検出漏れやり直し

BM25

/Volumes/HD/false_negative_50_jar/false_negative ❯❯❯ go run intersection.go pro_result_parse/2gram-0.75.csv ../pre_result_remove/2grampre_0.75_greater.csv
==> done reading from file
==> done reading from file
12716
8100
7725

/Volumes/HD/false_negative_50_jar/false_negative ❮❮❮ go run intersection.go pro_result_parse/2gram-0.5.csv ../pre_result_remove/2grampre_0.75_greater.csv
==> done reading from file
==> done reading from file
73761
8100
7747

/Volumes/HD/false_negative_50_jar/false_negative ❯❯❯ go run intersection.go pro_result_parse/2gram-0.25.csv ../pre_result_remove/2grampre_0.75_greater.csv
==> done reading from file
==> done reading from file
1650830
8100
7748

見なかったことに

各類似度の頻度

/Volumes/HD/false_negative_50_jar/false_negative_jw ❮❮❮ cat pro_result_parse/2gram-0.25.csv | awk -F ',' '{if($3 >= 0.9){ a+=1 } else if($3 >= 0.8){ b+=1 }  else if($3 >= 0.7) { c+=1 } else if($3 >= 0.6) { d+=1 } else if($3 >= 0.5) { e+=1 } else if($3 >= 0.4) { f+=1 } else if($3 >= 0.3) { g+=1 } else if($3 >= 0.2) { h+=1 } else if($3 >= 0.1) { i+=1 } else if($3 >= 0.0) { j+=1} } END {print a,b,c,d,e,f,g,h,i j}'
8123 210144 3595094 4824120 1479238 219