mse = (error * error).mean()
mse_delta = mse
print 'Initial mean squared error: {0}'.format(mse)
# Iterate until convergence is reached
iteration = 1
while mse_delta >= CONVERGENCE_THRESHOLD:
# Calculate the features using the previous step's values where necessary
for i,x in enumerate(X):
# Get the partial residual
error = y - np.sum(features[0:i], axis=0) - np.sum(features[i+1:], axis=0)
# Update our kernel parameters for the partial derivative
sqexp = partial(squared_exponential, BANDWIDTHS[i], 0.5 * (error.max() - error.min()), TAU2)
gp.cov = sqexp
# Get the new feature
f_i = gp.predict(x, x, error, error.std(), percentile=None)[0]
# Update the feature list
features[i] = f_i
# Calculate the total error
error = y - np.sum(features, axis=0)
# Track the squared error of the estimates
prev_mse = mse
mse = (error * error).mean()
mse_delta = np.abs(prev_mse - mse)
