def pls_train(self, X, Y, verbose=True):
Xn = simple_normalize(X)
pls = PLSRegression()
if verbose:
print 'fitting canonical pls...'
pls.fit(Xn, Y)
return pls
def plss(X, y, cv, n_components=1):
"""
"""
pls = PLSRegression(n_components=n_components)
sse = np.zeros(y.shape[1])
for train, test in cv:
X_train, X_test = X[train], X[test]
y_train, y_test = y[train], y[test]
y0 = y_train.mean(0)
X0 = X_train.mean(0)
pls.fit(X_train - X0, y_train - y0)
sse += np.sum((y_test - y0 - pls.predict(X_test - X0)) ** 2, 0)
return sse
def plss(X, y, cv, n_components=1):
"""
"""
pls = PLSRegression(n_components=n_components)
sse = np.zeros(y.shape[1])
for train, test in cv:
X_train, X_test = X[train], X[test]
y_train, y_test = y[train], y[test]
y0 = y_train.mean(0)
X0 = X_train.mean(0)
pls.fit(X_train - X0, y_train - y0)
sse += np.sum((y_test - y0 - pls.predict(X_test - X0))**2, 0)
return sse
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
)
pl.xticks(())
pl.yticks(())
pl.show()
###############################################################################
# PLS regression, with multivariate response, a.k.a. PLS2
n = 1000
q = 3
p = 10
X = np.random.normal(size=n * p).reshape((n, p))
B = np.array([[1, 2] + [0] * (p - 2)] * q).T
# each Yj = 1*X1 + 2*X2 + noize
Y = np.dot(X, B) + np.random.normal(size=n * q).reshape((n, q)) + 5
pls2 = PLSRegression(n_components=3)
pls2.fit(X, Y)
print ("True B (such that: Y = XB + Err)")
print (B)
# compare pls2.coefs with B
print ("Estimated B")
print (np.round(pls2.coefs, 1))
pls2.predict(X)
###############################################################################
# PLS regression, with univariate response, a.k.a. PLS1
n = 1000
p = 10
X = np.random.normal(size=n * p).reshape((n, p))
y = X[:, 0] + 2 * X[:, 1] + np.random.normal(size=n * 1) + 5
def dict2mean(X, dict):
plsca = PLSRegression(n_components=np.shape(dict['coefs'])[0])
plsca.x_mean_ = dict['x_mean']
plsca.y_mean_ = dict['y_mean']
plsca.coefs = dict['coefs']
return plsca.predict(X)
np.corrcoef(Y_test_r[:, 0], Y_test_r[:, 1])[0, 1]) pl.legend() pl.show() ############################################################################### # PLS regression, with multivariate response, a.k.a. PLS2 n = 1000 q = 3 p = 10 X = np.random.normal(size=n * p).reshape((n, p)) B = np.array([[1, 2] + [0] * (p - 2)] * q).T # each Yj = 1*X1 + 2*X2 + noize Y = np.dot(X, B) + np.random.normal(size=n * q).reshape((n, q)) + 5 pls2 = PLSRegression(n_components=3) pls2.fit(X, Y) print "True B (such that: Y = XB + Err)" print B # compare pls2.coefs with B print "Estimated B" print np.round(pls2.coefs, 1) pls2.predict(X) ############################################################################### # PLS regression, with univariate response, a.k.a. PLS1 n = 1000 p = 10 X = np.random.normal(size=n * p).reshape((n, p)) y = X[:, 0] + 2 * X[:, 1] + np.random.normal(size=n * 1) + 5
yf = []
ym = []
ypca = []
yplsm = []
yplsf = []
X_fmri = scale(np.concatenate(good_data['fmri'], axis=1))
X_meg = scale(np.concatenate(good_data['meg'], axis=1))
for ncomp in max_comps:
mse_fmri = []
mse_meg = []
mse_pca = []
mse_plsm = []
mse_plsf = []
print 'Trying %d components' % ncomp
plsca = PLSRegression(n_components=ncomp)
dumb = DummyRegressor(strategy='mean')
for oidx, (train, test) in enumerate(cv):
X_fmri_train = X_fmri[train]
X_fmri_test = X_fmri[test]
X_meg_train = X_meg[train]
X_meg_test = X_meg[test]
y_train = sx.iloc[train].tolist()
y_test = sx.iloc[test].tolist()
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))
from sklearn.cross_validation import ShuffleSplit
from sklearn.pls import PLSRegression
from sklearn.metrics import mean_absolute_error
from sklearn.dummy import DummyRegressor
nobs = X_meg.shape[0]
max_comps = range(2, 30, 2)
nfolds = 50
cv = ShuffleSplit(nobs, n_iter=nfolds, test_size=.1)
# Trying the prediction with different components
comp_scores = []
dumb_scores = []
for ncomp in max_comps:
print 'Trying %d components' % ncomp
pls = PLSRegression(n_components=ncomp)
dumb = DummyRegressor(strategy='mean')
mae = 0
dumb_mae = 0
for oidx, (train, test) in enumerate(cv):
X_fmri_train = X_fmri[train]
X_fmri_test = X_fmri[test]
X_meg_train = X_meg[train]
X_meg_test = X_meg[test]
pls.fit(X_fmri_train, X_meg_train)
pred = pls.predict(X_fmri_test)
mae += mean_absolute_error(X_meg_test, pred)
from dataset_creator import DatasetCreator
params = {"LAMBDA": 0.4, "dimension": 4096}
c = DatasetCreator(dtk_params=params, encoder_params=[4096, 3])
D = c.get_d()
n = len(D[0])
print(D[1])
train_X, train_Y = D[0][:n / 2], D[1][:n / 2]
test_X, test_Y = D[0][n / 2:], D[1][n / 2:]
pls2 = PLSRegression()
pls2.fit(train_X, train_Y)
#print(pls2.coefs)
pred = pls2.predict(test_X)
mean_err = np.mean((pred - test_Y)**2)
print(mean_err)
mean_cos = 0
mean_cos_original = 0
for i, j in zip(pred, test_Y):
mean_cos = mean_cos + np.dot(i, j) / np.sqrt(np.dot(i, i) * np.dot(j, j))
from sklearn.metrics import mean_absolute_error
from sklearn.dummy import DummyRegressor
nobs = X_meg.shape[0]
max_comps = range(5,30,5)
nfolds=50
cv = ShuffleSplit(nobs,n_iter=nfolds,test_size=.1)
y = inatt
# Trying the prediction with different components
comp_scores = []
dumb_scores = []
meg_scores, fmri_scores = [], []
for ncomp in max_comps:
print 'Trying %d components'%ncomp
pls = PLSRegression(n_components=ncomp)
dumb = DummyRegressor(strategy='mean')
mae = 0
dumb_mae = 0
meg_mae, fmri_mae = 0, 0
for oidx, (train, test) in enumerate(cv):
X_fmri_train = X_fmri[train]
X_fmri_test = X_fmri[test]
X_meg_train = X_meg[train]
X_meg_test = X_meg[test]
y_train = y[train]
y_test = y[test]
X_train = np.hstack([X_fmri_train,X_meg_train])
X_test = np.hstack([X_fmri_test,X_meg_test])
mds = AttrDict(load("out23/pred.npz"))
X, Y, expa = mds.X, mds.Y, mds.expa
X[X<0.5]=0.5 #0.7
X = X**0.25
group_count = 11
n_components_list = range(9,20)
for n_components in n_components_list:
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())
print n_components, RMSEP(Y[:,0],Ypred[:,0])
#n, bins, patches = plt.hist(X.flatten(),40,range=(0,2))
#plt.show()
"""
stuff:
print [v for v in X.flatten() if v<-0.4] #only 3 numbers from X <-0.4
X = (1-X)**2/X*2 #Kubelka-Munk function
"""
"""-
def test_predictions():
d = load_linnerud()
X = d.data
Y = d.target
tol = 5e-12
miter = 1000
num_comp = 2
Xorig = X.copy()
Yorig = Y.copy()
# SSY = np.sum(Yorig**2)
# center = True
scale = False
pls1 = PLSRegression(n_components = num_comp, scale = scale,
tol = tol, max_iter = miter, copy = True)
pls1.fit(Xorig, Yorig)
Yhat1 = pls1.predict(Xorig)
SSYdiff1 = np.sum((Yorig-Yhat1)**2)
# print "PLSRegression: R2Yhat = %.4f" % (1 - (SSYdiff1 / SSY))
# Compare PLSR and sklearn.PLSRegression
pls3 = PLSR(num_comp = num_comp, center = True, scale = scale,
tolerance = tol, max_iter = miter)
pls3.fit(X, Y)
Yhat3 = pls3.predict(X)
assert_array_almost_equal(Yhat1, Yhat3, decimal = 5,
err_msg = "PLSR gives wrong prediction")
SSYdiff3 = np.sum((Yorig-Yhat3)**2)
# print "PLSR : R2Yhat = %.4f" % (1 - (SSYdiff3 / SSY))
assert abs(SSYdiff1 - SSYdiff3) < 0.00005
pls2 = PLSCanonical(n_components = num_comp, scale = scale,
tol = tol, max_iter = miter, copy = True)
pls2.fit(Xorig, Yorig)
Yhat2 = pls2.predict(Xorig)
SSYdiff2 = np.sum((Yorig-Yhat2)**2)
# print "PLSCanonical : R2Yhat = %.4f" % (1 - (SSYdiff2 / SSY))
# Compare PLSC and sklearn.PLSCanonical
pls4 = PLSC(num_comp = num_comp, center = True, scale = scale,
tolerance = tol, max_iter = miter)
pls4.fit(X, Y)
Yhat4 = pls4.predict(X)
SSYdiff4 = np.sum((Yorig-Yhat4)**2)
# print "PLSC : R2Yhat = %.4f" % (1 - (SSYdiff4 / SSY))
# Compare O2PLS and sklearn.PLSCanonical
pls5 = O2PLS(num_comp = [num_comp, 1, 0], center = True, scale = scale,
tolerance = tol, max_iter = miter)
pls5.fit(X, Y)
Yhat5 = pls5.predict(X)
SSYdiff5 = np.sum((Yorig-Yhat5)**2)
# print "O2PLS : R2Yhat = %.4f" % (1 - (SSYdiff5 / SSY))
assert abs(SSYdiff2 - SSYdiff4) < 0.00005
assert SSYdiff2 > SSYdiff5
def pls(coords, intens): print PLSRegression().fit(coords, intens)
disa = l['disa']
exa = l['exa']
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..."
def dict2mean(X, dict):
plsca = PLSRegression(n_components=np.shape(dict['coefs'])[0])
plsca.x_mean_ = dict['x_mean']
plsca.y_mean_ = dict['y_mean']
plsca.coefs = dict['coefs']
return plsca.predict(X)
reader.next()
data =np.array(filter(lambda row: '' not in row and 'NA' not in row and '?' not in row,
[[convert(row[i]) for i in good_cols] for row in reader if 'evd' in row])).astype(float)
data = data[~np.isnan(data).any(axis=1)]
loc = data[:,9]
tumor = data[:,4]
#data = (data- data.min(axis=0))/(data.max(axis=0)-data.min(axis=0))
y = data[:,7]
x = np.delete(data,7,1)
x = (x-x.min(axis=0))/(x.max(axis=0)-x.min(axis=0))
print x.shape
pls1 = PLSRegression(n_components = x.shape[1])
pls1.fit(x,y)
cfs = np.nan_to_num(np.log(pls1.coefs))
fig, (coeffs,dist) = plt.subplots(nrows=1,ncols=2)
coeffs.barh(range(len(cfs)),cfs, edgecolor='k',
color = ['r' if x<0 else 'g' for x in cfs],
linewidth=1)
artist.adjust_spines(coeffs)
coeffs.axvline(x=0,color='k',linestyle='--',linewidth=2)
coeffs.axvline(x=-5.3,color='r',linestyle='--',linewidth=1)
coeffs.axvline(x=5.3,color='r',linestyle='--',linewidth=1)
coeffs.set_xlabel(r'\Large \textbf{Importance} $\left(\log \beta\right)$')
coeffs.set_yticks(range(len(labels)))