def pls_kfold( sample_set, kfold_group_count, max_components, preprocess ):
print "load...";
l = AttrDict(load('linre_big'+sample_set+'.npz'))
disa = l.disa
expa = l.expa
Y = disa[:,None]
X = l.flum.T
X, Y, expa = shuffle(X, Y, expa, random_state=1)
print "fix...";
X_err, X = find_peaks(X,l.exa)
pls = PLSRegression( scale=False, algorithm='svd' )
pls.fit(X=X,Y=Y)
PC = pls.transform(X.copy())
PC1 = PC[:,0]
good = PC1 > -PC1.std()*2
X, Y, expa = X[good,:], Y[good,:], expa[good]
if preprocess:
X[X<0.5]=0.5
X = X**0.25
#save?
print "cross-validation...";
group_count = kfold_group_count(len(disa))
Ypred4n_components = empty((len(Y),max_components))
for n_components in arange(max_components)+1:
Ypred = empty_like(Y)
loo = KFold( n=len(Y), k=group_count, indices=False )
for fit, test in loo:
pls = PLSRegression(
scale=False,
algorithm='svd',
n_components=n_components
)
pls.fit( X=X[fit].copy(), Y=Y[fit].copy() )
Ypred[test] = pls.predict(X[test].copy())
Ypred4n_components[:,n_components-1] = Ypred[:,0]
print "done for "+str(n_components)+" components"
savez('out23/'+preprocess+'pred.npz',
X=X, Y=Y, expa=expa, Ypred4n_components=Ypred4n_components
)
expa = l['expa']
Y = disa[:,None]
X = flum.T
X, Y, expa = shuffle(X, Y, expa, random_state=1)
print "fix peaks..."
X_err, X = find_peaks(X,exa)
print "fix outliers..."
pls = PLSRegression( scale=False, algorithm='svd' )
pls.fit(X=X,Y=Y)
PC = pls.transform(X.copy())
PC1, PC2 = PC[:,0], PC[:,1]
good = PC1 > -PC1.std()*2
plot_scores(fn='_bad_1', expa=expa, x=PC1,y=PC2, xl='T1',yl='T2', title=', bad')
print expa[logical_not(good)]
X, Y, expa = X[good,:], Y[good,:], expa[good]
print "preprocess with power..."
if preprocess:
X[X<0.5]=0.5
X = X**0.25
print "fit..."
a4fit = arange(len(X)) >= samples_in_testing_set
a4test = logical_not(a4fit)
pca = RandomizedPCA(n_components=ncomp, whiten=True)
clf = LinearRegression().fit(pca.fit_transform(X_fmri_train), y_train)
mse_fmri.append(mean_squared_error(clf.predict(pca.transform(X_fmri_test)), y_test))
clf = LinearRegression().fit(pca.fit_transform(X_meg_train), y_train)
mse_meg.append(mean_squared_error(clf.predict(pca.transform(X_meg_test)), y_test))
both_train = np.hstack([X_meg_train, X_fmri_train])
both_test = np.hstack([X_meg_test, X_fmri_test])
clf = LinearRegression().fit(pca.fit_transform(both_train), y_train)
mse_pca.append(mean_squared_error(clf.predict(pca.transform(both_test)), y_test))
plsca.fit(X_meg_train, X_fmri_train)
X_mc_train, X_fc_train = plsca.transform(X_meg_train, X_fmri_train)
X_mc_test, X_fc_test = plsca.transform(X_meg_test, X_fmri_test)
clf = LinearRegression().fit(X_mc_train, y_train)
mse_plsm.append(mean_squared_error(clf.predict(X_mc_test), y_test))
mse_plsf.append(mean_squared_error(clf.predict(X_fc_test), y_test))
# dumb.fit(X_fmri_train, X_meg_train)
# dumb_pred = dumb.predict(X_fmri_test)
# dumb_mae += mean_absolute_error(X_meg_test,dumb_pred)
yf.append(np.sqrt(np.mean(mse_fmri)))
ym.append(np.sqrt(np.mean(mse_meg)))
ypca.append(np.sqrt(np.mean(mse_pca)))
yplsm.append(np.sqrt(np.mean(mse_plsm)))
yplsf.append(np.sqrt(np.mean(mse_plsf)))
# dumb_scores.append(dumb_mae/nfolds)
