%pylab inline

from sklearn.datasets import load_diabetes
data = load_diabetes()
X, y = data.data, data.target

print X.shape

print y.shape

from sklearn.linear_model import Ridge, Lasso

from sklearn.cross_validation import cross_val_score

for Model in [Ridge, Lasso]:
    model = Model()
    print Model.__name__, cross_val_score(model, X, y).mean()

alphas = np.logspace(-3, -1, 30)

# plot the mean cross-validation score for a Ridge estimator and a Lasso estimator
# as a function of alpha.  Which is more difficult to tune?

%load solutions/06B_basic_grid_search.py

from sklearn.grid_search import GridSearchCV

for Model in [Ridge, Lasso]:
    gscv = GridSearchCV(Model(), dict(alpha=alphas), cv=3).fit(X, y)
    print Model.__name__, gscv.best_params_

from sklearn.linear_model import RidgeCV, LassoCV
for Model in [RidgeCV, LassoCV]:
    model = Model(alphas=alphas, cv=3).fit(X, y)
    print Model.__name__, model.alpha_

from sklearn.metrics import mean_squared_error
# define a function that computes the learning curve (i.e. mean_squared_error as a function
# of training set size, for both training and test sets) and plot the result


%load solutions/06B_learning_curves.py