ronojoy/pylearn

Bayesian machine learning in Python

pylearn's Issues

Titanic: How to use the "Name" attribute

Intuitively name seems to be directly not related with the survival of a person but how else can it be used? Can it be used in the case when one of age or sex is not given and we can estimate one of them using name?

Titanic - Getting ZeroDivisionError when I try to do network.bake()

I tried to run the code from master before making any changes and I got

network.bake()
File "pomegranate\BayesianNetwork.pyx", line 126, in pomegranate.BayesianNetwork.BayesianNetwork.bake (pomegranate/BayesianNetwork.c:3531)
File "pomegranate\distributions.pyx", line 2331, in pomegranate.distributions.ConditionalProbabilityTable.joint (pomegranate/distributions.c:38321)
ZeroDivisionError: float division by zero

Also found that both the given probability of survival and perish for third class was 0.0. I thought this was the issue, but giving 1 for one of it didn't solve the problem.

Also, I calculated probabilities from training data and assigned them in the truth table (Hope the approach is right?) You can check my changes here, didn't send a pull request cos its not working yet.
https://github.com/yeskarthik/pylearn/blob/master/scripts/ex4-titanic-disaster.py
But I'm still getting the above error during network.bake() cc: @ronojoy