def call_pls(chrom,xdata,factors,mask,data):
"""Runs pls on a subset of X-variables"""
scores = []
for i in range(chrom.shape[0]):
if _remdup(chrom[i]) == 0:
#extract vars from xdata
slice = scipy.take(xdata,chrom[i,:].tolist(),1)
collate = 0
for nF in range(mask.shape[1]):
#split in to training and test
try:
pls_output = pls(slice,data['class'][:,0][:,nA],mask[:,nF].tolist(),factors)
if min(pls_output['rmsec']) <= min(pls_output['rmsepc']):
collate += pls_output['RMSEPC']
else:
collate += 10.0**5
except:
collate = 0
if collate != 0:
scores.append(collate/float(mask.shape[1]))
else:
scores.append(10.0**5)
else:
scores.append(10.0**5)
return scipy.asarray(scores)[:,nA]
def call_pls(chrom, xdata, factors, mask, data):
"""Runs pls on a subset of X-variables"""
scores = []
for i in range(chrom.shape[0]):
if _remdup(chrom[i]) == 0:
#extract vars from xdata
slice = scipy.take(xdata, chrom[i, :].tolist(), 1)
collate = 0
for nF in range(mask.shape[1]):
#split in to training and test
try:
pls_output = pls(slice, data['class'][:, 0][:, nA],
mask[:, nF].tolist(), factors)
if min(pls_output['rmsec']) <= min(pls_output['rmsepc']):
collate += pls_output['RMSEPC']
else:
collate += 10.0**5
except:
collate = 0
if collate != 0:
scores.append(collate / float(mask.shape[1]))
else:
scores.append(10.0**5)
else:
scores.append(10.0**5)
return scipy.asarray(scores)[:, nA]
def call_dfa(chrom, xdata, DFs, mask, data):
"""Runs DFA on subset of variables from "xdata" as
defined by "chrom" and returns a vector of fitness
scores to be fed back into the GA
"""
Y = []
for x in range(len(chrom)):
if _remdup(chrom[x]) == 0:
#extract vars from xdata
slice = meancent(_slice(xdata, chrom[x]))
collate = 0
for nF in range(mask.shape[1]):
#split in to training and test
tr_slice, cv_slice, ts_slice, tr_grp, cv_grp, ts_grp, tr_nm, cv_nm, ts_nm = _split(
slice, data['class'][:, 0], mask[:, nF].tolist(),
data['label'])
try:
u, v, eigs, dummy = cva(tr_slice, tr_grp, DFs)
projU = scipy.dot(cv_slice, v)
u = scipy.concatenate((u, projU), 0)
group2 = scipy.concatenate((tr_grp, cv_grp), 0)
B, W = _BW(u, group2)
L, A = scipy.linalg.eig(B, W)
order = _flip(
scipy.argsort(scipy.reshape(L.real, (len(L), ))))
Ls = _flip(scipy.sort(L.real))
eigval = Ls[0:DFs]
collate += sum(eigval)
except:
continue
if collate != 0:
Y.append(float(mask.shape[1]) / collate)
else:
Y.append(10.0**5)
else:
Y.append(10.0**5)
return scipy.array(Y)[:, nA]
def call_dfa(chrom,xdata,DFs,mask,data):
"""Runs DFA on subset of variables from "xdata" as
defined by "chrom" and returns a vector of fitness
scores to be fed back into the GA
"""
Y = []
for x in range(len(chrom)):
if _remdup(chrom[x]) == 0:
#extract vars from xdata
slice = meancent(_slice(xdata,chrom[x]))
collate = 0
for nF in range(mask.shape[1]):
#split in to training and test
tr_slice,cv_slice,ts_slice,tr_grp,cv_grp,ts_grp,tr_nm,cv_nm,ts_nm=_split(slice,
data['class'][:,0],mask[:,nF].tolist(),data['label'])
try:
u,v,eigs,dummy = cva(tr_slice,tr_grp,DFs)
projU = scipy.dot(cv_slice,v)
u = scipy.concatenate((u,projU),0)
group2 = scipy.concatenate((tr_grp,cv_grp),0)
B,W = _BW(u,group2)
L,A = scipy.linalg.eig(B,W)
order = _flip(scipy.argsort(scipy.reshape(L.real,(len(L),))))
Ls = _flip(scipy.sort(L.real))
eigval = Ls[0:DFs]
collate += sum(eigval)
except:
continue
if collate != 0:
Y.append(float(mask.shape[1])/collate)
else:
Y.append(10.0**5)
else:
Y.append(10.0**5)
return scipy.array(Y)[:,nA]