tabacof

# -*- coding: utf-8 -*-
"""
Reproducing the results of Auto-Encoding Variational Bayes by Kingma and Welling
With a little help from the code from van Amersfoort and Otto Fabius (https://github.com/y0ast)

@author: Pedro Tabacof (tabacof at gmail dot com)
"""

import random
import numpy as np

tabacof

# -*- coding: utf-8 -*-
import numpy as np
from scipy.special import binom

#Jaynes' PT:TLoS exercise 4.2

def db(x): # Decibel transform
    return 10.0*np.log10(x)

def evidence(x): # Equation 4.8

tabacof

# -*- coding: utf-8 -*-
import numpy as np
from scipy.special import binom
import random

#Jaynes' PT:TLoS exercise 4.4

def db(x): # Decibel transform
    return 10.0*np.log10(x)

tabacof

# -*- coding: utf-8 -*-
import numpy as np
import pylab
from scipy.special import binom
from bayespy.nodes import Categorical, Binomial, Gate, Beta

#Jaynes' PT:TLoS example 4.1

def db(x): # Decibel transform
    return 10.0*np.log10(x)

tabacof

# -*- coding: utf-8 -*-
import numpy as np
import pymc #2.3
import pylab
from scipy.special import binom

#Jaynes' PT:TLoS example 4.1

def db(x): # Decibel transform
    return 10.0*np.log10(x)

tabacof

# Jaynes' counter-intuitive equation
# 3.59 in PT:TLoS

import random

random.seed(1) # For experiment reproduction

# P(R1|R2)
count_reds1 = 0.0
count_total1 = 0.0

tabacof

from pymc import *
from scipy.stats import norm
import pylab as plt

# Same model as the tutorial    
n = 1000    
x1 = norm.rvs(0, 1, size=n)
x2 = -x1 + norm.rvs(0, 10**-3, size=n)
x3 = norm.rvs(0, 1, size=n)