Function Data File
Function data files are tab-delimited text files for storing
aggregation and discretization functions , which are exported and imported
through File Menu commands:
File/Export function... and File/Import function..., respectively.
One file contains one function, whose format can be specified with
Import/Export settings.
Examples
1. TECH.CHAR. function from the
Car Evaluation model,
exported in tab-delimited format, using ‘Base 1’ values and exporting
all rules. The character + represents an entered rule. Here, the TAB
character is denoted ¬.
¬COMFORT¬SAFETY¬TECH.CHAR.1¬1¬1¬1¬+2¬2¬1¬1¬+3¬3¬1¬1¬+4¬1¬1¬1¬+5¬2¬2¬2¬+6¬3¬3¬3¬+7¬1¬1¬1¬+8¬2¬3¬3¬+9¬3¬4¬4¬+2. The same function exported using text values and exporting only
entered rules (in this case there is no need to display the + or -
entered status).
¬COMFORT¬SAFETY¬TECH.CHAR.1¬bad¬bad¬bad2¬acc¬bad¬bad3¬good¬bad¬bad4¬bad¬bad¬bad5¬acc¬acc¬acc6¬good¬good¬good7¬bad¬bad¬bad8¬acc¬good¬good9¬good¬exc¬exc3. Experience discretization function from the Employee Selection model, using ‘Base 1’ values.
¬ExperYears¬¬Experience1¬¬¬1¬+¬0¬]¬2¬¬¬2¬+¬1¬]¬3¬¬¬3¬+¬5¬]¬4¬¬¬4¬+¬10¬[¬5¬¬¬5¬+Observe the alternating lines: lines beginning with 1 to 5 define output values of the corresponding input value intervals,
while the intermediate lines define interval boundaries. The characters ] and [ determine which interval,
previous or next, contains the corresponding bound. In this case, there are 5 intervals:
[-∞, 0] -> value 1 (“no”)
(0, 1] -> value 2 (“to1year”)
(1, 5] -> value 3 (“1-5”)
(5, 10) -> value 4 (“6-10”)
[10, +∞] -> value 5 (“more”)