def plot_vmf_fit(x, mu, kappa, scale, index, title):
subplot = plt.subplot(3, 1, 1 + index)
plt.hist(x, bins=8, normed=True, histtype='stepfilled')
domain = np.linspace(vonmises.ppf(0.01, kappa), vonmises.ppf(0.99, kappa),
100)
plt.plot(domain, vonmises.pdf(domain, kappa=kappa, loc=mu, scale=scale))
plt.title(title)
def plot(self, output, frame_number):
if (self.distribution_type == "vonmises"):
kappa = self.params[0]
fig, ax = plt.subplots(1, 1)
x = np.linspace(vonmises.ppf(0.01, kappa),
vonmises.ppf(0.99, kappa), 100)
ax.plot(x,
vonmises.pdf(x, kappa),
'r-',
lw=5,
alpha=0.6,
label='vonmises pdf')
ax.set_xlim([-np.pi - 0.1, np.pi + 0.1])
ax.set_ylim([0.0, 1.0])
if self.target is not []:
for target in self.target:
angle = target - self.parafoveal if target == min(
self.target) else target + self.parafoveal
ax.axvline(x=angle, label='line at x = {}'.format(target))
plt.xlabel("Angles (Degrees)")
plt.ylabel("Estimated Probability")
plt.title("Method 3a Distribution")
plt.show()
def bunny2circle2clusters():
with open('bunny.pickle', mode='r+b') as f:
bunny_dict = pickle.load(f)
for i in bunny_dict:
samples = np.linspace(0, len(bunny_dict[i]), num=200, endpoint=False,
dtype=np.int)
print(i, len(bunny_dict[i]), len(bunny_dict[i][samples]))
bunny_dict[i] = bunny_dict[i][samples]
idx_last = max([i for i in bunny_dict])
last_bunny = bunny_dict[idx_last]
centroid = np.mean(last_bunny, axis=0, keepdims=True)
norms = np.linalg.norm(last_bunny - centroid, axis=1)
r = norms.mean()
samples_per_cluster = np.linspace(0, 1, endpoint=False,
num=len(last_bunny) // 4 + 1)[1:]
circle_clustered_dict = {}
for kappa in range(1, 200):
print(kappa)
angles = []
for theta in [0, 0.5 * np.pi, np.pi, 1.5 * np.pi]:
angles.extend(vonmises.ppf(samples_per_cluster, kappa, loc=theta))
# plt.figure()
# plt.plot(angles)
# plt.show()
angles = np.sort(np.mod(angles, 2 * np.pi))
# plt.figure()
# plt.plot(angles)
# plt.show()
x = r * np.cos(angles) + centroid[0, 0]
y = r * np.sin(angles) + centroid[0, 1]
curve = np.vstack((x, y)).T
circle_clustered_dict[kappa] = curve
with open('bunny_processed.pickle', mode='w+b') as f:
pickle.dump(bunny_dict, f)
pickle.dump(circle_clustered_dict, f)
from scipy.stats import vonmises import matplotlib.pyplot as plt fig, ax = plt.subplots(1, 1) # Calculate a few first moments: kappa = 3.99 mean, var, skew, kurt = vonmises.stats(kappa, moments='mvsk') # Display the probability density function (``pdf``): x = np.linspace(vonmises.ppf(0.01, kappa), vonmises.ppf(0.99, kappa), 100) ax.plot(x, vonmises.pdf(x, kappa), 'r-', lw=5, alpha=0.6, label='vonmises pdf') # Alternatively, the distribution object can be called (as a function) # to fix the shape, location and scale parameters. This returns a "frozen" # RV object holding the given parameters fixed. # Freeze the distribution and display the frozen ``pdf``: rv = vonmises(kappa) ax.plot(x, rv.pdf(x), 'k-', lw=2, label='frozen pdf') # Check accuracy of ``cdf`` and ``ppf``: vals = vonmises.ppf([0.001, 0.5, 0.999], kappa) np.allclose([0.001, 0.5, 0.999], vonmises.cdf(vals, kappa)) # True # Generate random numbers:
def ppf(self, dist, p):
return vonmises.ppf(p, *self._get_params(dist))