Probabilistic-Programming-and-Bayesian-Methods-for-Hackers
Probabilistic-Programming-and-Bayesian-Methods-for-Hackers copied to clipboard
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
Update Ch2_MorePyMC_PyMC_current.ipynb print initial values, in accordance with latest pymc version
model.initial_values.items is deprecated. I updated it to model.rvs_to_initial_values to print variables and initial values correctly.
when i ran code bellow ~ with model: step1 = pm.Metropolis(vars=[p, sds, centers]) step2 = pm.ElemwiseCategorical(vars=[assignment]) trace = pm.sample(25000, step=[step1, step2]) show error message: TypeError: Unknown parameter type: Can anyone...
When accessing Chapter 1 of the Tensorflow port [here](https://nbviewer.org/github/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/blob/master/Chapter1_Introduction/Ch1_Introduction_TFP.ipynb) and clicking on the ["Run in Google Colab"](https://colab.research.google.com/github/CamDavidsonPilon/Probabilistic-Programming-and-Bayesian-Methods-for-Hackers/blob/master/Chapter1_Introduction/Ch1_Introduction_TFP.ipynb) button in the top right, when I execute the first code cell (with...
fixed deprecated syntax
In Chapter 2, the author states: "With regards to the above plot, we are still pretty uncertain about what the true frequency of cheaters might be, but we have narrowed...
this code doesn't produce the 5% quantile: `v = np.sort( posteriors[i] )[ int(0.05*N) ]` this would do it: `v = np.sort( posteriors[i] , axis=0)[ int(0.05*N) ]`
In Chapter 1 (_Ch1_Introduction_PyMC2.ipynb_) there's a **type error** in the first coin flipping algorithm (_Example: Mandatory coin-flip example_) at line: `sx = plt.subplot(len(n_trials) / 2, 2, k + 1)` inside...