시계열수치입력 수치 예측 모델 레시피(상태유지 스택 순환신경망 모델)

# 1. 사용할 패키지 불러오기

import keras
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, LSTM, Dropout
from sklearn.preprocessing import MinMaxScaler
import matplotlib.pyplot as plt
%matplotlib inline

# 2.함수와 클래스 만들기
def create_dataset(signal_data, look_back=1):
        dataX, dataY = [], []
        for i in range(len(signal_data)-look_back):

        dataX.append(signal_data[i:(i+look_back), 0])
        dataY.append(signal_data[i + look_back, 0])
return np.array(dataX), np.array(dataY)

class CustomHistory(keras.callbacks.Callback):
        def init(self):
        self.train_loss = []
        self.val_loss = []

def on_epoch_end(self, batch, logs={}):
        self.train_loss.append(logs.get('loss'))
        self.val_loss.append(logs.get('val_loss'))

look_back = 40

# 3. 데이터셋 생성하기
signal_data = np.cos(np.arange(1600)*(20*np.pi/1000))[:,None]

# 3.1 데이터 전처리
scaler = MinMaxScaler(feature_range=(0, 1))
signal_data = scaler.fit_transform(signal_data)

# 3.2 데이터 분리
train = signal_data[0:800]
val = signal_data[800:1200]
test = signal_data[1200:]

# 3.3 데이터셋 생성
x_train, y_train = create_dataset(train, look_back)
x_val, y_val = create_dataset(val, look_back)
x_test, y_test = create_dataset(test, look_back)

# 3.4 데이터셋 전처리
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))
x_val = np.reshape(x_val, (x_val.shape[0], x_val.shape[1], 1))
x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))

# 4. 모델 구성하기
model = Sequential()

for i in range(2):
        model.add(LSTM(32, batch_input_shape=(1, look_back, 1), stateful=True, return_sequences=True))
        model.add(Dropout(0.3))

model.add(LSTM(32, batch_input_shape=(1, look_back, 1), stateful=True))
model.add(Dropout(0.3))
model.add(Dense(1))

# 5. 모델 학습과정 설정하기
model.compile(loss='mean_squared_error', optimizer='adam')

# 6. 모델 학습시키기
custom_hist = CustomHistory()
custom_hist.init()

for i in range(200):
    model.fit(x_train, y_train, epochs=1, batch_size=1, shuffle=False, callbacks=[custom_hist], validation_data=(x_val, y_val))
    model.reset_states()

# 7. 학습과정 살펴보기
plt.plot(custom_hist.train_loss)
plt.plot(custom_hist.val_loss)
plt.ylim(0.0, 0.15)
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'val'], loc='upper left')
plt.show()

# 8. 모델 평가하기
trainScore = model.evaluate(x_train, y_train, batch_size=1, verbose=0)
model.reset_states()
print('Train Score: ', trainScore)

valScore = model.evaluate(x_val, y_val, batch_size=1, verbose=0)
model.reset_states()
print('Validataion Score: ', valScore)

testScore = model.evaluate(x_test, y_test, batch_size=1, verbose=0)
model.reset_states()
print('Test Score: ', testScore)

# 9. 모델 사용하기
look_ahead = 250
xhat = x_test[0]
predictions = np.zeros((look_ahead,1))

for i in range(look_ahead):
        prediction = model.predict(np.array([xhat]), batch_size=1)
        predictions[i] = prediction
        xhat = np.vstack([xhat[1:],prediction])

plt.figure(figsize=(12,5))
plt.plot(np.arange(look_ahead),predictions,'r',label="prediction")
plt.plot(np.arange(look_ahead),y_test[:look_ahead],label="test function")
plt.legend()
plt.show()

[출처] 블록과 함께하는 파이썬 딥러닝 케라스, 김태영 지음, DigitalBooks, p265~268