def KLscore(
x,
z,
returnQlog=False,
qlog=None,
qlogExp=None): #x are samples (change), z is measure data (unchanged!)
tree_d = BallTree(x)
plog = tree_d.kernel_density(xy_grid,
h=.5,
kernel='gaussian',
return_log=True,
rtol=.1)
computeQlog = (qlog == None)
if computeQlog:
tree_m = BallTree(z)
qlog = tree_m.kernel_density(xy_grid,
h=1,
kernel='gaussian',
return_log=True)
qlogExp = np.exp(qlog)
delta_log = (qlog - plog)
v = (qlogExp * delta_log).sum()
v -= (np.exp(plog) * delta_log).sum() #- since we want p * (log(p)-log(q))
v *= -0.5 * dz2
#-sign to make it work as a similarity
if returnQlog:
return v, qlog
else:
return v
def kde_density(x, tree=None, apply_mean=False):
if tree is None:
tree = BallTree(x)
data = tree.get_arrays()[0]
h = np.std(data) * (4 / 3 / len(data))**(1 / 5
) # Silverman's Rule of Thumb
density = tree.kernel_density(x, h)
if apply_mean:
return np.mean(density)
return density
def balltree_kde_density(x):
tree = BallTree(x)
h = np.std(x) * (4 / 3 / len(x))**(1 / 5) # Silverman's Rule of Thumb
density = tree.kernel_density(x, h)
return np.mean(density)
