def fitSamplingNull(response,nSamp, method='cv',
memlimit=None, largest=None, **kwargs):
nObs = len(response)
# lets partition the data via our sampling method
if method=='cv':
t,v = st.kFoldCV(range(nObs),nSamp,randomise=True)
elif (method=='bs') or (method=='bs632'):
t,v = st.kRoundBS(range(nObs),nSamp)
else:
raise ValueError('Sampling method not correct')
smse = 0
sSqmse = 0
for i in range(nSamp):
# get the training values
y = response[t[i]]
Yval = response[v[i]]
nVal = float(len(Yval))
mse = np.sum((Yval-np.mean(y))**2)/nVal
# sum the rows (errors for given model)
smse = smse + mse
sSqmse = sSqmse + mse**2
# now it is time to average and send back
# I am putting the errors in a container
nSampFlt = float(nSamp)
meanmse = smse/nSampFlt
varmse = sSqmse/nSampFlt - meanmse**2
if method=='bs632':
yhat = fullEnm.predict(regressors)
resubmse = np.sum((yhat.T-response)**2,1)/float(nObs)
meanmse = 0.632*meanmse+(1-0.632)*resubmse
return meanmse, varmse
def fitSampling(regressors, response, alpha, nSamp, method='cv',
memlimit=None, largest=None, **kwargs):
"""Performs an elastic net constrained linear regression,
see fit, with selected sampleing method to estimate errors
using nSamp number of sampleings.
methods:
'cv' cross validation with nSamp number of folds
'bs' bootstrap
'bs632' boostrap 632 (weighted average of bs and training error)
Returns a TrainingError object (cvTools) and an
ENetModel object for the full fit (err,enm).
Function requires cvTools
"""
nObs,nRegs = regressors.shape
# get the full model fit
fullEnm = enet.fit(regressors, response, alpha, memlimit,
largest, **kwargs)
# get the lambda values determined in the full fit (going to force these lambdas for all cv's)
lam = fullEnm.lambdas
# the lambdas may have been user defined, don't want it defined twice
if kwargs.has_key('lambdas'):
del kwargs['lambdas']
# lets partition the data via our sampling method
if method=='cv':
t,v = st.kFoldCV(range(nObs),nSamp,randomise=True)
elif (method=='bs') or (method=='bs632'):
t,v = st.kRoundBS(range(nObs),nSamp)
else:
raise ValueError('Sampling method not correct')
# lets consider many versions of errors
# with our error being mean squared error
# we want the epected mean squared error
# and the corisponding variance over the diffrent versions
nModels = len(lam)
smse = np.zeros(nModels)
sSqmse = np.zeros(nModels)
allVals = np.zeros((nModels,nSamp))
# loop through the folds
for i in range(nSamp):
# get the training values
X = regressors[t[i]]
y = response[t[i]]
enm = enet.fit(X, y, alpha, memlimit,
largest, lambdas=lam, **kwargs)
# get the validation values
Xval = regressors[v[i]]
Yval = response[v[i]]
nVal = float(len(Yval))
# get the predicted responses from validation regressors
Yhat = enm.predict(Xval)
# what is the mean squared error?
# notice the T was necassary to do the subtraction
# the rows are the models and the cols are the observations
mse = np.sum((Yhat.T-Yval)**2,1)/nVal
# sum the rows (errors for given model)
smse = smse + mse
sSqmse = sSqmse + mse**2
allVals[:,i] = mse
# now it is time to average and send back
# I am putting the errors in a container
nSampFlt = float(nSamp)
meanmse = smse/nSampFlt
varmse = sSqmse/nSampFlt - meanmse**2
if method=='bs632':
yhat = fullEnm.predict(regressors)
resubmse = np.sum((yhat.T-response)**2,1)/float(nObs)
meanmse = 0.632*meanmse+(1-0.632)*resubmse
err = enet.ENetTrainError(lam,nSamp,meanmse,varmse,[0],[0],alpha)
err.setParamName('lambda')
fullEnm.setErrors(err.mErr)
return err, fullEnm, allVals
