Contains a variety of machine learning algorithms implemented in python with decent explanations
- Basic data exploration contains the fundamentals of importing to pandas and using stat moments to find out more about the data
- Habermans survival contains good visualization and exploration of the Habermans cancer suriviors dataset
- KMeasn clustering contains the algorithm implemented on custom blobs (To show how it works) and on a weather dataset for more realisitc exposure
- LDA and PCA demo contains an in depth exploration of the PCA and the LDA algorithms as dimensionality reduction techniques and Classifiers(LDA) validated on tensorflow nets(Keras)
- Naive Bayes Classification has the algorithm worked on numerical and text classification (TFIDF)
- PCA Demo contains an overview of how PCA works and how exactly it helps, using Logistic Regression to validate results
- Logistic Regression has a description of sklearns methods for generating synthetic dataset along with logistic regression and also plotting probability boundaries
- Compare Classifiers compares four different classifiers, LDA,Neural Nets, Logistic Regression and KNN. Wisconsin breast Cancer data set is used.
- Dimensionality reduction contains a good amount of theory about Multidimensional scaling, LDA and PCA and usage of speeach features(Temporal) to see which method is useful (Used keras neural nets).
- Linear Regression shows how to visualize the hypothessis line and use regression with regularization both ridge and lasso and also explores what would be the ideal hypothesis function
- Support vector machines explore how the SVM behaves with large data and also explores how SVM cannot handle non numeric data and talks about how we could encode string into numeric data to use for the SVM
- Random Forest classifer explores the algorithm and also talks about the sklearn implementation and how its implenetation isn't really complete.