The toolkit contains a number of libraries and scripts. These have been produced to provide kdb+/q users with general-use functions and procedures to perform machine-learning tasks on a wide variety of datasets.
The toolkit contains:
- Utility functions relating to important aspects of machine-learning including data preprocessing, statistical metrics, and various other functionality useful in many machine-learning applications contained under utils.
- An implementation of the FRESH (FeatuRe Extraction and Scalable Hypothesis testing) algorithm in q. This lets a kdb+/q user perform feature-extraction and feature-significance tests on structured time-series data for forecasting, regression and classification.
Over time the machine-learning functionality in this library will be extended to include;
- q-specific implementations of machine-learning algorithms
- broader functionality
The following requirements cover all those needed to run the libraries in the current build of the toolkit.
A number of Python dependencies also exist for the running of embedPy functions within both the the machine-learning utilities and FRESH libraries. These can be installed as outlined at
pip install -r requirements.txt
conda install --file requirements.txt
Copy (a link to) the library into
$QHOME to install and load all libraries using
q)\l ml/ml.q q).ml.loadfile`:init.q / This can also be achieved in one line provided the library is located in `$QHOME`using q)\l ml/init.q