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 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 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))
def pls(coords, intens): print PLSRegression().fit(coords, intens)
