def test_knn_memory():
if not have_flann:
raise SkipTest("No flann, so skipping knn tests.")
dim = 3
n = 20
np.random.seed(47)
bags = Features([np.random.randn(np.random.randint(30, 100), dim)
for _ in xrange(n)])
tdir = tempfile.mkdtemp()
div_funcs = ('kl', 'js', 'renyi:.9', 'l2', 'tsallis:.8')
Ks = (3, 4)
est = KNNDivergenceEstimator(div_funcs=div_funcs, Ks=Ks, memory=tdir)
res1 = est.fit_transform(bags)
with LogCapture('skl_groups.divergences.knn', level=logging.INFO) as l:
res2 = est.transform(bags)
assert len(l.records) == 0
assert np.all(res1 == res2)
with LogCapture('skl_groups.divergences.knn', level=logging.INFO) as l:
res3 = est.fit_transform(bags)
for r in l.records:
assert not r.message.startswith("Getting divergences")
assert np.all(res1 == res3)
def test_knn_memory():
if not have_flann:
raise SkipTest("No flann, so skipping knn tests.")
dim = 3
n = 20
np.random.seed(47)
bags = Features(
[np.random.randn(np.random.randint(30, 100), dim) for _ in xrange(n)])
tdir = tempfile.mkdtemp()
div_funcs = ('kl', 'js', 'renyi:.9', 'l2', 'tsallis:.8')
Ks = (3, 4)
est = KNNDivergenceEstimator(div_funcs=div_funcs, Ks=Ks, memory=tdir)
res1 = est.fit_transform(bags)
with LogCapture('skl_groups.divergences.knn', level=logging.INFO) as l:
res2 = est.transform(bags)
assert len(l.records) == 0
assert np.all(res1 == res2)
with LogCapture('skl_groups.divergences.knn', level=logging.INFO) as l:
res3 = est.fit_transform(bags)
for r in l.records:
assert not r.message.startswith("Getting divergences")
assert np.all(res1 == res3)
def test_knn_kl():
if not have_flann:
raise SkipTest("No flann, so skipping knn tests.")
# verified by hand
# Dhat(P||Q) = \log m/(n-1) + d / n \sum_{i=1}^n \log \nu_k(i)/rho_k(i)
x = np.reshape([0., 1, 3], (3, 1))
y = np.reshape([.2, 1.2, 3.2, 7.2], (4, 1))
n = x.shape[0]
m = y.shape[0]
x_to_y = np.log(
m /
(n - 1)) + 1 / n * (np.log(1.2 / 3) + np.log(.8 / 2) + np.log(1.8 / 3))
y_to_x = np.log(n / (m - 1)) + 1 / m * (np.log(.8 / 3) + np.log(1.2 / 2) +
np.log(2.2 / 3) + np.log(6.2 / 6))
msg = "got {}, expected {}"
est = KNNDivergenceEstimator(div_funcs=['kl'], Ks=[2], clamp=False)
res = est.fit_transform([x, y]).squeeze()
assert res[0, 0] == 0
assert res[1, 1] == 0
assert np.allclose(res[0, 1], x_to_y), msg.format(res[0, 1], x_to_y)
assert np.allclose(res[1, 0], y_to_x), msg.format(res[1, 0], y_to_x)
def divergence_gen(gen, gt_db, batch=1000, metric='kl', normalize=False,
n_bins=100, whitening=True, classes=None, **kwargs):
"""
Given a generator and the gt function (the one generator
tries to approximate), we measure the discrepancy of the
generated from the gt signals.
"""
# # generate some samples.
batch = gt_db.shape[0]
if classes is None:
gen_samples = gen_images(gen, n=batch, batchsize=batch)
else:
# # conditional case.
gen_csamples, n_ms = [], int(batch // len(classes) + 10)
for cl in classes:
x = gen_images_with_condition(gen, n=n_ms, c=cl, batchsize=n_ms)
gen_csamples.append(x)
gen_csamples = np.concatenate(gen_csamples, 0)
gen_samples = gen_csamples[:gt_db.shape[0]]
if len(gt_db.shape) != 2:
gt_db = gt_db.reshape((batch, -1))
if len(gen_samples.shape) != 2:
gen_samples = gen_samples.reshape((batch, -1))
if gen_samples.dtype == np.uint8:
gen_samples = gen_samples.astype(np.float32)
if normalize:
# # Given that gen_images have a range [0, 255], normalize
# # the images in the [-1, 1] range for the KNN.
gen_samples1 = gen_samples / 127.5 - 1
else:
gen_samples1 = gen_samples
if metric == 'ndb':
global ndb
if ndb is None:
ndb = NDB(training_data=gt_db, number_of_bins=n_bins, whitening=whitening)
metric_val = ndb.evaluate(gen_samples)
chainer.reporter.report({'ndb': metric_val['NDB']})
chainer.reporter.report({'JS': metric_val['JS']})
diver = metric_val['NDB']
else:
# # define an estimator (e.g. KL divergence).
est = KNNDivergenceEstimator(div_funcs=[metric], Ks=[3], clamp=False)
# # fit and return the result.
res_diver = est.fit_transform([gt_db, gen_samples])
try:
diver = res_diver[0, 1]
except:
diver = res_diver[0][0][0, 1]
chainer.reporter.report({'kl': diver})
return diver
def kNNdiv_Kernel(X_white,
kernel,
Knn=3,
div_func='renyi:.5',
Nref=None,
compwise=True,
njobs=1,
W_ica_inv=None):
''' `div_func` kNN divergence estimate between some data X_white and a distribution specified by Kernel.
'''
if isinstance(Knn, int):
Knns = [Knn]
elif isinstance(Knn, list):
Knns = Knn
# if component wise there should be X_white.shape[1]
# kernels for each componenets
if compwise:
if X_white.shape[1] != len(kernel): raise ValueError
# construct reference "bag"
if compwise:
ref_dist = np.zeros((Nref, X_white.shape[1]))
for icomp in range(X_white.shape[1]):
samp = kernel[icomp].sample(Nref)
if isinstance(samp, tuple):
ref_dist[:, icomp] = samp[0].flatten()
else:
ref_dist[:, icomp] = samp.flatten()
else:
samp = kernel.sample(Nref)
if isinstance(samp, tuple):
ref_dist = samp[0]
else:
ref_dist = samp
if W_ica_inv is not None:
ref_dist = np.dot(ref_dist, W_ica_inv.T)
# estimate divergence
kNN = KNNDivergenceEstimator(div_funcs=[div_func],
Ks=Knns,
version='slow',
clamp=False,
n_jobs=njobs)
feat = Features([X_white, ref_dist])
div_knn = kNN.fit_transform(feat)
if len(Knns) == 1:
return div_knn[0][0][0][1]
div_knns = np.zeros(len(Knns))
for i in range(len(Knns)):
div_knns[i] = div_knn[0][i][0][1]
return div_knns
def test_knn_js():
if not have_flann:
raise SkipTest("No flann, so skipping knn tests.")
# verified by hand
x = np.reshape([0., 1, 3, 6], (4, 1))
n = 4
y = np.reshape([.2, 1.2, 3.2, 6.2, 10.2], (5, 1))
m = 5
M = 2
right_js = (
np.log(n + m - 1) + psi(M)
+ 1/(2*n) * ( # x weight is 1/7, y weight is 4/35, quantile 1/4
np.log(.2) - psi(1) # 0 => .2(y), 1(x)
+ np.log(.8) - psi(2) # 1 => 1.2(y), .2(y)
+ np.log(1.8) - psi(2) # 3 => 3.2(y), 1.2(y)
+ np.log(2.8) - psi(2) # 6 => 6.2(y), 3.2(y)
)
+ 1/(2*m) * ( # x weight is 5/36, y weight is 1/9, quantile 1/4
np.log(.2) - psi(1) # .2 => 0(x)
+ np.log(1) - psi(2) # 1.2 => 1(x), .2(y)
+ np.log(2) - psi(2) # 3.2 => 3(x), 1.2(y)
+ np.log(3) - psi(2) # 6.2 => 6(x), 3.2(y)
+ np.log(4.2) - psi(2) # 10.2 => 6.2(y), 6(x)
)
- 1/2 * np.log(n-1) - 1/(2*n) * (
np.log(3) + np.log(2) + np.log(3) + np.log(5))
- 1/2 * np.log(m-1) - 1/(2*m) * (
np.log(3) + np.log(2) + np.log(3) + np.log(4) + np.log(7))
)
msg = "got {}, expected {}"
est = KNNDivergenceEstimator(div_funcs=['js'], Ks=[2], clamp=False)
res = est.fit([x]).transform([y])
assert res.shape == (1, 1, 1, 1)
res = res[0, 0, 0, 0]
assert np.allclose(res, right_js, atol=1e-6), msg.format(res, right_js)
def distribution_divergence(X_s, X_l, k=10):
"""
This function computes l2 and js divergences from samples of two distributions.
The implementation use `skl-groups`, which implements non-parametric estimation
of divergences.
Args:
+ X_s: a numpy array containing point cloud in state space
+ X_e: a numpy array containing point cloud in latent space
"""
# We discard cases with too large dimensions
if X_s.shape[1] > 50:
return {'l2_divergence': -1., 'js_divergence': -1.}
# We instantiate the divergence object
div = KNNDivergenceEstimator(div_funcs=['l2', 'js'],
Ks=[k],
n_jobs=4,
clamp=True)
# We turn both data to float32
X_s = X_s.astype(np.float32)
X_l = X_l.astype(np.float32)
# We generate Features
f_s = Features(X_s, n_pts=[X_s.shape[0]])
f_l = Features(X_l, n_pts=[X_l.shape[0]])
# We create the knn graph
div.fit(X=f_s)
# We compute the divergences
l2, js = div.transform(X=f_l).squeeze()
# We construct the returned dictionnary
output = {'l2_divergence': l2, 'js_divergence': js}
return output
def kNNdiv_gauss(X_white,
cov_X,
Knn=3,
div_func='renyi:.5',
gauss=None,
Nref=None,
njobs=1):
''' `div_func` kNN divergence estimate between X_white and a
reference Gaussian with covariance matrix cov_X.
'''
if gauss is None:
if Nref is None:
raise ValueError
gauss = np.random.multivariate_normal(
np.zeros(X_white.shape[1]), cov_X,
size=Nref) # Gaussian reference distribution
if gauss.shape[1] != X_white.shape[1]:
raise ValueError(
'dimension between X_white and Gaussian reference distribution do not match'
)
if isinstance(Knn, int):
Knns = [Knn]
elif isinstance(Knn, list):
Knns = Knn
kNN = KNNDivergenceEstimator(div_funcs=[div_func],
Ks=Knns,
version='slow',
clamp=False,
n_jobs=njobs)
feat = Features([X_white, gauss])
div_knn = kNN.fit_transform(feat)
if len(Knns) == 1:
return div_knn[0][0][0][1]
div_knns = np.zeros(len(Knns))
for i in range(len(Knns)):
div_knns[i] = div_knn[0][i][0][1]
return div_knns
def test_knn_js():
if not have_flann:
raise SkipTest("No flann, so skipping knn tests.")
# verified by hand
x = np.reshape([0., 1, 3, 6], (4, 1))
n = 4
y = np.reshape([.2, 1.2, 3.2, 6.2, 10.2], (5, 1))
m = 5
M = 2
right_js = (
np.log(n + m - 1) + psi(M) + 1 / (2 * n) *
( # x weight is 1/7, y weight is 4/35, quantile 1/4
np.log(.2) - psi(1) # 0 => .2(y), 1(x)
+ np.log(.8) - psi(2) # 1 => 1.2(y), .2(y)
+ np.log(1.8) - psi(2) # 3 => 3.2(y), 1.2(y)
+ np.log(2.8) - psi(2) # 6 => 6.2(y), 3.2(y)
) + 1 / (2 * m) * ( # x weight is 5/36, y weight is 1/9, quantile 1/4
np.log(.2) - psi(1) # .2 => 0(x)
+ np.log(1) - psi(2) # 1.2 => 1(x), .2(y)
+ np.log(2) - psi(2) # 3.2 => 3(x), 1.2(y)
+ np.log(3) - psi(2) # 6.2 => 6(x), 3.2(y)
+ np.log(4.2) - psi(2) # 10.2 => 6.2(y), 6(x)
) - 1 / 2 * np.log(n - 1) - 1 / (2 * n) *
(np.log(3) + np.log(2) + np.log(3) + np.log(5)) -
1 / 2 * np.log(m - 1) - 1 / (2 * m) *
(np.log(3) + np.log(2) + np.log(3) + np.log(4) + np.log(7)))
msg = "got {}, expected {}"
est = KNNDivergenceEstimator(div_funcs=['js'], Ks=[2], clamp=False)
res = est.fit([x]).transform([y])
assert res.shape == (1, 1, 1, 1)
res = res[0, 0, 0, 0]
assert np.allclose(res, right_js, atol=1e-6), msg.format(res, right_js)
def test_knn_kl():
if not have_flann:
raise SkipTest("No flann, so skipping knn tests.")
# verified by hand
# Dhat(P||Q) = \log m/(n-1) + d / n \sum_{i=1}^n \log \nu_k(i)/rho_k(i)
x = np.reshape([0., 1, 3], (3, 1))
y = np.reshape([.2, 1.2, 3.2, 7.2], (4, 1))
n = x.shape[0]
m = y.shape[0]
x_to_y = np.log(m / (n-1)) + 1/n * (
np.log(1.2 / 3) + np.log(.8 / 2) + np.log(1.8 / 3))
y_to_x = np.log(n / (m-1)) + 1/m * (
np.log(.8 / 3) + np.log(1.2 / 2) + np.log(2.2 / 3) + np.log(6.2 / 6))
msg = "got {}, expected {}"
est = KNNDivergenceEstimator(div_funcs=['kl'], Ks=[2], clamp=False)
res = est.fit_transform([x, y]).squeeze()
assert res[0, 0] == 0
assert res[1, 1] == 0
assert np.allclose(res[0, 1], x_to_y), msg.format(res[0, 1], x_to_y)
assert np.allclose(res[1, 0], y_to_x), msg.format(res[1, 0], y_to_x)
def test_knn_sanity_slow():
if not have_flann:
raise SkipTest("No flann, so skipping knn tests.")
dim = 3
n = 20
np.random.seed(47)
bags = Features(
[np.random.randn(np.random.randint(30, 100), dim) for _ in xrange(n)])
# just make sure it runs
div_funcs = ('kl', 'js', 'renyi:.9', 'l2', 'tsallis:.8')
Ks = (3, 4)
est = KNNDivergenceEstimator(div_funcs=div_funcs, Ks=Ks)
res = est.fit_transform(bags)
assert res.shape == (len(div_funcs), len(Ks), n, n)
assert np.all(np.isfinite(res))
# test that JS blows up when there's a huge difference in bag sizes
# (so that K is too low)
assert_raises(
ValueError,
partial(est.fit_transform, bags + [np.random.randn(1000, dim)]))
# test fit() and then transform() with JS, with different-sized test bags
est = KNNDivergenceEstimator(div_funcs=('js', ), Ks=(5, ))
est.fit(bags, get_rhos=True)
with LogCapture('skl_groups.divergences.knn', level=logging.WARNING) as l:
res = est.transform([np.random.randn(300, dim)])
assert res.shape == (1, 1, 1, len(bags))
assert len(l.records) == 1
assert l.records[0].message.startswith('Y_rhos had a lower max_K')
# test that passing div func more than once raises
def blah(df):
est = KNNDivergenceEstimator(div_funcs=[df, df])
return est.fit(bags)
assert_raises(ValueError, lambda: blah('kl'))
assert_raises(ValueError, lambda: blah('renyi:.8'))
assert_raises(ValueError, lambda: blah('l2'))
def kNNdiv_general(
X,
Y,
Knn=3,
div_func='kl',
alpha=None,
njobs=1,
): #renyi:.5
"""
kNN divergence estimate for samples drawn from any two arbitrary distributions.
"""
if Y.shape[1] != X.shape[1]:
raise ValueError(
'dimension between X_white and Gaussian reference distribution do not match'
)
if isinstance(Knn, int):
Knns = [Knn]
elif isinstance(Knn, list):
Knns = Knn
if alpha is not None:
div_func = div_func + ':%s' % alpha
kNN = KNNDivergenceEstimator(div_funcs=[div_func],
Ks=Knns,
version='slow',
clamp=False,
n_jobs=njobs)
feat = Features([X, Y])
div_knn = kNN.fit_transform(feat)
if len(Knns) == 1:
return div_knn[0][0][0][1]
div_knns = np.zeros(len(Knns))
for i in range(len(Knns)):
div_knns[i] = div_knn[0][i][0][1]
return div_knns
def computePairwiseSimilarities2(patients, y):
"""
Compute the pairwise similarity between bags using Dougal code
Inputs:
- patients: the collection of patient features
- y: labels (number of abnormal nodes) for each patient. Used to fit the
KNNDivergenceEstimator
Returns:
- sims: the pairwise similarities between each patient
* Note: sims is a NxN symmetric matrix, where N is the number of patients
"""
# pass the features and labels to scikit-learn Features
feats = Features(patients, labels=y) # directly from Dougal
# note: learning methods won't use the labels, this is for conveinence
# estimate the distances between the bags (patients) using KNNDivergenceEstimator
# details: use the kl divergence, find 3 nearest neighbors
# not sure what the pairwise picker line does?
# rbf and projectPSD help ensure the data is separable?
distEstModel = Pipeline(
[ # div_funcs=['kl'], rewrite this to actually use PairwisePicker correctly next time
('divs',
KNNDivergenceEstimator(div_funcs=['kl'],
Ks=[3],
n_jobs=-1,
version='fast')),
('pick', PairwisePicker((0, 0))), ('symmetrize', Symmetrize()),
('rbf', RBFize(gamma=1, scale_by_median=True)),
('project', ProjectPSD())
])
# return the pairwise similarities between the bags (patients)
sims = distEstModel.fit_transform(feats)
return sims
def test_knn_sanity_slow():
if not have_flann:
raise SkipTest("No flann, so skipping knn tests.")
dim = 3
n = 20
np.random.seed(47)
bags = Features([np.random.randn(np.random.randint(30, 100), dim)
for _ in xrange(n)])
# just make sure it runs
div_funcs = ('kl', 'js', 'renyi:.9', 'l2', 'tsallis:.8')
Ks = (3, 4)
est = KNNDivergenceEstimator(div_funcs=div_funcs, Ks=Ks)
res = est.fit_transform(bags)
assert res.shape == (len(div_funcs), len(Ks), n, n)
assert np.all(np.isfinite(res))
# test that JS blows up when there's a huge difference in bag sizes
# (so that K is too low)
assert_raises(
ValueError,
partial(est.fit_transform, bags + [np.random.randn(1000, dim)]))
# test fit() and then transform() with JS, with different-sized test bags
est = KNNDivergenceEstimator(div_funcs=('js',), Ks=(5,))
est.fit(bags, get_rhos=True)
with LogCapture('skl_groups.divergences.knn', level=logging.WARNING) as l:
res = est.transform([np.random.randn(300, dim)])
assert res.shape == (1, 1, 1, len(bags))
assert len(l.records) == 1
assert l.records[0].message.startswith('Y_rhos had a lower max_K')
# test that passing div func more than once raises
def blah(df):
est = KNNDivergenceEstimator(div_funcs=[df, df])
return est.fit(bags)
assert_raises(ValueError, lambda: blah('kl'))
assert_raises(ValueError, lambda: blah('renyi:.8'))
assert_raises(ValueError, lambda: blah('l2'))
def blah(df):
est = KNNDivergenceEstimator(div_funcs=[df, df])
return est.fit(bags)
def computeSubjSubjKernel(subjects, div='KL', numNeighbors=3):
"""
Start by computing the pairwise similarities between subject
using Dougal's code. Then, for HE and KL, symmetrize, RBFize,
and project the similarities onto a positive semi-definite space.
Inputs:
- subjects: the collection of patient features
- div: which divergence to use. Options are
- 'KL': Kullback-Leibler divergence, 'kl' in the function (default)
- 'HE': Hellinger divergence, 'hellinger' in the function
- 'MMD': Maximum Mean Discrepancy, calls another function
- numNeighbors: how many neighbors to look at. Default is 3
Returns:
- kernel: the kernel calculated using the pairwise similarities between each subject
* Note: kernel is a NxN symmetric matrix, where N is the number of subjects
"""
# pass the features and labels to scikit-learn Features
feats = Features(subjects) # directly from Dougal
# specify the divergence to use
if div == 'KL':
# estimate the distances between the bags (patients) using KNNDivergenceEstimator
# details: use the kl divergence, find 3 nearest neighbors
# not sure what the pairwise picker line does?
# rbf and projectPSD help ensure the data is separable?
distEstModel = Pipeline(
[ # div_funcs=['kl'], rewrite this to actually use PairwisePicker correctly next time
('divs',
KNNDivergenceEstimator(div_funcs=['kl'],
Ks=[numNeighbors],
n_jobs=-1,
version='fast')),
('pick', PairwisePicker((0, 0))), ('symmetrize', Symmetrize())
# ('rbf', RBFize(gamma=1, scale_by_median=True)),
# ('project', ProjectPSD())
])
# return the pairwise similarities between the bags (patients)
sims = distEstModel.fit_transform(feats)
# Great, we have the similarities and they're symmetric
# Now RBFize them, but do the scale by median by hand
rbf = RBFize(gamma=1, scale_by_median=False)
simsMedian = np.median(sims[np.triu_indices_from(sims)])
medianScaledSims = sims / simsMedian
rbfedSims = rbf.fit_transform(medianScaledSims)
# Final step in building the kernel: project the rbf'ed similarities
# onto a positive semi-definite space
psd = ProjectPSD()
kernel = psd.fit_transform(rbfedSims)
elif div == 'HE':
# estimate the distances between the bags (patients) using KNNDivergenceEstimator
# details: use the hellinger divergence, find 3 nearest neighbors
# not sure what the pairwise picker line does?
# rbf and projectPSD help ensure the data is separable?
distEstModel = Pipeline(
[ # div_funcs=['kl'], rewrite this to actually use PairwisePicker correctly next time
('divs',
KNNDivergenceEstimator(div_funcs=['hellinger'],
Ks=[numNeighbors],
n_jobs=-1,
version='fast')),
('pick', PairwisePicker((0, 0))), ('symmetrize', Symmetrize())
# ('rbf', RBFize(gamma=1, scale_by_median=True)),
# ('project', ProjectPSD())
])
# return the pairwise similarities between the bags (patients)
sims = distEstModel.fit_transform(feats)
# Great, we have the similarities and they're symmetric
# Now RBFize them, but do the scale by median by hand
rbf = RBFize(gamma=1, scale_by_median=False)
simsMedian = np.median(sims[np.triu_indices_from(sims)])
# medianScaledSims = sims/simsMedian
# rbfedSims = rbf.fit_transform(medianScaledSims)
rbfedSims = rbf.fit_transform(sims)
# Final step in building the kernel: project the rbf'ed similarities
# onto a positive semi-definite space
psd = ProjectPSD()
kernel = psd.fit_transform(rbfedSims)
elif div == 'MMD':
# start by getting the median pairwise squared distance between subject,
# used as a heuristic for choosing the bandwidth of the inner RBF kernel
subset = np.vstack(feats)
subset = subset[np.random.choice(subset.shape[0],
min(2000, subset.shape[0]),
replace=False)]
subsetSquaredDists = euclidean_distances(subset, squared=True)
featsMedianSquaredDist = np.median(
subsetSquaredDists[np.triu_indices_from(subsetSquaredDists,
k=numNeighbors)],
overwrite_input=True)
# now we need to determine gamma (scaling factor, inverse of sigma)
# This was initially done in the library, but Kayhan believes there's
# a multiplication instead of a division, so it's being done by hand
firstGamma = 1 / featsMedianSquaredDist
# calculate the mmds
mmds, mmkDiagonals = mmd.rbf_mmd(feats,
gammas=firstGamma,
squared=True,
ret_X_diag=True)
# now let's turn the squared MMD distances into a kernel
# symmetrize it
sym = Symmetrize()
mmds = sym.fit_transform(mmds)
# get the median squared MMD distance
mmdMedianSquaredDist = np.median(mmds[np.triu_indices_from(
mmds, k=numNeighbors)])
kernel = np.exp(np.multiply(mmds, -1 / mmdMedianSquaredDist))
else:
print("Error: divergence entered is not valid.")
return -1
return kernel
def train_KNNDivergence(divergence, X_tr, y_tr, X_ts, y_ts, k=5, C=1, name=''):
from skl_groups.divergences import KNNDivergenceEstimator
from skl_groups.kernels import PairwisePicker, Symmetrize, RBFize, ProjectPSD
"""
Parameters
----------
divergence: string,
Type of divergence to use when estimating distance among distribution.
Options 'kl','renyi:.8','tsallis:.8','hellinger','bc','l2','linear', 'jensen-shannon'.
X_tr: array-like
Training data
y_tr: array-like
Training output
X_ts: array-like
Test data
y_ts: array-like
Test output
k: int, optional default=5
Number of k-nearest niehgbours to use for the estimation of the distances.
C: float, optional default=1
Regularization parameter for SVM.
"""
warnings.simplefilter('ignore')
pipeline = [
('divs', KNNDivergenceEstimator(div_funcs=[divergence], Ks=[k])),
('pick', PairwisePicker((0, 0))),
('symmetrize', Symmetrize()),
('rbf', RBFize(gamma=1, scale_by_median=True)),
('project', ProjectPSD()),
]
classification = isinstance(y_tr[0][0], str) or isinstance(
y_tr[0][0], bool) or isinstance(y_tr[0][0], np.bool_)
if classification:
pipeline.append(('svm', SVC(C=C, kernel='precomputed')), )
else:
pipeline.append(('svm', SVR(C=C, kernel='precomputed')), )
model = Pipeline(pipeline)
X_tr = [x for x in X_tr]
y_tr = [y for y in y_tr]
X_ts = [x for x in X_ts]
y_ts = [y for y in y_ts]
# X_tr = list(X_tr)
# y_tr - list(y_tr)
# X_ts = list(X_ts)
# y_ts = list(y_ts)
model.fit(X_tr, y_tr)
preds = model.predict(X_ts)
pd.DataFrame.from_dict({
'preds': preds,
'labels': np.array(y_ts).flatten()
}).to_csv(name + '.csv')
if classification:
train_score = accuracy_score(
np.array(y_tr).flatten(), model.predict(X_tr))
test_score = accuracy_score(np.array(y_ts).flatten(), preds)
else:
train_score = mean_squared_error(y_tr, model.predict(X_tr))
test_score = mean_squared_error(y_ts, model.predict(X_ts))
# wandb.log({'train_mse': train_score, 'test_mse': test_score})
#print(train_score, test_score)
return train_score, test_score
def blah(df):
est = KNNDivergenceEstimator(div_funcs=[df, df])
return est.fit(bags)
