def main():
loss_norm = []
loss_difference = []
countries = [
'Afghanistan', 'Indien', 'Irak', 'Kolumbien', 'Pakistan',
'Philippinen', 'sandbox_attacks', 'test_exp_chirp'
]
for country in countries:
test_len = 30
data_name = country
data_dir = '../../' + data_name + '.csv'
train_data, train_date, test_data, test_date, std = prepare_data(
data_dir, test_len=test_len, normalize=False)
scale_down_mean = np.mean(train_data[-365 - 365 + test_len:-365])
scale_down_std = np.std(train_data[-365 - 365 + test_len:-365])
scale_up_mean = np.mean(train_data[-365 + 30:])
scale_up_std = np.std(train_data[-365 + 30:])
prediction = ((train_data[-365:-365 + 30] - scale_down_mean) /
scale_down_std) * scale_up_std + scale_up_mean
loss_norm.append(normed_loss(prediction, test_data))
loss_difference.append(differential_loss(prediction, test_data))
plt.figure()
plt.plot_date(test_date, test_data, xdate=True, label='Labels', ls="-")
plt.plot_date(test_date,
prediction,
xdate=True,
label='Predictions',
ls="-")
plt.xticks(rotation="vertical")
plt.title('Prediction')
plt.legend()
plt.xlabel('Days')
plt.ylabel('Attack')
save_fig(data_name, './Images/')
loss_dict = {
'Countries': countries,
'Normed_loss': loss_norm,
'Differential_loss': loss_difference
}
pd.DataFrame(loss_dict).to_csv('./Last_year_scaling_loss.csv')
def main():
loss_norm = []
loss_difference = []
countries = [
'Afghanistan', 'Indien', 'Irak', 'Kolumbien', 'Pakistan',
'Philippinen', 'sandbox_attacks', 'test_exp_chirp'
]
for country in countries:
data_name = country
data_dir = '../../' + data_name + '.csv'
train_data, train_date, test_data, test_date, std = prepare_data(
data_dir, test_len=30, normalize=False)
weight_aray = np.linspace(0, 1, 100)
feed = train_data[-100:].flatten()
pred = np.divide(np.sum(np.multiply(weight_aray, feed)),
np.sum(weight_aray))
prediction = np.ones((len(test_data))) * pred
loss_norm.append(normed_loss(prediction, test_data))
loss_difference.append(differential_loss(prediction, test_data))
plt.figure()
plt.plot_date(test_date, test_data, xdate=True, label='Labels', ls="-")
plt.plot_date(test_date,
prediction,
xdate=True,
label='Predictions',
ls="-")
plt.xticks(rotation="vertical")
plt.title('Prediction')
plt.legend()
plt.xlabel('Days')
plt.ylabel('Attack')
save_fig(data_name, './Images/')
loss_dict = {
'Countries': countries,
'Normed_loss': loss_norm,
'Differential_loss': loss_difference
}
pd.DataFrame(loss_dict).to_csv('./Average_loss.csv')
def main():
loss_norm = []
loss_difference = []
countries = [
'Afghanistan', 'Indien', 'Irak', 'Kolumbien', 'Pakistan',
'Philippinen', 'sandbox_attacks', 'test_exp_chirp'
]
for country in countries:
data_name = country
data_dir = '../../' + data_name + '.csv'
train_data_scaled, train_date, test_data, test_date, std = prepare_data(
data_dir, normalize=True, scaling='minmax')
model_dir = './model/'
num_epoch = 1000
n_steps = 100
n_inputs = 1
n_neurons = 30
n_layers = 1
print(country)
sess, train_loss, epoch_count = training(train_data_scaled,
model_dir,
num_epoch=num_epoch,
n_steps=n_steps,
n_inputs=n_inputs,
n_neurons=n_neurons,
n_layers=n_layers)
print()
prediction, true_labels, label_dates = predict(test_data, test_date,
sess, std, model_dir,
n_steps, n_inputs)
# rescaled_prediction = std.inverse_transform(prediction.reshape(-1,1))
# rescaled_labels = std.inverse_transform(true_labels.reshape(-1,1))
loss_norm.append(normed_loss(prediction, true_labels))
loss_difference.append(differential_loss(prediction, true_labels))
plt.figure()
plt.subplot(211)
plt.plot(epoch_count, train_loss)
plt.title('Training loss')
plt.xlabel('Epoch')
plt.ylabel('Training MSE')
plt.subplot(212)
plt.plot_date(label_dates,
true_labels,
xdate=True,
label='Labels',
ls="-")
plt.plot_date(label_dates,
prediction,
xdate=True,
label='Predictions',
ls="-")
plt.xticks(rotation="vertical")
plt.title('Prediction')
plt.legend()
plt.xlabel('Days')
plt.ylabel('Attack')
save_fig('predicted value feedback' + data_name, './Images/')
loss_dict = {
'Countries': countries,
'Normed_loss': loss_norm,
'Differential_loss': loss_difference
}
pd.DataFrame(loss_dict).to_csv('./RNN_loss.csv')
data_check = pd.read_csv("../random_new.csv",index_col=0)
data_check_val = data_check.values
print(data_check_val.shape)
random_check_set = data_check_val[:,1:]
random_check_dates = data_check_val[:,0]
print(random_check_set.shape)
print(random_check_dates.shape)
#std = StandardScaler()
random_check_std = std.transform(random_check_set)
#%%
img_dir = "../../../images/random_new/with_features/"
with tf.Session() as sess:
saver.restore(sess,'../saved_model/1_complex/with_features/')
for i in range(5):
X_check, y_check, date_check = fetch_batch(random_check_std,random_check_dates, 1, l, w, pred_window)
#X_check, y_check = fetch_batch(test_set, 1, l, w, pred_window)
prediction = sess.run(output,feed_dict={X:X_check, y: y_check})
plt.figure()
plt.plot_date(date_check.reshape(-1),y_check[0,:],xdate=True,label='actual',ls="-")
plt.plot_date(date_check.reshape(-1),prediction[0,:],xdate=True,label='predictions',ls="-")
plt.xticks(rotation="vertical")
plt.legend()
plt.xlabel('Days')
plt.ylabel('Attack')
save_fig(i,img_dir)
train_error = sess.run(mse, feed_dict = {X:X_batch[:,:,:,2:], y: y_batch})
test_x, test_y,_ = fetch_batch(test_std,test_date, 1, l, w, pred_window)
#test_x, test_y = fetch_batch(test_set, 1, l, w, pred_window)
test_error = sess.run(mse, feed_dict = {X:test_x[:,:,:,2:], y: test_y})
print("Epoch: ",epoch, " Training error: ", train_error, " Test error: ", test_error)
saver.save(sess,directory)
#plt.figure()
#plt.plot()
#print(mse)
#%%
#X_check, y_check = fetch_batch(test_set, 1, l, w, pred_window)
img_dir = "../../../images/1_complex/only_attack/"
with tf.Session() as sess:
saver.restore(sess,directory)
for i in range(10):
X_check, y_check, date_check = fetch_batch(test_std,test_date, 1, l, w, pred_window)
#X_check, y_check = fetch_batch(test_set, 1, l, w, pred_window)
prediction = sess.run(output,feed_dict={X:X_check[:,:,:,2:], y: y_check})
plt.figure()
plt.plot_date(date_check.reshape(-1),y_check[0,:],xdate=True,label='actual',ls="-")
plt.plot_date(date_check.reshape(-1),prediction[0,:],xdate=True,label='predictions',ls="-")
plt.xticks(rotation="vertical")
plt.legend()
plt.xlabel('Days')
plt.ylabel('Attack')
save_fig(i+10,img_dir)
