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 [2]:

    

#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 :  0.014828920364379883

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 [==============================] - 6s - loss: 0.0021 - val_loss: 0.0011






    
Out[5]:





<keras.callbacks.History at 0x7f2686a9dd30>

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)


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-6-c37cab15883e> in <module>()
      1 #Step 4 - Plot the predictions!
----> 2 predictions = lstm.predict_sequences_multiple(model, X_test, 50, 50)
      3 lstm.plot_results_multiple(predictions, y_test, 50)

/opt/notebooks/How-to-Predict-Stock-Prices-Easily/lstm.py in predict_sequences_multiple(model, data, window_size, prediction_len)
     99     #Predict sequence of 50 steps before shifting prediction run forward by 50 steps
    100     prediction_seqs = []
--> 101     for i in xrange(len(data)/prediction_len):
    102         curr_frame = data[i*prediction_len]
    103         predicted = []

NameError: name 'xrange' is not defined

In [ ]: