def test_on_numeric_madelon(self):
X, y = get_data('madelon')
X_test, y_test = get_data('madelon', test=True)
clf = DecisionTree()
clf.fit(X, y)
y_hat = clf.predict(X_test)
score = accuracy_score(y_test, y_hat)
self.assertTrue(score > 0.97)
def test_fit(self):
clf = LinearGradientDescent()
X, y = get_data('table2')
clf.fit(X, y)
y_hat = clf.predict(X)
score = accuracy_score(y, y_hat)
assert_almost_equal(score, 0.833333333)
def test_fit(self):
clf = Perceptron(weight_initialization='zeros', shuffle=False)
X, y = get_data('table2')
clf.fit(X, y)
y_hat = clf.predict(X)
score = accuracy_score(y, y_hat)
assert_almost_equal(score, 0.8333333)
def test_fit_madelon(self):
clf = SVM(shuffle=False, epochs=1, weight_initialization='zeros')
X, y = get_data('madelon')
clf.fit(X, y)
y_hat = clf.predict(X)
score = accuracy_score(y, y_hat)
assert_almost_equal(score, 0.5505, decimal=4)
def test_fit_madelon(self):
np.random.seed(0)
clf = SVMRandomForest(N=5, m=20)
X, y = get_data('madelon')
clf.fit(X, y)
y_hat = clf.predict(X)
score = accuracy_score(y, y_hat)
assert_almost_equal(score, -1)
def test_fit_handwriting(self):
np.random.seed(0)
clf = SVMRandomForest(N=5, m=100)
X, y = get_data('handwriting')
clf.fit(X, y)
y_hat = clf.predict(X)
score = accuracy_score(y, y_hat)
assert_almost_equal(score, 1)
def test_numerical_data_works_with_missing_method_choices(self):
X, y = get_data('blobs')
clf = DecisionTree(missing_method='majority_value')
clf.fit(X, y)
y_hat = clf.predict(X)
score = accuracy_score(y, y_hat)
self.assertTrue(score > 0.97)
def test_numerical_data(self):
X, y = get_data('blobs')
clf = DecisionTree()
clf.fit(X, y)
y_hat = clf.predict(X)
score = accuracy_score(y, y_hat)
self.assertTrue(score > 0.97)
def test_setting_a(self):
X, y = get_data('mushroom', setting='SettingA')
X_test, y_test = get_data('mushroom', setting='SettingA', test=True)
clf = DecisionTree()
clf.fit(X, y)
y_hat = clf.predict(X_test)
score = accuracy_score(y_test, y_hat)
self.assertEqual(score, 1)
# how does it compare to sklearn
clf = DecisionTreeClassifier()
Xt = pd.get_dummies(pd.DataFrame(X)).values
Xt_test = pd.get_dummies(pd.DataFrame(X_test)).values
clf.fit(Xt, y)
y_hat = clf.predict(Xt_test)
score = accuracy_score(y_test, y_hat)
self.assertEqual(score, 1)
def test_stuff(self):
return # TODO
# TODO how do you use the same base classifier over & over?
# nothing makes it any different, so how do you get it
# to select different things...
X,y = get_data('table2')
clf = AdaBoost([
DecisionTree(max_depth=1),
DecisionTree(max_depth=2),
DecisionTree(max_depth=3),
DecisionTree(max_depth=1, best_attr_method='gini'),
DecisionTree(max_depth=2, best_attr_method='gini'),
DecisionTree(max_depth=3, best_attr_method='gini'),
], T=5)
clf.fit(X, y)
y_hat = clf.predict(X)
score = accuracy_score(y, y_hat)
self.assertEqual(score, 1)