0
$\begingroup$

I was training my LSTM for time series prediction and my script is:

def create_dataset(dataset, look_back=1):
dataX, dataY = [], []
for i in range(len(dataset)-look_back-1):
    a = dataset[i:(i+look_back), 0]
    dataX.append(a)
    dataY.append(dataset[i + look_back, 0])
return np.array(dataX), np.array(dataY) 
df= pd.read_csv('/content/EXT1.csv', header=None,index_col=0, delimiter=';')
df.head()
df.plot(subplots=True)
all_y = df[1].values
dataset=all_y.reshape(-1, 1)
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset)
print(dataset)
train_size = int(len(dataset) * 0.75)
test_size = len(dataset) - train_size
train, test = dataset[0:train_size,:], dataset[train_size:len(dataset),:]
print(len(test),len(train) )
look_back = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
# reshape input to be [samples, time steps, features]
trainX = np.reshape(trainX, (trainX.shape[0], trainX.shape[1], 1))
testX = np.reshape(testX, (testX.shape[0], testX.shape[1], 1))
# create and fit the LSTM network
batch_size=500
model = Sequential()
model.add(LSTM(25, input_shape=(1, look_back)))
model.add(Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam')
model.fit(trainX, trainY, epochs=1000, batch_size=batch_size, verbose=1)

when I make prediction I use the testX, is it logical?

# make predictions
trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
# invert predictions
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform([trainY])
testY = scaler.inverse_transform([testY])
testPredict = scaler.inverse_transform(testPredict)
# calculate root mean squared error
trainScore = math.sqrt(mean_squared_error(trainY[0], trainPredict[:,0]))
print('Train Score: %.2f RMSE' % (trainScore))
testScore = math.sqrt(mean_squared_error(testY[0], testPredict[:,0]))
print('Test Score: %.2f RMSE' % (testScore))

I get these results for RMS: 0.06 for training and 0.07 for test I think that for validation I should not use testX here testPredict = model.predict(testX) because the data in testX and testY is similar. What do you think, please?

$\endgroup$
  • $\begingroup$ why do you think there is something wrong with those results? $\endgroup$ – Nikos M. Jul 20 at 7:24

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.