def test_get_stats_2_components():
np.random.seed(12)
X = X = np.random.rand(100,3)
Y = np.random.rand(100,4)
past_stats = {'r': np.array([0.22441608, 0.19056307]),
'Wilks': np.array([0.91515202, 0.96368572]),
'df1': np.array([12, 6]),
'df2': np.array([246.34637455, 188]),
'F': np.array([0.69962605, 0.58490315]),
'pF': np.array([0.75134965, 0.74212361]),
'chisq': np.array([8.42318331, 4.2115406 ]),
'pChisq': np.array([0.75124771, 0.64807349])
}
kcca2 = KCCA(n_components=2)
kcca2.fit_transform([X,Y])
stats = kcca2.get_stats()
nondegen = np.argwhere(stats['r'] < 1 - 2 * np.finfo(float).eps).squeeze()
assert np.array_equal(nondegen, np.array([0, 1]))
for key in stats:
assert np.allclose(stats[key], past_stats[key], rtol=1e-3, atol=1e-4)
def test_get_stats_1_component():
np.random.seed(12)
X = X = np.random.rand(100,3)
Y = np.random.rand(100,4)
past_stats = {'r': np.array([0.22441608326082138]),
'Wilks': np.array([0.94963742]),
'df1': np.array([12]),
'df2': np.array([246.34637455]),
'F': np.array([0.40489714]),
'pF': np.array([0.96096493]),
'chisq': np.array([4.90912773]),
'pChisq': np.array([0.9609454])
}
kcca1 = KCCA(n_components=1)
kcca1.fit_transform([X,Y])
stats = kcca1.get_stats()
assert not stats['r'] == 1
assert not stats['r'] + 2 * np.finfo(float).eps >= 1
for key in stats:
assert np.allclose(stats[key], past_stats[key], rtol=1e-3, atol=1e-4)
def test_ktype_polynomial():
kpoly = KCCA(ktype='poly', reg=0.0001, n_components=2, degree=3)
kpoly.fit_transform([train1, train2])
assert len(kpoly.components_) == 2
def test_ktype_gaussian():
kgauss = KCCA(ktype='gaussian', reg=0.0001, n_components=2, sigma=2.0)
kgauss.fit_transform([train1, train2])
assert len(kgauss.components_) == 2
data2 = 0.25 * indep2 + 0.75 * np.vstack(
(latvar1, latvar2, latvar1, latvar2, latvar1)).T
# Split each dataset into a training set and test set (10% of dataset is training data)
train1 = data1[:int(nSamples / 10)]
train2 = data2[:int(nSamples / 10)]
test1 = data1[int(nSamples / 10):]
test2 = data2[int(nSamples / 10):]
n_components = 4
# Initialize a linear kCCA class
kcca_l = KCCA(ktype="linear", reg=0.001, n_components=n_components)
# Use the methods to find a kCCA mapping and transform the views of data
kcca_ft = kcca_l.fit_transform([train1, train2])
kcca_f = kcca_l.fit([train1, train2])
kcca_t = kcca_l.transform([train1, train2])
# Test that cancorrs_ is equal to n_components
def test_numCC_cancorrs_():
assert len(kcca_ft.cancorrs_) == n_components
# Test that number of views is equal to number of ws_
def test_numCC_ws_():
assert len(kcca_ft.weights_) == 2
# Test that number of views is equal to number of comps_
def test_icd_mrank():
kcca_g_icd = KCCA(ktype ="gaussian", sigma = 1.0, n_components = 2, reg = 0.01, decomp = 'icd', mrank = 2)
icd = kcca_g_icd.fit_transform([x, y])
assert (len(icd) == 2)
(gr2, _) = stats.pearsonr(gausskcca[0][:, 1], gausskcca[1][:, 1])
print("Below are the canonical correlation of the two components:")
print(gr1, gr2)
###############################################################################
# ICD Decomposition
# ^^^^^^^^^^^^^^^^^
kcca_g_icd = KCCA(ktype="gaussian",
sigma=1.0,
n_components=2,
reg=0.01,
decomp='icd',
mrank=50)
icd_g = kcca_g_icd.fit_transform(Xsg)
crossviews_plot(icd_g, ax_ticks=False, ax_labels=True, equal_axes=True)
(icdr1, _) = stats.pearsonr(icd_g[0][:, 0], icd_g[1][:, 0])
(icdr2, _) = stats.pearsonr(icd_g[0][:, 1], icd_g[1][:, 1])
print("Below are the canonical correlation of the two components:")
print(icdr1, icdr2)
# The canonical correlations of full vs ICD (mrank=50) are very similar!
###############################################################################
# ICD Kernel Rank vs. Canonical Correlation
# -----------------------------------------
