def test_integration(self):
res = self.extractor.extract_features(self.files)
self.assertIsNotNone(res, "Failed to parse files.")
X, y, _, = res
train_X, test_X, train_y, test_y = \
model_selection.train_test_split(X, y, random_state=1989)
model = tree.DecisionTreeClassifier(min_samples_leaf=26,
random_state=1989,
max_depth=None,
max_features="auto",
min_samples_split=2)
model.fit(train_X, train_y)
rules = TrainableRules(
base_model_name="sklearn.tree.DecisionTreeClassifier",
prune_branches_algorithms=[],
prune_attributes=False,
min_samples_leaf=26,
random_state=1989,
max_depth=None,
max_features="auto",
min_samples_split=2,
confidence_threshold=0)
rules.fit(train_X, train_y)
model_score_train = model.score(train_X, train_y)
model_score_test = model.score(test_X, test_y)
rules_score_train = rules.score(train_X, train_y)
rules_score_test = rules.score(test_X, test_y)
self.assertEqual(rules_score_train, model_score_train)
self.assertEqual(rules_score_test, model_score_test)
def test_integration(self):
X, y, _ = self.extractor.extract_features(self.files)
train_X, test_X, train_y, test_y = \
model_selection.train_test_split(X, y, random_state=1989)
model = tree.DecisionTreeClassifier(min_samples_leaf=26,
random_state=1989,
max_depth=None,
max_features="auto",
min_samples_split=2)
model.fit(train_X, train_y)
rules = TrainableRules("sklearn.tree.DecisionTreeClassifier",
prune_branches_algorithms=[],
prune_attributes=False,
min_samples_leaf=26,
random_state=1989,
max_depth=None,
max_features="auto",
min_samples_split=2)
rules.fit(train_X, train_y)
model_score_train = model.score(train_X, train_y)
model_score_test = model.score(test_X, test_y)
rules_score_train = rules.score(train_X, train_y)
rules_score_test = rules.score(test_X, test_y)
self.assertEqual(rules_score_train, model_score_train)
self.assertEqual(rules_score_test, model_score_test)
def test_budget(budget):
rules = TrainableRules(
"sklearn.tree.DecisionTreeClassifier",
prune_branches_algorithms=["top-down-greedy"],
prune_attributes=False,
top_down_greedy_budget=(False, budget),
random_state=1989)
rules.fit(self.train_x, self.train_y)
return rules.score(self.train_x, self.train_y)
def test_tree_attr_pruning(self):
model = tree.DecisionTreeClassifier(min_samples_leaf=26,
random_state=1989)
model = model.fit(self.train_x, self.train_y)
rules = TrainableRules("sklearn.tree.DecisionTreeClassifier",
prune_branches_algorithms=[],
prune_attributes=True,
min_samples_leaf=26,
random_state=1989)
rules.fit(self.train_x, self.train_y)
tree_score = model.score(self.test_x, self.test_y)
rules_score = rules.score(self.test_x, self.test_y)
self.assertGreater(rules_score * 1.1, tree_score)
def test_tree_no_pruning(self):
model = tree.DecisionTreeClassifier(min_samples_leaf=26,
random_state=1989)
model = model.fit(self.train_x, self.train_y)
rules = TrainableRules(
base_model_name="sklearn.tree.DecisionTreeClassifier",
prune_branches_algorithms=[],
confidence_threshold=0,
prune_attributes=False,
min_samples_leaf=26,
random_state=1989)
rules.fit(self.train_x, self.train_y)
tree_score = model.score(self.train_x, self.train_y)
rules_score = rules.score(self.train_x, self.train_y)
self.assertGreater(rules_score * 1.1, tree_score)
def test_forest_no_pruning(self):
model = ensemble.RandomForestClassifier(n_estimators=50,
min_samples_leaf=26,
random_state=1989)
model = model.fit(self.train_x, self.train_y)
rules = TrainableRules("sklearn.ensemble.RandomForestClassifier",
prune_branches_algorithms=[],
prune_attributes=False,
n_estimators=50,
min_samples_leaf=26,
random_state=1989)
rules.fit(self.train_x, self.train_y)
forest_score = model.score(self.train_x, self.train_y)
rules_score = rules.score(self.train_x, self.train_y)
self.assertGreater(rules_score * 1.1, forest_score)