Skip to content
/ funq Public

Source files for "Fun Q: A Functional Introduction to Machine Learning in Q"

License

Notifications You must be signed in to change notification settings

psaris/funq

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Fun Q

This project contains the source files for "Fun Q: A Functional Introduction to Machine Learning in Q".1

The Book

Fun Q can be purchased on Amazon and Amazon UK. A Kindle version is also available. Books may be purchased in quantity and/or special sales by contacting the publisher, Vector Sigma. Read a review by Daniel Krizian published by Vector, the Journal of the British APL Association.

The Source

Install q from Kx System's kdb+ download page and grab a copy of the Fun Q source.

$ git clone https://github.com/psaris/funq

The Fun Q Environment

The following command starts the q interpreter with all Fun Q libraries loaded and 4 secondary threads for parallel computing.

$ q funq.q -s 4

The Errors

Any typos or errors are listed here and are incorporated into recent printings of the book as well as the kindle version.

The Swag

Swag can be found on the Vector Sigma Spring site.

More Fun

Start q with any of the following or read the comments and run the examples one by one.

Plotting

$ q plot.q -s 4

K-Nearest Neighbors (KNN)

$ q knn.q -s 4

K-Means/Medians/Medoids Clustering

$ q kmeans.q -s 4

Hierarchical Agglomerative Clustering (HAC)

$ q hac.q -s 4

Expectation Maximization (EM)

$ q em.q -s 4

Naive Bayes

$ q nb.q -s 4

Vector Space Model (tf-idf)

$ q tfidf.q -s 4

Decision Tree (ID3,C4.5,CART)

$ q decisiontree.q -s 4

Discrete Adaptive Boosting (AdaBoost)

$ q adaboost.q -s 4

Random Forest (and Boosted Aggregating BAG)

$ q randomforest.q -s 4

Linear Regression

$ q linreg.q -s 4

Logistic Regression

$ q logreg.q -s 4

One vs. All

$ q onevsall.q -s 4

Neural Network Classification/Regression

$ q nn.q -s 4

Content-Based/Collaborative Filtering (Recommender Systems)

$ q recommend.q -s 4

Google PageRank

$ q pagerank.q -s 4

Footnotes

  1. More presentations, competitions and books by Nick Psaris can be found at https://nick.psaris.com