def testQuantPickle(self):
# " testing QuantDataSet pickling "
self.setUpQuantLoad()
DataUtils.WritePickledData(
RDConfig.RDCodeDir + '/ML/Data/test_data/testquant.qdat.pkl',
self.d)
with open(RDConfig.RDCodeDir + '/ML/Data/test_data/testquant.qdat.pkl',
'rb') as f:
vNames = pickle.load(f)
qBounds = pickle.load(f)
ptNames = pickle.load(f)
examples = pickle.load(f)
d = MLData.MLQuantDataSet(examples,
varNames=vNames,
qBounds=qBounds,
ptNames=ptNames)
assert self.d.GetNPts() == d.GetNPts(), 'nPts wrong'
assert self.d.GetNVars() == d.GetNVars(), 'nVars wrong'
assert self.d.GetNResults() == d.GetNResults(), 'nResults wrong'
assert self.d.GetVarNames() == d.GetVarNames(), 'varNames wrong'
assert self.d.GetPtNames() == d.GetPtNames(), 'ptNames wrong'
assert self.d.GetNPossibleVals() == d.GetNPossibleVals(
), 'nPossible Wrong'
assert self.d.GetQuantBounds() == d.GetQuantBounds(
), 'quantBounds Wrong'
assert self.d.GetResults() == d.GetResults(), 'GetResults wrong'
assert self.d.GetAllData()[1] == d.GetAllData()[1], 'GetAllData wrong'
assert self.d.GetInputData()[3] == d.GetInputData(
)[3], 'GetInputData wrong'
assert self.d.GetNamedData()[2] == d.GetNamedData(
)[2], 'GetNamedData wrong'
def _setupMultiTree(self):
examples = [[0, 1, 0, 0], [0, 0, 0, 1], [0, 0, 1, 2], [0, 1, 1, 2],
[1, 0, 0, 2], [1, 0, 1, 2], [1, 1, 0, 2], [1, 1, 1, 0]]
data = MLData.MLQuantDataSet(examples)
attrs = range(0, data.GetNVars())
t1 = ID3.ID3Boot(data.GetAllData(), attrs, data.GetNPossibleVals())
self.t1 = t1
self.examples = examples
def _setupPyMultiTree(self):
from rdkit.ML.InfoTheory import entropy
ID3.entropy.InfoEntropy = entropy.PyInfoEntropy
ID3.entropy.InfoGain = entropy.PyInfoGain
examples = [[0, 1, 0, 0], [0, 0, 0, 1], [0, 0, 1, 2], [0, 1, 1, 2],
[1, 0, 0, 2], [1, 0, 1, 2], [1, 1, 0, 2], [1, 1, 1, 0]]
data = MLData.MLQuantDataSet(examples)
attrs = range(0, data.GetNVars())
t1 = ID3.ID3Boot(data.GetAllData(), attrs, data.GetNPossibleVals())
self.t1 = t1
self.examples = examples
def BuildQuantDataSet(fileName):
""" builds a data set from a .qdat file
**Arguments**
- fileName: the name of the .qdat file
**Returns**
an _MLData.MLQuantDataSet_
"""
with open(fileName, 'r') as inFile:
varNames, qBounds = ReadVars(inFile)
ptNames, examples = ReadQuantExamples(inFile)
data = MLData.MLQuantDataSet(examples, qBounds=qBounds, varNames=varNames, ptNames=ptNames)
return data
