def Ipc(mol, avg=0, dMat=None, forceDMat=0):
"""This returns the information content of the coefficients of the characteristic
polynomial of the adjacency matrix of a hydrogen-suppressed graph of a molecule.
'avg = 1' returns the information content divided by the total population.
From D. Bonchev & N. Trinajstic, J. Chem. Phys. vol 67, 4517-4533 (1977)
"""
if forceDMat or dMat is None:
if forceDMat:
dMat = Chem.GetDistanceMatrix(mol, 0)
mol._adjMat = dMat
else:
try:
dMat = mol._adjMat
except AttributeError:
dMat = Chem.GetDistanceMatrix(mol, 0)
mol._adjMat = dMat
adjMat = numpy.equal(dMat, 1)
cPoly = abs(Graphs.CharacteristicPolynomial(mol, adjMat))
if avg:
return entropy.InfoEntropy(cPoly)
else:
return sum(cPoly) * entropy.InfoEntropy(cPoly)
def _CalculateEntropies(connectionDict, atomTypeDict, numAtoms):
"""
Used by BertzCT
"""
connectionList = list(connectionDict.values())
totConnections = sum(connectionList)
connectionIE = totConnections * (entropy.InfoEntropy(
numpy.array(connectionList)) + math.log(totConnections) / _log2val)
atomTypeList = list(atomTypeDict.values())
atomTypeIE = numAtoms * entropy.InfoEntropy(numpy.array(atomTypeList))
return atomTypeIE + connectionIE
def CalcTotalEntropy(examples, nPossibleVals):
""" Calculates the total entropy of the data set (w.r.t. the results)
**Arguments**
- examples: a list (nInstances long) of lists of variable values + instance
values
- nPossibleVals: a list (nVars long) of the number of possible values each variable
can adopt.
**Returns**
a float containing the informational entropy of the data set.
"""
nRes = nPossibleVals[-1]
resList = numpy.zeros(nRes, 'i')
for example in examples:
res = int(example[-1])
resList[res] += 1
return entropy.InfoEntropy(resList)
