Small bug in notebook 06_learning_curves.ipynb

[NobleKennamer]

In the file doc/notebooks/06_learning_curves.ipynb, I believe there is a small mistake in the code box directly under the section "Cross-validation and Testing". The data that is supposed to be used for testing is defined by:

xtest = x[Ntrain:-Ntest]
ytest = y[Ntrain:-Ntest]

Making it the same data that is used for the Cross-Validation set. I think the above code should be replaced with:

xtest = x[-Ntest:]
ytest = y[-Ntest:]

I hope this helps and thanks for putting up this great tutorial. Your book has also been really helpful

[mycarta]

I noticed that too, and fixed it in a similar way:

xtest = x[(Ntrain + Ncrossval):]
ytest = y[(Ntrain + Ncrossval):]

Also, is the test set defined only for illustrative purposes in this notebook?
In the second box in the same "Cross-validation and Testing" section a test error is initialized as:
test_err = np.zeros(len(degrees))
but never used.

[mycarta]

Unless I'm mistaken, there's also a small bug in the third code box in the "Learning Curves: Exploring the Bias-Variance Tradeoff" section. When calculating the 1st order polynomial error for the three (x_new, y_new) points, shouldn't
print abs(np.sin(x_new) - y_new)
be instead
print abs(np.sin(2 * x_new) - y_new)