def print_tree(self, data, visual):
"""
Decision Tree from the data set
"""
tree = learner(data)
orngTree.printTxt(tree)
if visual: # visual equals true allows plotting a visual tree. A .dot file is written into the current directory.
orngTree.printDot(tree, fileName='tree.dot', internalNodeShape="ellipse", leafShape="box")
def print_tree(self, data, visual):
"""
Decision Tree from the data set
"""
tree = learner(data)
orngTree.printTxt(tree)
if visual: # visual equals true allows plotting a visual tree. A .dot file is written into the current directory.
orngTree.printDot(tree,
fileName='tree.dot',
internalNodeShape="ellipse",
leafShape="box")
def report_tree(self, name):
filename = name + '.tsv'
stream = file(filename, 'wt')
# header
stream.write('\t'.join(self.names) + '\n')
stream.write('\t'.join(self.types) + '\n')
stream.write('class\n')
# rows
for row in self.rows:
if row[0] == 'skip':
continue
row += [''] * (len(self.names) - len(row))
stream.write('\t'.join(row) + '\n')
stream.close()
# See http://www.ailab.si/orange/doc/ofb/c_otherclass.htm
try:
import orange
import orngTree
except ImportError:
sys.stderr.write(
'Install Orange from http://www.ailab.si/orange/ for a classification tree.\n'
)
return None
data = orange.ExampleTable(filename)
tree = orngTree.TreeLearner(data, sameMajorityPruning=1, mForPruning=2)
orngTree.printTxt(tree, maxDepth=4)
text_tree = orngTree.dumpTree(tree)
file(name + '.txt', 'wt').write(text_tree)
orngTree.printDot(tree,
fileName=name + '.dot',
nodeShape='ellipse',
leafShape='box')
return text_tree
def main():
"""Main script"""
paper_table = build_papers_table()
tree = orngTree.TreeLearner(minSubset=5, sameMajorityPruning=True)
learners = [tree]
FOLDS = 10
results = Orange.evaluation.testing.cross_validation(learners,
paper_table,
folds=FOLDS,
storeClassifiers=1)
confusions = []
print "Learner CA Brier AUC"
for i in range(len(learners)):
print "%-8s %5.3f %5.3f %5.3f" % (learners[i].name, \
Orange.evaluation.scoring.CA(results)[i],
Orange.evaluation.scoring.Brier_score(results)[i],
Orange.evaluation.scoring.AUC(results)[i])
for k in range(0, FOLDS):
indices = [
paper_table[x] for x in range(0, len(paper_table))
if results.results[x].iteration_number == k
]
confusions.append(
buildConfusion(indices, results.classifiers[k][i],
TYPE_DIRS.keys()))
confusion = buildTotalConfusions(confusions, TYPE_DIRS.keys())
printConfusion(confusion, TYPE_DIRS.keys())
printMeasures(confusion)
orngTree.printTxt(results.classifiers[k][i],
leafStr="%V (%M / %N)",
nodeStr="(%M / %N)",
leafFields=['major', 'contingency'])
def summary(self):
sys.stdout.write("%u tests, %u passed, %u skipped, %u failed\n\n" %
(self.tests, self.passed, self.skipped, self.failed))
sys.stdout.flush()
name, ext = os.path.splitext(os.path.basename(sys.argv[0]))
filename = name + '.tsv'
stream = file(filename, 'wt')
# header
stream.write('\t'.join(self.names) + '\n')
stream.write('\t'.join(self.types) + '\n')
stream.write('class\n')
# rows
for row in self.rows:
row += [''] * (len(self.names) - len(row))
stream.write('\t'.join(row) + '\n')
stream.close()
# See http://www.ailab.si/orange/doc/ofb/c_otherclass.htm
try:
import orange
import orngTree
except ImportError:
sys.stderr.write(
'Install Orange from http://www.ailab.si/orange/ for a classification tree.\n'
)
return
data = orange.ExampleTable(filename)
tree = orngTree.TreeLearner(data, sameMajorityPruning=1, mForPruning=2)
orngTree.printTxt(tree, maxDepth=4)
file(name + '.txt', 'wt').write(orngTree.dumpTree(tree))
orngTree.printDot(tree,
fileName=name + '.dot',
nodeShape='ellipse',
leafShape='box')
def report_tree(self, name):
filename = name + '.tsv'
stream = file(filename, 'wt')
# header
stream.write('\t'.join(self.names) + '\n')
stream.write('\t'.join(self.types) + '\n')
stream.write('class\n')
# rows
for row in self.rows:
if row[0] == 'skip':
continue
row += ['']*(len(self.names) - len(row))
stream.write('\t'.join(row) + '\n')
stream.close()
# See http://www.ailab.si/orange/doc/ofb/c_otherclass.htm
try:
import orange
import orngTree
except ImportError:
sys.stderr.write('Install Orange from http://www.ailab.si/orange/ for a classification tree.\n')
return None
data = orange.ExampleTable(filename)
tree = orngTree.TreeLearner(data, sameMajorityPruning=1, mForPruning=2)
orngTree.printTxt(tree, maxDepth=4)
text_tree = orngTree.dumpTree(tree)
file(name + '.txt', 'wt').write(text_tree)
orngTree.printDot(tree, fileName=name+'.dot', nodeShape='ellipse', leafShape='box')
return text_tree
def summary(self):
sys.stdout.write("%u tests, %u passed, %u skipped, %u failed\n\n" % (self.tests, self.passed, self.skipped, self.failed))
sys.stdout.flush()
name, ext = os.path.splitext(os.path.basename(sys.argv[0]))
filename = name + '.tsv'
stream = file(filename, 'wt')
# header
stream.write('\t'.join(self.names) + '\n')
stream.write('\t'.join(self.types) + '\n')
stream.write('class\n')
# rows
for row in self.rows:
row += ['']*(len(self.names) - len(row))
stream.write('\t'.join(row) + '\n')
stream.close()
# See http://www.ailab.si/orange/doc/ofb/c_otherclass.htm
try:
import orange
import orngTree
except ImportError:
sys.stderr.write('Install Orange from http://www.ailab.si/orange/ for a classification tree.\n')
return
data = orange.ExampleTable(filename)
tree = orngTree.TreeLearner(data, sameMajorityPruning=1, mForPruning=2)
orngTree.printTxt(tree, maxDepth=4)
file(name+'.txt', 'wt').write(orngTree.dumpTree(tree))
orngTree.printDot(tree, fileName=name+'.dot', nodeShape='ellipse', leafShape='box')
# Description: Builds a regression tree and prints it out
# Category: modelling
# Uses: housing
# Classes: orngTree.TreeLearner
# Referenced: regression.htm
import orange, orngTree
data = orange.ExampleTable("../datasets/housing.tab")
rt = orngTree.TreeLearner(data, measure="retis", mForPruning=2, minExamples=20)
orngTree.printTxt(rt, leafStr="%V %I")
#!/usr/bin/env python
#
# See also:
# http://www.ailab.si/orange/doc/ofb/c_otherclass.htm
import os.path
import sys
import orange
import orngTree
for arg in sys.argv[1:]:
name, ext = os.path.splitext(arg)
data = orange.ExampleTable(arg)
tree = orngTree.TreeLearner(data, sameMajorityPruning=1, mForPruning=2)
orngTree.printTxt(tree)
file(name + '.txt', 'wt').write(orngTree.dumpTree(tree) + '\n')
orngTree.printDot(tree,
fileName=name + '.dot',
nodeShape='ellipse',
leafShape='box')
# Description: Learn decision tree from data and output class probabilities for first few instances
# Category: modelling
# Uses: voting.tab
# Classes: orngTree.TreeLearner
# Referenced: c_otherclass.htm
import orange, orngTree
data = orange.ExampleTable("voting")
tree = orngTree.TreeLearner(data, sameMajorityPruning=1, mForPruning=2)
print "Possible classes:", data.domain.classVar.values
print "Probabilities for democrats:"
for i in range(5):
p = tree(data[i], orange.GetProbabilities)
print "%d: %5.3f (originally %s)" % (i+1, p[1], data[i].getclass())
print
orngTree.printTxt(tree)
orngTree.printDot(tree, fileName='tree.dot', internalNodeShape="ellipse", leafShape="box")
print "\n*** CUSTOM IMPUTATION BY MODELS ***\n"
imputer = orange.Imputer_model()
imputer.models = [None] * len(data.domain)
imputer.models[data.domain.index("LANES")] = orange.DefaultClassifier(2.0)
tord = orange.DefaultClassifier(orange.Value(data.domain["T-OR-D"], "THROUGH"))
imputer.models[data.domain.index("T-OR-D")] = tord
import orngTree
len_domain = orange.Domain(["MATERIAL", "SPAN", "ERECTED", "LENGTH"], data.domain)
len_data = orange.ExampleTable(len_domain, data)
len_tree = orngTree.TreeLearner(len_data, minSubset=20)
imputer.models[data.domain.index("LENGTH")] = len_tree
orngTree.printTxt(len_tree)
spanVar = data.domain["SPAN"]
def computeSpan(ex, rw):
if ex["TYPE"] == "WOOD" or ex["PURPOSE"] == "WALK":
return orange.Value(spanVar, "SHORT")
else:
return orange.Value(spanVar, "MEDIUM")
imputer.models[data.domain.index("SPAN")] = computeSpan
for i in range(20, 25):
print data[i]
print impdata[i]
print
# Description: Reads a data from MySQL data base and constructs a classification tree
# Category: file formats
# Classes: orngMySQL.Connect
# Referenced: orngMySQL.htm
import orange, orngMySQL, orngTree
t = orngMySQL.Connect('localhost','root','','test')
data = t.query("SELECT * FROM busclass")
tree = orngTree.TreeLearner(data)
orngTree.printTxt(tree, nodeStr="%V (%1.0N)", leafStr="%V (%1.0N)")
# Description: Reads a data from MySQL data base and constructs a classification tree
# Category: file formats
# Classes: orngMySQL.Connect
# Referenced: orngMySQL.htm
import orange, orngMySQL, orngTree
t = orngMySQL.Connect('localhost', 'root', '', 'test')
data = t.query("SELECT * FROM busclass")
tree = orngTree.TreeLearner(data)
orngTree.printTxt(tree, nodeStr="%V (%1.0N)", leafStr="%V (%1.0N)")
# Author: J Zabkar
# Version: 1.0
# Description: Grow classification tree with a self-defined stopping criteria
# Category: modelling
# Uses: iris.tab
# Referenced: orngTree.htm
import orange, orngTree
from random import randint, seed
seed(0)
data = orange.ExampleTable("iris.tab")
print "SOME RANDOMNESS IN STOPING:"
defStop = orange.TreeStopCriteria()
f = lambda examples, weightID, contingency: defStop(examples, weightID, contingency) or randint(1, 5)==1
l = orngTree.TreeLearner(data, stop=f)
orngTree.printTxt(l)
print "\nRANDOM STOPING:"
f = lambda x,y,z: randint(1, 5)==1
l = orngTree.TreeLearner(data, stop=f)
orngTree.printTxt(l)
# Author: J Zabkar
# Version: 1.0
# Description: Grow classification tree with a self-defined stopping criteria
# Category: modelling
# Uses: iris.tab
# Referenced: orngTree.htm
import orange, orngTree
from random import randint, seed
seed(0)
data = orange.ExampleTable("iris.tab")
print "SOME RANDOMNESS IN STOPING:"
defStop = orange.TreeStopCriteria()
f = lambda examples, weightID, contingency: defStop(
examples, weightID, contingency) or randint(1, 5) == 1
l = orngTree.TreeLearner(data, stop=f)
orngTree.printTxt(l)
print "\nRANDOM STOPING:"
f = lambda x, y, z: randint(1, 5) == 1
l = orngTree.TreeLearner(data, stop=f)
orngTree.printTxt(l)
