def testPointPickles(self):
pt = geom.Point3D(2.0,-3.0,1.0)
pt2 = cPickle.loads(cPickle.dumps(pt))
self.assertTrue(feq(pt.x,pt2.x,1e-6))
self.assertTrue(feq(pt.y,pt2.y,1e-6))
self.assertTrue(feq(pt.z,pt2.z,1e-6))
pt = geom.Point2D(2.0,-4.0)
pt2 = cPickle.loads(cPickle.dumps(pt))
self.assertTrue(feq(pt.x,pt2.x,1e-6))
self.assertTrue(feq(pt.y,pt2.y,1e-6))
def testPkl2(self):
""" further pickle tests """
smis = self.bigSmiList
for smi in smis:
m = Chem.MolFromSmiles(smi)
newM1 = cPickle.loads(cPickle.dumps(m))
newM2 = cPickle.loads(cPickle.dumps(newM1))
oldSmi = Chem.MolToSmiles(newM1)
newSmi = Chem.MolToSmiles(newM2)
assert newM1.GetNumAtoms() == m.GetNumAtoms(), "num atoms comparison failed"
assert newM2.GetNumAtoms() == m.GetNumAtoms(), "num atoms comparison failed"
assert oldSmi == newSmi, "string compare failed: %s != %s" % (oldSmi, newSmi)
def test2CatStringPickle(self):
self._fillCat(self.smiList2)
# test non-binary pickle:
cat2 = cPickle.loads(cPickle.dumps(self.fragCat))
assert cat2.GetNumEntries()==21
assert cat2.GetFPLength()==21
self._testBits(cat2)
# test binary pickle:
cat2 = cPickle.loads(cPickle.dumps(self.fragCat,1))
assert cat2.GetNumEntries()==21
assert cat2.GetFPLength()==21
self._testBits(cat2)
def testPickle(self):
ffeat = ChemicalFeatures.FreeChemicalFeature("HBondDonor", "HBondDonor1", geom.Point3D(1.0, 2.0, 3.0),123)
pkl = cPickle.dumps(ffeat)
ffeat2 = cPickle.loads(pkl, encoding='bytes')
self.assertTrue(ffeat2.GetId()==ffeat.GetId());
self.assertTrue(ffeat2.GetFamily()==ffeat.GetFamily())
self.assertTrue(ffeat2.GetType()==ffeat.GetType())
self.assertTrue(ptFeq(ffeat2.GetPos(),ffeat.GetPos()))
# Check that the old pickled versions have not been broken
inF = open(os.path.join(RDConfig.RDBaseDir,
'Code/ChemicalFeatures/Wrap/testData/feat.pkl'),'rb')
ffeat2=cPickle.load(inF, encoding='bytes')
# this version (1.0) does not have an id in the byte stream
self.assertTrue(ffeat2.GetFamily()==ffeat.GetFamily())
self.assertTrue(ffeat2.GetType()==ffeat.GetType())
self.assertTrue(ptFeq(ffeat2.GetPos(),ffeat.GetPos()))
# Test the new version also has the id and works as expected
# uncomment the following to generate (overrwrite) new version of pickled
# data file
#cPickle.dump(ffeat,file(os.path.join(RDConfig.RDBaseDir, 'Code/ChemicalFeatures/Wrap/testData/featv2.pkl'),'wb+'))
inF = open(os.path.join(RDConfig.RDBaseDir,
'Code/ChemicalFeatures/Wrap/testData/featv2.pkl'),'rb')
ffeat2=cPickle.load(inF, encoding='bytes')
self.assertTrue(ffeat2.GetId()==ffeat.GetId());
self.assertTrue(ffeat2.GetFamily()==ffeat.GetFamily())
self.assertTrue(ffeat2.GetType()==ffeat.GetType())
self.assertTrue(ptFeq(ffeat2.GetPos(),ffeat.GetPos()))
def test4Serialize(self):
with open(self.smiName, 'r') as smiF:
smiLines = smiF.readlines()
fparams = FragmentCatalog.FragCatParams(1, 6, self.fName)
fcat = FragmentCatalog.FragCatalog(fparams)
fgen = FragmentCatalog.FragCatGenerator()
suppl = Chem.SmilesMolSupplier(self.smiName, " ", 0, 1, 0)
smiles = []
for mol in suppl:
nent = fgen.AddFragsFromMol(mol, fcat)
smiles.append(Chem.MolToSmiles(mol))
self.assertEqual(fcat.GetNumEntries(), 21)
self.assertEqual(fcat.GetFPLength(), 21)
pkl = cPickle.dumps(fcat)
fcat2 = cPickle.loads(pkl)
self.assertEqual(fcat2.GetNumEntries(), 21)
self.assertEqual(fcat2.GetFPLength(), 21)
fpgen = FragmentCatalog.FragFPGenerator()
for i in range(len(smiles)):
smi = smiles[i]
mol = Chem.MolFromSmiles(smi)
fp1 = fpgen.GetFPForMol(mol, fcat)
fp2 = fpgen.GetFPForMol(mol, fcat2)
self.assertEqual(fp1.GetNumOnBits(), fp2.GetNumOnBits())
obl1 = fp1.GetOnBits()
obl2 = fp2.GetOnBits()
self.assertEqual(tuple(obl1), tuple(obl2))
def test3Pickle2(self):
"""
"""
l=1<<21
v1 = ds.IntSparseIntVect(l)
self.assertRaises(IndexError,lambda:v1[l+1])
v1[0]=1
v1[2]=2
v1[1<<12]=3
self.assertTrue(v1==v1)
v2= cPickle.loads(cPickle.dumps(v1))
self.assertTrue(v2==v1)
v3= ds.IntSparseIntVect(v2.ToBinary())
self.assertTrue(v2==v3)
self.assertTrue(v1==v3)
#cPickle.dump(v1,file('isiv.pkl','wb+'))
with open(
os.path.join(RDConfig.RDBaseDir,
'Code/DataStructs/Wrap/testData/isiv.pkl'),
'r'
) as tf:
buf = tf.read().replace('\r\n', '\n').encode('utf-8')
tf.close()
with io.BytesIO(buf) as f:
v3 = cPickle.load(f)
self.assertTrue(v3==v1)
def test3Pickle2(self):
"""
"""
l=1<<21
v1 = ds.IntSparseIntVect(l)
self.assertRaises(IndexError,lambda:v1[l+1])
v1[0]=1
v1[2]=2
v1[1<<12]=3
self.assertTrue(v1==v1)
v2= cPickle.loads(cPickle.dumps(v1))
self.assertTrue(v2==v1)
v3= ds.IntSparseIntVect(v2.ToBinary())
self.assertTrue(v2==v3)
self.assertTrue(v1==v3)
#cPickle.dump(v1,file('isiv.pkl','wb+'))
with open(
os.path.join(RDConfig.RDBaseDir,
'Code/DataStructs/Wrap/testData/isiv.pkl'),
'rb'
) as f:
v3 = cPickle.load(f)
self.assertTrue(v3==v1)
def testPkl1(self):
" testing single molecule pickle "
m = Chem.MolFromSmiles("CCOC")
outS = Chem.MolToSmiles(m)
m2 = cPickle.loads(cPickle.dumps(m))
outS2 = Chem.MolToSmiles(m2)
assert outS == outS2, "bad pickle: %s != %s" % (outS, outS2)
def _testPkl10(self):
" testing 5k molecule pickles "
inLines = open('%s/NCI/first_5K.smi'%(RDConfig.RDDataDir),'r').readlines()
smis = []
for line in inLines:
smis.append(line.split('\t')[0])
for smi in smis:
m = Chem.MolFromSmiles(smi)
newM1 = cPickle.loads(cPickle.dumps(m))
newSmi1 = Chem.MolToSmiles(newM1)
newM2 = cPickle.loads(cPickle.dumps(newM1))
newSmi2 = Chem.MolToSmiles(newM2)
assert newM1.GetNumAtoms()==m.GetNumAtoms(),'num atoms comparison failed'
assert newM2.GetNumAtoms()==m.GetNumAtoms(),'num atoms comparison failed'
assert len(newSmi1)>0,'empty smi1'
assert len(newSmi2)>0,'empty smi2'
assert newSmi1==newSmi2,'string compare failed:\n%s\n\t!=\n%s\norig smiles:\n%s'%(newSmi1,newSmi2,smi)
def test6PickleEquals(self):
" testing pickled tree equals "
self._readyTree()
pkl = cPickle.dumps(self.baseTree)
oTree = cPickle.loads(pkl)
assert oTree == self.baseTree, 'Pickle inequality test failed'
self.baseTree.PruneChild(self.baseTree.GetChildren()[0])
assert oTree != self.baseTree, 'Pickle inequality test failed (bad Tree.__cmp__)'
def test6PickleEquals(self):
" testing pickled tree equals "
self._readyTree()
pkl = cPickle.dumps(self.baseTree)
oTree = cPickle.loads(pkl)
assert oTree == self.baseTree,'Pickle inequality test failed'
self.baseTree.PruneChild(self.baseTree.GetChildren()[0])
assert oTree != self.baseTree,'Pickle inequality test failed (bad Tree.__cmp__)'
def test2ExplicitPickle(self):
nbits = 10000
bv1 = DataStructs.ExplicitBitVect(nbits)
for i in range(1000):
x = random.randrange(0, nbits)
bv1.SetBit(x)
pkl = pickle.dumps(bv1, 1)
bv2 = pickle.loads(pkl)
for i in range(nbits):
assert bv1[i] == bv2[i]
def test2ExplicitPickle(self):
nbits = 10000
bv1 = DataStructs.ExplicitBitVect(nbits)
for i in range(1000):
x = random.randrange(0, nbits)
bv1.SetBit(x)
pkl = pickle.dumps(bv1, 1)
bv2 = pickle.loads(pkl)
for i in range(nbits):
assert bv1[i] == bv2[i]
def test3Pickles(self):
#outF = file('../testData/rvvs.pkl','wb+')
with open(os.path.join(RDConfig.RDBaseDir,
'Code/DataStructs/Wrap/testData/rvvs.pkl'),
'rb') as inF:
v1 = ds.RealValueVect(30)
for i in range(15):
v1[2*i] = 1.3
v2 = cPickle.loads(cPickle.dumps(v1))
self.assertAlmostEqual(ds.ComputeL1Norm(v1, v2), 0)
#cPickle.dump(v1,outF)
v2=cPickle.load(inF, encoding='bytes')
self.assertAlmostEqual(ds.ComputeL1Norm(v1, v2), 0)
self.assertAlmostEqual(v1.GetTotalVal(), v2.GetTotalVal())
self.failUnless(v2.GetTotalVal()!=0)
def test4GridPickles(self):
grd = geom.UniformGrid3D(10.0, 9.0, 8.0, 0.5)
self.assertTrue(grd.GetNumX() == 20)
self.assertTrue(grd.GetNumY() == 18)
self.assertTrue(grd.GetNumZ() == 16)
grd.SetSphereOccupancy(geom.Point3D(-2.0, -2.0, 0.0), 1.5, 0.25)
grd.SetSphereOccupancy(geom.Point3D(-2.0, 2.0, 0.0), 1.5, 0.25)
grd.SetSphereOccupancy(geom.Point3D(2.0, -2.0, 0.0), 1.5, 0.25)
grd.SetSphereOccupancy(geom.Point3D(2.0, 2.0, 0.0), 1.5, 0.25)
self.assertTrue(geom.TanimotoDistance(grd,grd)==0.0)
grd2 = cPickle.loads(cPickle.dumps(grd))
self.assertTrue(grd2.GetNumX() == 20)
self.assertTrue(grd2.GetNumY() == 18)
self.assertTrue(grd2.GetNumZ() == 16)
self.assertTrue(geom.TanimotoDistance(grd,grd2)==0.0)
def test4GridPickles(self):
grd = geom.UniformGrid3D(10.0, 9.0, 8.0, 0.5)
self.assertTrue(grd.GetNumX() == 20)
self.assertTrue(grd.GetNumY() == 18)
self.assertTrue(grd.GetNumZ() == 16)
grd.SetSphereOccupancy(geom.Point3D(-2.0, -2.0, 0.0), 1.5, 0.25)
grd.SetSphereOccupancy(geom.Point3D(-2.0, 2.0, 0.0), 1.5, 0.25)
grd.SetSphereOccupancy(geom.Point3D(2.0, -2.0, 0.0), 1.5, 0.25)
grd.SetSphereOccupancy(geom.Point3D(2.0, 2.0, 0.0), 1.5, 0.25)
self.assertTrue(geom.TanimotoDistance(grd, grd) == 0.0)
grd2 = cPickle.loads(cPickle.dumps(grd))
self.assertTrue(grd2.GetNumX() == 20)
self.assertTrue(grd2.GetNumY() == 18)
self.assertTrue(grd2.GetNumZ() == 16)
self.assertTrue(geom.TanimotoDistance(grd, grd2) == 0.0)
def test12Pickles(self):
rxn = rdChemReactions.ReactionFromSmarts('[C:1]1[O:2][N:3]1>>[C:1]1[O:2].[N:3]1')
pkl = cPickle.dumps(rxn)
rxn = cPickle.loads(pkl)
mol = Chem.MolFromSmiles('C1ON1')
products = rxn.RunReactants([mol])
self.assertEqual(len(products),1)
for p in products:
self.assertEqual(len(p),1)
self.assertEqual(p[0].GetNumAtoms(),3)
self.assertEqual(p[0].GetNumBonds(),2)
rxn = rdChemReactions.ChemicalReaction(rxn.ToBinary())
products = rxn.RunReactants([mol])
self.assertEqual(len(products),1)
for p in products:
self.assertEqual(len(p),1)
self.assertEqual(p[0].GetNumAtoms(),3)
self.assertEqual(p[0].GetNumBonds(),2)
def testPickle(self):
ffeat = ChemicalFeatures.FreeChemicalFeature(
"HBondDonor", "HBondDonor1", geom.Point3D(1.0, 2.0, 3.0), 123)
pkl = cPickle.dumps(ffeat)
ffeat2 = cPickle.loads(pkl, encoding='bytes')
self.assertTrue(ffeat2.GetId() == ffeat.GetId())
self.assertTrue(ffeat2.GetFamily() == ffeat.GetFamily())
self.assertTrue(ffeat2.GetType() == ffeat.GetType())
self.assertTrue(ptFeq(ffeat2.GetPos(), ffeat.GetPos()))
# Check that the old pickled versions have not been broken
inTF = open(
os.path.join(RDConfig.RDBaseDir,
'Code/ChemicalFeatures/Wrap/testData/feat.pkl'), 'r')
buf = inTF.read().replace('\r\n', '\n').encode('utf-8')
inTF.close()
inF = io.BytesIO(buf)
ffeat2 = cPickle.load(inF, encoding='bytes')
# this version (1.0) does not have an id in the byte stream
self.assertTrue(ffeat2.GetFamily() == ffeat.GetFamily())
self.assertTrue(ffeat2.GetType() == ffeat.GetType())
self.assertTrue(ptFeq(ffeat2.GetPos(), ffeat.GetPos()))
# Test the new version also has the id and works as expected
# uncomment the following to generate (overrwrite) new version of pickled
# data file
#cPickle.dump(ffeat,file(os.path.join(RDConfig.RDBaseDir, 'Code/ChemicalFeatures/Wrap/testData/featv2.pkl'),'wb+'))
inTF = open(
os.path.join(RDConfig.RDBaseDir,
'Code/ChemicalFeatures/Wrap/testData/featv2.pkl'),
'r')
buf = inTF.read().replace('\r\n', '\n').encode('utf-8')
inTF.close()
inF = io.BytesIO(buf)
ffeat2 = cPickle.load(inF, encoding='bytes')
self.assertTrue(ffeat2.GetId() == ffeat.GetId())
self.assertTrue(ffeat2.GetFamily() == ffeat.GetFamily())
self.assertTrue(ffeat2.GetType() == ffeat.GetType())
self.assertTrue(ptFeq(ffeat2.GetPos(), ffeat.GetPos()))
def test1(self):
cat = MolCatalog.CreateMolCatalog()
es = []
for smi in ('C1CCC1OC','C1CCC1','C'):
m = Chem.MolFromSmiles(smi)
entry = MolCatalog.MolCatalogEntry()
entry.SetMol(m)
self.assertTrue(entry.GetMol())
eSmi = Chem.MolToSmiles(entry.GetMol())
self.assertTrue(eSmi==Chem.MolToSmiles(m))
entry.SetDescription(smi)
self.assertTrue(entry.GetDescription()==smi)
es.append(entry)
v=cat.AddEntry(es[0])
self.assertTrue(v==0)
self.assertTrue(cat.GetNumEntries()==1)
v=cat.AddEntry(es[1])
self.assertTrue(v==1)
self.assertTrue(cat.GetNumEntries()==2)
v=cat.AddEntry(es[2])
self.assertTrue(v==2)
self.assertTrue(cat.GetNumEntries()==3)
cat.AddEdge(0,1)
cat.AddEdge(0,2)
cat.AddEdge(1,2)
d = cPickle.dumps(cat)
es = None
entry = None
cat=None
cat = cPickle.loads(d)
self.assertTrue(cat.GetNumEntries()==3)
cat=None
def test1(self):
cat = MolCatalog.CreateMolCatalog()
es = []
for smi in ('C1CCC1OC', 'C1CCC1', 'C'):
m = Chem.MolFromSmiles(smi)
entry = MolCatalog.MolCatalogEntry()
entry.SetMol(m)
self.assertTrue(entry.GetMol())
eSmi = Chem.MolToSmiles(entry.GetMol())
self.assertTrue(eSmi == Chem.MolToSmiles(m))
entry.SetDescription(smi)
self.assertTrue(entry.GetDescription() == smi)
es.append(entry)
v = cat.AddEntry(es[0])
self.assertTrue(v == 0)
self.assertTrue(cat.GetNumEntries() == 1)
v = cat.AddEntry(es[1])
self.assertTrue(v == 1)
self.assertTrue(cat.GetNumEntries() == 2)
v = cat.AddEntry(es[2])
self.assertTrue(v == 2)
self.assertTrue(cat.GetNumEntries() == 3)
cat.AddEdge(0, 1)
cat.AddEdge(0, 2)
cat.AddEdge(1, 2)
d = cPickle.dumps(cat)
es = None
entry = None
cat = None
cat = cPickle.loads(d)
self.assertTrue(cat.GetNumEntries() == 3)
cat = None
def test12Pickles(self):
# 08/05/14
# This test is changed due to a new behavior of the smarts
# reaction parser which now allows using parenthesis in products
# as well. original smiles: '[C:1]1[O:2][N:3]1>>[C:1]1[O:2].[N:3]1'
rxn = rdChemReactions.ReactionFromSmarts('[C:1]1[O:2][N:3]1>>([C:1]1[O:2].[N:3]1)')
pkl = cPickle.dumps(rxn)
rxn = cPickle.loads(pkl)
mol = Chem.MolFromSmiles('C1ON1')
products = rxn.RunReactants([mol])
self.assertEqual(len(products),1)
for p in products:
self.assertEqual(len(p),1)
self.assertEqual(p[0].GetNumAtoms(),3)
self.assertEqual(p[0].GetNumBonds(),2)
rxn = rdChemReactions.ChemicalReaction(rxn.ToBinary())
products = rxn.RunReactants([mol])
self.assertEqual(len(products),1)
for p in products:
self.assertEqual(len(p),1)
self.assertEqual(p[0].GetNumAtoms(),3)
self.assertEqual(p[0].GetNumBonds(),2)
def test12Pickles(self):
# 08/05/14
# This test is changed due to a new behavior of the smarts
# reaction parser which now allows using parenthesis in products
# as well. original smiles: '[C:1]1[O:2][N:3]1>>[C:1]1[O:2].[N:3]1'
rxn = rdChemReactions.ReactionFromSmarts('[C:1]1[O:2][N:3]1>>([C:1]1[O:2].[N:3]1)')
pkl = cPickle.dumps(rxn)
rxn = cPickle.loads(pkl)
mol = Chem.MolFromSmiles('C1ON1')
products = rxn.RunReactants([mol])
self.assertEqual(len(products),1)
for p in products:
self.assertEqual(len(p),1)
self.assertEqual(p[0].GetNumAtoms(),3)
self.assertEqual(p[0].GetNumBonds(),2)
rxn = rdChemReactions.ChemicalReaction(rxn.ToBinary())
products = rxn.RunReactants([mol])
self.assertEqual(len(products),1)
for p in products:
self.assertEqual(len(p),1)
self.assertEqual(p[0].GetNumAtoms(),3)
self.assertEqual(p[0].GetNumBonds(),2)
def RunOnData(details, data, progressCallback=None, saveIt=1, setDescNames=0):
if details.lockRandom:
seed = details.randomSeed
else:
import random
seed = (random.randint(0, 1e6), random.randint(0, 1e6))
DataUtils.InitRandomNumbers(seed)
testExamples = []
if details.shuffleActivities == 1:
DataUtils.RandomizeActivities(data, shuffle=1, runDetails=details)
elif details.randomActivities == 1:
DataUtils.RandomizeActivities(data, shuffle=0, runDetails=details)
namedExamples = data.GetNamedData()
if details.splitRun == 1:
trainIdx, testIdx = SplitData.SplitIndices(
len(namedExamples), details.splitFrac, silent=not _verbose)
trainExamples = [namedExamples[x] for x in trainIdx]
testExamples = [namedExamples[x] for x in testIdx]
else:
testExamples = []
testIdx = []
trainIdx = list(range(len(namedExamples)))
trainExamples = namedExamples
if details.filterFrac != 0.0:
# if we're doing quantization on the fly, we need to handle that here:
if hasattr(details, 'activityBounds') and details.activityBounds:
tExamples = []
bounds = details.activityBounds
for pt in trainExamples:
pt = pt[:]
act = pt[-1]
placed = 0
bound = 0
while not placed and bound < len(bounds):
if act < bounds[bound]:
pt[-1] = bound
placed = 1
else:
bound += 1
if not placed:
pt[-1] = bound
tExamples.append(pt)
else:
bounds = None
tExamples = trainExamples
trainIdx, temp = DataUtils.FilterData(tExamples, details.filterVal, details.filterFrac, -1,
indicesOnly=1)
tmp = [trainExamples[x] for x in trainIdx]
testExamples += [trainExamples[x] for x in temp]
trainExamples = tmp
counts = DataUtils.CountResults(trainExamples, bounds=bounds)
ks = counts.keys()
ks.sort()
message('Result Counts in training set:')
for k in ks:
message(str((k, counts[k])))
counts = DataUtils.CountResults(testExamples, bounds=bounds)
ks = counts.keys()
ks.sort()
message('Result Counts in test set:')
for k in ks:
message(str((k, counts[k])))
nExamples = len(trainExamples)
message('Training with %d examples' % (nExamples))
nVars = data.GetNVars()
attrs = list(range(1, nVars + 1))
nPossibleVals = data.GetNPossibleVals()
for i in range(1, len(nPossibleVals)):
if nPossibleVals[i - 1] == -1:
attrs.remove(i)
if details.pickleDataFileName != '':
pickleDataFile = open(details.pickleDataFileName, 'wb+')
cPickle.dump(trainExamples, pickleDataFile)
cPickle.dump(testExamples, pickleDataFile)
pickleDataFile.close()
if details.bayesModel:
composite = BayesComposite.BayesComposite()
else:
composite = Composite.Composite()
composite._randomSeed = seed
composite._splitFrac = details.splitFrac
composite._shuffleActivities = details.shuffleActivities
composite._randomizeActivities = details.randomActivities
if hasattr(details, 'filterFrac'):
composite._filterFrac = details.filterFrac
if hasattr(details, 'filterVal'):
composite._filterVal = details.filterVal
composite.SetModelFilterData(details.modelFilterFrac, details.modelFilterVal)
composite.SetActivityQuantBounds(details.activityBounds)
nPossibleVals = data.GetNPossibleVals()
if details.activityBounds:
nPossibleVals[-1] = len(details.activityBounds) + 1
if setDescNames:
composite.SetInputOrder(data.GetVarNames())
composite.SetDescriptorNames(details._descNames)
else:
composite.SetDescriptorNames(data.GetVarNames())
composite.SetActivityQuantBounds(details.activityBounds)
if details.nModels == 1:
details.internalHoldoutFrac = 0.0
if details.useTrees:
from rdkit.ML.DecTree import CrossValidate, PruneTree
if details.qBounds != []:
from rdkit.ML.DecTree import BuildQuantTree
builder = BuildQuantTree.QuantTreeBoot
else:
from rdkit.ML.DecTree import ID3
builder = ID3.ID3Boot
driver = CrossValidate.CrossValidationDriver
pruner = PruneTree.PruneTree
composite.SetQuantBounds(details.qBounds)
nPossibleVals = data.GetNPossibleVals()
if details.activityBounds:
nPossibleVals[-1] = len(details.activityBounds) + 1
composite.Grow(
trainExamples, attrs, nPossibleVals=[0] + nPossibleVals, buildDriver=driver, pruner=pruner,
nTries=details.nModels, pruneIt=details.pruneIt, lessGreedy=details.lessGreedy,
needsQuantization=0, treeBuilder=builder, nQuantBounds=details.qBounds,
startAt=details.startAt, maxDepth=details.limitDepth, progressCallback=progressCallback,
holdOutFrac=details.internalHoldoutFrac, replacementSelection=details.replacementSelection,
recycleVars=details.recycleVars, randomDescriptors=details.randomDescriptors,
silent=not _verbose)
elif details.useSigTrees:
from rdkit.ML.DecTree import CrossValidate
from rdkit.ML.DecTree import BuildSigTree
builder = BuildSigTree.SigTreeBuilder
driver = CrossValidate.CrossValidationDriver
nPossibleVals = data.GetNPossibleVals()
if details.activityBounds:
nPossibleVals[-1] = len(details.activityBounds) + 1
if hasattr(details, 'sigTreeBiasList'):
biasList = details.sigTreeBiasList
else:
biasList = None
if hasattr(details, 'useCMIM'):
useCMIM = details.useCMIM
else:
useCMIM = 0
if hasattr(details, 'allowCollections'):
allowCollections = details.allowCollections
else:
allowCollections = False
composite.Grow(
trainExamples, attrs, nPossibleVals=[0] + nPossibleVals, buildDriver=driver,
nTries=details.nModels, needsQuantization=0, treeBuilder=builder, maxDepth=details.limitDepth,
progressCallback=progressCallback, holdOutFrac=details.internalHoldoutFrac,
replacementSelection=details.replacementSelection, recycleVars=details.recycleVars,
randomDescriptors=details.randomDescriptors, biasList=biasList, useCMIM=useCMIM,
allowCollection=allowCollections, silent=not _verbose)
elif details.useKNN:
from rdkit.ML.KNN import CrossValidate
from rdkit.ML.KNN import DistFunctions
driver = CrossValidate.CrossValidationDriver
dfunc = ''
if (details.knnDistFunc == "Euclidean"):
dfunc = DistFunctions.EuclideanDist
elif (details.knnDistFunc == "Tanimoto"):
dfunc = DistFunctions.TanimotoDist
else:
assert 0, "Bad KNN distance metric value"
composite.Grow(trainExamples, attrs, nPossibleVals=[0] + nPossibleVals, buildDriver=driver,
nTries=details.nModels, needsQuantization=0, numNeigh=details.knnNeighs,
holdOutFrac=details.internalHoldoutFrac, distFunc=dfunc)
elif details.useNaiveBayes or details.useSigBayes:
from rdkit.ML.NaiveBayes import CrossValidate
driver = CrossValidate.CrossValidationDriver
if not (hasattr(details, 'useSigBayes') and details.useSigBayes):
composite.Grow(trainExamples, attrs, nPossibleVals=[0] + nPossibleVals, buildDriver=driver,
nTries=details.nModels, needsQuantization=0, nQuantBounds=details.qBounds,
holdOutFrac=details.internalHoldoutFrac,
replacementSelection=details.replacementSelection,
mEstimateVal=details.mEstimateVal, silent=not _verbose)
else:
if hasattr(details, 'useCMIM'):
useCMIM = details.useCMIM
else:
useCMIM = 0
composite.Grow(trainExamples, attrs, nPossibleVals=[0] + nPossibleVals, buildDriver=driver,
nTries=details.nModels, needsQuantization=0, nQuantBounds=details.qBounds,
mEstimateVal=details.mEstimateVal, useSigs=True, useCMIM=useCMIM,
holdOutFrac=details.internalHoldoutFrac,
replacementSelection=details.replacementSelection, silent=not _verbose)
# # elif details.useSVM:
# # from rdkit.ML.SVM import CrossValidate
# # driver = CrossValidate.CrossValidationDriver
# # composite.Grow(trainExamples, attrs, nPossibleVals=[0]+nPossibleVals,
# # buildDriver=driver, nTries=details.nModels,
# # needsQuantization=0,
# # cost=details.svmCost,gamma=details.svmGamma,
# # weights=details.svmWeights,degree=details.svmDegree,
# # type=details.svmType,kernelType=details.svmKernel,
# # coef0=details.svmCoeff,eps=details.svmEps,nu=details.svmNu,
# # cache_size=details.svmCache,shrinking=details.svmShrink,
# # dataType=details.svmDataType,
# # holdOutFrac=details.internalHoldoutFrac,
# # replacementSelection=details.replacementSelection,
# # silent=not _verbose)
else:
from rdkit.ML.Neural import CrossValidate
driver = CrossValidate.CrossValidationDriver
composite.Grow(trainExamples, attrs, [0] + nPossibleVals, nTries=details.nModels,
buildDriver=driver, needsQuantization=0)
composite.AverageErrors()
composite.SortModels()
modelList, counts, avgErrs = composite.GetAllData()
counts = numpy.array(counts)
avgErrs = numpy.array(avgErrs)
composite._varNames = data.GetVarNames()
for i in range(len(modelList)):
modelList[i].NameModel(composite._varNames)
# do final statistics
weightedErrs = counts * avgErrs
averageErr = sum(weightedErrs) / sum(counts)
devs = (avgErrs - averageErr)
devs = devs * counts
devs = numpy.sqrt(devs * devs)
avgDev = sum(devs) / sum(counts)
message('# Overall Average Error: %%% 5.2f, Average Deviation: %%% 6.2f' %
(100. * averageErr, 100. * avgDev))
if details.bayesModel:
composite.Train(trainExamples, verbose=0)
# blow out the saved examples and then save the composite:
composite.ClearModelExamples()
if saveIt:
composite.Pickle(details.outName)
details.model = DbModule.binaryHolder(cPickle.dumps(composite))
badExamples = []
if not details.detailedRes and (not hasattr(details, 'noScreen') or not details.noScreen):
if details.splitRun:
message('Testing all hold-out examples')
wrong = testall(composite, testExamples, badExamples)
message('%d examples (%% %5.2f) were misclassified' % (len(wrong), 100. * float(len(wrong)) /
float(len(testExamples))))
_runDetails.holdout_error = float(len(wrong)) / len(testExamples)
else:
message('Testing all examples')
wrong = testall(composite, namedExamples, badExamples)
message('%d examples (%% %5.2f) were misclassified' % (len(wrong), 100. * float(len(wrong)) /
float(len(namedExamples))))
_runDetails.overall_error = float(len(wrong)) / len(namedExamples)
if details.detailedRes:
message('\nEntire data set:')
resTup = ScreenComposite.ShowVoteResults(
range(data.GetNPts()), data, composite, nPossibleVals[-1], details.threshold)
nGood, nBad, nSkip, avgGood, avgBad, avgSkip, voteTab = resTup
nPts = len(namedExamples)
nClass = nGood + nBad
_runDetails.overall_error = float(nBad) / nClass
_runDetails.overall_correct_conf = avgGood
_runDetails.overall_incorrect_conf = avgBad
_runDetails.overall_result_matrix = repr(voteTab)
nRej = nClass - nPts
if nRej > 0:
_runDetails.overall_fraction_dropped = float(nRej) / nPts
if details.splitRun:
message('\nHold-out data:')
resTup = ScreenComposite.ShowVoteResults(
range(len(testExamples)), testExamples, composite, nPossibleVals[-1], details.threshold)
nGood, nBad, nSkip, avgGood, avgBad, avgSkip, voteTab = resTup
nPts = len(testExamples)
nClass = nGood + nBad
_runDetails.holdout_error = float(nBad) / nClass
_runDetails.holdout_correct_conf = avgGood
_runDetails.holdout_incorrect_conf = avgBad
_runDetails.holdout_result_matrix = repr(voteTab)
nRej = nClass - nPts
if nRej > 0:
_runDetails.holdout_fraction_dropped = float(nRej) / nPts
if details.persistTblName and details.dbName:
message('Updating results table %s:%s' % (details.dbName, details.persistTblName))
details.Store(db=details.dbName, table=details.persistTblName)
if details.badName != '':
badFile = open(details.badName, 'w+')
for i in range(len(badExamples)):
ex = badExamples[i]
vote = wrong[i]
outStr = '%s\t%s\n' % (ex, vote)
badFile.write(outStr)
badFile.close()
composite.ClearModelExamples()
return composite
def test1cPointND(self):
dim=4
pt = geom.PointND(4);
for i in range(dim):
self.assertTrue(feq(pt[i], 0.0))
pt[0]=3
pt[3]=4
self.assertTrue(feq(pt[0], 3.0))
self.assertTrue(feq(pt[3], 4.0))
self.assertTrue(feq(pt[-4], 3.0))
self.assertTrue(feq(pt[-1], 4.0))
lst = list(pt)
self.assertTrue(feq(lst[0], 3.0))
self.assertTrue(feq(lst[3], 4.0))
pt2 = geom.PointND(4)
pt2[0]=1.
pt2[2]=1.
pt3 = pt+pt2
self.assertTrue(feq(pt3[0], 4.0))
self.assertTrue(feq(pt3[2], 1.0))
self.assertTrue(feq(pt3[3], 4.0))
pt += pt2
self.assertTrue(feq(pt[0], 4.0))
self.assertTrue(feq(pt[2], 1.0))
self.assertTrue(feq(pt[3], 4.0))
pt3 = pt-pt2
self.assertTrue(feq(pt3[0], 3.0))
self.assertTrue(feq(pt3[2], 0.0))
self.assertTrue(feq(pt3[3], 4.0))
pt -= pt2
self.assertTrue(feq(pt[0], 3.0))
self.assertTrue(feq(pt[2], 0.0))
self.assertTrue(feq(pt[3], 4.0))
pt *= 2.0
self.assertTrue(feq(pt[0], 6.0))
self.assertTrue(feq(pt[1], 0.0))
self.assertTrue(feq(pt[2], 0.0))
self.assertTrue(feq(pt[3], 8.0))
pt /= 2
self.assertTrue(feq(pt[0], 3.0))
self.assertTrue(feq(pt[1], 0.0))
self.assertTrue(feq(pt[2], 0.0))
self.assertTrue(feq(pt[3], 4.0))
self.assertTrue(feq(pt.Length(), 5.0))
self.assertTrue(feq(pt.LengthSq(), 25.0))
pt.Normalize()
self.assertTrue(feq(pt.Length(), 1.0))
pkl = cPickle.dumps(pt)
pt2 = cPickle.loads(pkl)
self.assertTrue(len(pt)==len(pt2))
for i in range(len(pt)):
self.assertTrue(feq(pt2[i],pt[i]))
if nWeights==1:
outName = _runDetails.outName
composites[0].Pickle(outName)
else:
for i in range(nWeights):
weight = int(100*_runDetails.balWeight[i])
model = composites[i]
outName = '%s.%d.pkl'%(_runDetails.outName.split('.pkl')[0],weight)
model.Pickle(outName)
if _runDetails.persistTblName and _runDetails.dbName:
message('Updating results table %s:%s'%(_runDetails.dbName,_runDetails.persistTblName))
if(len(_runDetails.balWeight))>1:
message('WARNING: updating results table with models having different weights')
# save the composite
for i in range(len(composites)):
_runDetails.model = cPickle.dumps(composites[i])
_runDetails.Store(db=_runDetails.dbName,table=_runDetails.persistTblName)
elif nModels==1:
composite = GrowIt(_runDetails,initModels[0],setDescNames=1)
if _runDetails.balTable and _runDetails.balCnt:
composites = BalanceComposite(_runDetails,composite)
else:
composites=[composite]
for mdl in composites:
mdl.ClearModelExamples()
if _runDetails.outName:
nWeights = len(_runDetails.balWeight)
if nWeights==1:
outName = _runDetails.outName
composites[0].Pickle(outName)
else:
def RunOnData(details, data, progressCallback=None, saveIt=1, setDescNames=0):
nExamples = data.GetNPts()
if details.lockRandom:
seed = details.randomSeed
else:
import random
seed = (random.randint(0, 1e6), random.randint(0, 1e6))
DataUtils.InitRandomNumbers(seed)
testExamples = []
if details.shuffleActivities == 1:
DataUtils.RandomizeActivities(data, shuffle=1, runDetails=details)
elif details.randomActivities == 1:
DataUtils.RandomizeActivities(data, shuffle=0, runDetails=details)
namedExamples = data.GetNamedData()
if details.splitRun == 1:
trainIdx, testIdx = SplitData.SplitIndices(len(namedExamples),
details.splitFrac,
silent=not _verbose)
trainExamples = [namedExamples[x] for x in trainIdx]
testExamples = [namedExamples[x] for x in testIdx]
else:
testExamples = []
testIdx = []
trainIdx = range(len(namedExamples))
trainExamples = namedExamples
if details.filterFrac != 0.0:
# if we're doing quantization on the fly, we need to handle that here:
if hasattr(details, 'activityBounds') and details.activityBounds:
tExamples = []
bounds = details.activityBounds
for pt in trainExamples:
pt = pt[:]
act = pt[-1]
placed = 0
bound = 0
while not placed and bound < len(bounds):
if act < bounds[bound]:
pt[-1] = bound
placed = 1
else:
bound += 1
if not placed:
pt[-1] = bound
tExamples.append(pt)
else:
bounds = None
tExamples = trainExamples
trainIdx, temp = DataUtils.FilterData(tExamples,
details.filterVal,
details.filterFrac,
-1,
indicesOnly=1)
tmp = [trainExamples[x] for x in trainIdx]
testExamples += [trainExamples[x] for x in temp]
trainExamples = tmp
counts = DataUtils.CountResults(trainExamples, bounds=bounds)
ks = counts.keys()
ks.sort()
message('Result Counts in training set:')
for k in ks:
message(str((k, counts[k])))
counts = DataUtils.CountResults(testExamples, bounds=bounds)
ks = counts.keys()
ks.sort()
message('Result Counts in test set:')
for k in ks:
message(str((k, counts[k])))
nExamples = len(trainExamples)
message('Training with %d examples' % (nExamples))
nVars = data.GetNVars()
attrs = range(1, nVars + 1)
nPossibleVals = data.GetNPossibleVals()
for i in range(1, len(nPossibleVals)):
if nPossibleVals[i - 1] == -1:
attrs.remove(i)
if details.pickleDataFileName != '':
pickleDataFile = open(details.pickleDataFileName, 'wb+')
cPickle.dump(trainExamples, pickleDataFile)
cPickle.dump(testExamples, pickleDataFile)
pickleDataFile.close()
if details.bayesModel:
composite = BayesComposite.BayesComposite()
else:
composite = Composite.Composite()
composite._randomSeed = seed
composite._splitFrac = details.splitFrac
composite._shuffleActivities = details.shuffleActivities
composite._randomizeActivities = details.randomActivities
if hasattr(details, 'filterFrac'):
composite._filterFrac = details.filterFrac
if hasattr(details, 'filterVal'):
composite._filterVal = details.filterVal
composite.SetModelFilterData(details.modelFilterFrac,
details.modelFilterVal)
composite.SetActivityQuantBounds(details.activityBounds)
nPossibleVals = data.GetNPossibleVals()
if details.activityBounds:
nPossibleVals[-1] = len(details.activityBounds) + 1
if setDescNames:
composite.SetInputOrder(data.GetVarNames())
composite.SetDescriptorNames(details._descNames)
else:
composite.SetDescriptorNames(data.GetVarNames())
composite.SetActivityQuantBounds(details.activityBounds)
if details.nModels == 1:
details.internalHoldoutFrac = 0.0
if details.useTrees:
from rdkit.ML.DecTree import CrossValidate, PruneTree
if details.qBounds != []:
from rdkit.ML.DecTree import BuildQuantTree
builder = BuildQuantTree.QuantTreeBoot
else:
from rdkit.ML.DecTree import ID3
builder = ID3.ID3Boot
driver = CrossValidate.CrossValidationDriver
pruner = PruneTree.PruneTree
composite.SetQuantBounds(details.qBounds)
nPossibleVals = data.GetNPossibleVals()
if details.activityBounds:
nPossibleVals[-1] = len(details.activityBounds) + 1
composite.Grow(trainExamples,
attrs,
nPossibleVals=[0] + nPossibleVals,
buildDriver=driver,
pruner=pruner,
nTries=details.nModels,
pruneIt=details.pruneIt,
lessGreedy=details.lessGreedy,
needsQuantization=0,
treeBuilder=builder,
nQuantBounds=details.qBounds,
startAt=details.startAt,
maxDepth=details.limitDepth,
progressCallback=progressCallback,
holdOutFrac=details.internalHoldoutFrac,
replacementSelection=details.replacementSelection,
recycleVars=details.recycleVars,
randomDescriptors=details.randomDescriptors,
silent=not _verbose)
elif details.useSigTrees:
from rdkit.ML.DecTree import CrossValidate
from rdkit.ML.DecTree import BuildSigTree
builder = BuildSigTree.SigTreeBuilder
driver = CrossValidate.CrossValidationDriver
nPossibleVals = data.GetNPossibleVals()
if details.activityBounds:
nPossibleVals[-1] = len(details.activityBounds) + 1
if hasattr(details, 'sigTreeBiasList'):
biasList = details.sigTreeBiasList
else:
biasList = None
if hasattr(details, 'useCMIM'):
useCMIM = details.useCMIM
else:
useCMIM = 0
if hasattr(details, 'allowCollections'):
allowCollections = details.allowCollections
else:
allowCollections = False
composite.Grow(trainExamples,
attrs,
nPossibleVals=[0] + nPossibleVals,
buildDriver=driver,
nTries=details.nModels,
needsQuantization=0,
treeBuilder=builder,
maxDepth=details.limitDepth,
progressCallback=progressCallback,
holdOutFrac=details.internalHoldoutFrac,
replacementSelection=details.replacementSelection,
recycleVars=details.recycleVars,
randomDescriptors=details.randomDescriptors,
biasList=biasList,
useCMIM=useCMIM,
allowCollection=allowCollections,
silent=not _verbose)
elif details.useKNN:
from rdkit.ML.KNN import CrossValidate
from rdkit.ML.KNN import DistFunctions
driver = CrossValidate.CrossValidationDriver
dfunc = ''
if (details.knnDistFunc == "Euclidean"):
dfunc = DistFunctions.EuclideanDist
elif (details.knnDistFunc == "Tanimoto"):
dfunc = DistFunctions.TanimotoDist
else:
assert 0, "Bad KNN distance metric value"
composite.Grow(trainExamples,
attrs,
nPossibleVals=[0] + nPossibleVals,
buildDriver=driver,
nTries=details.nModels,
needsQuantization=0,
numNeigh=details.knnNeighs,
holdOutFrac=details.internalHoldoutFrac,
distFunc=dfunc)
elif details.useNaiveBayes or details.useSigBayes:
from rdkit.ML.NaiveBayes import CrossValidate
driver = CrossValidate.CrossValidationDriver
if not (hasattr(details, 'useSigBayes') and details.useSigBayes):
composite.Grow(trainExamples,
attrs,
nPossibleVals=[0] + nPossibleVals,
buildDriver=driver,
nTries=details.nModels,
needsQuantization=0,
nQuantBounds=details.qBounds,
holdOutFrac=details.internalHoldoutFrac,
replacementSelection=details.replacementSelection,
mEstimateVal=details.mEstimateVal,
silent=not _verbose)
else:
if hasattr(details, 'useCMIM'):
useCMIM = details.useCMIM
else:
useCMIM = 0
composite.Grow(trainExamples,
attrs,
nPossibleVals=[0] + nPossibleVals,
buildDriver=driver,
nTries=details.nModels,
needsQuantization=0,
nQuantBounds=details.qBounds,
mEstimateVal=details.mEstimateVal,
useSigs=True,
useCMIM=useCMIM,
holdOutFrac=details.internalHoldoutFrac,
replacementSelection=details.replacementSelection,
silent=not _verbose)
## elif details.useSVM:
## from rdkit.ML.SVM import CrossValidate
## driver = CrossValidate.CrossValidationDriver
## composite.Grow(trainExamples, attrs, nPossibleVals=[0]+nPossibleVals,
## buildDriver=driver, nTries=details.nModels,
## needsQuantization=0,
## cost=details.svmCost,gamma=details.svmGamma,
## weights=details.svmWeights,degree=details.svmDegree,
## type=details.svmType,kernelType=details.svmKernel,
## coef0=details.svmCoeff,eps=details.svmEps,nu=details.svmNu,
## cache_size=details.svmCache,shrinking=details.svmShrink,
## dataType=details.svmDataType,
## holdOutFrac=details.internalHoldoutFrac,
## replacementSelection=details.replacementSelection,
## silent=not _verbose)
else:
from rdkit.ML.Neural import CrossValidate
driver = CrossValidate.CrossValidationDriver
composite.Grow(trainExamples,
attrs, [0] + nPossibleVals,
nTries=details.nModels,
buildDriver=driver,
needsQuantization=0)
composite.AverageErrors()
composite.SortModels()
modelList, counts, avgErrs = composite.GetAllData()
counts = numpy.array(counts)
avgErrs = numpy.array(avgErrs)
composite._varNames = data.GetVarNames()
for i in range(len(modelList)):
modelList[i].NameModel(composite._varNames)
# do final statistics
weightedErrs = counts * avgErrs
averageErr = sum(weightedErrs) / sum(counts)
devs = (avgErrs - averageErr)
devs = devs * counts
devs = numpy.sqrt(devs * devs)
avgDev = sum(devs) / sum(counts)
message('# Overall Average Error: %%% 5.2f, Average Deviation: %%% 6.2f' %
(100. * averageErr, 100. * avgDev))
if details.bayesModel:
composite.Train(trainExamples, verbose=0)
# blow out the saved examples and then save the composite:
composite.ClearModelExamples()
if saveIt:
composite.Pickle(details.outName)
details.model = DbModule.binaryHolder(cPickle.dumps(composite))
badExamples = []
if not details.detailedRes and (not hasattr(details, 'noScreen')
or not details.noScreen):
if details.splitRun:
message('Testing all hold-out examples')
wrong = testall(composite, testExamples, badExamples)
message('%d examples (%% %5.2f) were misclassified' %
(len(wrong),
100. * float(len(wrong)) / float(len(testExamples))))
_runDetails.holdout_error = float(len(wrong)) / len(testExamples)
else:
message('Testing all examples')
wrong = testall(composite, namedExamples, badExamples)
message('%d examples (%% %5.2f) were misclassified' %
(len(wrong),
100. * float(len(wrong)) / float(len(namedExamples))))
_runDetails.overall_error = float(len(wrong)) / len(namedExamples)
if details.detailedRes:
message('\nEntire data set:')
resTup = ScreenComposite.ShowVoteResults(range(data.GetNPts()), data,
composite, nPossibleVals[-1],
details.threshold)
nGood, nBad, nSkip, avgGood, avgBad, avgSkip, voteTab = resTup
nPts = len(namedExamples)
nClass = nGood + nBad
_runDetails.overall_error = float(nBad) / nClass
_runDetails.overall_correct_conf = avgGood
_runDetails.overall_incorrect_conf = avgBad
_runDetails.overall_result_matrix = repr(voteTab)
nRej = nClass - nPts
if nRej > 0:
_runDetails.overall_fraction_dropped = float(nRej) / nPts
if details.splitRun:
message('\nHold-out data:')
resTup = ScreenComposite.ShowVoteResults(range(len(testExamples)),
testExamples, composite,
nPossibleVals[-1],
details.threshold)
nGood, nBad, nSkip, avgGood, avgBad, avgSkip, voteTab = resTup
nPts = len(testExamples)
nClass = nGood + nBad
_runDetails.holdout_error = float(nBad) / nClass
_runDetails.holdout_correct_conf = avgGood
_runDetails.holdout_incorrect_conf = avgBad
_runDetails.holdout_result_matrix = repr(voteTab)
nRej = nClass - nPts
if nRej > 0:
_runDetails.holdout_fraction_dropped = float(nRej) / nPts
if details.persistTblName and details.dbName:
message('Updating results table %s:%s' %
(details.dbName, details.persistTblName))
details.Store(db=details.dbName, table=details.persistTblName)
if details.badName != '':
badFile = open(details.badName, 'w+')
for i in range(len(badExamples)):
ex = badExamples[i]
vote = wrong[i]
outStr = '%s\t%s\n' % (ex, vote)
badFile.write(outStr)
badFile.close()
composite.ClearModelExamples()
return composite
def test1cPointND(self):
dim = 4
pt = geom.PointND(4)
for i in range(dim):
self.assertTrue(feq(pt[i], 0.0))
pt[0] = 3
pt[3] = 4
self.assertTrue(feq(pt[0], 3.0))
self.assertTrue(feq(pt[3], 4.0))
self.assertTrue(feq(pt[-4], 3.0))
self.assertTrue(feq(pt[-1], 4.0))
lst = list(pt)
self.assertTrue(feq(lst[0], 3.0))
self.assertTrue(feq(lst[3], 4.0))
pt2 = geom.PointND(4)
pt2[0] = 1.
pt2[2] = 1.
pt3 = pt + pt2
self.assertTrue(feq(pt3[0], 4.0))
self.assertTrue(feq(pt3[2], 1.0))
self.assertTrue(feq(pt3[3], 4.0))
pt += pt2
self.assertTrue(feq(pt[0], 4.0))
self.assertTrue(feq(pt[2], 1.0))
self.assertTrue(feq(pt[3], 4.0))
pt3 = pt - pt2
self.assertTrue(feq(pt3[0], 3.0))
self.assertTrue(feq(pt3[2], 0.0))
self.assertTrue(feq(pt3[3], 4.0))
pt -= pt2
self.assertTrue(feq(pt[0], 3.0))
self.assertTrue(feq(pt[2], 0.0))
self.assertTrue(feq(pt[3], 4.0))
pt *= 2.0
self.assertTrue(feq(pt[0], 6.0))
self.assertTrue(feq(pt[1], 0.0))
self.assertTrue(feq(pt[2], 0.0))
self.assertTrue(feq(pt[3], 8.0))
pt /= 2
self.assertTrue(feq(pt[0], 3.0))
self.assertTrue(feq(pt[1], 0.0))
self.assertTrue(feq(pt[2], 0.0))
self.assertTrue(feq(pt[3], 4.0))
self.assertTrue(feq(pt.Length(), 5.0))
self.assertTrue(feq(pt.LengthSq(), 25.0))
pt.Normalize()
self.assertTrue(feq(pt.Length(), 1.0))
pkl = cPickle.dumps(pt)
pt2 = cPickle.loads(pkl)
self.assertTrue(len(pt) == len(pt2))
for i in range(len(pt)):
self.assertTrue(feq(pt2[i], pt[i]))
from __future__ import print_function
from rdkit import RDConfig
from rdkit.Dbase import DbModule
from rdkit.Dbase.DbConnection import DbConnect
from rdkit.six.moves import cPickle
from rdkit import Chem
if RDConfig.usePgSQL:
dbName = "::RDTests"
else:
dbName = "data.sqlt"
molTblName = 'simple_mols1'
fpTblName = 'simple_mols1_fp'
conn = DbConnect(dbName, molTblName)
conn.AddTable(fpTblName,
'id varchar(10),autofragmentfp %s' % DbModule.binaryTypeName)
d = conn.GetData()
for smi, id in d:
print(repr(id), repr(smi))
mol = Chem.MolFromSmiles(smi)
fp = Chem.RDKFingerprint(mol)
pkl = cPickle.dumps(fp)
conn.InsertData(fpTblName, (id, DbModule.binaryHolder(pkl)))
conn.Commit()
def test3Pickles(self):
#outF = file('dvvs.pkl','wb+')
with open(
os.path.join(RDConfig.RDBaseDir,
'Code/DataStructs/Wrap/testData/dvvs.pkl'),
'r'
) as inTF:
buf = inTF.read().replace('\r\n', '\n').encode('utf-8')
inTF.close()
with io.BytesIO(buf) as inF:
v1 = ds.DiscreteValueVect(ds.DiscreteValueType.ONEBITVALUE, 30)
for i in range(15):
v1[2*i] = 1
v2 = pickle.loads(pickle.dumps(v1))
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
#cPickle.dump(v1,outF)
v2=pickle.load(inF, encoding='bytes')
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
self.assertTrue(v1.GetTotalVal()==v2.GetTotalVal())
self.assertTrue(v2.GetTotalVal()!=0)
v1 = ds.DiscreteValueVect(ds.DiscreteValueType.TWOBITVALUE, 30)
for i in range(30):
v1[i] = i%4
v2 = pickle.loads(pickle.dumps(v1))
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
#pickle.dump(v1,outF)
v2=pickle.load(inF, encoding='bytes')
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
self.assertTrue(v1.GetTotalVal()==v2.GetTotalVal())
self.assertTrue(v2.GetTotalVal()!=0)
v1 = ds.DiscreteValueVect(ds.DiscreteValueType.FOURBITVALUE, 16)
for i in range(16):
v1[i] = i%16
v2 = pickle.loads(pickle.dumps(v1))
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
#pickle.dump(v1,outF)
v2=pickle.load(inF, encoding='bytes')
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
self.assertTrue(v1.GetTotalVal()==v2.GetTotalVal())
self.assertTrue(v2.GetTotalVal()!=0)
v1 = ds.DiscreteValueVect(ds.DiscreteValueType.EIGHTBITVALUE, 5)
v1[0] = 34
v1[1] = 167
v1[2] = 3
v1[3] = 56
v1[4] = 128
v2 = pickle.loads(pickle.dumps(v1))
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
#pickle.dump(v1,outF)
v2=pickle.load(inF, encoding='bytes')
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
self.assertTrue(v1.GetTotalVal()==v2.GetTotalVal())
self.assertTrue(v2.GetTotalVal()!=0)
v1 = ds.DiscreteValueVect(ds.DiscreteValueType.SIXTEENBITVALUE, 3)
v1[0] = 2345
v1[1] = 64578
v1[2] = 34
v2 = pickle.loads(pickle.dumps(v1))
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
#pickle.dump(v1,outF)
v2=pickle.load(inF, encoding='bytes')
self.assertTrue(ds.ComputeL1Norm(v1, v2) == 0)
self.assertTrue(v1.GetTotalVal()==v2.GetTotalVal())
self.assertTrue(v2.GetTotalVal()!=0)
from __future__ import print_function from rdkit import RDConfig from rdkit.Dbase import DbModule from rdkit.Dbase.DbConnection import DbConnect from rdkit.six.moves import cPickle from rdkit import Chem if RDConfig.usePgSQL: dbName = "::RDTests" else: dbName = "data.sqlt" molTblName = 'simple_mols1' fpTblName = 'simple_mols1_fp' conn = DbConnect(dbName, molTblName) conn.AddTable(fpTblName, 'id varchar(10),autofragmentfp %s' % DbModule.binaryTypeName) d = conn.GetData() for smi, id in d: print(repr(id), repr(smi)) mol = Chem.MolFromSmiles(smi) fp = Chem.RDKFingerprint(mol) pkl = cPickle.dumps(fp) conn.InsertData(fpTblName, (id, DbModule.binaryHolder(pkl))) conn.Commit()
