feat: statistics tests

This commit is contained in:
2025-09-28 23:50:40 +02:00
parent 9039e9a4cf
commit 9e35f95107
18 changed files with 7645 additions and 4872 deletions
+7
View File
@@ -0,0 +1,7 @@
sex,position,2-grams,3-grams,4-grams
female,prefix,"ma, ch, be, na, an, sa, es, jo, ju, me","mar, cha, est, chr, gra, dor, sar, rut, ben, mer","mari, chri, esth, grac, sara, dorc, ruth, rach, naom, jean"
female,suffix,"ne, ie, te, le, ce, ia, se, el, ah, th","ine, tte, lle, rah, nce, ene, nne, her, lie, rie","ette, line, tine, elle, ther, arie, ille, rcas, ruth, arah"
female,any,"ne, in, el, an, ie, ri, ra, li, ar, er","ine, tte, ett, mar, ari, lle, lin, eli, the, ell","ette, line, ther, mari, tine, elle, rist, chri, ance, hris"
male,prefix,"jo, je, pa, ch, ma, da, al, ju, be, fr","jea, jos, chr, pat, mar, jon, fra, dan, cha, ben","jean, chri, jose, jona, patr, fran, mich, emma, davi, dieu"
male,suffix,"in, el, an, ck, on, re, ce, er, se, is","ean, tin, ick, ier, ard, uel, ert, ain, iel, ise","jean, stin, rick, bert, seph, than, oise, avid, ndre, tian"
male,any,"an, er, el, ie, in, ri, is, on, en, re","ric, sti, jea, ean, tin, ris, ier, ist, ick, jos","jean, stin, rist, rick, chri, hris, usti, bert, jose, atha"
1 sex position 2-grams 3-grams 4-grams
2 female prefix ma, ch, be, na, an, sa, es, jo, ju, me mar, cha, est, chr, gra, dor, sar, rut, ben, mer mari, chri, esth, grac, sara, dorc, ruth, rach, naom, jean
3 female suffix ne, ie, te, le, ce, ia, se, el, ah, th ine, tte, lle, rah, nce, ene, nne, her, lie, rie ette, line, tine, elle, ther, arie, ille, rcas, ruth, arah
4 female any ne, in, el, an, ie, ri, ra, li, ar, er ine, tte, ett, mar, ari, lle, lin, eli, the, ell ette, line, ther, mari, tine, elle, rist, chri, ance, hris
5 male prefix jo, je, pa, ch, ma, da, al, ju, be, fr jea, jos, chr, pat, mar, jon, fra, dan, cha, ben jean, chri, jose, jona, patr, fran, mich, emma, davi, dieu
6 male suffix in, el, an, ck, on, re, ce, er, se, is ean, tin, ick, ier, ard, uel, ert, ain, iel, ise jean, stin, rick, bert, seph, than, oise, avid, ndre, tian
7 male any an, er, el, ie, in, ri, is, on, en, re ric, sti, jea, ean, tin, ris, ier, ist, ick, jos jean, stin, rist, rick, chri, hris, usti, bert, jose, atha