from rdkit.SimDivFilters import rdSimDivPickers as rdsimdiv
import numpy
from rdkit import RDRandom
RDRandom.seed(23)
pkr = rdsimdiv.MaxMinPicker()
n = 1000
m = 80
dataPts = []
for i in range(n) :
pt = numpy.zeros(2, 'd')
pt[0] = 10.*RDRandom.random()
pt[1] = 10.*RDRandom.random()
dataPts.append(pt)
# compute the distance matrix
distMat = numpy.zeros(n*(n-1)/2, 'd')
for i in range(n-1) :
itab = n*i - ((i+1)*(i+2))/2
pt1 = dataPts[i]
for j in range(i+1, n) :
id = itab + j
pt2 = dataPts[j]
diff = pt2 - pt1
dist = numpy.sqrt(numpy.dot(diff, diff))
distMat[id] = dist
from rdkit.SimDivFilters import rdSimDivPickers as rdsimdiv
import numpy
from rdkit import RDRandom
RDRandom.seed(23)
pkr = rdsimdiv.MaxMinPicker()
n = 1000
m = 80
dataPts = []
for i in range(n):
pt = numpy.zeros(2, 'd')
pt[0] = 10. * RDRandom.random()
pt[1] = 10. * RDRandom.random()
dataPts.append(pt)
# compute the distance matrix
distMat = numpy.zeros(n * (n - 1) / 2, 'd')
for i in range(n - 1):
itab = n * i - ((i + 1) * (i + 2)) / 2
pt1 = dataPts[i]
for j in range(i + 1, n):
id = itab + j
pt2 = dataPts[j]
diff = pt2 - pt1
dist = numpy.sqrt(numpy.dot(diff, diff))
distMat[id] = dist
# now do the picking
res = pkr.Pick(distMat, n, m)
def SplitIndices(nPts,frac,silent=1,legacy=0,replacement=0):
""" splits a set of indices into a data set into 2 pieces
**Arguments**
- nPts: the total number of points
- frac: the fraction of the data to be put in the first data set
- silent: (optional) toggles display of stats
- legacy: (optional) use the legacy splitting approach
- replacement: (optional) use selection with replacement
**Returns**
a 2-tuple containing the two sets of indices.
**Notes**
- the _legacy_ splitting approach uses randomly-generated floats
and compares them to _frac_. This is provided for
backwards-compatibility reasons.
- the default splitting approach uses a random permutation of
indices which is split into two parts.
- selection with replacement can generate duplicates.
**Usage**:
We'll start with a set of indices and pick from them using
the three different approaches:
>>> from rdkit.ML.Data import DataUtils
The base approach always returns the same number of compounds in
each set and has no duplicates:
>>> DataUtils.InitRandomNumbers((23,42))
>>> test,train = SplitIndices(10,.5)
>>> test
[1, 5, 6, 4, 2]
>>> train
[3, 0, 7, 8, 9]
>>> test,train = SplitIndices(10,.5)
>>> test
[5, 2, 9, 8, 7]
>>> train
[6, 0, 3, 1, 4]
The legacy approach can return varying numbers, but still has no
duplicates. Note the indices come back ordered:
>>> DataUtils.InitRandomNumbers((23,42))
>>> test,train = SplitIndices(10,.5,legacy=1)
>>> test
[0, 1, 2, 3, 4, 7, 9]
>>> train
[5, 6, 8]
>>> test,train = SplitIndices(10,.5,legacy=1)
>>> test
[4, 5, 7, 8, 9]
>>> train
[0, 1, 2, 3, 6]
The replacement approach returns a fixed number in the training set,
a variable number in the test set and can contain duplicates in the
training set.
>>> DataUtils.InitRandomNumbers((23,42))
>>> test,train = SplitIndices(10,.5,replacement=1)
>>> test
[1, 1, 3, 0, 1]
>>> train
[2, 4, 5, 6, 7, 8, 9]
>>> test,train = SplitIndices(10,.5,replacement=1)
>>> test
[9, 5, 4, 8, 0]
>>> train
[1, 2, 3, 6, 7]
"""
if frac<0. or frac > 1.:
raise ValueError('frac must be between 0.0 and 1.0 (frac=%f)'%(frac))
if replacement:
nTrain = int(nPts*frac)
resData = [None]*nTrain
resTest = []
for i in range(nTrain):
val = int(RDRandom.random()*nPts)
if val==nPts: val = nPts-1
resData[i] = val
for i in range(nPts):
if i not in resData:
resTest.append(i)
elif legacy:
resData = []
resTest = []
for i in range(nPts):
val = RDRandom.random()
if val < frac:
resData.append(i)
else:
resTest.append(i)
else:
perm = range(nPts)
random.shuffle(perm)
nTrain = int(nPts*frac)
resData = list(perm[:nTrain])
resTest = list(perm[nTrain:])
if not silent:
print 'Training with %d (of %d) points.'%(len(resData),nPts)
print '\t%d points are in the hold-out set.'%(len(resTest))
return resData,resTest
def SplitIndices(nPts, frac, silent=1, legacy=0, replacement=0):
""" splits a set of indices into a data set into 2 pieces
**Arguments**
- nPts: the total number of points
- frac: the fraction of the data to be put in the first data set
- silent: (optional) toggles display of stats
- legacy: (optional) use the legacy splitting approach
- replacement: (optional) use selection with replacement
**Returns**
a 2-tuple containing the two sets of indices.
**Notes**
- the _legacy_ splitting approach uses randomly-generated floats
and compares them to _frac_. This is provided for
backwards-compatibility reasons.
- the default splitting approach uses a random permutation of
indices which is split into two parts.
- selection with replacement can generate duplicates.
**Usage**:
We'll start with a set of indices and pick from them using
the three different approaches:
>>> from rdkit.ML.Data import DataUtils
The base approach always returns the same number of compounds in
each set and has no duplicates:
>>> DataUtils.InitRandomNumbers((23,42))
>>> test,train = SplitIndices(10,.5)
>>> test
[1, 5, 6, 4, 2]
>>> train
[3, 0, 7, 8, 9]
>>> test,train = SplitIndices(10,.5)
>>> test
[5, 2, 9, 8, 7]
>>> train
[6, 0, 3, 1, 4]
The legacy approach can return varying numbers, but still has no
duplicates. Note the indices come back ordered:
>>> DataUtils.InitRandomNumbers((23,42))
>>> test,train = SplitIndices(10,.5,legacy=1)
>>> test
[0, 1, 2, 3, 4, 7, 9]
>>> train
[5, 6, 8]
>>> test,train = SplitIndices(10,.5,legacy=1)
>>> test
[4, 5, 7, 8, 9]
>>> train
[0, 1, 2, 3, 6]
The replacement approach returns a fixed number in the training set,
a variable number in the test set and can contain duplicates in the
training set.
>>> DataUtils.InitRandomNumbers((23,42))
>>> test,train = SplitIndices(10,.5,replacement=1)
>>> test
[1, 1, 3, 0, 1]
>>> train
[2, 4, 5, 6, 7, 8, 9]
>>> test,train = SplitIndices(10,.5,replacement=1)
>>> test
[9, 5, 4, 8, 0]
>>> train
[1, 2, 3, 6, 7]
"""
if frac < 0. or frac > 1.:
raise ValueError('frac must be between 0.0 and 1.0 (frac=%f)' % (frac))
if replacement:
nTrain = int(nPts * frac)
resData = [None] * nTrain
resTest = []
for i in range(nTrain):
val = int(RDRandom.random() * nPts)
if val == nPts: val = nPts - 1
resData[i] = val
for i in range(nPts):
if i not in resData:
resTest.append(i)
elif legacy:
resData = []
resTest = []
for i in range(nPts):
val = RDRandom.random()
if val < frac:
resData.append(i)
else:
resTest.append(i)
else:
perm = range(nPts)
random.shuffle(perm)
nTrain = int(nPts * frac)
resData = list(perm[:nTrain])
resTest = list(perm[nTrain:])
if not silent:
print 'Training with %d (of %d) points.' % (len(resData), nPts)
print '\t%d points are in the hold-out set.' % (len(resTest))
return resData, resTest
