def predict():
#Step 1 Load Data
X_train, y_train, X_test, y_test = lstm.load_data('aapl.csv', 50, True)
#Step 2 Build Model
model = Sequential()
model.add(LSTM(input_dim=1, output_dim=2, 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
#Step 3 Train the model
model.fit(X_train,
y_train,
batch_size=512,
nb_epoch=1,
validation_split=0.05)
#Step 4 - Plot the predictions!
predictions = lstm.predict_sequences_multiple(model, X_test, 50, 50)
lstm.plot_results_multiple(predictions, y_test, 50)
def treina_modelo(model, x_train, y_train, existe=False):
if existe == False:
model.add(LSTM(input_dim=1, output_dim=50, return_sequences=True))
model.add(Dropout(0.2))
model.add(LSTM(50, return_sequences=False))
model.add(Dropout(0.2))
model.add(Dense(20, activation='relu'))
model.add(Dense(output_dim=1))
model.add(Activation('linear'))
start = time.time()
model.compile(loss='mse', optimizer='adam', metrics=['accuracy'])
print("Compilation time: ", time.time() - start)
# # Para quando não melhorar
es = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=5)
callbacks_list = [es]
# Treinando o modelo
model.fit(x_train,
y_train,
batch_size=512,
epochs=10,
validation_split=0.05,
callbacks=callbacks_list,
verbose=1)
model.save('meu_modelo.h5')
#Step 4 - Plot the predictions!
predictions = lstm.predict_sequences_multiple(model, x_test, 50, 50)
lstm.plot_results_multiple(predictions, y_test, 50)
def predict(batch, dropout):
x_train, y_train, x_test, y_test = lstm.load_data('SP500_5YR.csv',50,True)
model = Sequential()
model.add(LSTM(input_dim = 1, output_dim = 50, return_sequences=True))
model.add(Dropout(dropout))
model.add(LSTM(100,return_sequences=False))
model.add(Dropout(dropout))
model.add(Dense(output_dim=1))
model.add(Activation('linear'))
model.compile(loss = 'mse', optimizer = 'rmsprop')
model.fit(x_train,y_train,batch_size=batch, nb_epoch = 1, validation_split = 0.05)
predict = lstm.predict_sequence_multiple(model, x_test, 50, 50)
lstm.plot_results_multiple(predict, y_test, 50)
def main():
outdir = './data'
if not os.path.exists(outdir):
os.mkdir(outdir)
aapl = pdr.get_data_yahoo('AAPL', start=datetime.datetime(2006, 10, 1), end=datetime.datetime(2019, 1, 1))
aapl.to_csv('data/aapl_ohlc.csv')
df = pd.read_csv('data/aapl_ohlc.csv', index_col='Date', header=0, parse_dates=True)
close = df['Close']
window_size = 30
predict_len = 15
batch_size = 80
epochs = 1
x_train, y_train, x_test, y_test = lstm.load_data(close, window_size, True)
#date_price = df['Close']
#date_price = np.array(date_price).astype('float32')
#train, test = split_train_test(date_price, 0.8)
#x_train, y_train = create_dataset(train, 1)
#x_test, y_test = create_dataset(test, 1)
#x_train = np.reshape(x_train, (x_train.shape[0], 1, x_train.shape[1]))
#x_test = np.reshape(x_test, (x_test.shape[0], 1, x_test.shape[1]))
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)
model.fit(x_train, y_train, batch_size=batch_size, epochs=epochs, validation_split=0.05)
predictions = lstm.predict_sequences_multiple(model, x_test, window_size, predict_len)
lstm.plot_results_multiple(predictions, y_test, predict_len)
def exp_layer_depth(layers):
prediction_len = 20
predict(batch_size = 512, nb_epoch = 70,timestep = 50,hidden_state = 50, layers = layers, save = True,
predict_multiple = True, prediction_len = prediction_len, predict_full = True)
# Plot the predictions
orig = np.load("./data/y_test.npy")
predictions = np.load("./data/predictions.npy")
rmse,tp_acc,tpp_acc,cm1,cm2 = performance(orig, predictions)
print "Tendency Prediction Confusion Matrix (0:down; 1:up or equal): "
print cm1
print "Turning Point Prediction Confusion Matrix (0:not a turning point; 1:summit; 2:vale): "
print cm2
print "rmse: " + str(rmse) + "TPA: " + str(tp_acc) + "TPPA: " + str(tpp_acc)
predictions_multi = np.load("./data/predictions_multi.npy")
predictions_full = np.load("./data/predictions_full.npy")
fig = plt.figure(facecolor='white')
plot_results(predictions, orig, fig, sublocation = 121, show = False)
# plot_results(predictions_full, orig, fig, sublocation = 222, show = False)
plot_results_multiple(predictions_multi, orig, prediction_len = prediction_len,
fig = fig, sublocation = 122, show = True)
# =============================================================================
# #Step 3 Train the model
# =============================================================================
model.fit(
X_train,
y_train,
batch_size=512,
nb_epoch=1,
validation_split=0.05)
# =============================================================================
# #Step 4 - Plot the predictions!
# =============================================================================
predictions = lstm.predict_sequences_multiple(model, X_test, 50, 50)
lstm.plot_results_multiple(predictions, y_test, 50)
# we will train our model with the function then we can test it to see what it predicts
# for the next 50 steps at several points in our graph
# and visualize it using that with mapplotlit
# it seems that for a lot of the price movement espacially the big ones
# there is quite a correlation between our models prediction and the actual data
# so it's time to some money!!
# but will our model be able to correcly predict the closing price one hundred percent of time?
# the answer is no
# it's an analystical tool to help us make educated guesses about the direction of the market,
# that's slightly better than random
# so to break it down, conclusions:
# 1. rnn can model sequential data because the hidden state is affected by the input and
# the previous hidden state
#Step 3 Train the model
model.fit(
X_train,
y_train,
batch_size=512,
nb_epoch=1,
validation_split=0.05)
X_test = X_test[:30]
y_test = y_test[:30]
# Step 4 - Plot the predictions!
prediction_len = 3
predictions = lstm.predict_sequences_multiple(model, X_test, 30, prediction_len)
lstm.plot_results_multiple(predictions, y_test, prediction_len)
#hilo_pred = []
#for prediction in predictions:
# if prediction[0] > prediction[-1]:
# hilo_pred.append(0)
# else:
# hilo_pred.append(1)
#
#
#hilo_real = []
#for i in range(0, 147, prediction_len):
# if y_test[i] > y_test[i + prediction_len]:
# hilo_real.append(0)
# else:
# hilo_real.append(1)
model.add(LSTM(64, return_sequences=False))
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)
#Set hyperparameter
model.fit(X_train, y_train, batch_size=512, nb_epoch=100, validation_split=0.1)
#Make prediction
predictions = lstm.predict_sequences_multiple(model, X_test, seqence_length,
seqence_length)
lstm.plot_results_multiple(predictions, y_test, seqence_length)
#Save Model
model_json = model.to_json()
with open("model.json", "w") as json_file:
json_file.write(model_json)
# serialize weights to HDF5
model.save_weights("model.h5")
p = model.predict(X_test)
#Show result
plt2.plot(p, color='red', label='prediction')
plt2.plot(y_test, color='blue', label='actural')
plt2.legend(loc='upper left')
plt2.title("388 Days Prediction")
