EM 算法 returns 使用 pykalman 的不同答案

Question

我在 Python 3.6.3

中使用 pykalman 0.9.5 时遇到问题

参考下面的代码，为什么kf2和kf3的结果不一样，而kf1和kf3的结果是一样的？

kf2和kf3过程的区别在于我只是将迭代分成运行 kf2函数的2次。

感谢大家的关注。

>>>pri_mean[:10]
array([ 2827.2222,  2829.6   ,  2831.    ,  2832.1   ,  2833.1   ,  2835.3   ,  2833.9   ,
        2833.8   ,  2833.6   ,  2833.    ])

>>>kf1 = KalmanFilter()
>>>kf1 = kf1.em(pri_mean, 10, em_vars='all')
>>>print(kf1.transition_matrices, kf1.transition_offsets, kf1.transition_covariance)
[[ 0.99741876]] [ 10.04426882] [[ 2896.92752373]]
>>>kf2 = kf1.em(pri_mean, 10, em_vars='all')
>>>print(kf2.transition_matrices, kf2.transition_offsets, kf2.transition_covariance)
[[ 0.99364606]] [ 20.02260806] [[ 2600.94151188]]

>>>kf3 = KalmanFilter()
>>>kf3 = kf3.em(pri_mean, 20, em_vars='all')
>>>print(kf3.transition_matrices, kf3.transition_offsets, kf3.transition_covariance)
[[ 0.99741876]] [ 10.04426882] [[ 2896.92752373]]

Answer 1

我编辑了答案，因为我误解了这个问题。我认为问题是您缺少关键字 n_iter

查看此代码：

kf1 = KalmanFilter()
kf1 = kf1.em(pri_mean, n_iter=10, em_vars='all')
print(kf1.transition_matrices, kf1.transition_offsets, kf1.transition_covariance)
kf1 = kf1.em(pri_mean, n_iter=10, em_vars='all')
print(kf1.transition_matrices, kf1.transition_offsets, kf1.transition_covariance)
kf1 = KalmanFilter()
kf1 = kf1.em(pri_mean, n_iter=20, em_vars='all')
print(kf1.transition_matrices, kf1.transition_offsets, kf1.transition_covariance)

我通过 KalmanFilter() 创建一个过滤器，循环 10 次迭代并打印，然后再循环 10 次并打印。这相当于直接调用 .em() 20 次迭代。

会产生以下输出

[[ 0.95500561]] [ 113.29118228] [[ 6431.66262464]]
[[ 0.93636512]] [ 119.32378005] [[ 249.67547612]]
[[ 0.93636512]] [ 119.32378005] [[ 249.67547612]]

EM 算法 returns 使用 pykalman 的不同答案

EM algo returns different answers using pykalman

python

state-space

kalman-filter

pykalman

expectation-maximization