def entropy(x, data):
"""entropy of an attribute x from dataset data"""
if type(x)==orange.EnumVariable:
return _entropy(p2f(orange.Distribution(x, data)))
if type(x)==list:
if len(x)==2: # joint entropy of a pair of attributes
c = orange.ContingencyAttrAttr(x, y, data)
return _entropy(p2f(flatten(c)))
else: # joint entropy of for a set of attributes
pass
# Description: Demonstrates the use of ContingencyClassAttr
# Category: statistics
# Classes: Contingency, ContingencyClassAttr
# Uses: monk1
# Referenced: contingency.htm
import orange
data = orange.ExampleTable("bridges")
cont = orange.ContingencyAttrAttr("SPAN", "MATERIAL", data)
print "Distributions:"
for val in cont.outerVariable:
print " p(.|%s) = %s" % (val.native(), cont.p_attr(val))
print
cont.normalize()
for val in cont.outerVariable:
print "%s:" % val.native()
for inval, p in cont[val].items():
if p:
print " %s (%i%%)" % (inval, int(100 * p + 0.5))
print
cont = orange.ContingencyAttrAttr(data.domain["SPAN"], data.domain["MATERIAL"])
for ex in data:
cont.add(ex["SPAN"], ex["MATERIAL"])
print "Distributions from a matrix computed manually:"
for val in cont.outerVariable:
print " p(.|%s) = %s" % (val.native(), cont.p_attr(val))
print
def joint_entropy(x, y, data):
"""return H(x,y), a joint entropy of attributes x and y"""
c = orange.ContingencyAttrAttr(x, y, data)
return _entropy(p2f(flatten(c)))
# Description: Demonstrates the use of correspondence analysis
# Category: correspondence, projection
# Classes: CA
# Uses: bridges.tab
import orange
import orngCA
data = orange.ExampleTable("bridges")
cm = orange.ContingencyAttrAttr("PURPOSE", "MATERIAL", data)
ca = orngCA.CA([list(col) for col in cm])
def report(coors, labels):
for coor, label in zip(coors, labels):
print " %-10s (%.3f, %.3f)" % (label + ":", coor[0], coor[1])
print "PURPOSE"
report(ca.getPrincipalColProfilesCoordinates(), data.domain["PURPOSE"].values)
print
print "MATERIAL"
report(ca.getPrincipalRowProfilesCoordinates(), data.domain["PURPOSE"].values)
print