def Choosing_the_Best_Split(): print '>>Choosing the Best Split' reload(treepredict) print treepredict.giniimpurity(treepredict.my_data) print treepredict.entropy(treepredict.my_data) set1,set2=treepredict.divideset(treepredict.my_data,2,'yes') print treepredict.entropy(set1) print treepredict.giniimpurity(set1)
results = treepredict.divideset(treepredict.my_data, 2, "yes")
# results is now a list of lists
# See if records are divided according to FAQ field (column) ...
print "\nDivision on Read FAQ field...\n"
for list in results:
for item in list:
print "%15s %15s %5s %10d %15s" % tuple(item)
# Let's see the difference between gini- and entropy-based impurities
# of the current data (no splitting)
print "\nParent node...\n"
gini = treepredict.giniimpurity(treepredict.my_data)
entr = treepredict.entropy(treepredict.my_data)
print "Gini: %8f Entropy: %8f" % (gini, entr)
# Let's now split on the Read FAQ field and assess impurity
node1, node2 = treepredict.divideset(treepredict.my_data, 2, "yes")
print "\nRead FAQ = Yes leaf node...\n"
gini = treepredict.giniimpurity(node1)
entr = treepredict.entropy(node1)
print "Gini: %8f Entropy: %8f" % (gini, entr)
# Build the DT recursively using the buildtree function; assumes
# last column/field is the classification attribute.
tree = treepredict.buildtree(treepredict.my_data)
# Let's see what it looks like...
#! /usr/bin/.env python2 import treepredict print "Gini impurity\n" print treepredict.giniimpurity(treepredict.my_data) print "\n" print "treepredict.entropy\n" print treepredict.entropy(treepredict.my_data) print "\n" set1, set2 = treepredict.divideset(treepredict.my_data, 2, 'yes') print "Gini impurity\n" print treepredict.giniimpurity(set1) print "treepredict.entropy\n" print treepredict.entropy(set1) print '\n' tree = treepredict.buildtree(treepredict.my_data) print 'tree: ', tree print '\n' print 'classify: ', treepredict.classify(['(direct)', 'USA', 'yes', 5], tree)
pprint(treepredict.divideset(treepredict.my_data, 2, 'yes')) # ([['slashdot', 'USA', 'yes', 18, 'None'], # ['google', 'France', 'yes', 23, 'Premium'], # ['digg', 'USA', 'yes', 24, 'Basic'], # ['kiwitobes', 'France', 'yes', 23, 'Basic'], # ['slashdot', 'France', 'yes', 19, 'None'], # ['digg', 'New Zealand', 'yes', 12, 'Basic'], # ['google', 'UK', 'yes', 18, 'Basic'], # ['kiwitobes', 'France', 'yes', 19, 'Basic']], # [['google', 'UK', 'no', 21, 'Premium'], # ['(direct)', 'New Zealand', 'no', 12, 'None'], # ['(direct)', 'UK', 'no', 21, 'Basic'], # ['google', 'USA', 'no', 24, 'Premium'], # ['digg', 'USA', 'no', 18, 'None'], # ['google', 'UK', 'no', 18, 'None'], # ['kiwitobes', 'UK', 'no', 19, 'None'], # ['slashdot', 'UK', 'no', 21, 'None']]) print(treepredict.giniimpurity(treepredict.my_data)) # 0.6328125 print(treepredict.entropy(treepredict.my_data)) # 1.50524081494 set1, set2 = treepredict.divideset(treepredict.my_data, 2, 'yes') print(treepredict.entropy(set1)) # 1.2987949407 print(treepredict.entropy(set2)) # 1.2987949407
def testBasics(self):
d = treepredict.testdata()
self.assertAlmostEquals(1.5052408, treepredict.entropy(d))
s1, s2 = treepredict.divideset(d, 2, 'yes')
self.assertAlmostEquals(1.2987949, treepredict.entropy(s1))
def testBasics(self):
d = treepredict.testdata()
self.assertAlmostEquals(1.5052408, treepredict.entropy(d))
s1, s2 = treepredict.divideset(d, 2, 'yes')
self.assertAlmostEquals(1.2987949, treepredict.entropy(s1))