Geek Answers Handbook

Pymc warning: value is neither numeric nor floating point dtype array

I have a Bayes net (DAG) model that I created using pymc 2.3. All variables in it are random Bernoulli variables. When I call the MAP.fit () method on it before fetching, I get the following warning for all my random variables:

value is neither numerical nor array with floating-point dtype. Recommend fitting method fmin (default)

From gythub repo pymc, it seems that this warning is printed if the underlying type of the stochastic variable is not a float. For Bernoulli RV type (and should be) bool.

Does this mean that the MAP step will have erratic results?

+7
python bayesian-networks pymc
source share

No one has answered this question yet.

See similar questions:

5
MAP warning pymc: The stochastic value of tau is neither a numeric nor a floating point dtype array. Recommend fmin installation method (default)

or similar:

152
Why does a 4 * 0.1 floating-point value look beautiful in Python 3, but 3 * 0.1 doesn't?
5
MAP warning pymc: The stochastic value of tau is neither a numeric nor a floating point dtype array. Recommend fmin installation method (default)
2
Opencv TypeError: points are not a numpy array, nor scalar
one
Numpy n-tuple array with dtype float
one
convert numpy array from dtype to float
one
A function argument that has a value that is not passed by the caller or the default value
0
Gradient Acceleration with Sklearn
0
How to get the numeric read output of a float dtype in a Numpy array?
0
Can pandas SparseSeries store values ​​in float16 format?
-one
How to determine if an array of a numeric type contains only logical values?

More articles:


All Articles