4. Extending FLinK

This section documents the building blocks of the FLinK system.

The functionalities they provide can be combined to define new activities and new linearization systems.

• 4.1. Activities of the linearization process: flink.activities
  • 4.1.1. Learning and classification
  • 4.1.2. Kernel Space Mining (KSM)
  • 4.1.3. Linear Space Generation (LSG)
  • 4.1.4. Evaluation and miscellaneous activities
  • 4.1.5. Optimization activities: flink.optimize
• 4.2. A Python3K interface to SVMLightTK: flink.pytk
  • 4.2.1. Mining relevant fragments in the kernel space: flink.pytk.miners
  • 4.2.2. Fragment generation and indexing
• 4.3. A collection of utility functions: flink.utils
  • 4.3.1. flink.utils.pool — multiprocessing in FLinK activities
  • 4.3.2. flink.utils.logging — a very simple logging facility
  • 4.3.3. flink.utils.props — handle configuration properties
  • 4.3.4. flink.utils.mathutils — mathematical functions
  • 4.3.5. flink.utils.fileutils — filesystem related functions
  • 4.3.6. flink.utils.persistency — a facility for object persistency
  • 4.3.7. flink.utils.tree — manage parenthesized trees
  • 4.3.8. flink.utils.cli — command line parsing facilities