pathPlot = input("Insert plot path folder (tips: plot):")
df = pd.read_csv(os.path.join(pathFolder, pathDataset), delimiter=",")
print("Dataset shape: ", df.shape)
print("Dataset before preprocessing: ")
print(df.head(5))
#Show distinct classification target
distinctLabels = df[df.columns[-1]].unique().tolist()
N_CLASSES = len(distinctLabels)
print("Start preprocessing step")
numericColumn = df.select_dtypes(include=[np.number]).columns.tolist(
) #retrieve all numerical columns for standard scaler
classificationCol = df.columns[-1] #name of target column
print(classificationCol)
#preprocessing: map target from categorical to numeric and one-hot encoding at categorical columns
df = preprocessingDS(df)
print("Dataset after one-hot encoding:")
print(df.head(5))
#preprocessing: standar scaler
df = scaler(df, numericColumn)
#Split function on train and testing set
sizesplit = split_dataset()
pl = Plot(pathPlot)
train, test = train_test_split(df, test_size=sizesplit)
print("Train shape after split: ", train.shape)
print("Test shape after split: ", test.shape)
pl.plotStatistics(train, test, classificationCol)
train_X, train_Y, test_X, test_Y = getXY(train, test, classificationCol)
# convert class vectors to binary class matrices
train_Y2 = np_utils.to_categorical(train_Y, N_CLASSES)
callbacks_list = [
callbacks.EarlyStopping(monitor='val_loss',
patience=4,
restore_best_weights=True)
]
m = Models(N_CLASSES)
VALIDATION_SPLIT = 0.1
print('Model with autoencoder+softmax with fixed encoder weights')
# parametri per autoencoder
p1 = {
'first_layer': 60,
'second_layer': 30,
'third_layer': 10,
'batch_size': 64,
'epochs': 150,
'optimizer': optimizers.Adam,
'kernel_initializer': 'glorot_uniform',
'losses': 'mse',
'first_activation': 'tanh',
'second_activation': 'tanh',
'third_activation': 'tanh'
}
autoencoder = m.deepAutoEncoder(train_X, p1)
autoencoder.summary()
#get encoder for feature extraction
encoder = Model(inputs=autoencoder.input,
outputs=autoencoder.get_layer('encoder3').output)
encoder.summary()
history2 = autoencoder.fit(train_X,
train_X,
validation_split=VALIDATION_SPLIT,
batch_size=p1['batch_size'],
epochs=p1['epochs'],
shuffle=False,
callbacks=callbacks_list,
verbose=1)
pl.printPlotLoss(history2, 'autoencoder')
plot_model(autoencoder,
to_file='autoencoder.png',
show_shapes=True,
show_layer_names=True)
'''
Save weigths from autoencoder model
Weights are fixed in the classifier model
'''
weights = []
i = 0
for layer in autoencoder.layers:
weights.append(layer.get_weights())
# parameters for final model
p2 = {
'batch_size': 256,
'epochs': 100,
'optimizer': optimizers.Adam,
'kernel_initializer': 'glorot_uniform',
'losses': 'binary_crossentropy',
'first_activation': 'tanh',
'second_activation': 'tanh',
'third_activation': 'relu'
}
model = m.MLP_WeightFixed(encoder, train_X, p2)
history3 = model.fit(train_X,
train_Y2,
validation_split=VALIDATION_SPLIT,
batch_size=p1['batch_size'],
epochs=p1['epochs'],
shuffle=False,
callbacks=callbacks_list,
verbose=1)
pl.printPlotAccuracy(history3, 'finalModel1')
pl.printPlotLoss(history2, 'finalModel1')
model.save('modelfixedW.h5')
plot_model(model,
to_file='classifier.png',
show_shapes=True,
show_layer_names=True)
predictions = model.predict(test_X)
# Predicting the Test set results
y_pred = np.argmax(predictions, axis=1)
cm = confusion_matrix(test_Y, y_pred)
acc = accuracy_score(test_Y, y_pred, normalize=True)
LABELS = ["Attacks", "Normal"]
print("Confusion matrix on test set")
print(cm)
print("Accuracy model on test set: " + str(acc))
plt.figure(figsize=(12, 12))
sns.heatmap(cm,
xticklabels=LABELS,
yticklabels=LABELS,
annot=True,
fmt="d")
plt.title("Confusion matrix on test set")
plt.ylabel('True class')
plt.xlabel('Predicted class')
plt.savefig(os.path.join(pathPlot, "confusion matrix"))
plt.show()
plt.close()
