def Kernel_density_estimate(data, var_name1, var_name2, time, z):
from sklearn.neighbors.kde import KernelDensity
''' Kerne Density Estimation:
from sklearn.neighbors import KernelDensity
Parameters:
- bandwidth: The bandwidth here acts as a smoothing parameter, controlling the tradeoff between bias and variance
in the result. A large bandwidth leads to a very smooth (i.e. high-bias) density distribution.
A small bandwidth leads to an unsmooth (i.e. high-variance) density distribution.
'metric': 'euclidean' (distance metric to use. Note that not all metrics are valid with all algorithms.)
'atol': 0 (The desired absolute tolerance of the result.)
'leaf_size': 40
'kernel': 'gaussian'
'rtol': 0 (The desired relative tolerance of the result. )
'breadth_first': True
'metric_params': None
'algorithm': 'auto'
'''
amp = 100
data_aux = np.ndarray(shape=((nx * ny), nvar))
data_aux[:, 0] = data[:, 0]
data_aux[:, 1] = data[:, 1] * amp
# 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])
# Plotting
n_sample = 100
x_ = np.linspace(np.amin(data[:, 0]), np.amax(data[:, 0]), n_sample)
y_ = np.linspace(np.amin(data[:, 1]), np.amax(data[:, 1]), n_sample)
X, Y = np.meshgrid(x_, y_)
XX = np.array([X.ravel(), Y.ravel()]).T
x_aux = np.linspace(np.amin(data_aux[:, 0]), np.amax(data_aux[:, 0]),
n_sample)
y_aux = np.linspace(np.amin(data_aux[:, 1]), np.amax(data_aux[:, 1]),
n_sample)
X_aux, Y_aux = np.meshgrid(x_aux, y_aux)
XX_aux = np.array([X_aux.ravel(), Y_aux.ravel()]).T
fig = plt.figure(figsize=(12, 16))
plt.subplot(3, 2, 1)
bw = 5e-2
kde = KernelDensity(kernel='gaussian', bandwidth=bw).fit(data_aux)
# kde.score_samples(data)
# Z = np.exp(kde.score_samples(XX_aux)).reshape(X.shape)
Z_log = kde.score_samples(XX_aux).reshape(X.shape)
plt.scatter(data_aux[:, 0], data_aux[:, 1], s=5, alpha=0.2)
ax1 = plt.contour(X_aux, Y_aux, Z_log)
plt.colorbar(ax1, shrink=0.8)
labeling(var_name1, var_name2, amp)
plt.title('bw = ' + str(bw))
plt.subplot(3, 2, 2)
bw = 3e-2
kde = KernelDensity(kernel='gaussian', bandwidth=bw).fit(data_aux)
# kde.score_samples(data)
# Z = np.exp(kde.score_samples(XX_aux)).reshape(X.shape)
Z_log = kde.score_samples(XX_aux).reshape(X.shape)
plt.scatter(data_aux[:, 0], data_aux[:, 1], s=5, alpha=0.2)
ax1 = plt.contour(X_aux, Y_aux, Z_log)
plt.colorbar(ax1, shrink=0.8)
labeling(var_name1, var_name2, amp)
plt.title('bw = ' + str(bw))
plt.subplot(3, 2, 3)
bw = 1e-2
kde = KernelDensity(kernel='gaussian', bandwidth=bw).fit(data_aux)
# kde.score_samples(data)
# Z = np.exp(kde.score_samples(XX_aux)).reshape(X.shape)
Z_log = kde.score_samples(XX_aux).reshape(X.shape)
plt.scatter(data_aux[:, 0], data_aux[:, 1], s=5, alpha=0.2)
ax1 = plt.contour(X_aux, Y_aux, Z_log)
plt.colorbar(ax1, shrink=0.8)
labeling(var_name1, var_name2, amp)
plt.title('bw = ' + str(bw))
plt.subplot(3, 2, 4)
bw = 8e-3
kde = KernelDensity(kernel='gaussian', bandwidth=bw).fit(data_aux)
# kde.score_samples(data)
# Z = np.exp(kde.score_samples(XX_aux)).reshape(X.shape)
Z_log = kde.score_samples(XX_aux).reshape(X.shape)
plt.scatter(data_aux[:, 0], data_aux[:, 1], s=5, alpha=0.2)
ax1 = plt.contour(X_aux, Y_aux, Z_log)
plt.colorbar(ax1, shrink=0.8)
labeling(var_name1, var_name2, amp)
plt.title('bw = ' + str(bw))
plt.subplot(3, 2, 5)
bw = 5e-3
kde = KernelDensity(kernel='gaussian', bandwidth=bw).fit(data_aux)
# kde.score_samples(data)
# Z = np.exp(kde.score_samples(XX_aux)).reshape(X.shape)
Z_log = kde.score_samples(XX_aux).reshape(X.shape)
plt.scatter(data_aux[:, 0], data_aux[:, 1], s=5, alpha=0.2)
ax1 = plt.contour(X_aux, Y_aux, Z_log)
plt.colorbar(ax1, shrink=0.8)
labeling(var_name1, var_name2, amp)
plt.title('bw = ' + str(bw))
plt.subplot(3, 2, 6)
bw = 2e-3
kde = KernelDensity(kernel='gaussian', bandwidth=bw).fit(data_aux)
# kde.score_samples(data)
# Z = np.exp(kde.score_samples(XX_aux)).reshape(X.shape)
Z_log = kde.score_samples(XX_aux).reshape(X.shape)
plt.scatter(data_aux[:, 0], data_aux[:, 1], s=5, alpha=0.2)
ax1 = plt.contour(X_aux, Y_aux, Z_log)
plt.colorbar(ax1, shrink=0.8)
labeling(var_name1, var_name2, amp)
plt.title('bw = ' + str(bw))
fig.suptitle('Cloud Closure: Kernel Density Estimate (gaussian)',
fontsize=20)
plt.savefig(
os.path.join(
fullpath_out, 'CloudClosure_alltimes_figures', 'CC_' + var_name1 +
'_' + var_name2 + '_z' + str(np.int(z)) + 'm_KDE_alltime.png'))
plt.close()
print('KDE shapes: ', kde.score_samples(XX).shape, X.shape)
print(kde.get_params())
return kde, kde
