In [1]:
from keras.layers.core import Dense, Activation, Dropout
from keras.layers.recurrent import LSTM
from keras.models import Sequential
import lstm, time #helper libraries
Using TensorFlow backend.
In [3]:
#Step 1 Load Data
X_train, y_train, X_test, y_test = lstm.load_data('sp500.csv', 50, True)
In [4]:
#Step 2 Build Model
model = Sequential()

model.add(LSTM(
    input_dim=1,
    output_dim=50,
    return_sequences=True))
model.add(Dropout(0.2))

model.add(LSTM(
    100,
    return_sequences=False))
model.add(Dropout(0.2))

model.add(Dense(
    output_dim=1))
model.add(Activation('linear'))

start = time.time()
model.compile(loss='mse', optimizer='rmsprop')
print 'compilation time : ', time.time() - start
compilation time :  0.0409510135651
In [5]:
#Step 3 Train the model
model.fit(
    X_train,
    y_train,
    batch_size=512,
    nb_epoch=1,
    validation_split=0.05)
Train on 3523 samples, validate on 186 samples
Epoch 1/1
3523/3523 [==============================] - 8s - loss: 0.0098 - val_loss: 0.0011
Out[5]:
<keras.callbacks.History at 0x10f8b9b90>
In [6]:
#Step 4 - Plot the predictions!
predictions = lstm.predict_sequences_multiple(model, X_test, 50, 50)
lstm.plot_results_multiple(predictions, y_test, 50)
yo