def draw(self):
"""
Sample from the categorical distribution, and payout corresponding to the selected index
:return: payouts[i], where i is sampled from the categorical distribution given by pvals
"""
return random.multinomial(1, pvals=self.pvals).dot(self.payouts)
def draw(self):
"""
if sample_priors = True and random_sample = True:
draw returns a random draw of a categorical distribution with parameters drawn from a Dirichlet distribution
the hyperparameters on the Dirichlet are given by the bandit's metric with laplacian smoothing
if sample_priors = False and random_sample = True:
draw returns a random draw of a categorical distribution with parameters given by the bandit's metric
if sample_priors = True and random_sample = False:
draw returns argmax(random.dirichlet((x_0 + 1, ... , x_n_arms + 1))) where x_i is the ith value returned by
the bandit's metric.
if sample_priors = False and random_sample = False:
become a purely greedy bandit with the selected arm given by argmax(metric)
:return: The numerical index of the selected arm
"""
temp = self._schedule_fn(self.total_draws)
x = array(self._metric_fn()) * temp + 1
if self.sample_priors:
pvals = random.dirichlet(x)
else:
pvals = x / sum(x)
if self.random_sample:
return argmax(random.multinomial(1, pvals=pvals))
else:
return argmax(pvals)
def draw(self):
"""
Selects arm i with probability distribution given by the softmax:
P(arm_i) = exp(metric_i) / Z
Where Z is the normalizing constant:
Z = sum(exp(metric_i) for i in range(n_arms))
:return: The numerical index of the selected arm
"""
return argmax(random.multinomial(1, pvals=softmax(self._metric_fn())))
def draw(self):
"""
Selects arm i with probability distribution given by the softmax:
P(arm_i) = exp(metric_i / temperature) / Z
Where Z is the normalizing constant:
Z = sum(exp(metric_i / temperature) for i in range(n_arms))
:return: The numerical index of the selected arm
"""
temp = self._schedule_fn(self.total_draws)
return argmax(random.multinomial(1, pvals=softmax(array(self._metric_fn()) / temp)))
cov1 = np.eye(2)
mu2 = np.array([5, 3])
cov2 = np.eye(2) * 2
mu3 = np.array([8, 12])
cov3 = np.array([3.4, 0, 0, 5.1]).reshape(2, 2)
# multinom params
p1 = 0.2
p2 = 0
p3 = 1 - p2 - p1
# random draws
rnd.seed(1)
knum = rnd.multinomial(draws, (p1, p2, p3))
gaus1 = rnd.multivariate_normal(mu1, cov1, knum[0])
gaus2 = rnd.multivariate_normal(mu2, cov2, knum[1])
gaus3 = rnd.multivariate_normal(mu3, cov3, knum[2])
# join columns into dataframe
x1 = pd.Series(np.r_[gaus1[:, 0], gaus2[:, 0], gaus3[:, 0]])
x2 = pd.Series(np.r_[gaus1[:, 1], gaus2[:, 1], gaus3[:, 1]])
c = pd.Series(np.r_[np.zeros(knum[0]), np.ones(knum[1]), np.ones(knum[2]) * 2])
dat = {"x1" : x1, "x2" : x2, "c" : c}
clustData = pd.DataFrame(dat)
# plot clusters
#plt.scatter(clustData["x1"], clustData["x2"], c = clustData["c"])
#plt.show()