A careful walk through probability distributions, using Python
summary
Python code and SciPy.stats power an interactive Streamlit app at python-prob.ericmjl.com that constructs a Gaussian class with mu=1.7 and sigma=2.4, visualizes the PDF, and samples numbers (example run draws ~1000 points showing density proportionality). The demo implements PDF/log‑PDF, a draw method, and a small MLE exercise on six data points that maximizes the joint log likelihood to recover best‑fit parameters. It shows concrete code, numbers, and a working live generator.
AI-written summary · about
chapters (9)
- 0:00Intro
- 0:28Novartis Institutes for Biomedical Research
- 0:57Insight Health Data Fellow
- 4:10Probability distributions are number generators!
- 8:13What's the probability of a single value?
- 10:36Probability Area under PDF
- 11:38A probability distribution gives rules for drawing random numbers
- 16:37Probability distributions have a PDF/PMF
- 16:48Probability Area under curve
related talks
01h 30mA Primer on Gaussian Processes for Regression Analysis
01h 33mMastering Gaussian Processes with PyMC
14mProbabilistic Programming in Python
43mProbabilistic Programming in the Real World
01h 30mMaking Gaussian Processes Useful
42mBayesian Non-parametric Models for Data Science using PyMC3
01h 26mProbabilistic Programming and Bayesian Computing with PyMC
01h 27mProbabilistic Python: An Introduction to Bayesian Modeling with PyMC