####
#training the first neural network
#for Category 1 [LOS<=7]
train_data = final_array[0:int(0.8 * len(final_array)), 0:len(final_array[0])]
train_target = main_target.reshape(-1, 1)[0:int(0.8 * len(final_array)), 0]
test_data = final_array[int(0.8 * len(final_array)):len(final_array),
0:len(final_array[0])]
test_target = main_target.reshape(
-1, 1)[int(0.8 * len(final_array)):len(final_array), 0]
model = Sequential()
model.add(
keras.layers.core.Dense(len(train_data[0]),
input_dim=len(train_data[0]),
init='uniform',
activation='relu',
bias=True))
model.add(
keras.layers.core.Dense(8, init='uniform', activation='relu', bias=True))
model.add(keras.layers.core.Dense(1, init='uniform', bias=True))
model.compile(loss='mean_squared_error', optimizer='adam')
keras.layers.core.Dropout(0.1)
model.fit(train_data, train_target, nb_epoch=150, batch_size=10)
model.evaluate(train_data, train_target, batch_size=10)
#training the 2nd Neural network
#For category II LOS>7
#array_2 = scipy.delete(array_2,0,1);
train_data_2 = array_2[0:int(0.9 * len(array_2)), 0:len(array_2[0])]
},
ignore_index=True)
##################
#DNN
import tensorflow as tf
from keras.models import Sequential
import pandas as pd
from keras.layers import Dense
from keras.models import Sequential
from keras.layers import Dense
model = Sequential()
#Swish
model.add(Dense(8, activation='swish', input_shape=(8, )))
model.add(Dense(8, activation='swish'))
model.add(Dense(8, activation='swish'))
model.add(Dense(1, activation='sigmoid'))
model.compile(loss='binary_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
model.fit(X_train, y_train, epochs=5, batch_size=1, verbose=1)
y_pred = model.predict_classes(X_test)
lrcm = confusion_matrix(y_test, y_pred)
AlSumm = AlSumm.append(
for i in range(len(y_pred_local) - 1, -1, -1):
if ((y_pred_iso[i] == -1) and (y_pred_local[i] == -1)):
x_clean = np.delete(x_clean, i, axis=0)
y_clean = np.delete(y_clean, i, axis=0)
############## CV for paramter tuning
# x_ktrain, x_ktest, y_ktrain, y_ktest = train_test_split(x_clean, y_clean, test_size=0.4, random_state=0)
# y_ktrain = keras.utils.to_categorical(y_ktrain, 3)
############# model construction
model = Sequential()
model.name = 'model'
model.add(
Dense(200,
activation='relu',
kernel_initializer='random_uniform',
input_shape=(x_clean.shape[1], )))
model.add(Dropout(0.3))
model.add(Dense(3, activation='softmax'))
optim = keras.optimizers.Adadelta()
model.compile(optimizer=optim,
loss='categorical_crossentropy',
metrics=['accuracy'])
# model.fit(x_ktrain, y_ktrain, batch_size=100, epochs=100, verbose=1)
# y_kpred = np.argmax(model.predict(x_ktest), axis=1)
features = []
print('%i features identified as important:' % nb_features)
indices = np.argsort(fsel.feature_importances_)[::-1][:nb_features]
for f in range(nb_features):
print("%d. feature %s (%f)" % (f + 1, data.columns[2+indices[f]], fsel.feature_importances_[indices[f]]))
# XXX : take care of the feature order
for f in sorted(np.argsort(fsel.feature_importances_)[::-1][:nb_features]):
features.append(data.columns[2+f])
# Deep learning:
# create model
model = Sequential()
model.add(Dense(12, input_dim=54, activation='relu'))
model.add(Dense(256, activation='relu'))
model.add(Dense(1, activation='sigmoid'))
# Compile model
model.compile(loss='binary_crossentropy', optimizer='adam', metrics=['accuracy'])
# Fit the model
model.fit(X, y, epochs=10, batch_size=10)
# evaluate the model
scores = model.evaluate(X, y)
print("\n%s: %.2f%%" % (model.metrics_names[1], scores[1]*100))
# Save model
model.save('C:/Users/Rahul/Desktop/antivirus_demo-master/deep_calssifier/deep_classifier.h5')
