FCA4J v0.4.6
Relational concept analysis

RCA

to create a conceptual structure family from a relational context family. The output is a JSON file that can be opened in RCAviz, a DOT file that contains the graph of the conceptual structure family at the end of the process,TXT files for tracing the size of structures at each step, and traces.csv that contains the formal and relational contexts and other settings used at each step.The input is a relational context family.

Usage

java -jar fca4j-cli.jar RCA <input> [<output-folder>] [options]

Options

OptionDescription
-clean remove relational attributes concerning disappeared target concepts. Be careful, this option can cause the algorithm to loop
-ra rename relational attributes using concept reduced intents
-rai rename relational attributes using concept full intents only when reduced intent is empty (object concepts)
-ri rename relational attributes using concept full intents
-na this option must be combined with a renaming option, it limits the construction of intents to native (non-relational) attributes
-x <LIMIT> stop execution after LIMIT steps
-e store the final extended family
-es store the extended family at each step
-dot build dot files at each step
-d <DISPLAY-MODE> display format of the concepts for GraphViz. Available formats are:
  • FULL
  • SIMPLIFIED (default)
  • MINIMAL
-sta compute concept stability for dot file
-json build json files at each step
-xml build xml files
-fe add full concept extents
-fi add full concept intents
-a <ALGO> supported algorithms are:
  • ARES
  • CERES
  • PLUTON
  • HERMES
  • ADD_EXTENT
  • ADD_INTENT
  • ICEBERG
-p <PERCENT> for ICEBERG: percentage (of extent) to keep the top-most concepts
-f <FAMILY-FORMAT> supported formats are:
  • RCFT (default)
  • RCFGZ (compressed RCFT)
  • RCFAL (adjacency list JSON)
-cd <PATH> folder to generate a datalog file by concept for results
-cdu <DLGPFILE> generate a unique datalog file with all concepts descriptions
-nds limit datalog concept descriptions to immediate siblings (it reduces production of negative constraints)
-s <SEPARATOR> separator (CSV format only):
  • COMMA (default)
  • SEMICOLON
  • TAB
-timeout <SECONDS> set timeout for algorithm execution, in seconds
-v, --verbose print a final report of the algorithm execution