本文整理汇总了Python中sklearn.cluster.KMeans.predict_proba方法的典型用法代码示例。如果您正苦于以下问题：Python KMeans.predict_proba方法的具体用法？Python KMeans.predict_proba怎么用？Python KMeans.predict_proba使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类sklearn.cluster.KMeans的用法示例。
在下文中一共展示了KMeans.predict_proba方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: ModalPolicy
# 需要导入模块: from sklearn.cluster import KMeans [as 别名]
# 或者: from sklearn.cluster.KMeans import predict_proba [as 别名]
class ModalPolicy(object):
"""Clusters the input space and returns local policies.
"""
def __init__(self, optimizer=None, reward_model=None, mode_classifier=KNeighborsClassifier,
mode_args=None):
if reward_model is None:
self.reward_model = GPRewardModel()
else:
self.reward_model = reward_model
self.reward_model_fitted = False
self.mode_classifier = mode_classifier
if mode_args is None:
self.mode_args = {'weights': 'distance'}
self.states = []
self.actions = []
self.rewards = []
self.clusters = None
self.clusters_init = False
self.cluster_actions = []
self.cluster_rewards = []
self.active_clusters = []
self.n_modes = 0
self.sa_kde = KernelDensity() # TODO
if optimizer is None:
self.optimizer = BFGSOptimizer(mode='max', num_restarts=3)
self.optimizer.lower_bounds = -1
self.optimizer.upper_bounds = 1 # TODO
else:
self.optimizer = optimizer
def report_sample(self, s, a, r):
x = np.hstack((s, a))
# try:
self.reward_model.report_sample(x, r)
self.reward_model_fitted = True
# except AttributeError:
# self.reward_model_fitted = False
self.states.append(s)
self.actions.append(a)
self.rewards.append(r)
def get_action(self, s):
s = np.asarray(s)
if len(s.shape) < 2:
s = s.reshape(1, -1)
# TODO Support multiple queries?
probs = self.clusters.predict_proba(s)
ind = np.random.choice(self.active_clusters,
size=1,
p=np.atleast_1d(np.squeeze(probs)))
a = [self.cluster_actions[i] for i in ind]
return np.squeeze(a)
def expected_reward(self, normalize=False):
self.fit_reward_model()
X = np.hstack((self.states, self.actions))
r_pred, r_std = self.reward_model.predict(X, return_std=True)
if normalize:
logq = self.sa_kde.score_samples(X)
logp = np.mean(logq)
return importance_sample(x=r_pred, p_gen=logq, p_tar=logp,
normalize=True, log_weight_lim=3)
else:
return np.mean(r_pred)
def initialize_modes(self, n_modes, init_clusterer=None):
if init_clusterer is None:
self.clusters = KMeans(n_clusters=n_modes)
else:
self.clusters = init_clusterer
self.n_modes = n_modes
self.clusters.fit(X=self.states)
self.cluster_actions = [None] * n_modes
self.cluster_rewards = [None] * n_modes
self.active_clusters = range(self.n_modes)
self.optimize_mode_actions()
def fit_reward_model(self):
if self.reward_model_fitted:
return
# X = np.hstack((self.states, self.actions))
# r = np.asarray(self.rewards).reshape(-1, 1)
# self.reward_model.fit(X, r)
# self.reward_model_fitted = True
def optimize(self, n_iters, beta=1.0):
for i in range(n_iters):
#.........这里部分代码省略.........