No posts match your search.
Why accuracy lies on imbalanced data, and how precision, recall, F1, ROC-AUC, and precision-recall curves tell the real story — built up from the math and implemented in Julia with MLJ.jl, on a synthetic churn dataset with a known, verified answer.
Simple random, systematic, stratified, and cluster sampling, plus the bootstrap — explained with the math, implemented in both R and Julia, and checked with a Monte Carlo simulation that shows exactly why stratified sampling wins and cluster sampling doesn't.
What a p-value actually means, why 'statistically significant' isn't the same as 'real,' and why peeking at your A/B test results early quietly wrecks your false-positive rate — demonstrated with a runnable Monte Carlo simulation, not just formulas.
How Principal Component Analysis actually works — covariance matrices, eigenvectors, and explained variance — built from scratch in NumPy, cross-checked against scikit-learn, and visualized with Bokeh.
A comprehensive guide to MLJ.jl — Julia's unified machine learning framework — with worked examples, a feature-by-feature comparison against scikit-learn, and an honest look at where each one wins.
A comprehensive, example-driven tour of DataFrames.jl — every core feature explained and benchmarked against pandas, NumPy, and R, so you know exactly when Julia's data tooling pulls ahead.
A comprehensive guide to Logistic Regression covering math fundamentals, loss functions, regularization (L1/L2), and a complete, interactively-plotted Python implementation with NumPy, Pandas, Scikit-Learn, and Bokeh.
