Kernel: Python 3 (Ubuntu Linux)
Pymc3: Probabilistic Programming in Python: Bayesian Modeling and Probabilistic Machine Learning
Available in the "Python 3 (Ubuntu Linux)" kernel.
In [1]:
/usr/local/lib/python3.5/dist-packages/h5py/__init__.py:36: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
from ._conv import register_converters as _register_converters
'3.3'
In [2]:
In [3]:
In [4]:
logp = -149.58, ||grad|| = 12.242: 100%|██████████| 19/19 [00:00<00:00, 792.13it/s]
{'alpha': array(0.90660093),
'beta': array([0.94848596, 2.60711845]),
'sigma': array(0.96298858),
'sigma_log__': array(-0.03771373)}
In [5]:
Auto-assigning NUTS sampler...
Initializing NUTS using jitter+adapt_diag...
Sequential sampling (2 chains in 1 job)
NUTS: [sigma_log__, beta, alpha]
100%|██████████| 1000/1000 [00:01<00:00, 630.44it/s]
100%|██████████| 1000/1000 [00:01<00:00, 581.02it/s]
In [6]:
array([0.9572314 , 0.93554263, 0.86782858, 0.97563444, 0.70462067])
In [7]:
In [8]:
mean | sd | mc_error | hpd_2.5 | hpd_97.5 | n_eff | Rhat | |
---|---|---|---|---|---|---|---|
alpha | 0.904619 | 0.097804 | 0.002686 | 0.720830 | 1.092549 | 1000.0 | 0.999163 |
beta__0 | 0.947115 | 0.092629 | 0.002394 | 0.744485 | 1.128060 | 1000.0 | 1.001146 |
beta__1 | 2.608587 | 0.538713 | 0.016015 | 1.602050 | 3.685764 | 1000.0 | 0.999511 |
sigma | 0.989664 | 0.072976 | 0.001916 | 0.857547 | 1.140489 | 1000.0 | 0.999216 |
In [0]: