def cvmultnet(fit, \
lambdau, \
x, \
y, \
weights, \
offset, \
foldid, \
ptype, \
grouped, \
keep = False):
typenames = {
'deviance': 'Multinomial Deviance',
'mse': 'Mean-Squared Error',
'mae': 'Mean Absolute Error',
'class': 'Misclassification Error'
}
if ptype == 'default':
ptype = 'deviance'
ptypeList = ['mse', 'mae', 'deviance', 'class']
if not ptype in ptypeList:
print('Warning: only ', ptypeList, 'available for multinomial models; '
'deviance'
' used')
ptype = 'deviance'
prob_min = 1.0e-5
prob_max = 1 - prob_min
nc = y.shape
if nc[1] == 1:
classes, sy = numpy.unique(y, return_inverse=True)
nc = len(classes)
indexes = numpy.eye(nc, nc)
y = indexes[sy, :]
else:
nc = nc[1]
is_offset = not (len(offset) == 0)
predmat = numpy.ones([y.shape[0], nc, lambdau.size]) * numpy.NAN
nfolds = numpy.amax(foldid) + 1
nlams = []
for i in range(nfolds):
which = foldid == i
fitobj = fit[i].copy()
if is_offset:
off_sub = offset[which, ]
else:
off_sub = numpy.empty([0])
preds = glmnetPredict(fitobj, x[which, ], numpy.empty([0]), 'response',
False, off_sub)
nlami = numpy.size(fit[i]['lambdau'])
predmat[which, 0:nlami] = preds
nlams.append(nlami)
# convert nlams to scipy array
nlams = numpy.array(nlams, dtype=numpy.integer)
ywt = numpy.sum(y, axis=1, keepdims=True)
y = y / numpy.tile(ywt, [1, y.shape[1]])
weights = weights * ywt
N = y.shape[0] - numpy.sum(
numpy.isnan(predmat[:, 1, :]), axis=0, keepdims=True)
bigY = numpy.tile(y[:, :, None], [1, 1, lambdau.size])
if ptype == 'mse':
cvraw = numpy.sum((bigY - predmat)**2, axis=1).squeeze()
elif ptype == 'deviance':
predmat = numpy.minimum(numpy.maximum(predmat, prob_min), prob_max)
lp = bigY * numpy.log(predmat)
ly = bigY * numpy.log(bigY)
ly[y == 0] = 0
cvraw = numpy.sum(2 * (ly - lp), axis=1).squeeze()
elif ptype == 'mae':
cvraw = numpy.sum(numpy.absolute(bigY - predmat), axis=1).squeeze()
elif ptype == 'class':
classid = numpy.zeros([y.shape[0], lambdau.size]) * numpy.NaN
for i in range(lambdau.size):
classid[:, i] = glmnet_softmax(predmat[:, :, i])
classid = classid.reshape([classid.size, 1])
yperm = bigY.transpose((0, 2, 1))
yperm = yperm.reshape([yperm.size, 1])
idx = sub2ind(yperm.shape, range(len(classid)), classid.transpose())
cvraw = numpy.reshape(1 - yperm[idx], [-1, lambdau.size])
if grouped == True:
cvob = cvcompute(cvraw, weights, foldid, nlams)
cvraw = cvob['cvraw']
weights = cvob['weights']
N = cvob['N']
cvm = wtmean(cvraw, weights)
sqccv = (cvraw - cvm)**2
cvsd = numpy.sqrt(wtmean(sqccv, weights) / (N - 1))
result = dict()
result['cvm'] = cvm
result['cvsd'] = cvsd
result['name'] = typenames[ptype]
if keep:
result['fit_preval'] = predmat
return (result)
def cvlognet(fit, \
lambdau, \
x, \
y, \
weights, \
offset, \
foldid, \
ptype, \
grouped, \
keep = False):
typenames = {
'deviance': 'Binomial Deviance',
'mse': 'Mean-Squared Error',
'mae': 'Mean Absolute Error',
'auc': 'AUC',
'class': 'Misclassification Error'
}
if ptype == 'default':
ptype = 'deviance'
ptypeList = ['mse', 'mae', 'deviance', 'auc', 'class']
if not ptype in ptypeList:
print('Warning: only ', ptypeList, 'available for binomial models; '
'deviance'
' used')
ptype = 'deviance'
prob_min = 1.0e-5
prob_max = 1 - prob_min
nc = y.shape[1]
if nc == 1:
classes, sy = scipy.unique(y, return_inverse=True)
nc = len(classes)
indexes = scipy.eye(nc, nc)
y = indexes[sy, :]
else:
classes = scipy.arange(nc) + 1 # 1:nc
N = y.size
nfolds = scipy.amax(foldid) + 1
if (N / nfolds < 10) and (type == 'auc'):
print(
'Warning: Too few (<10) observations per fold for type.measure=auc in cvlognet'
)
print(
'Warning: changed to type.measure = deviance. Alternately, use smaller value '
)
print('Warning: for nfolds')
ptype = 'deviance'
if (N / nfolds < 3) and grouped:
print(
'Warning: option grouped = False enforced in cvglmnet as there are < 3 observations per fold'
)
grouped = False
is_offset = not (len(offset) == 0)
predmat = scipy.ones([y.shape[0], lambdau.size]) * scipy.NAN
nfolds = scipy.amax(foldid) + 1
nlams = []
for i in range(nfolds):
which = foldid == i
fitobj = fit[i].copy()
if is_offset:
off_sub = offset[which, ]
else:
off_sub = scipy.empty([0])
preds = glmnetPredict(fitobj, x[which, ], scipy.empty([0]), 'response',
False, off_sub)
nlami = scipy.size(fit[i]['lambdau'])
predmat[which, 0:nlami] = preds
nlams.append(nlami)
# convert nlams to scipy array
nlams = scipy.array(nlams, dtype=scipy.integer)
if ptype == 'auc':
cvraw = scipy.zeros([nfolds, lambdau.size]) * scipy.NaN
good = scipy.zeros([nfolds, lambdau.size])
for i in range(nfolds):
good[i, 0:nlams[i]] = 1
which = foldid == i
for j in range(nlams[i]):
cvraw[i, j] = auc_mat(y[which, ], predmat[which, j],
weights[which])
N = scipy.sum(good, axis=0)
sweights = scipy.zeros([nfolds, 1])
for i in range(nfolds):
sweights[i] = scipy.sum(weights[foldid == i], axis=0)
weights = sweights
else:
ywt = scipy.sum(y, axis=1, keepdims=True)
y = y / scipy.tile(ywt, [1, y.shape[1]])
weights = (weights * ywt.T).T
N = y.shape[0] - scipy.sum(scipy.isnan(predmat), axis=0, keepdims=True)
yy1 = scipy.tile(y[:, 0:1], [1, lambdau.size])
yy2 = scipy.tile(y[:, 1:2], [1, lambdau.size])
if ptype == 'mse':
cvraw = (yy1 - (1 - predmat))**2 + (yy2 - (1 - predmat))**2
elif ptype == 'deviance':
predmat = scipy.minimum(scipy.maximum(predmat, prob_min), prob_max)
lp = yy1 * scipy.log(1 - predmat) + yy2 * scipy.log(predmat)
ly = scipy.log(y)
ly[y == 0] = 0
ly = scipy.dot(y * ly, scipy.array([1.0, 1.0]).reshape([2, 1]))
cvraw = 2 * (scipy.tile(ly, [1, lambdau.size]) - lp)
elif ptype == 'mae':
cvraw = scipy.absolute(yy1 -
(1 - predmat)) + scipy.absolute(yy2 -
(1 - predmat))
elif ptype == 'class':
cvraw = yy1 * (predmat > 0.5) + yy2 * (predmat <= 0.5)
if y.size / nfolds < 3 and grouped == True:
print(
'Option grouped=false enforced in cv.glmnet, since < 3 observations per fold'
)
grouped = False
if grouped == True:
cvob = cvcompute(cvraw, weights, foldid, nlams)
cvraw = cvob['cvraw']
weights = cvob['weights']
N = cvob['N']
cvm = wtmean(cvraw, weights)
sqccv = (cvraw - cvm)**2
cvsd = scipy.sqrt(wtmean(sqccv, weights) / (N - 1))
result = dict()
result['cvm'] = cvm
result['cvsd'] = cvsd
result['name'] = typenames[ptype]
if keep:
result['fit_preval'] = predmat
return (result)
def cvfishnet(fit, \
lambdau, \
x, \
y, \
weights, \
offset, \
foldid, \
ptype, \
grouped, \
keep = False):
typenames = {
'deviance': 'Poisson Deviance',
'mse': 'Mean-Squared Error',
'mae': 'Mean Absolute Error'
}
if ptype == 'default':
ptype = 'deviance'
ptypeList = ['mse', 'mae', 'deviance']
if not ptype in ptypeList:
print('Warning: only ', ptypeList, 'available for Poisson models; '
'deviance'
' used')
ptype = 'deviance'
if len(offset) > 0:
is_offset = True
else:
is_offset = False
predmat = scipy.ones([y.size, lambdau.size]) * scipy.NAN
nfolds = scipy.amax(foldid) + 1
nlams = []
for i in range(nfolds):
which = foldid == i
fitobj = fit[i].copy()
if is_offset:
off_sub = offset[which]
else:
off_sub = scipy.empty([0])
preds = glmnetPredict(fitobj, x[which, ], offset=off_sub)
nlami = scipy.size(fit[i]['lambdau'])
predmat[which, 0:nlami] = preds
nlams.append(nlami)
# convert nlams to scipy array
nlams = scipy.array(nlams, dtype=scipy.integer)
N = y.shape[0] - scipy.sum(scipy.isnan(predmat), axis=0)
yy = scipy.tile(y, [1, lambdau.size])
if ptype == 'mse':
cvraw = (yy - predmat)**2
elif ptype == 'deviance':
cvraw = devi(yy, predmat)
elif ptype == 'mae':
cvraw = scipy.absolute(yy - predmat)
if y.size / nfolds < 3 and grouped == True:
print(
'Option grouped=false enforced in cvglmnet, since < 3 observations per fold'
)
grouped = False
if grouped == True:
cvob = cvcompute(cvraw, weights, foldid, nlams)
cvraw = cvob['cvraw']
weights = cvob['weights']
N = cvob['N']
cvm = wtmean(cvraw, weights)
sqccv = (cvraw - cvm)**2
cvsd = scipy.sqrt(wtmean(sqccv, weights) / (N - 1))
result = dict()
result['cvm'] = cvm
result['cvsd'] = cvsd
result['name'] = typenames[ptype]
if keep:
result['fit_preval'] = predmat
return (result)
def cvmrelnet(fit,
lambdau,
x,
y,
weights,
offset,
foldid,
ptype,
grouped,
keep=False):
typenames = {'deviance':'Mean-Squared Error', 'mse':'Mean-Squared Error',
'mae':'Mean Absolute Error'}
if ptype == 'default':
ptype = 'mse'
ptypeList = ['mse', 'mae', 'deviance']
if not ptype in ptypeList:
print('Warning: only ', ptypeList, 'available for Gaussian models; ''mse'' used')
ptype = 'mse'
nobs, nc = y.shape
if len(offset) > 0:
y = y - offset
predmat = scipy.ones([nobs, nc, lambdau.size])*scipy.NAN
nfolds = scipy.amax(foldid) + 1
nlams = []
for i in range(nfolds):
which = foldid == i
fitobj = fit[i].copy()
fitobj['offset'] = False
preds = glmnetPredict(fitobj, x[which, ])
nlami = scipy.size(fit[i]['lambdau'])
predmat[which, 0:nlami] = preds
nlams.append(nlami)
# convert nlams to scipy array
nlams = scipy.array(nlams, dtype=scipy.integer)
N = nobs - scipy.reshape(scipy.sum(scipy.isnan(predmat[:, 1, :]), axis=0), (1, -1))
bigY = scipy.tile(y[:, :, None], [1, 1, lambdau.size])
if ptype == 'mse':
cvraw = scipy.sum((bigY - predmat)**2, axis=1).squeeze()
elif ptype == 'mae':
cvraw = scipy.sum(scipy.absolute(bigY - predmat), axis=1).squeeze()
if y.size/nfolds < 3 and grouped == True:
print('Option grouped=false enforced in cv.glmnet, since < 3 observations per fold')
grouped = False
if grouped == True:
cvob = cvcompute(cvraw, weights, foldid, nlams)
cvraw = cvob['cvraw']
weights = cvob['weights']
N = cvob['N']
cvm = wtmean(cvraw, weights)
sqccv = (cvraw - cvm)**2
cvsd = scipy.sqrt(wtmean(sqccv, weights)/(N-1))
result = dict()
result['cvm'] = cvm
result['cvsd'] = cvsd
result['name'] = typenames[ptype]
if keep:
result['fit_preval'] = predmat
return result