I am trying to make forecasting on 12 months basis using a LSTM. The code I have know, inspired by machinelearningmastery.com, works by using walk forward validation using the observed values, from the test set, and I would like it to use the predicted value in the walk forward validation instead. So does any one know how to do walk forward validation on predicted values and not observed values? The code is shown below:
# frame a sequence as a supervised learning problem
def timeseries_to_supervised(data, lag=1):
df = DataFrame(data)
columns = [df.shift(i) for i in range(1, lag+1)]
columns.append(df)
df = concat(columns, axis=1)
df.fillna(0, inplace=True)
return df
# create a differenced series
def difference(dataset, interval=1):
diff = list()
for i in range(interval, len(dataset)):
value = dataset[i] - dataset[i - interval]
diff.append(value)
return Series(diff)
# invert differenced value
def inverse_difference(history, yhat, interval=1):
return yhat + history[-interval]
# scale train and test data to [-1, 1]
def scale(train, test):
# fit scaler
scaler = MinMaxScaler(feature_range=(-1, 1))
scaler = scaler.fit(train)
# transform train
train = train.reshape(train.shape[0], train.shape[1])
train_scaled = scaler.transform(train)
# transform test
test = test.reshape(test.shape[0], test.shape[1])
test_scaled = scaler.transform(test)
return scaler, train_scaled, test_scaled
# inverse scaling for a forecasted value
def invert_scale(scaler, X, value):
new_row = [x for x in X] + [value]
array = np.array(new_row)
array = array.reshape(1, len(array))
inverted = scaler.inverse_transform(array)
return inverted[0, -1]
# fit an LSTM network to training data
def fit_lstm(train, batch_size, nb_epoch, neurons):
X, y = train[:, 0:-1], train[:, -1]
X = X.reshape(X.shape[0], 1, X.shape[1])
model = Sequential()
model.add(LSTM(neurons, batch_input_shape=(batch_size, X.shape[1], X.shape[2]), stateful=True))
model.add(Dense(32, 'relu'))
model.add(Dense(4, 'linear'))
opt = keras.optimizers.Adam(learning_rate=0.001)
model.compile(loss='mean_squared_error', optimizer=opt)
for i in range(nb_epoch):
model.fit(X, y, epochs=1, batch_size=batch_size, verbose=0, shuffle=False)
model.reset_states()
return model
# make a one-step forecast
def forecast_lstm(model, batch_size, X):
X = X.reshape(1, 1, len(X))
yhat = model.predict(X, batch_size=batch_size)
return yhat[0,0]
# MDAPE
def mean_absolute_percentage_error(y_true, y_pred):
y_true, y_pred = np.array(y_true), np.array(y_pred)
return np.median(np.abs((y_true - y_pred) / y_true)) * 100
# transform data to be stationary
raw_values = df['tmp'].values
diff_values = difference(raw_values, 1)
# transform data to be supervised learning
supervised = timeseries_to_supervised(diff_values, 1)
supervised_values = supervised.values
# split data into train and test-sets
train, test = supervised_values[0:-12], supervised_values[-12:]
# transform the scale of the data
scaler, train_scaled, test_scaled = scale(train, test)
batch = 1
# repeat experiment
repeats = 10
error_scores = list()
error_scores_MDAPE = list()
percent_error = []
for r in range(repeats):
# fit the model
lstm_model = fit_lstm(train_scaled, batch, 100, 4)
# forecast the entire training dataset to build up state for forecasting
train_reshaped = train_scaled[:, 0].reshape(len(train_scaled), 1, 1)
lstm_model.predict(train_reshaped, batch_size=1)
# walk-forward validation on the test data
predictions = list()
for i in range(len(test_scaled)):
# make one-step forecast
X, y = test_scaled[i, 0:-1], test_scaled[i, -1]
yhat = forecast_lstm(lstm_model, batch, X)
# invert scaling
yhat = invert_scale(scaler, X, yhat)
# invert differencing
yhat = inverse_difference(raw_values, yhat, len(test_scaled)+1-i)
# store forecast
predictions.append(yhat)