-
-
Save lukovkin/1aefa4509e066690b892 to your computer and use it in GitHub Desktop.
# Time Series Testing | |
import keras.callbacks | |
from keras.models import Sequential | |
from keras.layers.core import Dense, Activation, Dense, Dropout | |
from keras.layers.recurrent import LSTM | |
# Call back to capture losses | |
class LossHistory(keras.callbacks.Callback): | |
def on_train_begin(self, logs={}): | |
self.losses = [] | |
def on_batch_end(self, batch, logs={}): | |
self.losses.append(logs.get('loss')) | |
# You should get data frames with prices somewhere, e.g. on Quandl - implementation is up to you | |
# merge data frames | |
merged = df1.merge(df2, left_index=True, right_index=True, how='inner').dropna() | |
# data prep | |
# use 100 days of historical data to predict 10 days in the future | |
data = merged.values | |
examples = 100 | |
y_examples = 10 | |
nb_samples = len(data) - examples - y_examples | |
# input - 2 features | |
input_list = [np.expand_dims(np.atleast_2d(data[i:examples+i,:]), axis=0) for i in xrange(nb_samples)] | |
input_mat = np.concatenate(input_list, axis=0) | |
# target - the first column in merged dataframe | |
target_list = [np.atleast_2d(data[i+examples:examples+i+y_examples,0]) for i in xrange(nb_samples)] | |
target_mat = np.concatenate(target_list, axis=0) | |
# set up model | |
trials = input_mat.shape[0] | |
features = input_mat.shape[2] | |
hidden = 64 | |
model = Sequential() | |
model.add(LSTM(hidden, input_shape=(examples, features))) | |
model.add(Dropout(.2)) | |
model.add(Dense(y_examples)) | |
model.add(Activation('linear')) | |
model.compile(loss='mse', optimizer='rmsprop') | |
# Train | |
history = LossHistory() | |
model.fit(input_mat, target_mat, nb_epoch=100, batch_size=400, callbacks=[history]) |
Hi,
Could you please tell me how to predict the next 10 days in future? (i.e.) the steps after model.fit and how to evaluate this model.
Also is it possible to do multiple sequences input with Stateful LSTM?Thanks in advance.
u need tu put a Dense layer as output with 10 units, and train your network with the same structure N-imputs and 10 outputs values
Hello!
Would you like to help me?
I am stuck on a problem, how to fit a multiple input CNN or LSTM model.
I have a time series data divided (split) into train, test, and validation
I want to give the same training data to two different CNN models and concatenate them. I have built the model as shown in the figure, input shape =168,23
My network is;
but I am not getting how to fit this model.
once I tried to fit the model I face the error
@sarahboufelja @bv123 @kascesar @Sudarsan9966 will be waiting for your kind reply.
Thank you
Dear lukovkin, Suppose I have multiple time series as input and I need to predict all these time series at once for the next 10 days, how should I reshape the input and target datasets?
Regards