def model_selection(learner, dataset, k=10, trials=1):
"""[Fig 18.8]
Return the optimal value of size having minimum error
on validation set.
err_train: A training error array, indexed by size
err_val: A validation error array, indexed by size
"""
errs = []
size = 1
while True:
err = cross_validation(learner, size, dataset, k, trials)
# Check for convergence provided err_val is not empty
if err and not isclose(err[-1], err, rel_tol=1e-6):
best_size = 0
min_val = math.inf
i = 0
while i < size:
if errs[i] < min_val:
min_val = errs[i]
best_size = i
i += 1
return learner(dataset, best_size)
errs.append(err)
size += 1
def normalize(self):
"""Make sure the probabilities of all values sum to 1.
Returns the normalized distribution.
Raises a ZeroDivisionError if the sum of the values is 0."""
total = sum(self.prob.values())
if not isclose(total, 1.0):
for val in self.prob:
self.prob[val] /= total
return self