def main():
import sys
import Orange
argv = sys.argv
if len(argv) > 1:
filename = argv[1]
else:
filename = 'iris'
app = QtGui.QApplication(argv)
ow = OWPythagorasTree()
data = Orange.data.Table(filename)
if data.domain.has_discrete_class:
from Orange.classification.tree import TreeLearner
else:
from Orange.regression.tree import TreeLearner
model = TreeLearner(max_depth=1000)(data)
model.instances = data
ow.set_tree(model)
ow.show()
ow.raise_()
ow.handleNewSignals()
app.exec_()
sys.exit(0)
def main(argv=sys.argv):
from AnyQt.QtWidgets import QApplication
import Orange
app = QApplication(list(argv))
argv = app.arguments()
if len(argv) > 1:
filename = argv[1]
else:
filename = 'iris'
ow = OWPythagorasTree()
data = Orange.data.Table(filename)
if data.domain.has_discrete_class:
from Orange.classification.tree import TreeLearner
else:
from Orange.regression.tree import TreeLearner
model = TreeLearner(max_depth=1000)(data)
model.instances = data
ow.set_tree(model)
ow.show()
ow.raise_()
ow.handleNewSignals()
app.exec_()
sys.exit(0)
def main():
import sys
import Orange
argv = sys.argv
if len(argv) > 1:
filename = argv[1]
else:
filename = 'iris'
app = QtGui.QApplication(argv)
ow = OWPythagorasTree()
data = Orange.data.Table(filename)
if data.domain.has_discrete_class:
from Orange.classification.tree import TreeLearner
model = TreeLearner(max_depth=1000)(data)
else:
from Orange.regression.tree import TreeRegressionLearner
model = TreeRegressionLearner(max_depth=1000)(data)
model.instances = data
ow.set_tree(model)
ow.show()
ow.raise_()
ow.handleNewSignals()
app.exec_()
sys.exit(0)
def test_report_widgets_classify(self):
rep = OWReport.get_instance()
data = Table("titanic")
widgets = self.clas_widgets
w = self.create_widget(OWTreeGraph)
clf = TreeLearner(max_depth=3)(data)
clf.instances = data
w.ctree(clf)
w.create_report_html()
rep.make_report(w)
self._create_report(widgets, rep, data)
def test_report_widgets_model(self):
rep = OWReport.get_instance()
data = Table("titanic")
widgets = self.model_widgets
w = self.create_widget(OWTreeGraph)
clf = TreeLearner(max_depth=3)(data)
clf.instances = data
w.ctree(clf)
w.create_report_html()
rep.make_report(w)
self._create_report(widgets, rep, data)
def test_report_widgets_classify(self):
rep = OWReport.get_instance()
data = Table("zoo")
widgets = self.clas_widgets
w = OWClassificationTreeGraph()
clf = TreeLearner(max_depth=3)(data)
clf.instances = data
w.ctree(clf)
w.create_report_html()
rep.make_report(w)
self.assertEqual(len(widgets) + 1, 8)
self._create_report(widgets, rep, data)
def test_report_widgets_classify(self):
rep = OWReport.get_instance()
data = Table("zoo")
widgets = self.clas_widgets
w = OWClassificationTreeGraph()
clf = TreeLearner(max_depth=3)(data)
clf.instances = data
w.ctree(clf)
w.create_report_html()
rep.make_report(w)
self.assertEqual(len(widgets) + 1, 8)
self._create_report(widgets, rep, data)
def set_learner(self):
self.learner = TreeLearner(
criterion=self.scores[self.attribute_score][1],
max_depth=self.max_depth,
min_samples_split=self.min_internal,
min_samples_leaf=self.min_leaf,
preprocessors=self.preprocessors)
self.learner.name = self.model_name
self.classifier = None
if self.data is not None:
self.error(1)
if not self.learner.check_learner_adequacy(self.data.domain):
self.error(1, self.learner.learner_adequacy_err_msg)
else:
self.classifier = self.learner(self.data)
self.classifier.name = self.model_name
self.classifier.instances = self.data
self.send("Learner", self.learner)
self.send("Classification Tree", self.classifier)
def main():
from AnyQt.QtWidgets import QApplication
import sys
app = QApplication(sys.argv)
ow = OWPythagorasTree()
data = Table(sys.argv[1] if len(sys.argv) > 1 else 'iris')
if data.domain.has_discrete_class:
from Orange.classification.tree import SklTreeLearner as TreeLearner
else:
from Orange.regression.tree import SklTreeRegressionLearner as TreeLearner
model = TreeLearner(max_depth=1000)(data)
model.instances = data
ow.set_tree(model)
ow.show()
ow.raise_()
ow.handleNewSignals()
app.exec_()
def set_learner(self):
self.learner = TreeLearner(
criterion=self.scores[self.attribute_score][1],
max_depth=self.max_depth,
min_samples_split=self.min_internal,
min_samples_leaf=self.min_leaf,
preprocessors=self.preprocessors
)
self.learner.name = self.model_name
self.classifier = None
if self.data is not None:
self.error(1)
if not self.learner.check_learner_adequacy(self.data.domain):
self.error(1, self.learner.learner_adequacy_err_msg)
else:
self.classifier = self.learner(self.data)
self.classifier.name = self.model_name
self.classifier.instances = self.data
self.send("Learner", self.learner)
self.send("Classification Tree", self.classifier)
def main():
import sys
import Orange
from Orange.classification.tree import TreeLearner
argv = sys.argv
if len(argv) > 1:
filename = argv[1]
else:
filename = 'iris'
app = QtGui.QApplication(argv)
ow = OWPythagorasTree()
data = Orange.data.Table(filename)
clf = TreeLearner(max_depth=1000)(data)
ow.set_tree(clf)
ow.show()
ow.raise_()
ow.handleNewSignals()
app.exec_()
sys.exit(0)
def toggle_node_color(self):
colors = self.scene.colors
for node in self.scene.nodes():
distr = node.get_distribution()
total = numpy.sum(distr)
if self.target_class_index:
p = distr[self.target_class_index - 1] / total
color = colors[self.target_class_index - 1].light(200 - 100 * p)
else:
modus = node.majority()
p = distr[modus] / (total or 1)
color = colors[int(modus)].light(400 - 300 * p)
node.backgroundBrush = QBrush(color)
self.scene.update()
if __name__ == "__main__":
from Orange.classification.tree import TreeLearner
a = QApplication(sys.argv)
ow = OWClassificationTreeGraph()
data = Table("iris")
clf = TreeLearner(max_depth=3)(data)
clf.instances = data
ow.ctree(clf)
ow.show()
ow.raise_()
a.exec_()
ow.saveSettings()
class OWClassificationTree(widget.OWWidget):
name = "Classification Tree"
icon = "icons/ClassificationTree.svg"
description = "Classification tree algorithm with forward pruning."
priority = 30
inputs = [("Data", Table, "set_data"),
("Preprocessor", Preprocess, "set_preprocessor")]
outputs = [
("Learner", TreeLearner),
("Classification Tree", TreeClassifier)
]
want_main_area = False
resizing_enabled = False
model_name = Setting("Classification Tree")
attribute_score = Setting(0)
limit_min_leaf = Setting(True)
min_leaf = Setting(2)
limit_min_internal = Setting(True)
min_internal = Setting(5)
limit_depth = Setting(True)
max_depth = Setting(100)
scores = (("Entropy", "entropy"), ("Gini Index", "gini"))
def __init__(self):
super().__init__()
self.data = None
self.learner = None
self.preprocessors = None
self.classifier = None
gui.lineEdit(self.controlArea, self, 'model_name', box='Name',
tooltip='The name will identify this model in other '
'widgets')
gui.comboBox(self.controlArea, self, "attribute_score",
box='Feature selection',
items=[name for name, _ in self.scores])
box = gui.widgetBox(self.controlArea, 'Pruning')
gui.spin(box, self, "min_leaf", 1, 1000,
label="Min. instances in leaves ", checked="limit_min_leaf")
gui.spin(box, self, "min_internal", 1, 1000,
label="Stop splitting nodes with less instances than ",
checked="limit_min_internal")
gui.spin(box, self, "max_depth", 1, 1000,
label="Limit the depth to ", checked="limit_depth")
self.btn_apply = gui.button(self.controlArea, self, "&Apply",
callback=self.set_learner, disabled=0,
default=True)
self.set_learner()
def sendReport(self):
self.reportSettings(
"Model parameters",
[("Attribute selection", self.scores[self.attribute_score][0]),
("Pruning", ", ".join(s for s, c in (
("%i instances in leaves" % self.min_leaf,
self.limit_min_leaf),
("%i instance in internal node" % self.min_internal,
self.limit_min_internal),
("maximum depth %i" % self.max_depth, self.limit_depth)) if c)
or ": None")])
self.reportData(self.data)
def set_learner(self):
self.learner = TreeLearner(
criterion=self.scores[self.attribute_score][1],
max_depth=self.max_depth,
min_samples_split=self.min_internal,
min_samples_leaf=self.min_leaf,
preprocessors=self.preprocessors
)
self.learner.name = self.model_name
self.classifier = None
if self.data is not None:
self.error(1)
if not self.learner.check_learner_adequacy(self.data.domain):
self.error(1, self.learner.learner_adequacy_err_msg)
else:
self.classifier = self.learner(self.data)
self.classifier.name = self.model_name
self.classifier.instances = self.data
self.send("Learner", self.learner)
self.send("Classification Tree", self.classifier)
@check_sql_input
def set_data(self, data):
self.error(0)
self.data = data
if data is not None and data.domain.class_var is None:
self.error(0, "Data has no target variable")
self.data = None
self.set_learner()
def set_preprocessor(self, preproc):
if preproc is None:
self.preprocessors = None
else:
self.preprocessors = (preproc,)
self.set_learner()
class OWClassificationTree(widget.OWWidget):
name = "Classification Tree"
icon = "icons/ClassificationTree.svg"
description = "Classification tree algorithm with forward pruning."
priority = 30
inputs = [("Data", Table, "set_data"),
("Preprocessor", Preprocess, "set_preprocessor")]
outputs = [("Learner", TreeLearner),
("Classification Tree", TreeClassifier)]
want_main_area = False
resizing_enabled = False
model_name = Setting("Classification Tree")
attribute_score = Setting(0)
limit_min_leaf = Setting(True)
min_leaf = Setting(2)
limit_min_internal = Setting(True)
min_internal = Setting(5)
limit_depth = Setting(True)
max_depth = Setting(100)
scores = (("Entropy", "entropy"), ("Gini Index", "gini"))
def __init__(self):
super().__init__()
self.data = None
self.learner = None
self.preprocessors = None
self.classifier = None
gui.lineEdit(self.controlArea,
self,
'model_name',
box='Name',
tooltip='The name will identify this model in other '
'widgets')
gui.comboBox(self.controlArea,
self,
"attribute_score",
box='Feature selection',
items=[name for name, _ in self.scores])
box = gui.widgetBox(self.controlArea, 'Pruning')
gui.spin(box,
self,
"min_leaf",
1,
1000,
label="Min. instances in leaves ",
checked="limit_min_leaf")
gui.spin(box,
self,
"min_internal",
1,
1000,
label="Stop splitting nodes with less instances than ",
checked="limit_min_internal")
gui.spin(box,
self,
"max_depth",
1,
1000,
label="Limit the depth to ",
checked="limit_depth")
self.btn_apply = gui.button(self.controlArea,
self,
"&Apply",
callback=self.set_learner,
disabled=0,
default=True)
self.set_learner()
def sendReport(self):
self.reportSettings(
"Model parameters",
[("Attribute selection", self.scores[self.attribute_score][0]),
("Pruning", ", ".join(s for s, c in (
("%i instances in leaves" % self.min_leaf,
self.limit_min_leaf),
("%i instance in internal node" % self.min_internal,
self.limit_min_internal),
("maximum depth %i" % self.max_depth, self.limit_depth)) if c)
or ": None")])
self.reportData(self.data)
def set_learner(self):
self.learner = TreeLearner(
criterion=self.scores[self.attribute_score][1],
max_depth=self.max_depth,
min_samples_split=self.min_internal,
min_samples_leaf=self.min_leaf,
preprocessors=self.preprocessors)
self.learner.name = self.model_name
self.classifier = None
if self.data is not None:
self.error(1)
if not self.learner.check_learner_adequacy(self.data.domain):
self.error(1, self.learner.learner_adequacy_err_msg)
else:
self.classifier = self.learner(self.data)
self.classifier.name = self.model_name
self.classifier.instances = self.data
self.send("Learner", self.learner)
self.send("Classification Tree", self.classifier)
@check_sql_input
def set_data(self, data):
self.error(0)
self.data = data
if data is not None and data.domain.class_var is None:
self.error(0, "Data has no target variable")
self.data = None
self.set_learner()
def set_preprocessor(self, preproc):
if preproc is None:
self.preprocessors = None
else:
self.preprocessors = (preproc, )
self.set_learner()
def paint(self, painter, option, widget=None):
rect = self.rect()
if self.isSelected():
option.state ^= QStyle.State_Selected
painter.setFont(self.document().defaultFont())
draw_text = str(self.split_condition())
painter.drawText(QPointF(4, -self.line_descent - 1), draw_text)
painter.save()
painter.setBrush(self.backgroundBrush)
if self.isSelected():
painter.setPen(QPen(QBrush(Qt.black), 2))
else:
painter.setPen(QPen(Qt.gray))
if self.is_leaf():
painter.drawRect(rect.adjusted(-3, 0, 0, 0))
else:
painter.drawRoundedRect(rect.adjusted(-3, 0, 0, 0), 4, 4)
painter.restore()
painter.setClipRect(rect)
return QGraphicsTextItem.paint(self, painter, option, widget)
if __name__ == "__main__":
from Orange.classification.tree import TreeLearner
a = QApplication(sys.argv)
ow = OWClassificationTreeGraph()
ow.ctree(TreeLearner(max_depth=3)(Table('iris')))
ow.show()
a.exec_()
ow.saveSettings()
