I am trying to build a logistic regression model on the sklearn iris dataset. However, my model isn’t converging and my results do not look right. import pymc3 as pm from sklearn.datasets import load_iris iris = load_iris() X = iris.data[:, :2] y = ((iris.target != 0) * 1).reshape(-1, 1) print(f"X…

New To PyMC3 | Logistic Regression - Bug

ricardoV94 November 3, 2020, 9:15pm 4

Your code seems wrong. You are specifying yhat but not using it in the pm.Bernoulli likelihood. Have you tried pm.Bernoulli("y", p=yhat, observed=y)?

Topic		Replies	Views
Samples from prior appear to have wrong distribution Questions	2	606	October 8, 2018
Logistic Regression with severe divergences Questions	6	1084	January 11, 2021
Beta Regression in pyMC3 Questions	7	5589	September 18, 2017
Simple logistic model: Bad initial energy log p's -Inf and Inf Questions	2	415	July 28, 2021
Multivariate-multinomial logistic regression Questions	10	7147	June 19, 2020

New To PyMC3 | Logistic Regression - Bug

Related topics