Optimizing 2016 SD-Rule Set - Baseline
I. Get the stats (yes|no) from current year data
shell> cd ${SUFFIXD_DIR}/bin
shell> GetSuffixD ${YEAR}
11
ALL
II. Establish the baseline: remove all Child SD-Rules and use it as the baseline
shell> cd ${SUFFIXD_DIR}/data/${YEAR}/dateR/SdRulesOptimum/0.baseline
shell> cp -p ../../../data/sdRules.stats.rpt.pipe sdRules.stats.in.${YEAR}
shell> cp -p sdRules.stats.in.${YEAR} sdRules.stats.in.${YEAR}.removeChild
shell> fgrep "|CHILD" sdRules.stats.in.2016.removeChild | wc -l
shell> ln -sf ./sdRules.stats.in.${YEAR}.removeChild sdRules.stats.in
III. Get the Optimal Set
shell> cd ${SUFFIXD_DIR}/bin
shell> GetSdRule ${YEAR}
1
others
0.baseline
0
IV. Results
The result of this baseline set of SD-Rules includes 111 unique parents/self SD-Rules (no child rules). They are sorted by a descending order of precision (= relevant, retrieved No./retrieved No.) and then retrieved No. rate. The top 81 SD-Rules are used as the optimized SD-Rule set to cover 95.15% system (accumulated) precision and 94.85% system (accumulated) recall rate with a system performance of 1.9000. The total valid instance number is 50,814 (from: ./sdRules.stats.out).
-- Total line no: 135 -- Total comment no: 24 -- Total Sd-Rule no: 111 --------------------------------------- -- Optimum SD-Rules: 81|68.29%|123|84|39|0|ant$|adj|ate$|verb|2013|ORG_RULE|SELF|95.15%|94.85%|1.9000|48195|50649