擅长:python、mysql、java
<p>看起来您使用的是PyMC2,据我所知,您必须使用一些Python方法来进行并行计算,比如<a href="http://ipython.org/ipython-doc/dev/parallel/">IPython.parallel</a>。有很多方法可以做到这一点,但我知道的所有方法都有点复杂。这是<a href="http://continuum.io/blog/bayesian-estimation-hoops">an example of one, which uses PyMC2, IPCluster, and Wakari</a>。在</p>
<p>在PyMC3中,并行采样是在<code>psample</code>方法中实现的,但是需要将参考代码更新为PyMC3格式:</p>
<pre><code>with pm.Model() as model:
beta1 = pm.Laplace('beta1', mu=0, b=b)
beta2 = pm.Laplace('beta2', mu=0, b=b)
beta3 = pm.Laplace('beta3', mu=0, b=b)
y_hat = beta1 * x1 + beta2 * x2 + beta3 * x3
y_obs = pm.Normal('y_obs', mu=y_hat, tau=1.0, observed=y)
trace = pm.psample(draws=20000, step=pm.Slice(), threads=3)
</code></pre>