def crossvalidate(self, y, alphas, n_splits=10):
"""
lmmlasso cross-validation to get optimal alpha
alphas = list of alphas to perform cross-validation over
y = phenotype
"""
lasso = lmmlasso.LmmLasso(warm_start=True,
fit_intercept=False,
tol=0.5)
X = self.E
K = self.K
assert K is not None, 'no kinship matrix defined'
MSE_train, MSE_test, W_nonzero, rsquared = lmmlasso.runCrossValidation(
lasso, self.E, y, alphas, n_splits=n_splits, K=K, verbose=True)
train_inter = sp.interpolate.UnivariateSpline(
x=alphas, y=(MSE_train.mean(axis=0))).derivative(
n=2) #Interpolating the values for alphas within the range
test_inter = sp.interpolate.UnivariateSpline(
x=alphas, y=(MSE_test.mean(axis=0))).derivative(n=2)
alphas_inter = (sp.linspace(min(alphas), max(alphas), 100))
idx_train = sp.argmin(train_inter(alphas_inter)) # :/
idx_test = sp.argmin(test_inter(alphas_inter)) # :/
alpha_cv = (float(alphas_inter[idx_train]) +
float(alphas_inter[idx_test])) / 2
self.alpha = alpha_cv
return self.alpha
def fitmodel(self, y, alpha=None, tol=0.05):
"""
fit the model
"""
if alpha is None:
assert self.alpha is not None, 'Set an alpha value'
else:
self.alpha = alpha
assert y.shape[0] == self.G.shape[
0], 'No. of observations does not match'
lasso = lmmlasso.LmmLasso(warm_start=True,
fit_intercept=False,
tol=tol)
X = self.E
lasso.set_params(alpha=self.alpha)
assert self.K is not None, 'Include a Kinship matrix'
lasso = lasso.fit(X, y, K=self.K)
self.feweights = lasso.coef_ #fixed effect weights
self.feweights = np.reshape(self.feweights, (-1, 1))
self.lasso = lasso
#Running LMMLASSO
alphas = 2.**(sp.linspace(-2,10,10)) #list of alphas to test
n_splits=10
N = X.shape[0]
kf = KFold(n_splits,shuffle=True,random_state=None)
n_alphas = len(alphas)
MSE_train = sp.zeros((n_splits,n_alphas))
MSE_test = sp.zeros((n_splits,n_alphas))
W_nonzero = sp.zeros((n_splits,n_alphas))
kf.get_n_splits(X)
os.chdir("/srv/uom-data1-q.unimelb.edu.au/6300-afournier/home/student.unimelb.edu.au/andhikap/Clim_GWAS/Clim_GWAS_2")
import lmmlasso
lasso = lmmlasso.LmmLasso(warm_start=True,fit_intercept=False,tol=0.5) #note the tolerance value
MSE_train,MSE_test,W_nonzero = lmmlasso.runCrossValidation(lasso,X,y,alphas,n_splits=10,K=K,verbose=True)
MSE_train_inter=sp.interpolate.UnivariateSpline(x=alphas, y=(MSE_train.mean(axis=0))).derivative(n=2) #something about the rotation here is different from the original script
MSE_test_inter=sp.interpolate.UnivariateSpline(x=alphas, y=(MSE_test.mean(axis=0))).derivative(n=2)
alphas_inter = 2.**(sp.linspace(2,12,100))
idx_train = sp.argmin(MSE_train_inter(alphas_inter))
idx_test = sp.argmin(MSE_test_inter(alphas_inter))
alpha_cv = (float(alphas_inter[idx_train])+float(alphas_inter[idx_test]))/2
import pylab as pl
pl.figure(figsize=[20,4])
pls = pl.subplot(1,3,1)
pls.plot(sp.log2(alphas),MSE_train.mean(axis=0),linewidth=2)
pl.axvline(sp.log2(alpha_cv),color='r')
which='both',
bottom=False,
top=False,
labelbottom=False)
plt.ylabel('-log10(p-value)')
plt.xlabel('SNPs')
plt.title('GWAS using LMM; F-test; Unique SNPs only')
plt.show()
#Running LMM lasso (100k SNPs + covariance matrix)
import lmmlasso
#Cross validation to get the optimal parameters
alphas = 2.**(sp.linspace(2, 12, 10))
alphas = alphas[::-1]
from lmmlasso import runCrossValidation
lasso = lmmlasso.LmmLasso(
) #No need to set parameters because these will be decided through cross-validation [may need to set tolerance higher, use tol=0.05 as a baseline]
MSE_train, MSE_test, W_nonzero = lmmlasso.runCrossValidation(lasso,
SNP_data,
Pheno_data,
alphas,
n_splits=10,
K=K_data,
verbose=True)
#Then from Alex's code..
import pylab as pl
MSE_train_inter = sp.interpolate.UnivariateSpline(x=np.flip(alphas, axis=0),
y=np.flip(
MSE_train.mean(axis=0),
axis=0)).derivative(n=2)
else:
print(
str(n_snps_start - SNP_in) + '/' + str(n_snps_start) +
' SNPs did not meet the MAF threshold')
print(
str(SNP_data.shape[1]) + '/' + str(SNP_in) +
' SNPs included in this GWAS')
END_load = datetime.now()
print('Files were loaded in ' + str(END_load - START))
# running cross-validation
alphas = 2.**(sp.linspace(2, 12, 10))
alphas = alphas[::-1]
# running LMM-Lasso
lasso = lmmlasso.LmmLasso(warm_start=True, fit_intercept=False)
MSE_train, MSE_test, W_nonzero = lmmlasso.runCrossValidation(lasso,
SNP_data,
Pheno_data,
alphas,
n_folds=10,
K=K_data,
verbose=True)
# the dirty version
#idx = sp.argmin(MSE_test.mean(axis=0))
#alpha_cv = alphas[idx]
#OR
# the verion with secondary derivatives
MSE_train_inter = sp.interpolate.UnivariateSpline(
x=np.flip(alphas, axis=0), y=np.flip(MSE_train.mean(axis=0),
