def test_cv_shuffled(self):
"""Do not take folds in order
- shuffle because data is frequently clustered """
_, y = data_iris()
X = np.array([[i] for i in range(100)])
pred = solution.test_cv(DummyShuffleLearner(), X, y, k=4)
self.assertIsNotNone(pred)
def test_cv(self):
for X, y in [data1(), data2()]:
pred = solution.test_cv(DummyCVLearner(), X, y, k=4)
if len(y) == 8:
# training data should have 6 instances
self.assertEqual(pred[0][1], 6)
if len(set([a for _, a in pred])) != 1 and len(y) % 4 == 0:
raise FoldsNotEqualSize()
signatures = [a for a, _ in pred]
if len(set(signatures)) != len(y):
raise NotAllTested()
if signatures != list(map(lambda x: sum(list(x)), X)):
raise MixedOrder()
def test_cv(self):
for X, y in [data1(), data2()]:
X_copy = X.copy()
pred = test_cv(DummyCVLearner(), X, y, k=4)
if len(y) == 8:
# on the first DS training data should have 6 instances
self.assertEqual(pred[0][1], 6)
# on the dirst DS all folds should be of equal size
if len(set([a for _, a in pred])) != 1:
raise FoldsNotEqualSize()
signatures = [a for a, _ in pred]
if len(set(signatures)) != len(y):
raise NotAllTested()
if signatures != list(map(lambda x: sum(list(x)), X_copy)):
raise MixedOrder()
pylab.show()
X, y = solution.load('reg.data')
learner = solution.LogRegLearner(lambda_=0.)
classifier = learner(X, y)
draw_decision(X, y, classifier, 0, 1)
learner = solution.LogRegLearner(lambda_=0.01)
classifier = learner(X, y)
draw_decision(X, y, classifier, 0, 1)
learner = solution.LogRegLearner(lambda_=0.3)
classifier = learner(X, y)
draw_decision(X, y, classifier, 0, 1)
for lam in [0.0, 0.0001, 0.0005, 0.001, 0.01, 0.05, 0.1, 0.2, 0.3, 0.5]:
learner = solution.LogRegLearner(lambda_=lam)
res = solution.test_cv(learner, X, y)
res1 = solution.test_learning(learner, X, y)
print("Tocnost cv:", round(solution.CA(y, res),
3)) # argumenta sta pravi razredi, napovedani
print("Tocnost learning:",
round(solution.CA(y, res1),
3)) # argumenta sta pravi razredi, napovedani
print("\n")
#
# s.draw_decision(i, X, y, classifier, 0, 1)
# Part 3 test_cv:
X, y = s.load('reg.data')
lambdas = [10, 1, 0.5, 0.1, 0.075, 0.05, 0.03, 0.01, 0.001, 0.0001, 0.]
lambdas_ca = {l: 0 for l in lambdas}
for i in range(1,21):
for l in lambdas:
learner = s.LogRegLearner(lambda_=l)
res = s.test_cv(learner, X, y, seed=i)
ca = s.CA(y, res)
lambdas_ca[l] += ca
for l in lambdas_ca.keys():
print('Lambda:', l)
print('Tocnost', lambdas_ca[l]/20)
# # Part 3 test_learning:
#
# X, y = s.load('reg.data')
#
# lambdas = [10, 1, 0.5, 0.1, 0.05, 0.03, 0.01, 0.001, 0.0001, 0.]