def test_adaboost_base_estimator(self):
np.random.seed(0)
stump_estimator = SklTreeLearner(max_depth=1)
tree_estimator = SklTreeLearner()
stump = SklAdaBoostLearner(base_estimator=stump_estimator)
tree = SklAdaBoostLearner(base_estimator=tree_estimator)
results = CrossValidation(self.iris, [stump, tree], k=4)
ca = CA(results)
self.assertLess(ca[0], ca[1])
def test_adaboost_base_estimator(self):
np.random.seed(0)
stump_estimator = SklTreeLearner(max_depth=1)
tree_estimator = SklTreeLearner()
stump = SklAdaBoostClassificationLearner(
base_estimator=stump_estimator, n_estimators=5)
tree = SklAdaBoostClassificationLearner(base_estimator=tree_estimator,
n_estimators=5)
cv = CrossValidation(k=4)
results = cv(self.iris, [stump, tree])
ca = CA(results)
self.assertLessEqual(ca[0], ca[1])
def test_input_learner(self):
"""Check if base learner properly changes with learner on the input"""
max_depth = 2
default_base_est = self.widget.base_estimator
self.assertIsInstance(default_base_est, SklTreeLearner)
self.assertIsNone(default_base_est.params.get("max_depth"))
self.send_signal("Learner", SklTreeLearner(max_depth=max_depth))
self.assertEqual(self.widget.base_estimator.params.get("max_depth"),
max_depth)
self.widget.apply_button.button.click()
output_base_est = self.get_output("Learner").params.get("base_estimator")
self.assertEqual(output_base_est.max_depth, max_depth)
def test_tree(self):
tree = SklTreeLearner()
res = CrossValidation(self.iris, [tree], k=2)
self.assertGreater(AUC(res)[0], 0.8)
self.assertLess(AUC(res)[0], 1.)
def test_classification(self):
table = Table('iris')
learn = SklTreeLearner()
clf = learn(table)
Z = clf(table)
self.assertTrue(np.all(table.Y.flatten() == Z))
with open(exportFilePath, "w") as output:
datae1.to_csv(output, header=True, sep=",")
path1 = ("C:\\Users\\acer\\Desktop\\friends\\export.csv")
datae = p.read_csv(path1)
'''
now fro b part'''
from Orange.classification import SklTreeLearner
td = Table.from_file("C:\\Users\\acer\\Desktop\\friends\\export.csv")
#print(data1.domain)
#print(d)
feature_vars = list(td.domain.variables[1:])
class_label_var = td.domain.variables[7]
print(class_label_var)
md = Domain(feature_vars, class_label_var)
#print(d_dis[0])
td = Table.from_table(domain=md, source=td)
#print(.domain.variables[1:])
n1 = td.approx_len()
print(n1 * 80 / 100)
train_data_set = td[:1360]
test_data_set = td[1360:]
#print(train_data_set.domain)
#print(test_data_set.domain)
tree_learner = SklTreeLearner()
decision_tree = tree_learner(train_data_set)
results = CrossValidation(td, [tree_learner], k=10)
print(decision_tree(test_data_set))
print("Accuracy", scoring.CA(results)[0])
print("AUC", scoring.AUC(results)[0])
class OWAdaBoostClassification(OWBaseLearner):
name = "AdaBoost"
description = "An ensemble meta-algorithm that combines weak learners " \
"and adapts to the 'hardness' of each training sample. "
icon = "icons/AdaBoost.svg"
priority = 80
LEARNER = SklAdaBoostLearner
inputs = [("Learner", LearnerClassification, "set_base_learner")]
losses = ["SAMME", "SAMME.R"]
n_estimators = Setting(50)
learning_rate = Setting(1.)
algorithm = Setting(0)
DEFAULT_BASE_ESTIMATOR = SklTreeLearner()
class Error(OWBaseLearner.Error):
no_weight_support = Msg('The base learner does not support weights.')
def add_main_layout(self):
box = gui.widgetBox(self.controlArea, "Parameters")
self.base_estimator = self.DEFAULT_BASE_ESTIMATOR
self.base_label = gui.label(
box, self, "Base estimator: " + self.base_estimator.name)
self.n_estimators_spin = gui.spin(box,
self,
"n_estimators",
1,
100,
label="Number of estimators:",
alignment=Qt.AlignRight,
controlWidth=80,
callback=self.settings_changed)
self.learning_rate_spin = gui.doubleSpin(
box,
self,
"learning_rate",
1e-5,
1.0,
1e-5,
label="Learning rate:",
decimals=5,
alignment=Qt.AlignRight,
controlWidth=80,
callback=self.settings_changed)
self.add_specific_parameters(box)
def add_specific_parameters(self, box):
self.algorithm_combo = gui.comboBox(box,
self,
"algorithm",
label="Algorithm:",
items=self.losses,
orientation=Qt.Horizontal,
callback=self.settings_changed)
def create_learner(self):
if self.base_estimator is None:
return None
return self.LEARNER(base_estimator=self.base_estimator,
n_estimators=self.n_estimators,
learning_rate=self.learning_rate,
preprocessors=self.preprocessors,
algorithm=self.losses[self.algorithm])
def set_base_learner(self, learner):
self.Error.no_weight_support.clear()
if learner and not learner.supports_weights:
# Clear the error and reset to default base learner
self.Error.no_weight_support()
self.base_estimator = None
self.base_label.setText("Base estimator: INVALID")
else:
self.base_estimator = learner or self.DEFAULT_BASE_ESTIMATOR
self.base_label.setText("Base estimator: " +
self.base_estimator.name)
if self.auto_apply:
self.apply()
def get_learner_parameters(self):
return (("Base estimator", self.base_estimator),
("Number of estimators", self.n_estimators),
("Algorithm", self.losses[self.algorithm].capitalize()))
def build_decision_tree(max_leaf=None):
tree_learner = SklTreeLearner(max_leaf_nodes=max_leaf)
decision_tree = tree_learner(train_dataset)
print(decision_tree)
return tree_learner, decision_tree
"""
#rm_elem takes input list,l and index, i and returns a tuple (a,b), a is the
#element at l[i] and b is the list without a.
def rm_elem(l, i):
(a,b) = ('', [])
for x in range(len(l)):
if x==i: a = l[x]
else: b.append(l[x])
return (a,b)
data_tab = Table.from_file(csv_path_fixed)
class_label_var, feature_vars = rm_elem(data_tab.domain, inx_class_label)
assg1_domain = Domain(feature_vars, class_label_var)
data_tab = Table.from_table(domain=assg1_domain, source=data_tab)
tree_learner = SklTreeLearner()
eval_results = CrossValidation(data_tab, [tree_learner], k=10)
print("Accuracy of cross validation: {:.3f}".format(scoring.CA(eval_results)[0]))
print("AUC: {:.3f}".format(scoring.AUC(eval_results)[0]))
"""
Setting max_leaf_nodes to 4 instead of allowing it to be unlimited as in previous part.
"""
tree_learner_max = SklTreeLearner(max_leaf_nodes = 4)
eval_results_max = CrossValidation(data_tab, [tree_learner_max], k=10)
print("\n\nResult of a decision tree with the limitation to only use 4 leaf nodes\n ")
print("Accuracy of cross validation: {:.3f}".format(scoring.CA(eval_results_max)[0]))
print("AUC: {:.3f}".format(scoring.AUC(eval_results_max)[0]))