DataSklr.com

12/28/2020

A new book about Logistic Regression with Python is now available on datasklr.com
https://www.datasklr.com/shop/logistic-regression-an-applied-approach-using-python

A showcase of logistic regression theory and application of statistical machine learning with Python. Topics include logit, probit, complimentary log-log models with a binary target, multinomial regression and contingency tables. while using Scikit-Learn and statsmodels.

06/11/2020

https://www.datasklr.com/principal-component-analysis-and-factor-analysis/factor-analysis

Applied factor analysis with the factor_analyzer package in Python. The article touches on the following topics: testing the appropriateness of factor analysis, factor rotations, methods (smc vs. mac) and how to decided on the number of factors.

06/11/2020

https://www.datasklr.com/principal-component-analysis-and-factor-analysis/principal-component-analysis

The article explains how to conduct Principal Components Analysis with Sci-Kit Learn (sklearn) in Python. More specifically, It shows how to compute and interpret principal components. Key concepts such as eigenvalues, eigenvectors and the scree plot are introduced.

01/15/2020

A comparison of Linear and Quadratic Discriminant Analysis using Sci-Kit Learn

The blog contains a description of how to fit and interpret Linear and Quadratic Discriminant models with Python. The discussion includes both parameter tuning and assessment of accuracy for both LDA and QDA.

01/09/2020

Please see a new blog entry about how to fit multinomial logistic regression models with Sci-Kit Learn and the statsmodels package in Python. A discussion about how to interpret coefficients with both methods is included, and to make it short: it is complicated. If we pair the difficult explainability with accuracy issues, it is not surprising that a lot of us do not like this method.

Multinomial logistic regression with Python: a comparison of Sci-Kit Learn and the statsmodels package including an explanation of how to fit models and interpret coefficients with both

01/09/2020

Please see a new blog entry about how to fit multinomial logistic regression models with Sci-Kit Learn and the statsmodels package in Python. A discussion about how to interpret coefficients with both methods is included, and to make it short: it is complicated. If we pair the difficult explainability with accuracy issues, it is not surprising that a lot of us do not like this method.

Multinomial logistic regression with Python: a comparison of Sci-Kit Learn and the statsmodels package including an explanation of how to fit models and interpret coefficients with both

12/31/2019

An overview of binary logistic regression. I will expand to other topics within logistic regression in the very near future.

Binary logistic regression, multinomial logistic regression and analysis of discrete choice and ordered categorical data with Python

12/24/2019

Working on logistic regression blog. It’s an explanation of the concept. I will also publish a pretty comprehensive “how to” section with python.

12/16/2019

https://www.datasklr.com/tree-based-methods-for-regression
Articles about Regression Trees, Bagging, Random Forests and Boosting have been published on DataSklr.com

Applied machine learning approaches to regression trees, boosting, bagging and random forests using Sci-Kit Learn. Adaptive Boosting, Gradient Boosting and Extreme Gradient Boosting are discussed in detail.

12/10/2019

Blog post about Regression Trees published at
https://www.datasklr.com/tree-based-methods-for-regression/regression-trees