def check_results(kernel, bandwidth, atol, rtol, X, Y, dens_true):
kde = KernelDensity(kernel=kernel,
bandwidth=bandwidth,
atol=atol,
rtol=rtol)
log_dens = kde.fit(X).score_samples(Y)
assert_allclose(np.exp(log_dens),
dens_true,
atol=atol,
rtol=max(1E-7, rtol))
assert_allclose(np.exp(kde.score(Y)),
np.prod(dens_true),
atol=atol,
rtol=max(1E-7, rtol))
def test_kernel_density_sampling(n_samples=100, n_features=3):
rng = np.random.RandomState(0)
X = rng.randn(n_samples, n_features)
bandwidth = 0.2
for kernel in ['gaussian', 'tophat']:
# draw a tophat sample
kde = KernelDensity(bandwidth, kernel=kernel).fit(X)
samp = kde.sample(100)
assert X.shape == samp.shape
# check that samples are in the right range
nbrs = NearestNeighbors(n_neighbors=1).fit(X)
dist, ind = nbrs.kneighbors(X, return_distance=True)
if kernel == 'tophat':
assert np.all(dist < bandwidth)
elif kernel == 'gaussian':
# 5 standard deviations is safe for 100 samples, but there's a
# very small chance this test could fail.
assert np.all(dist < 5 * bandwidth)
# check unsupported kernels
for kernel in ['epanechnikov', 'exponential', 'linear', 'cosine']:
kde = KernelDensity(bandwidth, kernel=kernel).fit(X)
assert_raises(NotImplementedError, kde.sample, 100)
# non-regression test: used to return a scalar
X = rng.randn(4, 1)
kde = KernelDensity(kernel="gaussian").fit(X)
assert kde.sample().shape == (1, 1)
def test_kde_algorithm_metric_choice(algorithm, metric):
# Smoke test for various metrics and algorithms
rng = np.random.RandomState(0)
X = rng.randn(10, 2) # 2 features required for haversine dist.
Y = rng.randn(10, 2)
if algorithm == 'kd_tree' and metric not in KDTree.valid_metrics:
assert_raises(ValueError,
KernelDensity,
algorithm=algorithm,
metric=metric)
else:
kde = KernelDensity(algorithm=algorithm, metric=metric)
kde.fit(X)
y_dens = kde.score_samples(Y)
assert y_dens.shape == Y.shape[:1]
def test_kde_pipeline_gridsearch():
# test that kde plays nice in pipelines and grid-searches
X, _ = make_blobs(cluster_std=.1,
random_state=1,
centers=[[0, 1], [1, 0], [0, 0]])
pipe1 = make_pipeline(StandardScaler(with_mean=False, with_std=False),
KernelDensity(kernel="gaussian"))
params = dict(kerneldensity__bandwidth=[0.001, 0.01, 0.1, 1, 10])
search = GridSearchCV(pipe1, param_grid=params)
search.fit(X)
assert search.best_params_['kerneldensity__bandwidth'] == .1
def test_kde_badargs():
assert_raises(ValueError, KernelDensity, algorithm='blah')
assert_raises(ValueError, KernelDensity, bandwidth=0)
assert_raises(ValueError, KernelDensity, kernel='blah')
assert_raises(ValueError, KernelDensity, metric='blah')
assert_raises(ValueError,
KernelDensity,
algorithm='kd_tree',
metric='blah')
kde = KernelDensity()
assert_raises(ValueError,
kde.fit,
np.random.random((200, 10)),
sample_weight=np.random.random((200, 10)))
assert_raises(ValueError,
kde.fit,
np.random.random((200, 10)),
sample_weight=-np.random.random(200))
def test_pickling(tmpdir, sample_weight):
# Make sure that predictions are the same before and after pickling. Used
# to be a bug because sample_weights wasn't pickled and the resulting tree
# would miss some info.
kde = KernelDensity()
data = np.reshape([1., 2., 3.], (-1, 1))
kde.fit(data, sample_weight=sample_weight)
X = np.reshape([1.1, 2.1], (-1, 1))
scores = kde.score_samples(X)
file_path = str(tmpdir.join('dump.pkl'))
joblib.dump(kde, file_path)
kde = joblib.load(file_path)
scores_pickled = kde.score_samples(X)
assert_allclose(scores, scores_pickled)
from mrex.datasets import load_digits
from mrex.neighbors import KernelDensity
from mrex.decomposition import PCA
from mrex.model_selection import GridSearchCV
# load the data
digits = load_digits()
# project the 64-dimensional data to a lower dimension
pca = PCA(n_components=15, whiten=False)
data = pca.fit_transform(digits.data)
# use grid search cross-validation to optimize the bandwidth
params = {'bandwidth': np.logspace(-1, 1, 20)}
grid = GridSearchCV(KernelDensity(), params)
grid.fit(data)
print("best bandwidth: {0}".format(grid.best_estimator_.bandwidth))
# use the best estimator to compute the kernel density estimate
kde = grid.best_estimator_
# sample 44 new points from the data
new_data = kde.sample(44, random_state=0)
new_data = pca.inverse_transform(new_data)
# turn data into a 4x11 grid
new_data = new_data.reshape((4, 11, -1))
real_data = digits.data[:44].reshape((4, 11, -1))
X_plot = np.linspace(-5, 10, 1000)[:, np.newaxis]
bins = np.linspace(-5, 10, 10)
fig, ax = plt.subplots(2, 2, sharex=True, sharey=True)
fig.subplots_adjust(hspace=0.05, wspace=0.05)
# histogram 1
ax[0, 0].hist(X[:, 0], bins=bins, fc='#AAAAFF', **density_param)
ax[0, 0].text(-3.5, 0.31, "Histogram")
# histogram 2
ax[0, 1].hist(X[:, 0], bins=bins + 0.75, fc='#AAAAFF', **density_param)
ax[0, 1].text(-3.5, 0.31, "Histogram, bins shifted")
# tophat KDE
kde = KernelDensity(kernel='tophat', bandwidth=0.75).fit(X)
log_dens = kde.score_samples(X_plot)
ax[1, 0].fill(X_plot[:, 0], np.exp(log_dens), fc='#AAAAFF')
ax[1, 0].text(-3.5, 0.31, "Tophat Kernel Density")
# Gaussian KDE
kde = KernelDensity(kernel='gaussian', bandwidth=0.75).fit(X)
log_dens = kde.score_samples(X_plot)
ax[1, 1].fill(X_plot[:, 0], np.exp(log_dens), fc='#AAAAFF')
ax[1, 1].text(-3.5, 0.31, "Gaussian Kernel Density")
for axi in ax.ravel():
axi.plot(X[:, 0], np.full(X.shape[0], -0.01), '+k')
axi.set_xlim(-4, 9)
axi.set_ylim(-0.02, 0.34)
xy = np.vstack([Y.ravel(), X.ravel()]).T
xy = xy[land_mask]
xy *= np.pi / 180.
# Plot map of South America with distributions of each species
fig = plt.figure()
fig.subplots_adjust(left=0.05, right=0.95, wspace=0.05)
for i in range(2):
plt.subplot(1, 2, i + 1)
# construct a kernel density estimate of the distribution
print(" - computing KDE in spherical coordinates")
kde = KernelDensity(bandwidth=0.04,
metric='haversine',
kernel='gaussian',
algorithm='ball_tree')
kde.fit(Xtrain[ytrain == i])
# evaluate only on the land: -9999 indicates ocean
Z = np.full(land_mask.shape[0], -9999, dtype='int')
Z[land_mask] = np.exp(kde.score_samples(xy))
Z = Z.reshape(X.shape)
# plot contours of the density
levels = np.linspace(0, Z.max(), 25)
plt.contourf(X, Y, Z, levels=levels, cmap=plt.cm.Reds)
if basemap:
print(" - plot coastlines using basemap")
m = Basemap(projection='cyl',
def test_kde_sample_weights():
n_samples = 400
size_test = 20
weights_neutral = np.full(n_samples, 3.)
for d in [1, 2, 10]:
rng = np.random.RandomState(0)
X = rng.rand(n_samples, d)
weights = 1 + (10 * X.sum(axis=1)).astype(np.int8)
X_repetitions = np.repeat(X, weights, axis=0)
n_samples_test = size_test // d
test_points = rng.rand(n_samples_test, d)
for algorithm in ['auto', 'ball_tree', 'kd_tree']:
for metric in ['euclidean', 'minkowski', 'manhattan', 'chebyshev']:
if algorithm != 'kd_tree' or metric in KDTree.valid_metrics:
kde = KernelDensity(algorithm=algorithm, metric=metric)
# Test that adding a constant sample weight has no effect
kde.fit(X, sample_weight=weights_neutral)
scores_const_weight = kde.score_samples(test_points)
sample_const_weight = kde.sample(random_state=1234)
kde.fit(X)
scores_no_weight = kde.score_samples(test_points)
sample_no_weight = kde.sample(random_state=1234)
assert_allclose(scores_const_weight, scores_no_weight)
assert_allclose(sample_const_weight, sample_no_weight)
# Test equivalence between sampling and (integer) weights
kde.fit(X, sample_weight=weights)
scores_weight = kde.score_samples(test_points)
sample_weight = kde.sample(random_state=1234)
kde.fit(X_repetitions)
scores_ref_sampling = kde.score_samples(test_points)
sample_ref_sampling = kde.sample(random_state=1234)
assert_allclose(scores_weight, scores_ref_sampling)
assert_allclose(sample_weight, sample_ref_sampling)
# Test that sample weights has a non-trivial effect
diff = np.max(np.abs(scores_no_weight - scores_weight))
assert diff > 0.001
# Test invariance with respect to arbitrary scaling
scale_factor = rng.rand()
kde.fit(X, sample_weight=(scale_factor * weights))
scores_scaled_weight = kde.score_samples(test_points)
assert_allclose(scores_scaled_weight, scores_weight)