初始化内容
This commit is contained in:
@@ -0,0 +1,142 @@
|
||||
= Logs of language model for Arabic (ar) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2015-12-13 18:31:12.817808
|
||||
- Maximum depth: 2
|
||||
- Max number of pages: 50
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
الصفحة_الرئيسية (revision 17217037)
|
||||
11 ديسمبر (revision 17699159)
|
||||
12 ديسمبر (revision 17710194)
|
||||
13 ديسمبر (revision 17722318)
|
||||
1437 هـ (revision 17278274)
|
||||
14 ديسمبر (revision 17432010)
|
||||
15 ديسمبر (revision 17206233)
|
||||
1645 (revision 17168144)
|
||||
1954 (revision 17409780)
|
||||
1955 (revision 16826533)
|
||||
1972 (revision 17004868)
|
||||
1988 (revision 17671285)
|
||||
2003 (revision 17656994)
|
||||
2011 (revision 17589601)
|
||||
2015 (revision 17678287)
|
||||
216 ق.م (revision 17586752)
|
||||
25 يناير (revision 17325864)
|
||||
2 ربيع الأول (revision 17722146)
|
||||
6 (عدد) (revision 16972178)
|
||||
آريز (revision 17466671)
|
||||
آلهة اليونان (revision 17722617)
|
||||
أثينا (revision 17642941)
|
||||
أثينا (ميثولوجيا) (revision 17662932)
|
||||
أزمة المهاجرين إلى أوروبا (revision 17718437)
|
||||
أوروبا (revision 17713457)
|
||||
إس سي إي سانتا مونيكا ستوديو (revision 17035439)
|
||||
إسبارطة (revision 16733170)
|
||||
إسماعيل الصفوي (revision 17194218)
|
||||
إله الحرب (لعبة فيديو) (revision 17630201)
|
||||
إمارة دبي (revision 17602037)
|
||||
إيطاليا (revision 17586853)
|
||||
اتفاق باريس (revision 17718086)
|
||||
الأزمة الليبية (revision 17630232)
|
||||
الإمارات العربية المتحدة (revision 17722077)
|
||||
الإنتخابات البلدية السعودية 2015 (revision 17722004)
|
||||
الاتحاد الأوروبي لكرة القدم (revision 17596822)
|
||||
الاحتجاجات اللبنانية 2015 (revision 17315127)
|
||||
الانتفاضة الفلسطينية (2015) (revision 17710414)
|
||||
التمرد العراقي (revision 17708640)
|
||||
الجمعية العامة للأمم المتحدة (revision 17304227)
|
||||
الجمهورية الرومانية (revision 16472557)
|
||||
الجيش اللبناني (revision 17516533)
|
||||
الحرب الأهلية السورية (revision 17675300)
|
||||
الحرب الأهلية اليمنية (2015) (revision 17686236)
|
||||
الحرب في شمال غرب باكستان (revision 17490838)
|
||||
الدولة الصفوية (revision 17031046)
|
||||
الرياض (revision 17580586)
|
||||
السعودية (revision 17711339)
|
||||
السلطة الوطنية الفلسطينية (revision 17438123)
|
||||
العراق (revision 17704602)
|
||||
العلاقات الخارجية في تركيا (revision 17647409)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2015-12-13 18:33:58.846891
|
||||
|
||||
95 characters appeared 727795 times.
|
||||
|
||||
First 64 characters:
|
||||
[ 0] Char ا: 14.933875610577156 %
|
||||
[ 1] Char ل: 11.460782225764122 %
|
||||
[ 2] Char ي: 8.30302489025069 %
|
||||
[ 3] Char م: 6.3702003998378665 %
|
||||
[ 4] Char و: 5.952637762007158 %
|
||||
[ 5] Char ر: 4.9419135883043985 %
|
||||
[ 6] Char ن: 4.900967992360486 %
|
||||
[ 7] Char ت: 4.229625100474721 %
|
||||
[ 8] Char ة: 3.6022506337636284 %
|
||||
[ 9] Char ب: 3.5434428650925054 %
|
||||
[10] Char ع: 3.3116468236247845 %
|
||||
[11] Char د: 3.1756195082406444 %
|
||||
[12] Char س: 2.5401383631379715 %
|
||||
[13] Char ف: 2.3899587109007343 %
|
||||
[14] Char ق: 2.010868445097864 %
|
||||
[15] Char أ: 1.8763525443291036 %
|
||||
[16] Char ه: 1.8663222473361318 %
|
||||
[17] Char ك: 1.8573911609725264 %
|
||||
[18] Char ح: 1.8431014227907585 %
|
||||
[19] Char ج: 1.3270220323030524 %
|
||||
[20] Char ط: 1.0305099650313618 %
|
||||
[21] Char ش: 0.9638703206260004 %
|
||||
[22] Char إ: 0.8946200509758929 %
|
||||
[23] Char ص: 0.8509264284585631 %
|
||||
[24] Char ى: 0.7726076711161797 %
|
||||
[25] Char خ: 0.717097534333157 %
|
||||
[26] Char ز: 0.6687322666410184 %
|
||||
[27] Char ث: 0.6549921337739336 %
|
||||
[28] Char ض: 0.5409490309771295 %
|
||||
[29] Char غ: 0.4574090231452538 %
|
||||
[30] Char ذ: 0.44765352880962356 %
|
||||
[31] Char ئ: 0.39269299734128427 %
|
||||
[32] Char ء: 0.295138053984982 %
|
||||
[33] Char ظ: 0.2397653185306302 %
|
||||
[34] Char آ: 0.12324899181775088 %
|
||||
[35] Char ؤ: 0.08491402111858422 %
|
||||
[36] Char ـ: 0.047678261048784344 %
|
||||
[37] Char a: 0.03311372020967443 %
|
||||
[38] Char e: 0.029403884335561525 %
|
||||
[39] Char i: 0.027205463076827956 %
|
||||
[40] Char o: 0.02432003517474014 %
|
||||
[41] Char t: 0.02349562720271505 %
|
||||
[42] Char r: 0.02294602188803166 %
|
||||
[43] Char n: 0.020472797971956388 %
|
||||
[44] Char s: 0.01799957405588112 %
|
||||
[45] Char l: 0.012915724895059736 %
|
||||
[46] Char h: 0.011816514265692949 %
|
||||
[47] Char d: 0.011129507622338709 %
|
||||
[48] Char پ: 0.010717303636326163 %
|
||||
[49] Char c: 0.009480691678288529 %
|
||||
[50] Char u: 0.007969277062909199 %
|
||||
[51] Char m: 0.007694474405567502 %
|
||||
[52] Char A: 0.006870066433542411 %
|
||||
[53] Char گ: 0.006595263776200715 %
|
||||
[54] Char f: 0.006183059790188171 %
|
||||
[55] Char S: 0.005770855804175626 %
|
||||
[56] Char y: 0.0054960531468339294 %
|
||||
[57] Char T: 0.0049464478321505365 %
|
||||
[58] Char b: 0.0048090465034796885 %
|
||||
[59] Char G: 0.0046716451748088405 %
|
||||
[60] Char I: 0.004396842517467144 %
|
||||
[61] Char C: 0.0042594411887962955 %
|
||||
[62] Char p: 0.0039846385314545995 %
|
||||
[63] Char k: 0.003709835874112903 %
|
||||
|
||||
The first 64 characters have an accumulated ratio of 0.999523217389512.
|
||||
|
||||
1479 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9696025116913417
|
||||
Next 512 (512-1024): 1.3740132867084825e-06
|
||||
Rest: 0.0012305764497782395
|
||||
|
||||
- Processing end: 2015-12-13 18:33:59.193909
|
||||
@@ -0,0 +1,157 @@
|
||||
= Logs of language model for Croatian (hr) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-25 23:41:35.999066
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Fizika čvrstog stanja (revision 4776646)
|
||||
Agregatno stanje (revision 4663090)
|
||||
Alnico (revision 3915185)
|
||||
Aluminij (revision 4772363)
|
||||
Amorfna tvar (revision 4659679)
|
||||
Antimon (revision 4420072)
|
||||
Antoine Henri Becquerel (revision 4634966)
|
||||
Apsolutna nula (revision 4706683)
|
||||
Arsen (revision 4540773)
|
||||
Arthur Holly Compton (revision 4736068)
|
||||
Atom (revision 4778162)
|
||||
Atomska jezgra (revision 4540956)
|
||||
Bell Labs (revision 4769518)
|
||||
Bor (element) (revision 4602837)
|
||||
Brian Josephson (revision 4403761)
|
||||
Cink (revision 4537854)
|
||||
Coulombov zakon (revision 4710338)
|
||||
Dijamant (revision 4625335)
|
||||
Dimenzija (revision 4669110)
|
||||
Dinastija Han (revision 4541686)
|
||||
Dislokacija (revision 4668021)
|
||||
EV (revision 4538157)
|
||||
Eksponencijalna funkcija (revision 4160157)
|
||||
Električna struja (revision 4280621)
|
||||
Električna vodljivost (revision 4460160)
|
||||
Električni izolator (revision 4649046)
|
||||
Električni luk (revision 4646980)
|
||||
Električni naboj (revision 4727496)
|
||||
Električni otpor (revision 4593314)
|
||||
Električni vodič (revision 4333008)
|
||||
Električno polje (revision 4705679)
|
||||
Elektrolit (revision 4486319)
|
||||
Elektromagnetsko zračenje (revision 4537368)
|
||||
Elektron (revision 4630705)
|
||||
Elektronika (revision 4090016)
|
||||
Elektronska konfiguracija (revision 4420620)
|
||||
Elektronski mikroskop (revision 4413214)
|
||||
Elektrotehnika (revision 4596912)
|
||||
Energetika (revision 4586277)
|
||||
Energija (revision 4719089)
|
||||
Fermi-Diracova statistika (revision 3934172)
|
||||
Feromagnetizam (revision 4760511)
|
||||
Fizika (revision 4769955)
|
||||
Fizika kondenzirane tvari (revision 4769955)
|
||||
Fizikalna veličina (revision 4621676)
|
||||
Fosfor (revision 4602427)
|
||||
Fotodioda (revision 3939069)
|
||||
Fotoelektrični učinak (revision 4704417)
|
||||
Foton (revision 4537522)
|
||||
Fotonaponski sustavi (revision 4418887)
|
||||
Francuski jezik (revision 4771366)
|
||||
Galij (revision 4537855)
|
||||
Genitiv (revision 4625199)
|
||||
Germanij (revision 4537856)
|
||||
Helij (revision 4747001)
|
||||
Henri (revision 3922500)
|
||||
Indij (revision 4537867)
|
||||
Integrirani krug (revision 4447159)
|
||||
Ion (revision 4549144)
|
||||
Ioniziranje (revision 4566703)
|
||||
Izolator (revision 4649046)
|
||||
John Bardeen (revision 4403736)
|
||||
Kadmij (revision 3921860)
|
||||
Kelvin (revision 4624351)
|
||||
Keramika (revision 4599177)
|
||||
Kinetička energija (revision 4719090)
|
||||
Klasična mehanika (revision 4637127)
|
||||
Kompas (revision 4702880)
|
||||
Kondenzacija (revision 4477825)
|
||||
Kondenzirana tvar (revision 4776646)
|
||||
Konstrukcija (revision 4680450)
|
||||
Kovalentna veza (revision 4641419)
|
||||
Kristal (revision 4720329)
|
||||
Kristalna rešetka (revision 4479184)
|
||||
Kristalografija (revision 4105956)
|
||||
Krutine (revision 4625162)
|
||||
Kubični kristalni sustav (revision 4344344)
|
||||
Kubični metar (revision 4616551)
|
||||
Kvantna mehanika (revision 4541215)
|
||||
Latinski jezik (revision 4760544)
|
||||
Luminiscencija (revision 4708222)
|
||||
Magnet (revision 4603344)
|
||||
Magnetizam (revision 4760040)
|
||||
Magnetska permeabilnost (revision 4675996)
|
||||
Magnetska vodljivost (revision 4736934)
|
||||
Magnetski moment (revision 4410235)
|
||||
Magnetsko polje (revision 4678057)
|
||||
Materijal (revision 4669230)
|
||||
Mehanika (revision 4698699)
|
||||
Metal (revision 4671710)
|
||||
Metan (revision 4422418)
|
||||
Metar (revision 4655527)
|
||||
Mjerna veličina (revision 4621676)
|
||||
Molekula (revision 4539232)
|
||||
Molekule (revision 4539232)
|
||||
Napon (revision 4585417)
|
||||
Niskotemperaturna fizika (revision 4657522)
|
||||
Njemački jezik (revision 4731246)
|
||||
Optika (revision 4768098)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-25 23:50:27.589690
|
||||
|
||||
49 characters appeared 500582 times.
|
||||
|
||||
First 31 characters:
|
||||
[ 0] Char a: 10.808019465342342 %
|
||||
[ 1] Char i: 10.18554402675286 %
|
||||
[ 2] Char e: 9.571259054460608 %
|
||||
[ 3] Char o: 8.468143081453189 %
|
||||
[ 4] Char n: 6.952906816465634 %
|
||||
[ 5] Char t: 5.369549843981606 %
|
||||
[ 6] Char r: 5.331993559496746 %
|
||||
[ 7] Char j: 5.102860270644969 %
|
||||
[ 8] Char s: 4.717109284792501 %
|
||||
[ 9] Char k: 4.013927788054705 %
|
||||
[10] Char l: 3.854713113935379 %
|
||||
[11] Char u: 3.786792173909569 %
|
||||
[12] Char m: 3.730058212240951 %
|
||||
[13] Char v: 3.0989927724129114 %
|
||||
[14] Char p: 2.67308852495695 %
|
||||
[15] Char d: 2.6135578186990345 %
|
||||
[16] Char z: 1.8931963194841206 %
|
||||
[17] Char g: 1.5665765049482403 %
|
||||
[18] Char č: 1.161048539500022 %
|
||||
[19] Char b: 1.1440683044935693 %
|
||||
[20] Char c: 1.007627122029957 %
|
||||
[21] Char h: 0.8006680224219008 %
|
||||
[22] Char f: 0.5159993767254915 %
|
||||
[23] Char š: 0.422907735395999 %
|
||||
[24] Char ž: 0.3611795869607777 %
|
||||
[25] Char ć: 0.34959307366225717 %
|
||||
[26] Char đ: 0.2195444502598975 %
|
||||
[27] Char y: 0.11306838839590717 %
|
||||
[28] Char w: 0.07291512679241363 %
|
||||
[29] Char x: 0.04534721584076135 %
|
||||
[30] Char q: 0.02477116636235422 %
|
||||
|
||||
The first 31 characters have an accumulated ratio of 0.9997702674087363.
|
||||
|
||||
712 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9989731099787131
|
||||
Next 512 (512-1024): 1.9976747066414694e-06
|
||||
Rest: 3.7513395167998453e-17
|
||||
|
||||
- Processing end: 2016-09-25 23:50:27.987029
|
||||
@@ -0,0 +1,161 @@
|
||||
= Logs of language model for Czech (cs) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-21 03:20:56.824516
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Sociální fobie (revision 13567590)
|
||||
Adaptace (revision 13991192)
|
||||
Agorafobie (revision 13013445)
|
||||
Alkoholismus (revision 13822064)
|
||||
Alprazolam (revision 14082425)
|
||||
Antidepresivum (revision 14113423)
|
||||
Asertivita (revision 14111958)
|
||||
Atenolol (revision 12051880)
|
||||
Automatické negativní myšlenky (revision 13567590)
|
||||
Benzodiazepin (revision 13947546)
|
||||
Beta-blokátory (revision 13428762)
|
||||
Blud (revision 13888988)
|
||||
Bohatství (revision 13556478)
|
||||
Bupropion (revision 13686045)
|
||||
Citaloparam (revision 13567590)
|
||||
Clonazepan (revision 13567590)
|
||||
Crohnova nemoc (revision 13745254)
|
||||
Deprese (psychologie) (revision 13695735)
|
||||
Diagnostický a statický manuál mentálních poruch (revision 13567590)
|
||||
Diagnostický a statistický manuál mentálních poruch (revision 13714660)
|
||||
Diagnóza (medicína) (revision 13052239)
|
||||
Dichotomické myšlení (revision 13567590)
|
||||
Digital object identifier (revision 14138049)
|
||||
Dopamin (revision 13714274)
|
||||
Dystymie (revision 13567267)
|
||||
Důkaz kruhem (revision 13190761)
|
||||
Elektivní mutismus (revision 9940891)
|
||||
Emoce (revision 14110033)
|
||||
Escitalopram (revision 12954987)
|
||||
Evoluce (revision 13951488)
|
||||
Expozice (psychologie) (revision 14119474)
|
||||
Extraverze a introverze (revision 13872996)
|
||||
Fluoxetin (revision 12955006)
|
||||
Fluvoxamin (revision 12955006)
|
||||
Gen (revision 13907182)
|
||||
Generalizovaná úzkostná porucha (revision 14006709)
|
||||
Halucinaci (revision 12188143)
|
||||
Hněv (revision 14057864)
|
||||
Inteligence (revision 14009781)
|
||||
International Standard Serial Number (revision 12869806)
|
||||
Interpersonální psychoterapie (revision 13567590)
|
||||
Iracionalita (revision 4765977)
|
||||
Ján Praško Pavlov (revision 14086840)
|
||||
Klinické testování (revision 13530979)
|
||||
Kognitivní omyl (revision 13107294)
|
||||
Kognitivní psychologie (revision 11629465)
|
||||
Kognitivní restrukturalizace (revision 13567360)
|
||||
Kognitivně behaviorální terapie (revision 13980494)
|
||||
Komorbidita (revision 11351714)
|
||||
Lymská borelióza (revision 14068446)
|
||||
Malé sebevědomí (revision 13567590)
|
||||
Medical Subject Headings (revision 12239331)
|
||||
Meditace (revision 13180783)
|
||||
Mentální černý filtr (revision 13567590)
|
||||
Mezinárodní klasifikace nemocí (revision 12531067)
|
||||
Michael Liebowitz (revision 13567590)
|
||||
Moclobemid (revision 13567590)
|
||||
Moritova terapie (revision 11960292)
|
||||
Musturbace (revision 13567590)
|
||||
Nervozita (revision 13847097)
|
||||
Noradrenalin (revision 14054165)
|
||||
Obsedantně kompulzivní porucha (revision 13950365)
|
||||
Panická ataka (revision 13253537)
|
||||
Panická porucha (revision 13253537)
|
||||
Paranoia (revision 14027052)
|
||||
Paroxetin (revision 12955006)
|
||||
Pohlavnost (revision 13564689)
|
||||
Porucha (revision 11039108)
|
||||
Pravděpodobnost (revision 13596041)
|
||||
Predestinace (revision 12467403)
|
||||
Profese (revision 13975485)
|
||||
Propanolol (revision 12972658)
|
||||
Psychiatr (revision 12767960)
|
||||
Psychické trauma (revision 11227535)
|
||||
Psychoaktivní droga (revision 13939232)
|
||||
Psychodynamická léčba (revision 13567590)
|
||||
Psychofarmaka (revision 9928215)
|
||||
Psycholog (revision 12358728)
|
||||
Psychoterapie (revision 13874178)
|
||||
Puberta (revision 12540014)
|
||||
RIMA (revision 10234728)
|
||||
Remise (revision 9896748)
|
||||
Richard Heimberg (revision 13567590)
|
||||
Rámování myšlenek (revision 13567590)
|
||||
Schizofrenie (revision 13977456)
|
||||
Sebevražda (revision 14053884)
|
||||
Selektivní abstrakce (revision 13567590)
|
||||
Selektivní inhibitor zpětného vychytávání serotoninu (revision 12955027)
|
||||
Serotonin (revision 13975104)
|
||||
Sertralin (revision 12955006)
|
||||
Skupinová terapie (revision 11964235)
|
||||
Sociální chování (revision 13507313)
|
||||
Sociální dovednost (revision 12226347)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-21 03:28:11.731386
|
||||
|
||||
47 characters appeared 594800 times.
|
||||
|
||||
First 41 characters:
|
||||
[ 0] Char o: 8.323806321452588 %
|
||||
[ 1] Char e: 8.040013449899126 %
|
||||
[ 2] Char n: 6.895595158036315 %
|
||||
[ 3] Char a: 6.263113651647613 %
|
||||
[ 4] Char i: 5.650470746469401 %
|
||||
[ 5] Char t: 5.40383322125084 %
|
||||
[ 6] Char s: 4.588937457969065 %
|
||||
[ 7] Char v: 3.8685272360457295 %
|
||||
[ 8] Char p: 3.6914929388029587 %
|
||||
[ 9] Char r: 3.6302958977807664 %
|
||||
[10] Char l: 3.6017148621385338 %
|
||||
[11] Char í: 3.5733019502353733 %
|
||||
[12] Char k: 3.301950235373235 %
|
||||
[13] Char u: 3.1782111634162744 %
|
||||
[14] Char c: 3.1383658372562206 %
|
||||
[15] Char d: 3.120208473436449 %
|
||||
[16] Char m: 2.758406186953598 %
|
||||
[17] Char h: 2.2747141896435776 %
|
||||
[18] Char á: 2.156186953597848 %
|
||||
[19] Char z: 2.0260591795561536 %
|
||||
[20] Char y: 1.9894082044384667 %
|
||||
[21] Char j: 1.8979488903833224 %
|
||||
[22] Char b: 1.8189307330195021 %
|
||||
[23] Char ě: 1.277236045729657 %
|
||||
[24] Char é: 1.2291526563550772 %
|
||||
[25] Char č: 0.9502353732347008 %
|
||||
[26] Char ž: 0.9214862138533961 %
|
||||
[27] Char ř: 0.8955951580363146 %
|
||||
[28] Char ý: 0.7646267652992602 %
|
||||
[29] Char š: 0.6605581708137189 %
|
||||
[30] Char f: 0.6260928043039677 %
|
||||
[31] Char ů: 0.5016812373907196 %
|
||||
[32] Char g: 0.47041022192333554 %
|
||||
[33] Char ú: 0.19502353732347008 %
|
||||
[34] Char x: 0.13685272360457296 %
|
||||
[35] Char ň: 0.05447209145931405 %
|
||||
[36] Char w: 0.04488903833221251 %
|
||||
[37] Char ó: 0.03429724277067922 %
|
||||
[38] Char ť: 0.02269670477471419 %
|
||||
[39] Char ď: 0.012104909213180902 %
|
||||
[40] Char q: 0.007229320780094149 %
|
||||
|
||||
The first 41 characters have an accumulated ratio of 0.9999613315400132.
|
||||
|
||||
1025 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9786035192432675
|
||||
Next 512 (512-1024): 1.6812373907195695e-06
|
||||
Rest: 2.0246480655940202e-06
|
||||
|
||||
- Processing end: 2016-09-21 03:28:12.235582
|
||||
@@ -0,0 +1,256 @@
|
||||
= Logs of language model for Danish (da) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2022-11-30 19:37:01.097250
|
||||
- Maximum depth: 2
|
||||
- Max number of pages: 200
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Forside (revision 10000691)
|
||||
Hans Magnus Enzensberger (revision 11341046)
|
||||
28. november (revision 9410945)
|
||||
Golfkrigen (revision 11144370)
|
||||
29. november (revision 6877900)
|
||||
8. december (revision 10277754)
|
||||
Det Konservative Folkeparti (revision 11313857)
|
||||
1990 (revision 11340072)
|
||||
1940 (revision 11263756)
|
||||
Angolas håndboldlandshold (damer) (revision 11331888)
|
||||
Skjoldvulkan (revision 10870812)
|
||||
Casper & Mandrilaftalen (revision 11221713)
|
||||
26. november (revision 10617630)
|
||||
Døde i 2022 (revision 11343986)
|
||||
Vikingetidens rustning og våben (revision 11332607)
|
||||
Middelaldercentret (revision 11339897)
|
||||
Ruslands invasion af Ukraine 2022 (revision 11335164)
|
||||
Saddam Hussein (revision 11002258)
|
||||
The Jimi Hendrix Experience (revision 10497780)
|
||||
Færøerne (revision 11333678)
|
||||
27. november (revision 9745974)
|
||||
Thomas Vinterberg (revision 11234643)
|
||||
Anwar Ibrahim (revision 11342876)
|
||||
Mandatområdet i Palæstina (revision 11341286)
|
||||
Kunst (revision 11336917)
|
||||
Afrikamesterskabet i håndbold 2022 (kvinder) (revision 11341917)
|
||||
Dansk (sprog) (revision 11313509)
|
||||
Sergej Sjojgu (revision 11309097)
|
||||
Fernando Gomes (revision 11340427)
|
||||
Folketinget (revision 11330485)
|
||||
15. januar (revision 10515606)
|
||||
Rock and Roll Hall of Fame (revision 8408189)
|
||||
Thomas Edison (revision 11052704)
|
||||
Ukraine (revision 11334630)
|
||||
1947 (revision 11252357)
|
||||
1937 (revision 11303923)
|
||||
IC4 (revision 11317878)
|
||||
Jimi Hendrix (revision 11341476)
|
||||
Ismail Sabri Yaakob (revision 11105534)
|
||||
Okipa-ceremonien (revision 11340589)
|
||||
SI-præfiks (revision 11332802)
|
||||
Sporvejsmuseet Skjoldenæsholms historie (revision 11338275)
|
||||
Irak (revision 11255676)
|
||||
Woodstockfestivalen (revision 11226413)
|
||||
Nikolaj Lie Kaas (revision 11322663)
|
||||
Torben Rechendorff (revision 11342962)
|
||||
Folketingsvalget 2022 (revision 11339557)
|
||||
Kherson (revision 11314559)
|
||||
Keltere (revision 11318773)
|
||||
Little Richard (revision 11226619)
|
||||
Invasion (revision 10307980)
|
||||
Tate Gallery (revision 8312688)
|
||||
24. januar (revision 10441562)
|
||||
Hans Christian Ægidius (revision 9773029)
|
||||
Slaget ved Irpin (1321) (revision 11230064)
|
||||
Auschwitz (revision 11310714)
|
||||
Jazz fusion (revision 11223082)
|
||||
Lutsk (revision 11248429)
|
||||
Planetarium (revision 11266837)
|
||||
Bibliothèque nationale de France (revision 11055813)
|
||||
Digtsamling (revision 10585337)
|
||||
Kenneth Gøtterup (revision 11027437)
|
||||
Straf (revision 11007456)
|
||||
1716 (revision 11339928)
|
||||
Kamel (revision 11285016)
|
||||
Amnesti (revision 10831621)
|
||||
Zulu Royal (revision 10969220)
|
||||
Stephen Roche (revision 11239346)
|
||||
13. december (revision 10768225)
|
||||
Enhed (politisk parti) (revision 10158693)
|
||||
The Everly Brothers (revision 10865882)
|
||||
3. november (revision 9423371)
|
||||
Annelise Gotfredsen (revision 11306090)
|
||||
Virtual International Authority File (revision 8702589)
|
||||
Europæiske Fællesskab (revision 10868689)
|
||||
Væringer (revision 11331002)
|
||||
Rom (revision 11341285)
|
||||
Decentralisering (revision 11154770)
|
||||
Kreml (Moskva) (revision 11045482)
|
||||
Folketingsvalget 1994 (revision 11266325)
|
||||
28. december (revision 6878014)
|
||||
Østjyllands Storkreds (revision 11201505)
|
||||
Bruxelles (revision 10802416)
|
||||
Erik Haunstrup Clemmensen (revision 10627614)
|
||||
Hviderussere (revision 10750673)
|
||||
Hvidmelet Gåsefod (revision 11317723)
|
||||
Mario Draghi (revision 11302527)
|
||||
Folketingsvalget 1968 (revision 11300317)
|
||||
Skudår (revision 10360386)
|
||||
1921 (revision 11303917)
|
||||
Rundkørsel (revision 11103019)
|
||||
Valerij Zaluzjnyj (revision 11335164)
|
||||
Angrebet på Pearl Harbor (revision 11309782)
|
||||
Folketingsmedlemmer valgt i 2007 (revision 11187293)
|
||||
Ingeniørvidenskab (revision 9816520)
|
||||
Vikinger (revision 11327511)
|
||||
Martin Luther King (revision 11320659)
|
||||
1757 (revision 11186195)
|
||||
Dieseltogsæt (revision 8177984)
|
||||
El-værk (revision 11334293)
|
||||
Soul (revision 11283982)
|
||||
John McVie (revision 11040471)
|
||||
Botswanas håndboldlandshold (herrer) (revision 11333322)
|
||||
1971 (revision 11243510)
|
||||
Rana Hussein (revision 11266594)
|
||||
DR (revision 11342995)
|
||||
Ewan McGregor (revision 11331681)
|
||||
Eliane Paulo (revision 10589121)
|
||||
Zepto- (revision 11332802)
|
||||
København (revision 11336925)
|
||||
Gallien (revision 9984925)
|
||||
Augustoprøret (revision 11234324)
|
||||
1991 (revision 11250037)
|
||||
Afledte SI-enheder (revision 11097802)
|
||||
Gemeinsame Normdatei (revision 11281765)
|
||||
Litteraturvidenskab (revision 10931878)
|
||||
Thorvald Stauning (revision 11107677)
|
||||
Afrikamesterskabet i håndbold 2018 (mænd) (revision 11131830)
|
||||
Folkeforbundet (revision 11315450)
|
||||
Readymades (revision 10932287)
|
||||
Al Anbar (revision 9458175)
|
||||
2007 (revision 11250033)
|
||||
Varieté (revision 10934358)
|
||||
Damaskus (revision 11030795)
|
||||
Palæstina (revision 11311424)
|
||||
1569 (revision 10832219)
|
||||
Pædagog (revision 11251603)
|
||||
Carina Christensen (revision 11073847)
|
||||
Vest-Tyskland (revision 10580737)
|
||||
20. november (revision 6877846)
|
||||
Tessa Jowell (revision 11225831)
|
||||
Hillerød (revision 11317306)
|
||||
Påskekrisen (1920) (revision 11287865)
|
||||
Grad (vinkelmål) (revision 9624298)
|
||||
Kvinde (revision 11333939)
|
||||
1931 (revision 11236350)
|
||||
Afrikaans (revision 11080347)
|
||||
Den Store Danske Encyklopædi (revision 11301417)
|
||||
22. juni (revision 10375853)
|
||||
Automatic Train Control (revision 10619401)
|
||||
Luc Montagnier (revision 11162267)
|
||||
Reprise Records (revision 11081843)
|
||||
1966 (revision 11336105)
|
||||
Prosa (skriveform) (revision 11236012)
|
||||
Michael af Rumænien (revision 10819975)
|
||||
Mykolajiv (revision 11236676)
|
||||
Khmelnytskyj oblast (revision 11188686)
|
||||
Sierra Leones håndboldlandshold (herrer) (revision 11333322)
|
||||
1969 (revision 11340081)
|
||||
H. Edvard Hass (revision 10348478)
|
||||
Københavns Idrætspark (revision 9400386)
|
||||
Sanna Nielsen (revision 11315712)
|
||||
19. maj (revision 7148596)
|
||||
Patricia Schumann (revision 10952761)
|
||||
Torstenssonfejden (revision 11326728)
|
||||
International Standard Name Identifier (revision 10880739)
|
||||
Bent Mejding (revision 11335462)
|
||||
Afdeling Q (revision 11279134)
|
||||
Alfred Bindslev (revision 10398140)
|
||||
Sakser (revision 9042633)
|
||||
Folketingsmedlemmer valgt i 1998 (revision 11213304)
|
||||
1996 (revision 11229565)
|
||||
1 (tal) (revision 9378579)
|
||||
Farrah Fawcett (revision 10977527)
|
||||
Google+ (revision 10469085)
|
||||
1530 (revision 10865231)
|
||||
De største helte (revision 10737852)
|
||||
Afrikamesterskabet i håndbold 1974 (mænd) (revision 11018946)
|
||||
1902 (revision 11217211)
|
||||
ISO 639-3 (revision 10880691)
|
||||
1974 (revision 11336110)
|
||||
Dansk fonologi (revision 11226101)
|
||||
Europa (revision 11149054)
|
||||
Sovemedicin (revision 11327388)
|
||||
Slotsbryggen (Nykøbing Falster) (revision 11005548)
|
||||
Olieraffinaderi (revision 11322152)
|
||||
Slaget ved Stiklestad (revision 11261889)
|
||||
Rolling Stone (revision 11267586)
|
||||
Jørgen Hald (revision 10296412)
|
||||
Nikolaj Coster-Waldau (revision 11228953)
|
||||
Aserbajdsjan (revision 11297538)
|
||||
Kultstatus (revision 7820159)
|
||||
Al Kut (revision 9425606)
|
||||
Library of Congress Control Number (revision 8316539)
|
||||
Rwandas håndboldlandshold (herrer) (revision 11333322)
|
||||
Levon Helm (revision 11317127)
|
||||
Howard Hughes (revision 11040881)
|
||||
Wim Kieft (revision 10910953)
|
||||
Afrikamesterskabet i håndbold 2016 (mænd) (revision 11018957)
|
||||
24. februar (revision 10755036)
|
||||
Iværksætter (revision 10972242)
|
||||
1992 (revision 11303945)
|
||||
Internationalt Standardbognummer (revision 11037702)
|
||||
Afrikamesterskabet i håndbold 2014 (mænd) (revision 11018956)
|
||||
En mand kommer hjem (revision 10737861)
|
||||
Jamaica (revision 11243987)
|
||||
Henitjesk (revision 11328921)
|
||||
August (revision 11210562)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2022-11-30 19:41:17.518631
|
||||
|
||||
60 characters appeared 1532370 times.
|
||||
|
||||
First 31 characters:
|
||||
[ 0] Char e: 15.035728968852169 %
|
||||
[ 1] Char r: 8.617892545534042 %
|
||||
[ 2] Char n: 7.618264518360449 %
|
||||
[ 3] Char t: 6.856503324915001 %
|
||||
[ 4] Char a: 6.475133290262796 %
|
||||
[ 5] Char i: 6.3714377076032545 %
|
||||
[ 6] Char s: 6.279488635251278 %
|
||||
[ 7] Char d: 5.919523352715076 %
|
||||
[ 8] Char l: 5.094722553952375 %
|
||||
[ 9] Char o: 4.86860223053179 %
|
||||
[10] Char g: 3.8343872563414845 %
|
||||
[11] Char k: 3.3303314473658454 %
|
||||
[12] Char m: 3.2096034247603384 %
|
||||
[13] Char f: 2.608247355403721 %
|
||||
[14] Char v: 2.342188896937424 %
|
||||
[15] Char u: 1.9602967951604378 %
|
||||
[16] Char b: 1.9047619047619049 %
|
||||
[17] Char p: 1.5793183108518178 %
|
||||
[18] Char h: 1.45728512043436 %
|
||||
[19] Char ø: 0.8954103773892728 %
|
||||
[20] Char æ: 0.7449897870618715 %
|
||||
[21] Char å: 0.7295235484902471 %
|
||||
[22] Char y: 0.6777736447463732 %
|
||||
[23] Char j: 0.666418684782396 %
|
||||
[24] Char c: 0.5946344551250677 %
|
||||
[25] Char w: 0.12248999915164091 %
|
||||
[26] Char z: 0.06571519933175407 %
|
||||
[27] Char x: 0.045354581465311905 %
|
||||
[28] Char é: 0.021926819240783886 %
|
||||
[29] Char ó: 0.009592983417842949 %
|
||||
[30] Char q: 0.009397208246050236 %
|
||||
|
||||
The first 31 characters have an accumulated ratio of 0.9994694492844417.
|
||||
|
||||
1065 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9958348814328518
|
||||
Next 512 (512-1024): 2.6103356239028435e-06
|
||||
Rest: 3.268948339453948e-05
|
||||
|
||||
- Processing end: 2022-11-30 19:41:17.605842
|
||||
@@ -0,0 +1,110 @@
|
||||
= Logs of language model for Esperanto (eo) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2015-12-04 01:22:51.466573
|
||||
- Maximum depth: 3
|
||||
- Max number of pages: 50
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Vikipedio:Ĉefpaĝo (revision 5524911)
|
||||
10-a de novembro (revision 5792999)
|
||||
12-a de novembro (revision 5793854)
|
||||
13-a de novembro (revision 5795088)
|
||||
18-a de novembro (revision 5796972)
|
||||
2-a de novembro (revision 5772615)
|
||||
20-a de novembro (revision 5799664)
|
||||
2015 (revision 5791963)
|
||||
22-a de novembro (revision 5799355)
|
||||
24-a de novembro (revision 5800563)
|
||||
4-a de decembro (revision 5806422)
|
||||
4-a de novembro (revision 5789811)
|
||||
5-a de novembro (revision 5789774)
|
||||
6-a de novembro (revision 5790336)
|
||||
7-a de novembro (revision 5791066)
|
||||
8-a de novembro (revision 5791337)
|
||||
9-a de novembro (revision 5791916)
|
||||
A Night at the Opera (Queen) (revision 5184272)
|
||||
Abdelhamid Abaaoud (revision 5800134)
|
||||
André Glucksmann (revision 5792591)
|
||||
Anglio (revision 5693468)
|
||||
Argentino (revision 5804665)
|
||||
Atencoj de novembro 2015 en Parizo (revision 5800135)
|
||||
Aung San Suu Kyi (revision 5791362)
|
||||
Austin FX4 (revision 5583207)
|
||||
Azilo (revision 5751210)
|
||||
Aŭstrio (revision 5804014)
|
||||
Bahio (revision 5773065)
|
||||
Bamako (revision 5798202)
|
||||
Bataclan (revision 5795605)
|
||||
Bejruto (revision 5774306)
|
||||
Birmo (revision 5790386)
|
||||
Blonda (revision 5441229)
|
||||
Bohemian rhapsody (revision 5654078)
|
||||
Cayetano Redondo (revision 5591025)
|
||||
Ciro la 2-a (revision 5774667)
|
||||
DJ Abdel (revision 5628860)
|
||||
Daniela Mercury (revision 5764721)
|
||||
Decembro de 2015 (revision 5626904)
|
||||
Dilatkoeficiento (revision 5806460)
|
||||
Eksproprietigo (revision 5586845)
|
||||
Elektroniko (revision 5788966)
|
||||
Elle s'appelait Sarah (filmo) (revision 5475154)
|
||||
Esperanto (revision 5804190)
|
||||
Federaciero (revision 5696168)
|
||||
Fondaĵo Vikimedio (revision 5772681)
|
||||
Francio (revision 5759775)
|
||||
François Hollande (revision 5627721)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2015-12-04 01:27:38.176708
|
||||
|
||||
56 characters appeared 342524 times.
|
||||
|
||||
First 35 characters:
|
||||
[ 0] Char a: 12.557952143499435 %
|
||||
[ 1] Char o: 9.84719318938235 %
|
||||
[ 2] Char e: 9.10242785906973 %
|
||||
[ 3] Char i: 8.362333734278474 %
|
||||
[ 4] Char n: 7.6359612757062285 %
|
||||
[ 5] Char r: 6.630192336887342 %
|
||||
[ 6] Char t: 5.70821314710794 %
|
||||
[ 7] Char l: 5.610409781504361 %
|
||||
[ 8] Char s: 5.004320865107262 %
|
||||
[ 9] Char k: 3.8855671427403626 %
|
||||
[10] Char d: 3.7194473963868226 %
|
||||
[11] Char j: 3.28531723324497 %
|
||||
[12] Char u: 2.8465158645817517 %
|
||||
[13] Char m: 2.787833845219605 %
|
||||
[14] Char p: 2.6582078920017285 %
|
||||
[15] Char g: 1.6825098387266293 %
|
||||
[16] Char v: 1.4048650605505015 %
|
||||
[17] Char c: 1.3823848839789328 %
|
||||
[18] Char b: 1.1406499982482978 %
|
||||
[19] Char f: 1.077296773364786 %
|
||||
[20] Char z: 0.7342551178895493 %
|
||||
[21] Char h: 0.6735294461118053 %
|
||||
[22] Char ĝ: 0.53572888323154 %
|
||||
[23] Char ŭ: 0.4268314045147202 %
|
||||
[24] Char ĉ: 0.33545094650301877 %
|
||||
[25] Char y: 0.17079095187490512 %
|
||||
[26] Char ŝ: 0.15327393116978666 %
|
||||
[27] Char w: 0.1442234704721421 %
|
||||
[28] Char ĵ: 0.1039343228503696 %
|
||||
[29] Char á: 0.0814541462788009 %
|
||||
[30] Char ó: 0.05430276418586727 %
|
||||
[31] Char é: 0.053718863495696656 %
|
||||
[32] Char q: 0.04350060141771087 %
|
||||
[33] Char x: 0.040873048311943105 %
|
||||
[34] Char ĥ: 0.03824549520617533 %
|
||||
|
||||
The first 35 characters have an accumulated ratio of 0.9991971365510156.
|
||||
|
||||
989 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9942980632768038
|
||||
Next 512 (512-1024): 0.0015327393116978665
|
||||
Rest: -5.0306980803327406e-17
|
||||
|
||||
- Processing end: 2015-12-04 01:27:38.307198
|
||||
@@ -0,0 +1,159 @@
|
||||
= Logs of language model for Estonian (et) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-26 23:45:22.351942
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Harilik pohl (revision 4248853)
|
||||
A-vitamiin (revision 4330862)
|
||||
Aasta keskmine sademete hulk (revision 4266801)
|
||||
Aasta keskmine õhutemperatuur (revision 3902142)
|
||||
Ahm (revision 4343671)
|
||||
Ain Raal (revision 4464651)
|
||||
Alalehed (revision 2892741)
|
||||
Alamliik (revision 3522810)
|
||||
Alaska (revision 4216575)
|
||||
Aleksander Heintalu (revision 4445156)
|
||||
Aleuudid (revision 4335893)
|
||||
Ameerika jänes (revision 4325220)
|
||||
Ameerika valgejänes (revision 4355263)
|
||||
Anneli Sihvart (revision 4211078)
|
||||
Arbutiin (revision 4451788)
|
||||
Baribal (revision 4268462)
|
||||
Bensoehape (revision 3810308)
|
||||
Binaarne nomenklatuur (revision 3970950)
|
||||
C-vitamiin (revision 4444353)
|
||||
Droog (revision 4352968)
|
||||
E-vitamiin (revision 4336726)
|
||||
Eesti (revision 4474984)
|
||||
Eesti Entsüklopeediakirjastus (revision 4012421)
|
||||
Eesti köök (revision 4314947)
|
||||
Ellips (revision 4272113)
|
||||
Emakakael (botaanika) (revision 3521516)
|
||||
Euraasia (revision 3710768)
|
||||
Fenoloogia (revision 3512905)
|
||||
Folaadid (revision 4266628)
|
||||
Fosfor (revision 4270122)
|
||||
Fotosüntees (revision 4380600)
|
||||
Fruktoos (revision 4285660)
|
||||
Glükoos (revision 4047315)
|
||||
Gneiss (revision 4333338)
|
||||
Graniit (revision 4435351)
|
||||
Gröönimaa (revision 4331557)
|
||||
Halljänes (revision 4051603)
|
||||
Haned (revision 4127680)
|
||||
Happeline keskkond (revision 2966453)
|
||||
Heilongjiang (revision 4342364)
|
||||
Hendrik Relve (revision 4342591)
|
||||
Hiina (revision 4448121)
|
||||
Holland (revision 4307885)
|
||||
Hunt (revision 4427752)
|
||||
Hõimkond (revision 3489569)
|
||||
Hüdrofiilsus (revision 4309797)
|
||||
Ida-Euroopa (revision 4337624)
|
||||
Ida-sinilind (revision 4248853)
|
||||
Ida-vöötorav (revision 3520679)
|
||||
Igihaljus (revision 3536500)
|
||||
Ilves (revision 4404632)
|
||||
Imetaja (revision 4289188)
|
||||
Indiaanlased (revision 4479868)
|
||||
Indrek Rohtmets (revision 4218674)
|
||||
Itaalia (revision 4404119)
|
||||
Jaapan (revision 4465542)
|
||||
Jilin (revision 3894473)
|
||||
Jood (revision 4025060)
|
||||
Juurestik (revision 3341159)
|
||||
Jääkaru (revision 4372399)
|
||||
Jõhvikas (revision 4391549)
|
||||
Kaalium (revision 4486067)
|
||||
Kaheidulehelised (revision 4031352)
|
||||
Kaheli õiekate (revision 3063362)
|
||||
Kahesuguline õis (revision 3383221)
|
||||
Kaitsestaatus (revision 3527096)
|
||||
Kajakas (revision 4456839)
|
||||
Kalorsus (revision 3843290)
|
||||
Kaltsium (revision 4339861)
|
||||
Kanada (revision 4434682)
|
||||
Kanalised (revision 3616579)
|
||||
Kanarbikulaadsed (revision 4318215)
|
||||
Kanarbikulised (revision 3534760)
|
||||
Karboksüülhapped (revision 3659011)
|
||||
Karoteen (revision 4347634)
|
||||
Kasvuperiood (revision 4231717)
|
||||
Katteseemnetaimed (revision 4176294)
|
||||
Kaukasus (revision 4476003)
|
||||
Kesk-Euroopa (revision 3580746)
|
||||
Kimalane (revision 4261145)
|
||||
Kiudained (toit) (revision 3538655)
|
||||
Klass (bioloogia) (revision 3489567)
|
||||
Kliima (revision 4160781)
|
||||
Korea (revision 4329396)
|
||||
Kroom (revision 4030460)
|
||||
Kroonlehed (revision 3543291)
|
||||
Kuusepüü (revision 4028988)
|
||||
Kvertsetiin (revision 4448461)
|
||||
Laanemets (revision 4001157)
|
||||
Laanepüü (revision 4475093)
|
||||
Laiuskraad (revision 3990366)
|
||||
Leesikas (revision 4420533)
|
||||
Lehed (revision 4471821)
|
||||
Leheroots (revision 3595351)
|
||||
Liik (bioloogia) (revision 4320981)
|
||||
Liiv (revision 4399494)
|
||||
Liivakivi (revision 4330598)
|
||||
Linnaeus (revision 4276836)
|
||||
Linnud (revision 4479668)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-26 23:47:54.476445
|
||||
|
||||
55 characters appeared 433559 times.
|
||||
|
||||
First 33 characters:
|
||||
[ 0] Char a: 12.486881831538499 %
|
||||
[ 1] Char i: 10.26503889897338 %
|
||||
[ 2] Char e: 10.177622884082673 %
|
||||
[ 3] Char s: 8.710233209320991 %
|
||||
[ 4] Char t: 6.56634967789851 %
|
||||
[ 5] Char l: 6.051540851418146 %
|
||||
[ 6] Char u: 5.423944607308348 %
|
||||
[ 7] Char n: 5.131020230233947 %
|
||||
[ 8] Char k: 4.663033174262327 %
|
||||
[ 9] Char o: 4.526950195936424 %
|
||||
[10] Char d: 4.167368224393911 %
|
||||
[11] Char r: 3.6740097656835635 %
|
||||
[12] Char m: 3.552688330769284 %
|
||||
[13] Char v: 2.4700213811730354 %
|
||||
[14] Char p: 1.9229216784797456 %
|
||||
[15] Char g: 1.865259399528092 %
|
||||
[16] Char h: 1.8043680329551455 %
|
||||
[17] Char j: 1.6860450365463524 %
|
||||
[18] Char ä: 1.0247740215287884 %
|
||||
[19] Char b: 0.9255949017319443 %
|
||||
[20] Char õ: 0.9246723052687178 %
|
||||
[21] Char ü: 0.6536595941959457 %
|
||||
[22] Char f: 0.37342091849090897 %
|
||||
[23] Char c: 0.34851081398379463 %
|
||||
[24] Char ö: 0.24333481717597835 %
|
||||
[25] Char y: 0.1287022066200909 %
|
||||
[26] Char x: 0.06781084004714467 %
|
||||
[27] Char w: 0.04082489349777078 %
|
||||
[28] Char q: 0.020989069538401926 %
|
||||
[29] Char š: 0.018913227496142396 %
|
||||
[30] Char z: 0.017529332801302706 %
|
||||
[31] Char ō: 0.010379210211297655 %
|
||||
[32] Char ž: 0.009687262863877812 %
|
||||
|
||||
The first 33 characters have an accumulated ratio of 0.9995410082595447.
|
||||
|
||||
853 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9972721312183132
|
||||
Next 512 (512-1024): 9.687262863877811e-05
|
||||
Rest: -5.204170427930421e-18
|
||||
|
||||
- Processing end: 2016-09-26 23:47:54.561846
|
||||
@@ -0,0 +1,156 @@
|
||||
= Logs of language model for Finnish (fi) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-21 18:12:24.181917
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Yhdistynyt kuningaskunta (revision 15843357)
|
||||
1. toukokuuta (revision 15910178)
|
||||
1700-luku (revision 15493702)
|
||||
1707 (revision 15106709)
|
||||
1800-luku (revision 15708929)
|
||||
2014 (revision 15891601)
|
||||
409 (revision 12809782)
|
||||
5. marraskuuta (revision 15421719)
|
||||
927 (revision 12785964)
|
||||
Aasia (revision 15948161)
|
||||
Abhasia (revision 15730328)
|
||||
Adolf Hitler (revision 15951829)
|
||||
Afrikka (revision 15934209)
|
||||
Agatha Christie (revision 15760740)
|
||||
Aikavyöhyke (revision 15800313)
|
||||
Ajoneuvon kansallisuustunnus (revision 15897445)
|
||||
Akrotiri ja Dhekelia (revision 14625383)
|
||||
Alamaat (revision 15913741)
|
||||
Alan Turing (revision 15904871)
|
||||
Alankomaat (revision 15936643)
|
||||
Albania (revision 15767604)
|
||||
Alec Guinness (revision 15363805)
|
||||
Alexander Fleming (revision 15023225)
|
||||
Alfred Hitchcock (revision 15892843)
|
||||
Alfred Tennyson (revision 15856114)
|
||||
Allen Jones (revision 12871703)
|
||||
Andorra (revision 15913862)
|
||||
Andrew Lloyd Webber (revision 14978349)
|
||||
Anglit (revision 15902350)
|
||||
Anguilla (revision 15854041)
|
||||
Anne Brontë (revision 14287992)
|
||||
Anthony Eden (revision 14391831)
|
||||
Antigua ja Barbuda (revision 15196967)
|
||||
Arabian Lawrence (revision 15736417)
|
||||
Argentiina (revision 15676474)
|
||||
Armenia (revision 15634470)
|
||||
Arthur Conan Doyle (revision 15402837)
|
||||
Arts and Crafts (revision 15806930)
|
||||
Aurinko (revision 15934252)
|
||||
Australia (revision 15934255)
|
||||
Avara luonto (revision 15815943)
|
||||
Azerbaidžan (revision 15946891)
|
||||
BBC (revision 15866026)
|
||||
BKT (revision 15656549)
|
||||
Bahama (revision 15516869)
|
||||
Bangladesh (revision 15883994)
|
||||
Bank of England (revision 14481173)
|
||||
Barbados (revision 15839821)
|
||||
Barbara Hepworth (revision 15106880)
|
||||
Bath (revision 15869900)
|
||||
Beatrix Potter (revision 15057380)
|
||||
Belfast (revision 15715934)
|
||||
Belgia (revision 15932391)
|
||||
Belize (revision 15665086)
|
||||
Ben Nevis (revision 15610196)
|
||||
Bengalin kieli (revision 15551820)
|
||||
Benjamin Britten (revision 15081615)
|
||||
Bermuda (revision 15632621)
|
||||
Bertrand Russell (revision 14631969)
|
||||
Bhutan (revision 15377394)
|
||||
Big Ben (revision 14897401)
|
||||
Big Brother (revision 14641391)
|
||||
Birmingham (revision 15855259)
|
||||
Black Sabbath (revision 15839917)
|
||||
Bosnia ja Hertsegovina (revision 15934266)
|
||||
Botswana (revision 15524955)
|
||||
Bristol (revision 15891889)
|
||||
Bristolin kanaali (revision 15849713)
|
||||
Bristolin kansainvälinen lentoasema (revision 14452870)
|
||||
Britannia (provinssi) (revision 14557442)
|
||||
Britannian avoin golfturnaus (revision 14293265)
|
||||
Britannian kuninkaallinen perhe (revision 15522149)
|
||||
Britannian talous (revision 15470242)
|
||||
Britannian väestö (revision 15661241)
|
||||
Brittein saaret (revision 15805422)
|
||||
Brittiläinen Antarktiksen alue (revision 15836227)
|
||||
Brittiläinen Intia (revision 15593126)
|
||||
Brittiläinen Intian valtameren alue (revision 14272903)
|
||||
Brittiläinen imperiumi (revision 15906600)
|
||||
Brittiläinen kansainyhteisö (revision 15894379)
|
||||
Brittiläinen keittiö (revision 13393533)
|
||||
Brittiläinen kulttuuri (revision 15951407)
|
||||
Brittiläiset Neitsytsaaret (revision 15910520)
|
||||
Brittiläiset merentakaiset alueet (revision 15836213)
|
||||
Brunei (revision 15580824)
|
||||
Bruttokansantuote (revision 15656549)
|
||||
Bulgaria (revision 15944101)
|
||||
Burma (revision 15627218)
|
||||
Cambridge (revision 14641664)
|
||||
Cambridgen yliopisto (revision 15493340)
|
||||
Canterburyn tarinoita (revision 15232140)
|
||||
Cardiff (revision 15840398)
|
||||
Caymansaaret (revision 15914575)
|
||||
Channel 4 (revision 15882475)
|
||||
Charles Babbage (revision 15203616)
|
||||
Charles Chaplin (revision 15674652)
|
||||
Charles Darwin (revision 15894085)
|
||||
Charles Dickens (revision 15699592)
|
||||
Charles Dickensin joulutarina (revision 15116247)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-21 18:15:05.189221
|
||||
|
||||
61 characters appeared 940364 times.
|
||||
|
||||
First 30 characters:
|
||||
[ 0] Char a: 12.508773198463574 %
|
||||
[ 1] Char i: 10.969475649854738 %
|
||||
[ 2] Char n: 8.815841525196626 %
|
||||
[ 3] Char t: 8.80169806585535 %
|
||||
[ 4] Char e: 7.8206949649284745 %
|
||||
[ 5] Char s: 7.595782058862313 %
|
||||
[ 6] Char l: 5.963541777439374 %
|
||||
[ 7] Char o: 5.439808414613916 %
|
||||
[ 8] Char u: 5.0102938861972595 %
|
||||
[ 9] Char k: 4.589712068943515 %
|
||||
[10] Char r: 3.1231523112326713 %
|
||||
[11] Char ä: 3.041800834570443 %
|
||||
[12] Char m: 3.0392486313810396 %
|
||||
[13] Char v: 2.156292669647073 %
|
||||
[14] Char h: 1.996141919512019 %
|
||||
[15] Char j: 1.9248929138078446 %
|
||||
[16] Char p: 1.6324529650220552 %
|
||||
[17] Char y: 1.6323466232224966 %
|
||||
[18] Char d: 1.1981530556252684 %
|
||||
[19] Char b: 0.6835650875618378 %
|
||||
[20] Char g: 0.5793501239945382 %
|
||||
[21] Char c: 0.5056552569005194 %
|
||||
[22] Char ö: 0.38931732818355447 %
|
||||
[23] Char f: 0.215023118707224 %
|
||||
[24] Char w: 0.2106631049253268 %
|
||||
[25] Char z: 0.06593191572625068 %
|
||||
[26] Char x: 0.024458613898447838 %
|
||||
[27] Char š: 0.010421496356729947 %
|
||||
[28] Char ž: 0.007869293167326695 %
|
||||
[29] Char q: 0.007762951367768225 %
|
||||
|
||||
The first 30 characters have an accumulated ratio of 0.9996012182516557.
|
||||
|
||||
919 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9985378147555799
|
||||
Next 512 (512-1024): 1.0634179955846884e-06
|
||||
Rest: 3.881443777498106e-17
|
||||
|
||||
- Processing end: 2016-09-21 18:15:05.307164
|
||||
@@ -0,0 +1,116 @@
|
||||
= Logs of language model for French (fr) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2015-12-03 21:07:37.508739
|
||||
- Maximum depth: 2
|
||||
- Max number of pages: 50
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Wikipédia:Accueil_principal (revision 115957655)
|
||||
Bœuf (animal) (revision 115500130)
|
||||
1500 av. J.-C. (revision 110583603)
|
||||
1898 dans les chemins de fer (revision 106801806)
|
||||
1913 dans les chemins de fer (revision 112852042)
|
||||
1974 dans les chemins de fer (revision 90170756)
|
||||
1er décembre (revision 121012781)
|
||||
2009 dans les chemins de fer (revision 107042206)
|
||||
2011 dans les chemins de fer (revision 109560866)
|
||||
24 novembre (revision 120782024)
|
||||
26 novembre (revision 120833172)
|
||||
29 novembre (revision 120918160)
|
||||
2 décembre (revision 121025437)
|
||||
30 novembre (revision 120947714)
|
||||
3 décembre (revision 121030621)
|
||||
Amphibien (revision 120332329)
|
||||
Angleterre (revision 120784240)
|
||||
Anne-Josèphe Théroigne de Méricourt (revision 121009789)
|
||||
Années 1930 (revision 120558236)
|
||||
Antonio Troyo Calderón (revision 121028881)
|
||||
António Costa (revision 120993829)
|
||||
Attentat du 24 novembre 2015 à Tunis (revision 121015161)
|
||||
Balard (métro de Paris) (revision 118979088)
|
||||
Bois de Vincennes (revision 120822909)
|
||||
Buse à tête blanche (revision 121009499)
|
||||
Californie (revision 120922479)
|
||||
Charenton-le-Pont (revision 120210025)
|
||||
Charenton - Écoles (métro de Paris) (revision 108644873)
|
||||
Chronique médiévale (revision 100253272)
|
||||
Concorde (métro de Paris) (revision 120856751)
|
||||
Conférence de Paris de 2015 sur le climat (revision 121029398)
|
||||
Crise de la dette publique grecque (revision 120905208)
|
||||
Crise entre la Colombie et le Venezuela de 2015 (revision 120857143)
|
||||
Crise migratoire en Europe (revision 121002308)
|
||||
Crise russo-turque de 2015 (revision 121030214)
|
||||
Créteil (revision 120684618)
|
||||
Créteil - Préfecture (métro de Paris) (revision 113486387)
|
||||
Deuxième guerre civile libyenne (revision 121027704)
|
||||
Devise (monnaie) (revision 121015771)
|
||||
Droits de tirage spéciaux (revision 121009135)
|
||||
Décembre 2015 (revision 121010045)
|
||||
Département français (revision 120993190)
|
||||
Eldar Riazanov (revision 120996396)
|
||||
Enfants verts de Woolpit (revision 121002303)
|
||||
Ernst Larsen (revision 121026772)
|
||||
Fatima Mernissi (revision 120992271)
|
||||
Fejervarya cancrivora (revision 120353807)
|
||||
Fonds monétaire international (revision 120754406)
|
||||
Français (revision 120883858)
|
||||
Freyja (revision 121028677)
|
||||
Fusillade du 2 décembre 2015 en Californie (revision 121030353)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2015-12-03 21:10:27.682316
|
||||
|
||||
56 characters appeared 728239 times.
|
||||
|
||||
First 38 characters:
|
||||
[ 0] Char e: 14.339660468609894 %
|
||||
[ 1] Char s: 7.954806045817375 %
|
||||
[ 2] Char a: 7.864176458552756 %
|
||||
[ 3] Char n: 7.572102015959047 %
|
||||
[ 4] Char i: 7.34154583866011 %
|
||||
[ 5] Char r: 7.020222756540091 %
|
||||
[ 6] Char t: 6.833608197308851 %
|
||||
[ 7] Char l: 5.9446143367768 %
|
||||
[ 8] Char o: 5.386418469760614 %
|
||||
[ 9] Char u: 5.024861343597363 %
|
||||
[10] Char d: 4.169235649285468 %
|
||||
[11] Char c: 3.4240132703686568 %
|
||||
[12] Char p: 2.8882001650557028 %
|
||||
[13] Char m: 2.803063280049544 %
|
||||
[14] Char é: 2.498355622261373 %
|
||||
[15] Char g: 1.277739862874688 %
|
||||
[16] Char v: 1.1729665672945284 %
|
||||
[17] Char f: 1.1614318925517584 %
|
||||
[18] Char b: 0.9925312981040565 %
|
||||
[19] Char h: 0.8580974103282026 %
|
||||
[20] Char q: 0.7740590657737364 %
|
||||
[21] Char x: 0.43570860665248634 %
|
||||
[22] Char y: 0.41044217626356183 %
|
||||
[23] Char è: 0.4100302235941771 %
|
||||
[24] Char à: 0.363479571953713 %
|
||||
[25] Char j: 0.29591933417463223 %
|
||||
[26] Char k: 0.1359443808969308 %
|
||||
[27] Char ç: 0.11685724054877589 %
|
||||
[28] Char ê: 0.11218844362908331 %
|
||||
[29] Char z: 0.10738232915292918 %
|
||||
[30] Char w: 0.08239053387692777 %
|
||||
[31] Char ô: 0.04792382720507965 %
|
||||
[32] Char â: 0.03364280133307884 %
|
||||
[33] Char î: 0.029385957082770905 %
|
||||
[34] Char û: 0.024854477719539875 %
|
||||
[35] Char œ: 0.021146903695078125 %
|
||||
[36] Char ï: 0.017851282340001016 %
|
||||
[37] Char ù: 0.015242248767231636 %
|
||||
|
||||
The first 38 characters have an accumulated ratio of 0.999621003544166.
|
||||
|
||||
914 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.997057879992383
|
||||
Next 512 (512-1024): 1.3731755646154627e-06
|
||||
Rest: 3.8163916471489756e-17
|
||||
|
||||
- Processing end: 2015-12-03 21:10:27.987730
|
||||
@@ -0,0 +1,159 @@
|
||||
= Logs of language model for German (de) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2015-12-03 22:42:29.154759
|
||||
- Maximum depth: 3
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Wikipedia:Hauptseite (revision 140459035)
|
||||
1740 (revision 145584733)
|
||||
1890 (revision 148575121)
|
||||
1925 (revision 148682812)
|
||||
1965 (revision 148411693)
|
||||
3. Dezember (revision 148684818)
|
||||
Bundeswehreinsatz in Syrien (revision 148714599)
|
||||
Clara Klabunde (revision 148697193)
|
||||
Day Tripper (revision 145956669)
|
||||
Dezember 2015 (revision 148713161)
|
||||
Edwar al-Charrat (revision 148656295)
|
||||
Enzyklika (revision 148704406)
|
||||
Enzyklopädie (revision 148364925)
|
||||
Facebook Inc. (revision 148280344)
|
||||
Franz Neubauer (CSU) (revision 148710968)
|
||||
Freie Inhalte (revision 148123311)
|
||||
Gabriele Ferzetti (revision 148715582)
|
||||
Georg von Waldburg zu Zeil und Trauchburg (revision 148710609)
|
||||
Jim Loscutoff (revision 148690370)
|
||||
Katarina Witt (revision 148713884)
|
||||
Klavierkonzert (Gershwin) (revision 143900338)
|
||||
Ludolf Camphausen (revision 145088962)
|
||||
Mark Zuckerberg (revision 148714452)
|
||||
Montenegro (revision 148692773)
|
||||
NATO (revision 148697872)
|
||||
NATO-Osterweiterung (revision 148697354)
|
||||
Nekrolog 2015 (revision 148711617)
|
||||
Peter-Ulrich-Haus (revision 148654149)
|
||||
Philanthropie (revision 145561255)
|
||||
Präsidentschaftswahl in Burkina Faso 2015 (revision 148677453)
|
||||
Québec (Stadt) (revision 148716893)
|
||||
Rivka Zohar (revision 148708850)
|
||||
Roch Marc Kaboré (revision 148673951)
|
||||
Rubber Soul (revision 148665720)
|
||||
Salve Regina (Latry) (revision 148713279)
|
||||
Schießerei in San Bernardino (revision 148711974)
|
||||
Single (Musik) (revision 146450210)
|
||||
The Giving Pledge (revision 148711856)
|
||||
Ubi primum (Benedikt XIV.) (revision 136691297)
|
||||
VTech (revision 148704025)
|
||||
Walter Damrosch (revision 148716127)
|
||||
We Can Work It Out (revision 148706519)
|
||||
1. August (revision 148089156)
|
||||
1. Januar (revision 148659041)
|
||||
1. Juni (revision 148375663)
|
||||
1. November (revision 147888516)
|
||||
10. August (revision 148079904)
|
||||
10. November (revision 148658709)
|
||||
10. September (revision 148201788)
|
||||
11. August (revision 148315737)
|
||||
11. Oktober (revision 148087353)
|
||||
12. Januar (revision 147377586)
|
||||
12. September (revision 148359994)
|
||||
13. Dezember (revision 148614781)
|
||||
13. September (revision 148320520)
|
||||
14. August (revision 148513270)
|
||||
14. Dezember (revision 147968142)
|
||||
15. April (revision 146544147)
|
||||
15. August (revision 147827975)
|
||||
16. April (revision 148712866)
|
||||
16. Dezember (revision 148392316)
|
||||
16. Februar (revision 148221712)
|
||||
16. Jahrhundert (revision 147390194)
|
||||
16. Juli (revision 147928181)
|
||||
1652 (revision 142931287)
|
||||
1654 (revision 145531451)
|
||||
1656 (revision 144194148)
|
||||
1657 (revision 147492859)
|
||||
1662 (revision 147548355)
|
||||
1665 (revision 147757128)
|
||||
1666 (revision 147843417)
|
||||
1667 (revision 148566099)
|
||||
1668 (revision 145304760)
|
||||
1670 (revision 147643990)
|
||||
1672 (revision 145296252)
|
||||
1673 (revision 147879655)
|
||||
1674 (revision 146784434)
|
||||
1679 (revision 146069377)
|
||||
1685 (revision 148596629)
|
||||
1688 (revision 140370621)
|
||||
1692 (revision 146892539)
|
||||
1693 (revision 147464373)
|
||||
17. August (revision 148288443)
|
||||
17. Februar (revision 145814425)
|
||||
17. Jahrhundert (revision 147869798)
|
||||
17. Oktober (revision 148327370)
|
||||
1700er (revision 127393249)
|
||||
1707 (revision 148288721)
|
||||
1710er (revision 134739897)
|
||||
1720er (revision 127302296)
|
||||
1730 (revision 148694277)
|
||||
1730er (revision 127393280)
|
||||
1731 (revision 147730204)
|
||||
1735 (revision 145436596)
|
||||
1736 (revision 145680122)
|
||||
1737 (revision 146645905)
|
||||
1738 (revision 145094942)
|
||||
1739 (revision 147843445)
|
||||
1740er (revision 127393296)
|
||||
1741 (revision 146530178)
|
||||
1742 (revision 147010984)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2015-12-03 22:50:46.517106
|
||||
|
||||
59 characters appeared 1746165 times.
|
||||
|
||||
First 31 characters:
|
||||
[ 0] Char e: 14.27997926885489 %
|
||||
[ 1] Char r: 8.696257226550754 %
|
||||
[ 2] Char n: 8.464091308667852 %
|
||||
[ 3] Char i: 8.258784250056554 %
|
||||
[ 4] Char s: 6.690833913175444 %
|
||||
[ 5] Char a: 6.370703799469123 %
|
||||
[ 6] Char t: 5.925728668253001 %
|
||||
[ 7] Char h: 4.540979804314025 %
|
||||
[ 8] Char d: 4.367284878576767 %
|
||||
[ 9] Char l: 4.083634708060234 %
|
||||
[10] Char u: 3.899917819908199 %
|
||||
[11] Char o: 3.6450163644329145 %
|
||||
[12] Char c: 3.392405643223865 %
|
||||
[13] Char m: 2.578565026787274 %
|
||||
[14] Char g: 2.543631329227192 %
|
||||
[15] Char b: 1.9455206123132693 %
|
||||
[16] Char k: 1.7604292836014925 %
|
||||
[17] Char f: 1.6422273954637734 %
|
||||
[18] Char p: 1.519329502080273 %
|
||||
[19] Char w: 1.0273370500496803 %
|
||||
[20] Char z: 1.0037997554641171 %
|
||||
[21] Char v: 0.9010603236234834 %
|
||||
[22] Char ä: 0.4926224039538073 %
|
||||
[23] Char j: 0.4661644231787947 %
|
||||
[24] Char ü: 0.4094687500894818 %
|
||||
[25] Char y: 0.34229296773214446 %
|
||||
[26] Char ö: 0.3044958523392692 %
|
||||
[27] Char ß: 0.14477440562604335 %
|
||||
[28] Char x: 0.09918879372796958 %
|
||||
[29] Char é: 0.07633871942227682 %
|
||||
[30] Char q: 0.06099079983850323 %
|
||||
|
||||
The first 31 characters have an accumulated ratio of 0.9993385504806246.
|
||||
|
||||
1188 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9934041448127945
|
||||
Next 512 (512-1024): 1.1453671331174316e-06
|
||||
Rest: 0.0001130256702826099
|
||||
|
||||
- Processing end: 2015-12-03 22:50:46.681265
|
||||
@@ -0,0 +1,272 @@
|
||||
= Logs of language model for Greek (el) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-05-25 15:16:42.898905
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 200
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Πύλη:Κύρια (revision 5511929)
|
||||
14 Σεπτεμβρίου (revision 5808678)
|
||||
16 Σεπτεμβρίου (revision 5810117)
|
||||
1771 (revision 4940722)
|
||||
1829 (revision 5863423)
|
||||
1921 (revision 5819621)
|
||||
1948 (revision 5785943)
|
||||
1965 (revision 5846907)
|
||||
1970 (revision 5816968)
|
||||
1973 (revision 5423504)
|
||||
25 Μαΐου (revision 5865973)
|
||||
Eurovision (revision 5865484)
|
||||
Scorpions (revision 5586116)
|
||||
Wiki (revision 5859059)
|
||||
Wikimedia (revision 5771416)
|
||||
Αγία Πετρούπολη (revision 5782933)
|
||||
Αγγλική γλώσσα (revision 5851128)
|
||||
Αλεξάντρ Πούσκιν (revision 5790131)
|
||||
Βέλος ΙΙ (Αντιτορπιλικό) (revision 5178914)
|
||||
Βραζιλία (revision 5857981)
|
||||
Γαλλική γλώσσα (revision 5851119)
|
||||
Γαλλική εισβολή στην Ρωσία (revision 5858523)
|
||||
Γενικές εκλογές στη Δομινικανή Δημοκρατία 2016 (revision 5848770)
|
||||
Γηραιότερο πρόσωπο στον κόσμο (revision 5852034)
|
||||
Διαγωνισμός Τραγουδιού Eurovision 2016 (revision 5863783)
|
||||
Δικτατορία των Συνταγματαρχών (revision 5864405)
|
||||
Δομινικανή Δημοκρατία (revision 5848627)
|
||||
Εγκυκλοπαίδεια (revision 5566281)
|
||||
Ελεύθερο περιεχόμενο (revision 5824058)
|
||||
Ελλάδα (revision 5863759)
|
||||
Ελληνική γλώσσα (revision 5790854)
|
||||
Ιππικό (revision 5376587)
|
||||
Ιταλία (revision 5781867)
|
||||
Κίεβο (revision 5794613)
|
||||
Κατάληψη του Παρισιού (1814) (revision 5729368)
|
||||
Κλάους Μάιν (revision 5668218)
|
||||
Μάχη της Λειψίας (revision 5729316)
|
||||
Μάχη της Σαλτάνοφκα (revision 5865460)
|
||||
Μάχη του Μποροντίνο (revision 5670322)
|
||||
Μαξ Βερστάπεν (revision 5864745)
|
||||
Μπλουζ (revision 5846428)
|
||||
Νίκος Καχτίτσης (revision 5723615)
|
||||
Νικολάι Νικολάεβιτς Ραέφσκι (revision 5865460)
|
||||
Ντίλμα Ρούσεφ (revision 5843412)
|
||||
Ομοσπονδιακό Σοβιέτ της Ρωσικής Αυτοκρατορίας (revision 5865460)
|
||||
Ουκρανία (revision 5847651)
|
||||
Πάτρα (revision 5800331)
|
||||
Ποδόσφαιρο (revision 5864952)
|
||||
Πριμέρα Ντιβιζιόν (revision 5846965)
|
||||
Ρωσική Αυτοκρατορία (revision 5858419)
|
||||
Ρωσική γλώσσα (revision 5818960)
|
||||
Ρώσοι (revision 5376764)
|
||||
Σουζάνα Μούσατ Τζόουνς (revision 5848866)
|
||||
Στοκχόλμη (revision 5670508)
|
||||
Στρατηγός (revision 5464718)
|
||||
Τζακ Στάινμπεργκερ (revision 5820361)
|
||||
Τζαμάλα (revision 5863755)
|
||||
ΦΚ Μπαρτσελόνα (revision 5862032)
|
||||
Φόρμουλα Ένα (revision 5809160)
|
||||
10 Σεπτεμβρίου (revision 5841838)
|
||||
11 Σεπτεμβρίου (revision 5796866)
|
||||
12 Σεπτεμβρίου (revision 5795991)
|
||||
1321 (revision 5811404)
|
||||
13 Σεπτεμβρίου (revision 5830505)
|
||||
1435 (revision 5600729)
|
||||
1498 (revision 5831868)
|
||||
1523 (revision 5863396)
|
||||
1527 (revision 5579042)
|
||||
1580 (revision 5742938)
|
||||
15 Σεπτεμβρίου (revision 5817369)
|
||||
1712 (revision 5699806)
|
||||
1741 (revision 5817896)
|
||||
1752 (revision 5666171)
|
||||
1760 (revision 5490201)
|
||||
1769 (revision 5336004)
|
||||
17 Σεπτεμβρίου (revision 5843911)
|
||||
1812 (revision 5703237)
|
||||
1814 (revision 5751122)
|
||||
1851 (revision 5854460)
|
||||
1878 (revision 5863501)
|
||||
1889 (revision 5795061)
|
||||
1890 (revision 5705460)
|
||||
1898 (revision 5863504)
|
||||
18 Σεπτεμβρίου (revision 5661544)
|
||||
1901 (revision 5865687)
|
||||
1902 (revision 5779111)
|
||||
1905 (revision 5862599)
|
||||
1910 (revision 5794858)
|
||||
1916 (revision 5800363)
|
||||
1917 (revision 5865701)
|
||||
1925 (revision 5854774)
|
||||
1927 (revision 5839595)
|
||||
1928 (revision 5814308)
|
||||
1933 (revision 5854834)
|
||||
1936 (revision 5854290)
|
||||
1937 (revision 5794891)
|
||||
1943 (revision 5807315)
|
||||
1944 (revision 5865804)
|
||||
1950 (revision 5807377)
|
||||
1956 (revision 5795994)
|
||||
1960 (revision 5795065)
|
||||
1963 (revision 5863751)
|
||||
1966 (revision 5707508)
|
||||
1969 (revision 5668647)
|
||||
1980 (revision 5832053)
|
||||
1981 (revision 5817635)
|
||||
1982 (revision 5788879)
|
||||
1983 (revision 5812702)
|
||||
1984 (revision 5749754)
|
||||
1989 (revision 5846909)
|
||||
1994 (revision 5863999)
|
||||
1999 (revision 5795003)
|
||||
19 Σεπτεμβρίου (revision 5850863)
|
||||
1 Σεπτεμβρίου (revision 5630491)
|
||||
2000 (revision 5779037)
|
||||
2001 (revision 5779042)
|
||||
2005 (revision 5779066)
|
||||
2006 (revision 5808681)
|
||||
2009 (revision 5827105)
|
||||
2011 (revision 5808660)
|
||||
2016 (revision 5801621)
|
||||
20 Σεπτεμβρίου (revision 5808561)
|
||||
21 Σεπτεμβρίου (revision 5751207)
|
||||
22 Σεπτεμβρίου (revision 5807133)
|
||||
23 Σεπτεμβρίου (revision 5800012)
|
||||
24 Σεπτεμβρίου (revision 5662618)
|
||||
258 (revision 4952368)
|
||||
25 Σεπτεμβρίου (revision 5817621)
|
||||
26 Σεπτεμβρίου (revision 5817637)
|
||||
27 Σεπτεμβρίου (revision 5817648)
|
||||
28 Σεπτεμβρίου (revision 5817677)
|
||||
29 Σεπτεμβρίου (revision 5703562)
|
||||
2 Σεπτεμβρίου (revision 5701639)
|
||||
30 Σεπτεμβρίου (revision 5838312)
|
||||
326 (revision 5818811)
|
||||
3 Σεπτεμβρίου (revision 5816313)
|
||||
407 (revision 4952524)
|
||||
4 Σεπτεμβρίου (revision 5816970)
|
||||
5 Σεπτεμβρίου (revision 5817185)
|
||||
628 (revision 5398024)
|
||||
680 (revision 5365010)
|
||||
685 (revision 5819296)
|
||||
6 Σεπτεμβρίου (revision 5765157)
|
||||
775 (revision 5373211)
|
||||
786 (revision 5398031)
|
||||
7 Σεπτεμβρίου (revision 5749649)
|
||||
81 (revision 5397958)
|
||||
891 (revision 4952139)
|
||||
8 Σεπτεμβρίου (revision 5788878)
|
||||
9 Σεπτεμβρίου (revision 5817240)
|
||||
CIA (revision 5857678)
|
||||
Miyavi (revision 4944860)
|
||||
Άρμεν Κούπτσιος (revision 5766774)
|
||||
Έιμι Γουάινχαουζ (revision 5809279)
|
||||
Έρβιν Θάλμπεργκ (revision 5716376)
|
||||
Ίων Δραγούμης (revision 5818568)
|
||||
Αγία Ελένη (revision 5821916)
|
||||
Αλεξάντερ φον Χούμπολτ (revision 5773636)
|
||||
Αλμπέρτο Κόρντα (revision 5800055)
|
||||
Απρίλιος (revision 5766829)
|
||||
Αυτοκρατορία των Σασσανιδών (revision 5859880)
|
||||
Αύγουστος (revision 5461793)
|
||||
Β΄ Παγκόσμιος Πόλεμος (revision 5848530)
|
||||
Βέρμαχτ (revision 5212228)
|
||||
Βασίλης Λάσκος (revision 5695445)
|
||||
Βενεζουέλα (revision 5847962)
|
||||
Βρετανική Αυτοκρατορία (revision 5606306)
|
||||
Βόρεια Ελλάδα (revision 5670938)
|
||||
Γαλλία (revision 5776756)
|
||||
Γεώργιος Καρατζαφέρης (revision 5803114)
|
||||
Γιάννης Λάτσης (revision 5692530)
|
||||
Γιάννος Κρανιδιώτης (revision 5574536)
|
||||
Γιώργος Παπασιδέρης (μουσικός) (revision 5722203)
|
||||
Γκέοργκ Φρήντριχ Χαίντελ (revision 5807098)
|
||||
Γκρέις Κέλι (revision 5807168)
|
||||
Γρηγοριανό Hμερολόγιο (revision 5793842)
|
||||
Γρηγοριανό ημερολόγιο (revision 5793842)
|
||||
Γρηγόρης Λαμπράκης (revision 5752808)
|
||||
Δάντης Αλιγκέρι (revision 5648882)
|
||||
Δήμος Βιάννου (revision 4816422)
|
||||
Δεκέμβριος (revision 5461807)
|
||||
Δομιτιανός (revision 5735554)
|
||||
Δράμα (πόλη) (revision 5857326)
|
||||
Ενιαία Δημοκρατική Αριστερά (revision 5742309)
|
||||
Ετόρε Σότσας (revision 5785872)
|
||||
Ζιλ Αντριαμαχαζό (revision 5819706)
|
||||
Η.Π.Α. (revision 5845171)
|
||||
Ηράκλειος (revision 5778827)
|
||||
Θεσσαλονίκη (revision 5844955)
|
||||
Θεόδωρος Ρούζβελτ (revision 5815087)
|
||||
Ιανουάριος (revision 5615044)
|
||||
Ιερουσαλήμ (revision 5824734)
|
||||
Ιησούς Χριστός (revision 5859687)
|
||||
Ιούλιος (revision 5712711)
|
||||
Ιούνιος (revision 5461799)
|
||||
Ιράκ (revision 5820378)
|
||||
Ιράν (revision 5861249)
|
||||
Ισιδώρα Ντάνκαν (revision 5044778)
|
||||
Ιωάννης ο Χρυσόστομος (revision 5824898)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-05-25 15:21:50.071087
|
||||
|
||||
63 characters appeared 1875535 times.
|
||||
|
||||
First 46 characters:
|
||||
[ 0] Char α: 9.004097497514042 %
|
||||
[ 1] Char ο: 8.311015256980008 %
|
||||
[ 2] Char τ: 7.94493304577094 %
|
||||
[ 3] Char ι: 6.338831320129989 %
|
||||
[ 4] Char ν: 5.836627948825269 %
|
||||
[ 5] Char ε: 5.635565318695733 %
|
||||
[ 6] Char ρ: 4.717907157157825 %
|
||||
[ 7] Char σ: 4.307197679595422 %
|
||||
[ 8] Char κ: 4.061294510632965 %
|
||||
[ 9] Char ς: 3.766551943845356 %
|
||||
[10] Char η: 3.7565281373048225 %
|
||||
[11] Char π: 3.4156653968067783 %
|
||||
[12] Char υ: 3.30956233821283 %
|
||||
[13] Char μ: 3.1442761665338157 %
|
||||
[14] Char λ: 3.0899983204792236 %
|
||||
[15] Char ί: 2.429973314280992 %
|
||||
[16] Char ό: 2.076100952528212 %
|
||||
[17] Char ά: 1.922651403466211 %
|
||||
[18] Char γ: 1.8994047031913561 %
|
||||
[19] Char έ: 1.6641651582081913 %
|
||||
[20] Char δ: 1.508582884350332 %
|
||||
[21] Char ω: 1.2410325587099147 %
|
||||
[22] Char ή: 1.2077087337746297 %
|
||||
[23] Char χ: 1.0482342371643292 %
|
||||
[24] Char ύ: 0.9225101104484854 %
|
||||
[25] Char β: 0.8928652357860558 %
|
||||
[26] Char θ: 0.8681256281541001 %
|
||||
[27] Char φ: 0.806756472153279 %
|
||||
[28] Char ώ: 0.6969211451665791 %
|
||||
[29] Char ζ: 0.35515199663029484 %
|
||||
[30] Char e: 0.35488540603081253 %
|
||||
[31] Char ξ: 0.314736861748781 %
|
||||
[32] Char a: 0.2909036621550651 %
|
||||
[33] Char i: 0.2884510286398281 %
|
||||
[34] Char o: 0.24137112877125727 %
|
||||
[35] Char r: 0.23262695710823847 %
|
||||
[36] Char n: 0.2206303801315358 %
|
||||
[37] Char t: 0.21668483925919804 %
|
||||
[38] Char s: 0.2013825388489151 %
|
||||
[39] Char l: 0.14865091827131993 %
|
||||
[40] Char d: 0.1359078876160669 %
|
||||
[41] Char c: 0.12124540464454144 %
|
||||
[42] Char h: 0.1166600463334462 %
|
||||
[43] Char u: 0.10381037943840024 %
|
||||
[44] Char m: 0.09074744006376848 %
|
||||
[45] Char ψ: 0.08669526295163779 %
|
||||
|
||||
The first 46 characters have an accumulated ratio of 0.993456267145108.
|
||||
|
||||
1579 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.958419074626211
|
||||
Next 512 (512-1024): 0.006969211451665791
|
||||
Rest: 0.0018920066107342773
|
||||
|
||||
- Processing end: 2016-05-25 15:21:50.812982
|
||||
@@ -0,0 +1,109 @@
|
||||
= Logs of language model for Hungarian (hu) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2015-12-12 18:01:21.560682
|
||||
- Maximum depth: 2
|
||||
- Max number of pages: 50
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Kezdőlap (revision 12748721)
|
||||
1722 (revision 16471860)
|
||||
1780 (revision 16407861)
|
||||
1800 (revision 15028835)
|
||||
1831 (revision 16469576)
|
||||
1848–49-es forradalom és szabadságharc (revision 16955214)
|
||||
1875 (revision 16798555)
|
||||
1895 (revision 16649417)
|
||||
1900 (revision 16961019)
|
||||
1905 (revision 16601113)
|
||||
1915 (revision 16792868)
|
||||
1940 (revision 16936087)
|
||||
1950 (revision 16820817)
|
||||
1970 (revision 16093156)
|
||||
1985 (revision 16463340)
|
||||
1995 (revision 16945805)
|
||||
1998 (revision 16542908)
|
||||
2003 (revision 16943939)
|
||||
2015 (revision 16960983)
|
||||
73. Golden Globe-gála (revision 16937296)
|
||||
Akacuki (revision 16960353)
|
||||
Akasztottak erdeje (regény) (revision 16918702)
|
||||
Alan Hodgkinson (revision 16953214)
|
||||
Alfred Bernhard Nobel (revision 16654409)
|
||||
Alkotmány (revision 16784843)
|
||||
André-Marie Ampère (revision 16865419)
|
||||
Angela Merkel (revision 16960753)
|
||||
Anne Baxter (revision 15572176)
|
||||
Az irgalmasság rendkívüli szentéve (revision 16951018)
|
||||
Az év embereinek listája (revision 16961722)
|
||||
Bencések (revision 16853524)
|
||||
Boeing 747–400 (revision 16947261)
|
||||
Chantal Szent Johanna Franciska (revision 16371923)
|
||||
December 12. (revision 15637986)
|
||||
December 13. (revision 16546152)
|
||||
Dinamó (revision 15949492)
|
||||
Dionne Warwick (revision 16522754)
|
||||
Elektrodinamika (revision 14888277)
|
||||
Elektromosság (revision 16051899)
|
||||
Enciklopédia (revision 16556513)
|
||||
Eric Maskin (revision 16907781)
|
||||
Európai migrációs válság (revision 16922218)
|
||||
Eötvös Loránd (revision 16960057)
|
||||
Eötvös Loránd Tudományegyetem (revision 16684410)
|
||||
Fellner Jakab (revision 16960223)
|
||||
Feltaláló (revision 13609621)
|
||||
Ferenc pápa (revision 16928970)
|
||||
Frank Sinatra (revision 16927399)
|
||||
François Jean Dominique Arago (revision 16197941)
|
||||
Gabriella (revision 16906500)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2015-12-12 18:02:46.729734
|
||||
|
||||
55 characters appeared 375370 times.
|
||||
|
||||
First 32 characters:
|
||||
[ 0] Char e: 9.710685457015744 %
|
||||
[ 1] Char a: 8.803314063457389 %
|
||||
[ 2] Char t: 7.322375256413672 %
|
||||
[ 3] Char s: 6.666222660308496 %
|
||||
[ 4] Char l: 5.73967019207715 %
|
||||
[ 5] Char r: 5.4341050163838345 %
|
||||
[ 6] Char n: 5.39920611663159 %
|
||||
[ 7] Char i: 4.773689959240216 %
|
||||
[ 8] Char o: 4.347976663025815 %
|
||||
[ 9] Char k: 4.289634227562138 %
|
||||
[10] Char z: 4.244611982843594 %
|
||||
[11] Char á: 3.7855982097663636 %
|
||||
[12] Char m: 3.2144284306151265 %
|
||||
[13] Char g: 3.0727016010869277 %
|
||||
[14] Char é: 3.0295441830727015 %
|
||||
[15] Char b: 2.287609558568879 %
|
||||
[16] Char d: 1.9966965926952074 %
|
||||
[17] Char v: 1.8832085675466872 %
|
||||
[18] Char y: 1.8453792258305137 %
|
||||
[19] Char u: 1.5155713029810587 %
|
||||
[20] Char h: 1.2960545595012922 %
|
||||
[21] Char p: 1.288861656498921 %
|
||||
[22] Char j: 1.2363801049631031 %
|
||||
[23] Char c: 1.0951860830647095 %
|
||||
[24] Char f: 1.0256546873751233 %
|
||||
[25] Char ö: 1.020859418706876 %
|
||||
[26] Char ó: 0.9955510562911262 %
|
||||
[27] Char ő: 0.8399712283879905 %
|
||||
[28] Char í: 0.6340410794682579 %
|
||||
[29] Char ü: 0.4211844313610571 %
|
||||
[30] Char ú: 0.3295415190345526 %
|
||||
[31] Char ű: 0.2056637451048299 %
|
||||
|
||||
The first 32 characters have an accumulated ratio of 0.9975117883688093.
|
||||
|
||||
1084 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9748272224933486
|
||||
Next 512 (512-1024): 5.328076298052588e-06
|
||||
Rest: 0.0001889139024889644
|
||||
|
||||
- Processing end: 2015-12-12 18:02:46.902033
|
||||
@@ -0,0 +1,156 @@
|
||||
= Logs of language model for Irish (ga) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-27 00:31:16.489602
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Tracy Caldwell Dyson (revision 812158)
|
||||
14 Lúnasa (revision 716575)
|
||||
1969 (revision 810361)
|
||||
California (revision 790976)
|
||||
Ceimic (revision 759983)
|
||||
Ceimic fhisiciúil (revision 656896)
|
||||
NASA (revision 806394)
|
||||
Rúisis (revision 771746)
|
||||
SAM (revision 807668)
|
||||
Spáinnis (revision 812323)
|
||||
Stáisiún Idirnáisiúnta Spáis (revision 806394)
|
||||
Tointeálaí spáis (revision 761309)
|
||||
10 Lúnasa (revision 649045)
|
||||
11 Lúnasa (revision 776455)
|
||||
12 Lúnasa (revision 716531)
|
||||
13 Lúnasa (revision 716546)
|
||||
1598 (revision 703178)
|
||||
15 Lúnasa (revision 776986)
|
||||
16 Lúnasa (revision 648836)
|
||||
1740 (revision 791225)
|
||||
1771 (revision 776762)
|
||||
17 Lúnasa (revision 777131)
|
||||
1823 (revision 791774)
|
||||
1832 (revision 794492)
|
||||
1898 (revision 805176)
|
||||
18 Lúnasa (revision 777242)
|
||||
1911 (revision 801932)
|
||||
1956 (revision 797081)
|
||||
1962 (revision 801511)
|
||||
1966 (revision 807415)
|
||||
19 Lúnasa (revision 648524)
|
||||
1 Lúnasa (revision 647726)
|
||||
2001 (revision 801012)
|
||||
2004 (revision 795759)
|
||||
2016 (revision 812091)
|
||||
20 Lúnasa (revision 777924)
|
||||
21 Lúnasa (revision 647805)
|
||||
22 Lúnasa (revision 778960)
|
||||
23 Lúnasa (revision 778453)
|
||||
24 Lúnasa (revision 778495)
|
||||
25 Lúnasa (revision 778551)
|
||||
26 Lúnasa (revision 649051)
|
||||
27 Lúnasa (revision 778763)
|
||||
28 Lúnasa (revision 778813)
|
||||
29 Lúnasa (revision 778959)
|
||||
2 Lúnasa (revision 774393)
|
||||
30 Lúnasa (revision 648308)
|
||||
31 Lúnasa (revision 649053)
|
||||
3 Lúnasa (revision 647811)
|
||||
4 Lúnasa (revision 786284)
|
||||
5 Lúnasa (revision 776845)
|
||||
6 Lúnasa (revision 647834)
|
||||
7 Lúnasa (revision 775859)
|
||||
8 Lúnasa (revision 648745)
|
||||
9 Lúnasa (revision 648522)
|
||||
AK Parti (revision 792248)
|
||||
An Phacastáin (revision 759339)
|
||||
An Tuirc (revision 811970)
|
||||
Aoine (revision 717430)
|
||||
Bertolt Brecht (revision 800584)
|
||||
Czesław Miłosz (revision 780306)
|
||||
Céadaoin (revision 717606)
|
||||
Dan Boyle (revision 797926)
|
||||
Domhnach (revision 717663)
|
||||
Déardaoin (revision 647860)
|
||||
Féilire (revision 648837)
|
||||
Halle Berry (revision 759955)
|
||||
Henry Bagenal (revision 716575)
|
||||
Iúil (revision 647071)
|
||||
Luan (revision 717791)
|
||||
Lúnasa (revision 810265)
|
||||
Meán Fómhair (revision 779166)
|
||||
Pápa Pius VII (revision 758126)
|
||||
Satharn (revision 784525)
|
||||
Walter Scott (revision 759029)
|
||||
Áth Buí (revision 716575)
|
||||
11 Márta (revision 716519)
|
||||
17 Márta (revision 798614)
|
||||
1882 (revision 801198)
|
||||
1886 (revision 776624)
|
||||
1890 (revision 801200)
|
||||
1891 (revision 796677)
|
||||
1903 (revision 812849)
|
||||
1922 (revision 801227)
|
||||
1930í (revision 740221)
|
||||
1940í (revision 740219)
|
||||
1950í (revision 740217)
|
||||
1960í (revision 772724)
|
||||
1967 (revision 796983)
|
||||
1968 (revision 810926)
|
||||
1970 (revision 812852)
|
||||
1970í (revision 740213)
|
||||
1971 (revision 809746)
|
||||
1972 (revision 789490)
|
||||
1980í (revision 740211)
|
||||
1990í (revision 740208)
|
||||
19ú haois (revision 739964)
|
||||
1 Bealtaine (revision 647679)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-27 00:33:40.157338
|
||||
|
||||
44 characters appeared 183561 times.
|
||||
|
||||
First 31 characters:
|
||||
[ 0] Char a: 15.192769705983297 %
|
||||
[ 1] Char i: 10.534372769814938 %
|
||||
[ 2] Char n: 8.106297089250985 %
|
||||
[ 3] Char h: 7.243368689427493 %
|
||||
[ 4] Char r: 6.442544985045844 %
|
||||
[ 5] Char e: 6.198484427520007 %
|
||||
[ 6] Char s: 5.622654049607488 %
|
||||
[ 7] Char t: 4.776068990689743 %
|
||||
[ 8] Char c: 4.543448771797931 %
|
||||
[ 9] Char l: 4.1953356105054995 %
|
||||
[10] Char o: 3.9469168287381304 %
|
||||
[11] Char d: 3.2169142682813887 %
|
||||
[12] Char g: 2.811054635788648 %
|
||||
[13] Char m: 2.6269196615838877 %
|
||||
[14] Char á: 2.2749930540801153 %
|
||||
[15] Char u: 2.1932763495513754 %
|
||||
[16] Char b: 2.0478206154902185 %
|
||||
[17] Char í: 1.6599386579938005 %
|
||||
[18] Char é: 1.2829522611012143 %
|
||||
[19] Char f: 1.1494816437042727 %
|
||||
[20] Char ú: 1.0525111543301682 %
|
||||
[21] Char p: 0.9059658642086281 %
|
||||
[22] Char ó: 0.8890777452726886 %
|
||||
[23] Char v: 0.2522322279787101 %
|
||||
[24] Char y: 0.23479933101257894 %
|
||||
[25] Char k: 0.18195586208399386 %
|
||||
[26] Char w: 0.1688811893593955 %
|
||||
[27] Char j: 0.09697048937410452 %
|
||||
[28] Char z: 0.07735848028720697 %
|
||||
[29] Char x: 0.0343210159020707 %
|
||||
[30] Char q: 0.010895560603831969 %
|
||||
|
||||
The first 31 characters have an accumulated ratio of 0.9997058198636966.
|
||||
|
||||
701 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9974076651249096
|
||||
Next 512 (512-1024): 5.447780301915984e-06
|
||||
Rest: -2.7755575615628914e-17
|
||||
|
||||
- Processing end: 2016-09-27 00:33:40.258886
|
||||
@@ -0,0 +1,162 @@
|
||||
= Logs of language model for Italian (it) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-21 18:43:12.831409
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Pieve Ligure (revision 83186252)
|
||||
010 (prefisso) (revision 76157203)
|
||||
1000 (revision 83185341)
|
||||
1143 (revision 70627567)
|
||||
1162 (revision 70627612)
|
||||
118 - Emergenza sanitaria (revision 83267411)
|
||||
1201 (revision 77523243)
|
||||
1202 (revision 76764411)
|
||||
1374 (revision 78259457)
|
||||
1404 (revision 70628069)
|
||||
1520 (revision 76854924)
|
||||
1537 (revision 70628296)
|
||||
1582 (revision 80626188)
|
||||
1584 (revision 76837051)
|
||||
1600 (revision 76869356)
|
||||
1619 (revision 70628455)
|
||||
1742 (revision 70628675)
|
||||
1748 (revision 70628682)
|
||||
1749 (revision 70628684)
|
||||
1750 (revision 70628690)
|
||||
1754 (revision 70628697)
|
||||
1775 (revision 70628734)
|
||||
1797 (revision 78338823)
|
||||
1798 (revision 82047236)
|
||||
1803 (revision 77502534)
|
||||
1805 (revision 79369853)
|
||||
1809 (revision 70628789)
|
||||
1810 (revision 82930218)
|
||||
1814 (revision 78338825)
|
||||
1815 (revision 82669615)
|
||||
1816 (revision 83185384)
|
||||
1818 (revision 72407239)
|
||||
1823 (revision 74880156)
|
||||
1859 (revision 83185401)
|
||||
1860 (revision 83185403)
|
||||
1861 (revision 83185412)
|
||||
1868 (revision 83185430)
|
||||
1874 (revision 83185441)
|
||||
1897 (revision 83185267)
|
||||
1908 (revision 83185631)
|
||||
1909 (revision 83185630)
|
||||
1913 (revision 83185626)
|
||||
1915 (revision 83185625)
|
||||
1917 (revision 83185270)
|
||||
1920 (revision 83185621)
|
||||
1921 (revision 83185619)
|
||||
1923 (revision 83185616)
|
||||
1925 (revision 83185614)
|
||||
1926 (revision 83185612)
|
||||
1928 (revision 83185610)
|
||||
1929 (revision 83185609)
|
||||
1939 (revision 83185598)
|
||||
1946 (revision 83185590)
|
||||
1947 (revision 83185589)
|
||||
1948 (revision 83185587)
|
||||
1951 (revision 83185584)
|
||||
1956 (revision 83185478)
|
||||
1960 (revision 83185487)
|
||||
1964 (revision 83185493)
|
||||
1965 (revision 83185494)
|
||||
1969 (revision 83185500)
|
||||
1970 (revision 83185503)
|
||||
1971 (revision 83185505)
|
||||
1975 (revision 83185510)
|
||||
1976 (revision 83185513)
|
||||
1977 (revision 83185514)
|
||||
1980 (revision 83185518)
|
||||
1981 (revision 83308867)
|
||||
1983 (revision 83185524)
|
||||
1985 (revision 83185526)
|
||||
1988 (revision 83185280)
|
||||
1990 (revision 83185531)
|
||||
1995 (revision 83185538)
|
||||
1999 (revision 83326325)
|
||||
2000 (revision 83185544)
|
||||
2001 (revision 83309058)
|
||||
2002 (revision 83185545)
|
||||
2003 (revision 83185546)
|
||||
2004 (revision 83185283)
|
||||
2005 (revision 83185285)
|
||||
2006 (revision 83185547)
|
||||
2007 (revision 83185549)
|
||||
2008 (revision 83185551)
|
||||
2009 (revision 83185552)
|
||||
2010 (revision 83185287)
|
||||
2012 (revision 83185289)
|
||||
712 (revision 70630167)
|
||||
749 (revision 78272323)
|
||||
ATP (Provincia di Genova) (revision 82754117)
|
||||
Abbazia di San Colombano (revision 83062997)
|
||||
Abbazia di San Fruttuoso (revision 83288120)
|
||||
Acacia dealbata (revision 83036867)
|
||||
Acquedotto (revision 82973825)
|
||||
Affresco (revision 82000422)
|
||||
Agricoltura (revision 82578266)
|
||||
Allevamento (revision 82971452)
|
||||
Altitudine (revision 82971213)
|
||||
Angelo (revision 82333116)
|
||||
Anni 1960 (revision 83161222)
|
||||
Anni 1970 (revision 81663175)
|
||||
Antica Roma (revision 83125874)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-21 18:46:08.840718
|
||||
|
||||
59 characters appeared 823241 times.
|
||||
|
||||
First 34 characters:
|
||||
[ 0] Char i: 11.823147778111148 %
|
||||
[ 1] Char a: 11.252112078965942 %
|
||||
[ 2] Char e: 10.910170897707962 %
|
||||
[ 3] Char o: 8.936386793174782 %
|
||||
[ 4] Char n: 7.317055394471364 %
|
||||
[ 5] Char l: 6.931263141655967 %
|
||||
[ 6] Char r: 6.521784021932824 %
|
||||
[ 7] Char t: 6.386708145002497 %
|
||||
[ 8] Char s: 4.572415610981475 %
|
||||
[ 9] Char c: 4.116291584116923 %
|
||||
[10] Char d: 3.9770856893667834 %
|
||||
[11] Char u: 2.8944136650142545 %
|
||||
[12] Char m: 2.762860450342002 %
|
||||
[13] Char p: 2.6809889206198427 %
|
||||
[14] Char g: 2.1493098618751985 %
|
||||
[15] Char v: 1.5369739845318686 %
|
||||
[16] Char b: 1.2855287819727153 %
|
||||
[17] Char f: 0.9932692856648295 %
|
||||
[18] Char z: 0.9664241698360504 %
|
||||
[19] Char h: 0.7159507361756764 %
|
||||
[20] Char q: 0.2416060424590126 %
|
||||
[21] Char k: 0.18876610858788617 %
|
||||
[22] Char à: 0.15596890825408355 %
|
||||
[23] Char y: 0.12462936126844994 %
|
||||
[24] Char è: 0.11600491229178332 %
|
||||
[25] Char w: 0.10628722330398996 %
|
||||
[26] Char x: 0.10312897438295712 %
|
||||
[27] Char j: 0.07555503188009344 %
|
||||
[28] Char ù: 0.05575524056746445 %
|
||||
[29] Char ò: 0.03304014255849745 %
|
||||
[30] Char é: 0.021014502436103158 %
|
||||
[31] Char ì: 0.0191924357508919 %
|
||||
[32] Char á: 0.004737373381549267 %
|
||||
[33] Char ó: 0.003644133370422513 %
|
||||
|
||||
The first 34 characters have an accumulated ratio of 0.9997947138201325.
|
||||
|
||||
872 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9989484485502651
|
||||
Next 512 (512-1024): 1.214711123474171e-06
|
||||
Rest: -4.336808689942018e-17
|
||||
|
||||
- Processing end: 2016-09-21 18:46:08.920456
|
||||
@@ -0,0 +1,162 @@
|
||||
= Logs of language model for Latvian (lv) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-21 00:16:33.485953
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Zigfrīds Anna Meierovics (revision 2546984)
|
||||
1. Saeima (revision 2511127)
|
||||
1. Saeimas deputāti (revision 2303859)
|
||||
1. Saeimas frakcijas (revision 2429725)
|
||||
1. Saeimas vēlēšanas (revision 2464758)
|
||||
1887. gads (revision 2583253)
|
||||
1919. gada Parīzes miera konference (revision 2482078)
|
||||
1920 (revision 2401222)
|
||||
1921 (revision 2473337)
|
||||
1922 (revision 2486819)
|
||||
1923 (revision 2544643)
|
||||
1924 (revision 2539361)
|
||||
1925 (revision 2486795)
|
||||
22. augusts (revision 2583254)
|
||||
31. jūlijs (revision 2559648)
|
||||
5. februāris (revision 2581966)
|
||||
ASV (revision 2549746)
|
||||
Agrārā reforma Latvijā (revision 2473423)
|
||||
Agudas Izrael (Latvija) (revision 2311143)
|
||||
Aigars Kalvītis (revision 2545858)
|
||||
Alberts Kviesis (revision 2546934)
|
||||
Aleksandrs Bočagovs (revision 2329526)
|
||||
Aleksandrs Dauge (revision 2546805)
|
||||
Aleksandrs Jaunbērzs (revision 2462254)
|
||||
Aleksandrs Kerenskis (revision 2461214)
|
||||
Aleksandrs Millerāns (revision 2309419)
|
||||
Aleksandrs Neibergs (revision 2491897)
|
||||
Alfrēds Birznieks (revision 2567317)
|
||||
Alfrēds Jēkabs Bērziņš (revision 2564068)
|
||||
Alfrēds Riekstiņš (politiķis) (revision 2586148)
|
||||
Andrejs Bērziņš (revision 2564283)
|
||||
Andrejs Kurcijs (revision 2564338)
|
||||
Andrejs Petrevics (revision 2460269)
|
||||
Andrejs Sīmanis (revision 2547079)
|
||||
Andrejs Veckalns (revision 2564224)
|
||||
Andrievs Niedra (revision 2546988)
|
||||
Andris Bērziņš (politiķis, 1951) (revision 2218488)
|
||||
Andris Šķēle (revision 2457423)
|
||||
Angļu valoda (revision 2447598)
|
||||
Ansis Buševics (revision 2578312)
|
||||
Ansis Rudevics (revision 2414854)
|
||||
Antante (revision 2581862)
|
||||
Antons Dzenis (revision 2564295)
|
||||
Antons Laizāns (revision 2467408)
|
||||
Antons Rubins (1885) (revision 2465396)
|
||||
Antons Velkme (revision 2564425)
|
||||
Ants Pīps (revision 2564383)
|
||||
Apollo (portāls) (revision 2371202)
|
||||
Apolonija Laurinoviča (revision 2466232)
|
||||
Aprīļa pučs (revision 2150686)
|
||||
Apvienotā Karaliste (revision 2566258)
|
||||
Aristīds Briāns (revision 2536819)
|
||||
Arons Nuroks (revision 2337085)
|
||||
Arturs Alberings (revision 2442531)
|
||||
Arturs Ozols (inženieris) (revision 2491399)
|
||||
Artūrs Balfūrs (revision 2309461)
|
||||
Artūrs Vīgants (revision 2461471)
|
||||
Artūrs Žers (revision 2564230)
|
||||
Arveds Bergs (revision 2564118)
|
||||
Arveds Švābe (revision 2586288)
|
||||
Arvīds Kalniņš (revision 2545254)
|
||||
Aspazija (revision 2574081)
|
||||
Augusts Briedis (revision 2546879)
|
||||
Augusts Kalniņš (revision 2436647)
|
||||
Augusts Kirhenšteins (revision 2547109)
|
||||
Austroungārija (revision 2524307)
|
||||
Autoritatīvā vadība (revision 2385793)
|
||||
Balfūra nota (revision 2538973)
|
||||
Baltijas Antante (revision 2541901)
|
||||
Baltijas pārkrievošana (revision 2570657)
|
||||
Bermontiāde (revision 2499160)
|
||||
Bernards Kublinskis (revision 2441386)
|
||||
Bezpartijiskais nacionālais centrs (revision 2438819)
|
||||
Beļģija (revision 2579008)
|
||||
Brestļitovskas miera līgums (revision 2569020)
|
||||
Brizules muiža (revision 2584564)
|
||||
Bruno Kalniņš (revision 2566572)
|
||||
Brīvības piemineklis (revision 2578595)
|
||||
Bulduru konference (revision 2193449)
|
||||
Ceire-Cion (revision 2311779)
|
||||
Celmiņa 1. Ministru kabinets (revision 2112830)
|
||||
Delfi (portāls) (revision 2544918)
|
||||
Demokrātiskais Centrs (revision 2113060)
|
||||
Demokrātu savienība (revision 2179593)
|
||||
Diena (laikraksts) (revision 2548854)
|
||||
Donats Bicāns (revision 2479349)
|
||||
Dubulti (Jūrmala) (revision 2456811)
|
||||
Durbe (revision 2381790)
|
||||
Dāvids Komisārs (revision 2574685)
|
||||
Džovanni Džoliti (revision 2538055)
|
||||
Ebreju bloks (revision 2311643)
|
||||
Ebreju nacionāldemokrātu partija (revision 2312288)
|
||||
Eduards Grantskalns (revision 2565167)
|
||||
Eduards Jaunzems (revision 2452579)
|
||||
Eduards Laimiņš (revision 2449521)
|
||||
Eduards Radziņš (revision 2564393)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-21 00:19:18.361533
|
||||
|
||||
55 characters appeared 354745 times.
|
||||
|
||||
First 39 characters:
|
||||
[ 0] Char a: 11.905171320244119 %
|
||||
[ 1] Char i: 9.3977364022044 %
|
||||
[ 2] Char s: 8.224217395594017 %
|
||||
[ 3] Char e: 6.367108768270166 %
|
||||
[ 4] Char r: 5.854064186951191 %
|
||||
[ 5] Char t: 5.831230884156225 %
|
||||
[ 6] Char u: 4.939604504644181 %
|
||||
[ 7] Char n: 4.463769750102186 %
|
||||
[ 8] Char ā: 3.9498794909019157 %
|
||||
[ 9] Char l: 3.8030134321836813 %
|
||||
[10] Char o: 3.6296494665182033 %
|
||||
[11] Char k: 3.524785409237621 %
|
||||
[12] Char m: 3.2739009711201 %
|
||||
[13] Char d: 3.177775585279567 %
|
||||
[14] Char v: 3.0046935122411873 %
|
||||
[15] Char p: 2.827101157169234 %
|
||||
[16] Char j: 2.8166711299665956 %
|
||||
[17] Char b: 2.0279355593454453 %
|
||||
[18] Char ī: 1.8855797826607845 %
|
||||
[19] Char g: 1.6146809680192813 %
|
||||
[20] Char z: 1.5343415692962552 %
|
||||
[21] Char ē: 1.4593581304880971 %
|
||||
[22] Char c: 1.2231321089796898 %
|
||||
[23] Char š: 0.8876798827326671 %
|
||||
[24] Char ņ: 0.46596851259355315 %
|
||||
[25] Char f: 0.4203019070036223 %
|
||||
[26] Char ļ: 0.34700982395805435 %
|
||||
[27] Char ū: 0.30162511099522193 %
|
||||
[28] Char h: 0.20070755049401684 %
|
||||
[29] Char ž: 0.18774048964749326 %
|
||||
[30] Char ķ: 0.14207388405756247 %
|
||||
[31] Char ģ: 0.1268516821942522 %
|
||||
[32] Char č: 0.08287643236691145 %
|
||||
[33] Char w: 0.0324176521163089 %
|
||||
[34] Char y: 0.02734358482853881 %
|
||||
[35] Char x: 0.015785987117506943 %
|
||||
[36] Char ö: 0.005074067287770088 %
|
||||
[37] Char é: 0.003946496779376736 %
|
||||
[38] Char q: 0.0031008188980817205 %
|
||||
|
||||
The first 39 characters have an accumulated ratio of 0.9998590536864506.
|
||||
|
||||
970 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9904102202220861
|
||||
Next 512 (512-1024): 0.0018774048964749328
|
||||
Rest: -1.734723475976807e-17
|
||||
|
||||
- Processing end: 2016-09-21 00:19:18.484318
|
||||
@@ -0,0 +1,162 @@
|
||||
= Logs of language model for Lithuanian (lt) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-21 00:23:03.857157
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Karūna (laivas) (revision 5080379)
|
||||
1650 (revision 4990868)
|
||||
1654 (revision 4991037)
|
||||
1664 (revision 4991048)
|
||||
1665 (revision 4991050)
|
||||
1668 (revision 4991052)
|
||||
1669 (revision 4991053)
|
||||
1672 (revision 4991056)
|
||||
1676 (revision 4991060)
|
||||
1718 (revision 4990914)
|
||||
1909 (revision 4990667)
|
||||
1928 (revision 4990262)
|
||||
1932 (revision 4990613)
|
||||
1956 (revision 4990635)
|
||||
1980 (revision 4990655)
|
||||
Baltijos jūra (revision 5052833)
|
||||
Burinis laivas (revision 4657401)
|
||||
Flagmanas (laivas) (revision 5005271)
|
||||
Grimzlė (revision 4487052)
|
||||
Kalmaras (Švedija) (revision 4978519)
|
||||
Karo laivas (revision 4726931)
|
||||
Karolis XI (revision 4944621)
|
||||
Karolis XII (revision 4915230)
|
||||
Kilis (revision 4325533)
|
||||
Koordinačių sistema (revision 5033980)
|
||||
Laivo vėliava (revision 4986001)
|
||||
Liepos 1 d. (revision 4910200)
|
||||
Nyderlandai (revision 5080140)
|
||||
Rugpjūčio 10 (revision 4910281)
|
||||
Varytuvas (revision 4620792)
|
||||
Vaza (laivas) (revision 5079282)
|
||||
XVIII a. (revision 4896219)
|
||||
XVII a. (revision 4768242)
|
||||
Švedija (revision 5057665)
|
||||
Švedų kalba (revision 4687559)
|
||||
1590 (revision 4990983)
|
||||
1596 (revision 4990989)
|
||||
1608 (revision 4991000)
|
||||
1610 (revision 4991002)
|
||||
1623 m. (revision 4991015)
|
||||
1634 m. (revision 4991026)
|
||||
1643 m. (revision 4990870)
|
||||
1644 m. (revision 4990872)
|
||||
1645 m. (revision 4990873)
|
||||
1646 m. (revision 4990874)
|
||||
1647 m. (revision 4913295)
|
||||
1648 m. (revision 4990875)
|
||||
1649 m. (revision 4990876)
|
||||
1651 m. (revision 4991035)
|
||||
1652 m. (revision 4991072)
|
||||
1653 m. (revision 4991036)
|
||||
1654 m. (revision 4991037)
|
||||
1655 m. (revision 4991038)
|
||||
1662 m. (revision 4991046)
|
||||
1668 m. (revision 4991052)
|
||||
1677 m. (revision 4991061)
|
||||
1702 (revision 4990595)
|
||||
1704 (revision 4990863)
|
||||
1722 (revision 4990918)
|
||||
1723 (revision 4990919)
|
||||
1737 (revision 4990931)
|
||||
2 tūkstantmetis (revision 4296407)
|
||||
ATR (revision 5078529)
|
||||
Abiejų Tautų Respublika (revision 5078529)
|
||||
Adomas Freitagas (revision 4362991)
|
||||
Anglų kalba (revision 4911240)
|
||||
Armėnų kalendorius (revision 4817534)
|
||||
Bahajų kalendorius (revision 4706296)
|
||||
Bajorai (revision 5006456)
|
||||
Berberų kalendorius (revision 4926904)
|
||||
Birželio 21 (revision 4910142)
|
||||
Bizantijos kalendorius (revision 4927623)
|
||||
Budistų kalendorius (revision 4705734)
|
||||
Dešimtmetis (revision 4296419)
|
||||
Dominikonai (revision 4921895)
|
||||
Dominikonų ordinas (revision 4921895)
|
||||
Džohoro sultonatas (revision 4934526)
|
||||
Džu Ihai (revision 4991072)
|
||||
Džu Joulang (revision 4991072)
|
||||
Emanuelis Vladislovas Tiškevičius Logoiskis (revision 4939239)
|
||||
Filosofas (revision 5078172)
|
||||
Gegužės 26 (revision 4910130)
|
||||
Grafas (titulas) (revision 5008057)
|
||||
Grigaliaus kalendorius (revision 5000317)
|
||||
Hebrajų kalendorius (revision 4728592)
|
||||
Imperatorius Go-Komijas (revision 4907057)
|
||||
Inocentas X (revision 4905150)
|
||||
Iraniečių kalendorius (revision 4964854)
|
||||
Isaac Titsingh (revision 4990745)
|
||||
Japonija (revision 5035249)
|
||||
Japonijos imperatorius (revision 4720428)
|
||||
Japonų kalendorius (revision 4956765)
|
||||
John Churchill (revision 4903704)
|
||||
Jonas Kazimieras Vaza (revision 5037754)
|
||||
Jurgis Kasakauskis (revision 5047829)
|
||||
Jurgis Kazimieras Ancuta (revision 5059404)
|
||||
Jurgis Mikalojus Tiškevičius (revision 4939554)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-21 00:25:34.773941
|
||||
|
||||
60 characters appeared 353051 times.
|
||||
|
||||
First 38 characters:
|
||||
[ 0] Char i: 13.032394753165974 %
|
||||
[ 1] Char a: 11.167225131779828 %
|
||||
[ 2] Char s: 8.586578143101137 %
|
||||
[ 3] Char o: 7.018815978428046 %
|
||||
[ 4] Char e: 5.525830545728521 %
|
||||
[ 5] Char r: 5.469181506354606 %
|
||||
[ 6] Char n: 5.142599794363987 %
|
||||
[ 7] Char t: 5.105777918770942 %
|
||||
[ 8] Char u: 4.270487833202568 %
|
||||
[ 9] Char k: 3.9617505686147325 %
|
||||
[10] Char l: 3.9051015292408184 %
|
||||
[11] Char m: 3.359854525266888 %
|
||||
[12] Char d: 3.0372382460324427 %
|
||||
[13] Char v: 2.7270847554602593 %
|
||||
[14] Char j: 2.4472385009531203 %
|
||||
[15] Char p: 2.329125253858508 %
|
||||
[16] Char g: 1.9427788053284087 %
|
||||
[17] Char ė: 1.5657794482950054 %
|
||||
[18] Char b: 1.5074309377398734 %
|
||||
[19] Char y: 1.2236192504765602 %
|
||||
[20] Char ų: 1.181698961339863 %
|
||||
[21] Char š: 0.9630336693565519 %
|
||||
[22] Char ž: 0.8171623929687212 %
|
||||
[23] Char c: 0.5959478942135839 %
|
||||
[24] Char č: 0.48010060869392807 %
|
||||
[25] Char f: 0.428266737666796 %
|
||||
[26] Char h: 0.42515104050123065 %
|
||||
[27] Char z: 0.4010751987673169 %
|
||||
[28] Char ū: 0.3685020011273159 %
|
||||
[29] Char ą: 0.3526402701026197 %
|
||||
[30] Char į: 0.29004308159444386 %
|
||||
[31] Char ę: 0.14813723796278724 %
|
||||
[32] Char x: 0.08752276583269838 %
|
||||
[33] Char w: 0.059198246145740985 %
|
||||
[34] Char ō: 0.01812769259965274 %
|
||||
[35] Char ö: 0.008780601102956797 %
|
||||
[36] Char é: 0.0076476203154785 %
|
||||
[37] Char q: 0.007364375118608926 %
|
||||
|
||||
The first 38 characters have an accumulated ratio of 0.9996629382157253.
|
||||
|
||||
1016 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9928710196247589
|
||||
Next 512 (512-1024): 0.008171623929687212
|
||||
Rest: -4.85722573273506e-17
|
||||
|
||||
- Processing end: 2016-09-21 00:25:34.935858
|
||||
@@ -0,0 +1,147 @@
|
||||
= Logs of language model for Maltese (mt) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-21 02:05:23.411546
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Unjoni Ewropea (revision 246298)
|
||||
1951 (revision 229183)
|
||||
1952 (revision 229184)
|
||||
1957 (revision 229188)
|
||||
1958 (revision 229189)
|
||||
1973 (revision 223536)
|
||||
1979 (revision 243876)
|
||||
1981 (revision 205545)
|
||||
1985 (revision 216368)
|
||||
1986 (revision 231433)
|
||||
1990 (revision 237666)
|
||||
1992 (revision 244087)
|
||||
1995 (revision 214650)
|
||||
1 ta' Mejju (revision 245374)
|
||||
2007 (revision 214851)
|
||||
2013 (revision 245606)
|
||||
Albanija (revision 243079)
|
||||
Awstrija (revision 243627)
|
||||
Awtonomija (revision 245824)
|
||||
Ażores (revision 246298)
|
||||
Bank Ċentrali Ewropew (revision 246298)
|
||||
Belt kapitali (revision 237400)
|
||||
Belġju (revision 244363)
|
||||
Brussell (revision 243311)
|
||||
Bulgarija (revision 243622)
|
||||
Danimarka (revision 244419)
|
||||
De facto (revision 215102)
|
||||
Estonja (revision 243826)
|
||||
European Free Trade Association (revision 246298)
|
||||
Ewropa (revision 244177)
|
||||
Ex Repubblika Jugoslava tal-Maċedonja (revision 246298)
|
||||
Federazzjoni (revision 246226)
|
||||
Finlandja (revision 245824)
|
||||
Frankfurt (revision 243576)
|
||||
Franza (revision 244461)
|
||||
Greċja (revision 244423)
|
||||
Groenlandja (revision 243829)
|
||||
Indja (revision 244873)
|
||||
Islanda (revision 243771)
|
||||
Isle of Man (revision 246298)
|
||||
Istitut tal-Unjoni Ewropea għall-Istudji dwar is-Sigurtà (revision 244412)
|
||||
Italja (revision 246323)
|
||||
Kilometru kwadru (revision 244871)
|
||||
Komunitajiet Ewropej (revision 246298)
|
||||
Komunità Ekonomika Ewropea (revision 246298)
|
||||
Kroazja (revision 245711)
|
||||
Kummissjoni Ewropea (revision 243311)
|
||||
Kunsill Ewropew (revision 246298)
|
||||
Kunsill tal-Ewropa (revision 243334)
|
||||
Kunsill tal-Unjoni Ewropea (revision 243311)
|
||||
Latvja (revision 245746)
|
||||
Lista ta' pajjiżi skont id-daqs (revision 244419)
|
||||
Lista ta' pajjiżi skont il-popolazzjoni (revision 246128)
|
||||
Litwanja (revision 243114)
|
||||
Liġijiet tal-Unjoni Ewropea (revision 246298)
|
||||
Lussemburgu (revision 244239)
|
||||
Lussemburgu (belt) (revision 243587)
|
||||
Madejra (revision 243625)
|
||||
Malta (revision 247210)
|
||||
Montenegro (revision 243930)
|
||||
Norveġja (revision 243829)
|
||||
Olanda (revision 243989)
|
||||
Organizzazzjoni Internazzjonali (revision 246724)
|
||||
Pajjiżi l-Baxxi (revision 243989)
|
||||
Pajjiżi membri tal-Unjoni Ewropea (revision 243625)
|
||||
Pajjiżi ġirien li jdawru l-Unjoni Ewropea (revision 246298)
|
||||
Parlament Ewropew (revision 243907)
|
||||
Patt ta' Stabilità u Tkabbir (revision 246298)
|
||||
Politika agrikola komuni (revision 244363)
|
||||
Politika reġjonali tal-Unjoni Ewropea (revision 246298)
|
||||
Polonja (revision 244530)
|
||||
Portugall (revision 243625)
|
||||
Relazzjonijiet ta' terzi pajjiżi ma l-UE (revision 246298)
|
||||
Renju Unit (revision 247318)
|
||||
Repubblika Federali tal-Ġermanja (revision 244859)
|
||||
Repubblika tal-Irlanda (revision 243686)
|
||||
Repubblika Ċeka (revision 246832)
|
||||
Rumanija (revision 243623)
|
||||
Segretarjat tal-Parlament Ewropew (revision 246298)
|
||||
Serbja (revision 243728)
|
||||
Slovakkja (revision 243831)
|
||||
Slovenja (revision 244588)
|
||||
Spanja (revision 246856)
|
||||
Stati Uniti tal-Amerika (revision 243926)
|
||||
Stati membri tal-Unjoni Ewropea (revision 243114)
|
||||
Strasburgu (revision 243503)
|
||||
Sui generis (revision 247150)
|
||||
Suq komuni (revision 246298)
|
||||
Svezja (revision 244871)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-21 02:07:45.508113
|
||||
|
||||
48 characters appeared 474337 times.
|
||||
|
||||
First 31 characters:
|
||||
[ 0] Char a: 12.326257492036252 %
|
||||
[ 1] Char i: 12.069899670487438 %
|
||||
[ 2] Char t: 8.064941170518008 %
|
||||
[ 3] Char l: 7.795301652622502 %
|
||||
[ 4] Char e: 6.615971345267184 %
|
||||
[ 5] Char n: 6.128132530247482 %
|
||||
[ 6] Char r: 5.579577389071483 %
|
||||
[ 7] Char u: 4.376424356522894 %
|
||||
[ 8] Char o: 3.8337721915009797 %
|
||||
[ 9] Char j: 3.7378488289971057 %
|
||||
[10] Char m: 3.6084049947611088 %
|
||||
[11] Char s: 3.3533120966738834 %
|
||||
[12] Char k: 2.588033402412209 %
|
||||
[13] Char d: 2.3173397816320462 %
|
||||
[14] Char p: 2.0555006250830106 %
|
||||
[15] Char b: 2.017131280081461 %
|
||||
[16] Char f: 2.004692866042497 %
|
||||
[17] Char ħ: 1.6372326004507345 %
|
||||
[18] Char w: 1.4801712706366992 %
|
||||
[19] Char g: 1.4763765002519307 %
|
||||
[20] Char z: 1.3150987588992635 %
|
||||
[21] Char ż: 0.9910675321554084 %
|
||||
[22] Char h: 0.9750451683086075 %
|
||||
[23] Char ġ: 0.7640137708000851 %
|
||||
[24] Char ċ: 0.6723068198348432 %
|
||||
[25] Char x: 0.5892435125237964 %
|
||||
[26] Char v: 0.5668965313690478 %
|
||||
[27] Char q: 0.5647883255997318 %
|
||||
[28] Char c: 0.2759641352034524 %
|
||||
[29] Char à: 0.10730767365817974 %
|
||||
[30] Char y: 0.059029761540845424 %
|
||||
|
||||
The first 31 characters have an accumulated ratio of 0.9994708403519017.
|
||||
|
||||
870 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9959115850692665
|
||||
Next 512 (512-1024): 2.108205769315908e-06
|
||||
Rest: -4.423544863740858e-17
|
||||
|
||||
- Processing end: 2016-09-21 02:07:45.646198
|
||||
@@ -0,0 +1,154 @@
|
||||
= Logs of language model for Polish (pl) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-21 17:06:43.735784
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Krasnyj Krym (revision 46884814)
|
||||
1913 (revision 46708474)
|
||||
1915 (revision 46743905)
|
||||
1917 (revision 46559521)
|
||||
1925 (revision 46809935)
|
||||
1928 (revision 46875978)
|
||||
1929 (revision 46760445)
|
||||
1935 (revision 46487358)
|
||||
1936 (revision 46874348)
|
||||
1939 (revision 46789269)
|
||||
1941 (revision 46856112)
|
||||
1942 (revision 46851808)
|
||||
1943 (revision 46768330)
|
||||
1944 (revision 46866229)
|
||||
1949 (revision 46882598)
|
||||
1953 (revision 46437607)
|
||||
1957 (revision 46591716)
|
||||
1959 (revision 46255886)
|
||||
Admirał Butakow (revision 45993412)
|
||||
Admirał Spiridow (revision 45993412)
|
||||
Aparat torpedowy (revision 46633263)
|
||||
Askold (revision 45787848)
|
||||
Avro 504 (revision 44668646)
|
||||
Ałmaz (1903) (revision 46472283)
|
||||
Batumi (revision 46594611)
|
||||
Bomba głębinowa (revision 46011227)
|
||||
Brest (revision 45771242)
|
||||
Burta (revision 45569092)
|
||||
Cagliari (revision 46235605)
|
||||
Cesariewicz (revision 40031486)
|
||||
Czerwona Ukraina (revision 45993524)
|
||||
Daty nowego i starego porządku (revision 45622575)
|
||||
Drednot (revision 45789788)
|
||||
Działo przeciwlotnicze (revision 45160162)
|
||||
Flota Bałtycka Marynarki Wojennej Rosji (revision 45700667)
|
||||
Gromoboj (revision 44328986)
|
||||
Hulk (okręt) (revision 46020688)
|
||||
II wojna światowa (revision 46871591)
|
||||
I wojna światowa (revision 46869119)
|
||||
Imperator Nikołaj I (okręt lotniczy) (revision 45520638)
|
||||
Imperium Rosyjskie (revision 46604959)
|
||||
Impierator Nikołaj I (1916) (revision 46534166)
|
||||
Język rosyjski (revision 46433952)
|
||||
Kanonierka (revision 41091952)
|
||||
Kanonierki typu Ardagan (revision 46534166)
|
||||
Kanonierki typu Bobr (revision 45788694)
|
||||
Kanonierki typu Chiwiniec (revision 46534166)
|
||||
Kanonierki typu Groziaszczij (revision 46534166)
|
||||
Kanonierki typu Mandżur (revision 46534166)
|
||||
Karabin maszynowy DSzK (revision 45587452)
|
||||
Karabin maszynowy Vickers 12,7 mm (revision 44572918)
|
||||
Kocioł parowy (revision 46716473)
|
||||
Konstrukcyjna linia wodna (revision 37082620)
|
||||
Kontrtorpedowce typu Biesstrasznyj (revision 46534166)
|
||||
Kontrtorpedowce typu Brawyj (revision 46534166)
|
||||
Kontrtorpedowce typu Grozowoj (revision 46534166)
|
||||
Kontrtorpedowce typu Prytkij (revision 46534166)
|
||||
Koń mechaniczny (revision 44722357)
|
||||
Krab (1915) (revision 42791389)
|
||||
Kronsztad (revision 46425497)
|
||||
Krążownik lekki (revision 40661490)
|
||||
Krążownik liniowy (revision 40601776)
|
||||
Krążownik pancernopokładowy (revision 40055901)
|
||||
Krążownik pancerny (revision 40324458)
|
||||
Krążowniki lekkie typu Swietłana (revision 45993412)
|
||||
Krążowniki liniowe typu Borodino (revision 45990866)
|
||||
Krążowniki typu Admirał Nachimow (revision 45993521)
|
||||
Krążowniki typu Bajan (revision 45991279)
|
||||
Krążowniki typu Diana (revision 45991349)
|
||||
Krążowniki typu Izumrud (revision 45991349)
|
||||
Lend-Lease Act (revision 46877263)
|
||||
Marynarka Wojenna Związku Socjalistycznych Republik Radzieckich (revision 45795993)
|
||||
Maszyna sterowa (revision 28497888)
|
||||
Mecidiye (1903) (revision 43956539)
|
||||
Mila morska (revision 45754209)
|
||||
Mina morska (revision 45781427)
|
||||
Morze Czarne (revision 46729213)
|
||||
Nadbudówka (revision 45292731)
|
||||
Neapol (revision 46823083)
|
||||
Niszczyciel (revision 45799132)
|
||||
Niszczyciele rakietowe projektu 61 (revision 46498775)
|
||||
Niszczyciele typu Finn (revision 46620140)
|
||||
Niszczyciele typu Lejtienant Szestakow (revision 46620140)
|
||||
Niszczyciele typu Ochotnik (revision 46620140)
|
||||
Niszczyciele typu Ukraina (revision 46620140)
|
||||
Noworosyjsk (revision 44721836)
|
||||
Odessa (revision 45629804)
|
||||
Oerlikon 20 mm (revision 45493862)
|
||||
Okres międzywojenny (revision 46668249)
|
||||
Okręt-baza wodnosamolotów (revision 45115462)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-21 17:21:04.404471
|
||||
|
||||
78 characters appeared 1159291 times.
|
||||
|
||||
First 37 characters:
|
||||
[ 0] Char a: 9.685575062689178 %
|
||||
[ 1] Char i: 8.815819324052374 %
|
||||
[ 2] Char o: 7.920185699707839 %
|
||||
[ 3] Char e: 6.871613770830621 %
|
||||
[ 4] Char r: 5.8672067668945935 %
|
||||
[ 5] Char n: 5.763608964444647 %
|
||||
[ 6] Char s: 4.736688199942896 %
|
||||
[ 7] Char k: 4.722196583946568 %
|
||||
[ 8] Char z: 4.519227700378939 %
|
||||
[ 9] Char w: 4.279512219106333 %
|
||||
[10] Char t: 4.0191806888865695 %
|
||||
[11] Char c: 3.6891513864939864 %
|
||||
[12] Char y: 3.565282573572986 %
|
||||
[13] Char p: 3.0190004062828053 %
|
||||
[14] Char d: 2.851052928039638 %
|
||||
[15] Char l: 2.7930002044352973 %
|
||||
[16] Char m: 2.7530620008263673 %
|
||||
[17] Char u: 2.348504387595522 %
|
||||
[18] Char j: 1.881236031332944 %
|
||||
[19] Char ł: 1.6885320424293815 %
|
||||
[20] Char b: 1.394559260789569 %
|
||||
[21] Char g: 1.3928340684090534 %
|
||||
[22] Char h: 1.163901039514669 %
|
||||
[23] Char ę: 0.8066136975099435 %
|
||||
[24] Char ó: 0.5971753425153823 %
|
||||
[25] Char ą: 0.563275312238256 %
|
||||
[26] Char f: 0.5245447432956868 %
|
||||
[27] Char ż: 0.4545019326467643 %
|
||||
[28] Char ś: 0.39567287247119143 %
|
||||
[29] Char ń: 0.3857530162832283 %
|
||||
[30] Char ć: 0.1397405828217419 %
|
||||
[31] Char v: 0.12455888987320698 %
|
||||
[32] Char ź: 0.10204512930748191 %
|
||||
[33] Char x: 0.05468859846233603 %
|
||||
[34] Char é: 0.020961087423261287 %
|
||||
[35] Char á: 0.01707940456710179 %
|
||||
[36] Char q: 0.011386269711401192 %
|
||||
|
||||
The first 37 characters have an accumulated ratio of 0.9993892818972973.
|
||||
|
||||
1321 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9894531815946438
|
||||
Next 512 (512-1024): 1.7251923805153322e-06
|
||||
Rest: 0.0003530230403650733
|
||||
|
||||
- Processing end: 2016-09-21 17:21:04.878014
|
||||
@@ -0,0 +1,166 @@
|
||||
= Logs of language model for Portuguese (pt) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-20 23:44:39.722451
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Papagaio-das-mascarenhas (revision 46763149)
|
||||
Albinismo (revision 46498446)
|
||||
Alfred Newton (revision 43617011)
|
||||
Alphonse Milne-Edwards (revision 39740747)
|
||||
Animalia (revision 46727732)
|
||||
Asa (revision 46338820)
|
||||
August von Pelzeln (revision 34726241)
|
||||
Aves (revision 46728980)
|
||||
Bico (revision 45311553)
|
||||
Carl Wilhelm Hahn (revision 45025566)
|
||||
Carlos Lineu (revision 46625396)
|
||||
Carolus Linnaeus (revision 46625396)
|
||||
Cauda (revision 43275401)
|
||||
Charles Lucien Bonaparte (revision 45529712)
|
||||
Chordata (revision 46640101)
|
||||
Cladograma (revision 46700307)
|
||||
Classe (biologia) (revision 46701409)
|
||||
Classificação científica (revision 46306288)
|
||||
Coleção Leverian (revision 45026647)
|
||||
Comores (revision 46181501)
|
||||
Coracopsinae (revision 36946101)
|
||||
Coracopsis nigra (revision 44338845)
|
||||
Coracopsis vasa (revision 42905822)
|
||||
Cylindraspis indica (revision 42905410)
|
||||
Cúlmen (revision 45311553)
|
||||
Digital object identifier (revision 42172651)
|
||||
Eclectus roratus (revision 44380798)
|
||||
Edward Newton (revision 39261469)
|
||||
Endemismo (revision 45260961)
|
||||
Epíteto específico (revision 35101647)
|
||||
Espécie (revision 45685675)
|
||||
Esquilo-vermelho (revision 43489595)
|
||||
Estado de conservação (revision 46662839)
|
||||
Extinção (revision 46526607)
|
||||
Família (biologia) (revision 46636004)
|
||||
Filo (revision 46704246)
|
||||
França (revision 46740839)
|
||||
François-Nicolas Martinet (revision 43679514)
|
||||
François Levaillant (revision 40142351)
|
||||
Fredrik Hasselqvist (revision 44381122)
|
||||
Fregilupus varius (revision 46555765)
|
||||
Fumigação (revision 42458244)
|
||||
George Robert Gray (revision 39047844)
|
||||
Georges-Louis Leclerc, conde de Buffon (revision 45622418)
|
||||
Género (biologia) (revision 45296588)
|
||||
Hermann Schlegel (revision 43137605)
|
||||
Herpetologista (revision 46207704)
|
||||
Histoire Naturelle (revision 44293456)
|
||||
Holótipo (revision 44029660)
|
||||
Ilha da Reunião (revision 45458206)
|
||||
Ilha vulcânica (revision 37924535)
|
||||
Ilhas Mascarenhas (revision 45858660)
|
||||
Ilhas Molucas (revision 45476933)
|
||||
International Standard Book Number (revision 46326494)
|
||||
Jacques Barraband (revision 45007769)
|
||||
Jean Feuilley (revision 43140791)
|
||||
Johann Georg Wagler (revision 34585234)
|
||||
John Gerrard Keulemans (revision 39664498)
|
||||
Julian Hume (revision 41876605)
|
||||
Leiolopisma (revision 43997173)
|
||||
Lionel Walter Rothschild (revision 46022922)
|
||||
Lista Vermelha da IUCN (revision 46569884)
|
||||
Lista Vermelha da União Internacional para a Conservação da Natureza e dos Recursos Naturais (revision 46569884)
|
||||
Lista Vermelha de Espécies Ameaçadas da IUCN (revision 46569884)
|
||||
Lista de aves extintas (revision 45507420)
|
||||
Londres (revision 46310311)
|
||||
Língua inglesa (revision 46609785)
|
||||
Madagascar (revision 46617630)
|
||||
Mascarenotus grucheti (revision 43145662)
|
||||
Mathurin Jacques Brisson (revision 36018826)
|
||||
Maurício (revision 46723599)
|
||||
Maximiliano I José da Baviera (revision 46372080)
|
||||
Melanina (revision 46762903)
|
||||
Museu Nacional de História Natural (França) (revision 43731807)
|
||||
Naturhistorisches Museum (revision 46694247)
|
||||
Nesoenas duboisi (revision 43995805)
|
||||
Nome científico (revision 46671641)
|
||||
Nomenclatura binomial (revision 46671641)
|
||||
Nycticorax duboisi (revision 43816214)
|
||||
Nível do mar (revision 46414695)
|
||||
Ordem (biologia) (revision 46360024)
|
||||
Otto Finsch (revision 42362273)
|
||||
Papagaio (revision 46738207)
|
||||
Papagaio-cinzento (revision 46673943)
|
||||
Papagaio-cinzento-de-maurício (revision 46664408)
|
||||
Pedro Mascarenhas (c. 1484-1555) (revision 45541977)
|
||||
Periquito-de-maurício (revision 43010883)
|
||||
Periquito-de-reunião (revision 43048764)
|
||||
Peter Mundy (revision 43563846)
|
||||
Piton des Neiges (revision 45632497)
|
||||
Pleistoceno (revision 45916874)
|
||||
Plumagem (revision 34951058)
|
||||
Ponto quente (revision 45375495)
|
||||
Porphyrio coerulescens (revision 43672493)
|
||||
Praslin (revision 40728143)
|
||||
Psitacídeos (revision 46598835)
|
||||
Psittaciformes (revision 46598835)
|
||||
Psittacula (revision 42856453)
|
||||
Psittaculinae (revision 46760737)
|
||||
Psittaculini (revision 43015966)
|
||||
Psittrichasiidae (revision 44385977)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-20 23:47:27.346826
|
||||
|
||||
51 characters appeared 558324 times.
|
||||
|
||||
First 38 characters:
|
||||
[ 0] Char a: 11.864795351802895 %
|
||||
[ 1] Char e: 11.44604208309154 %
|
||||
[ 2] Char o: 9.868284365350585 %
|
||||
[ 3] Char s: 8.346587286235232 %
|
||||
[ 4] Char i: 7.118089138206489 %
|
||||
[ 5] Char r: 6.394136737808154 %
|
||||
[ 6] Char n: 5.568272186042513 %
|
||||
[ 7] Char d: 5.243192125002687 %
|
||||
[ 8] Char t: 4.80061756256224 %
|
||||
[ 9] Char m: 4.498105042949971 %
|
||||
[10] Char c: 3.9747530107965985 %
|
||||
[11] Char u: 3.7229279056605127 %
|
||||
[12] Char l: 3.207814817202914 %
|
||||
[13] Char p: 2.77562848811801 %
|
||||
[14] Char g: 1.3850380782484721 %
|
||||
[15] Char v: 1.3210967108703908 %
|
||||
[16] Char f: 1.122466524813549 %
|
||||
[17] Char b: 0.9702251739133549 %
|
||||
[18] Char h: 0.9130898904578704 %
|
||||
[19] Char é: 0.7026386112723079 %
|
||||
[20] Char ã: 0.7022803963290133 %
|
||||
[21] Char q: 0.5903382265494588 %
|
||||
[22] Char ç: 0.5856814322866293 %
|
||||
[23] Char í: 0.41391736697688086 %
|
||||
[24] Char x: 0.3913498255493226 %
|
||||
[25] Char á: 0.34567742027926435 %
|
||||
[26] Char z: 0.3170202248156984 %
|
||||
[27] Char ó: 0.22925756370852768 %
|
||||
[28] Char j: 0.20454073262120204 %
|
||||
[29] Char ê: 0.20239144296143458 %
|
||||
[30] Char õ: 0.16155493942585308 %
|
||||
[31] Char y: 0.15080849112701586 %
|
||||
[32] Char w: 0.09241945537000021 %
|
||||
[33] Char ú: 0.08794176857881804 %
|
||||
[34] Char k: 0.08364318925928313 %
|
||||
[35] Char â: 0.07898639499645367 %
|
||||
[36] Char à: 0.06859816164091102 %
|
||||
[37] Char ô: 0.031164700066627977 %
|
||||
|
||||
The first 38 characters have an accumulated ratio of 0.9998137282294869.
|
||||
|
||||
891 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9953179582313172
|
||||
Next 512 (512-1024): 1.7910747164728723e-06
|
||||
Rest: 2.42861286636753e-17
|
||||
|
||||
- Processing end: 2016-09-20 23:47:27.489355
|
||||
@@ -0,0 +1,153 @@
|
||||
= Logs of language model for Romanian (ro) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-28 18:53:56.086095
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
The Loving Kind (revision 10166481)
|
||||
12 ianuarie (revision 10711676)
|
||||
13 decembrie (revision 9938353)
|
||||
2007 (revision 10716321)
|
||||
2008 (revision 10752084)
|
||||
2009 (revision 10654003)
|
||||
21 noiembrie (revision 10447643)
|
||||
25 ianuarie (revision 10228199)
|
||||
31 ianuarie (revision 10718063)
|
||||
4 Music (revision 9701591)
|
||||
Billboard (revision 10505294)
|
||||
Biology (revision 10112430)
|
||||
Bulgaria (revision 10481051)
|
||||
CD (revision 10477531)
|
||||
Call The Shots (revision 10101027)
|
||||
Call the Shots (revision 10101027)
|
||||
Can't Speak French (revision 9721506)
|
||||
Casă de discuri (revision 10611348)
|
||||
Channel 4 (revision 7953101)
|
||||
Chemistry (revision 10112479)
|
||||
Cheryl Cole (revision 10475016)
|
||||
Chitară (revision 10468266)
|
||||
Croația (revision 10737746)
|
||||
Dance (revision 10231736)
|
||||
Descărcare digitală (revision 10100743)
|
||||
Digital Spy (revision 9044016)
|
||||
Discografia Girls Aloud (revision 10172788)
|
||||
Estonia (revision 10749810)
|
||||
Europa (revision 10752724)
|
||||
Fascination Records (revision 9655292)
|
||||
Fiona Phillips (revision 5384082)
|
||||
Gen muzical (revision 10534645)
|
||||
Girls A Live (revision 10112444)
|
||||
Girls Aloud (revision 10112446)
|
||||
Good Morning Television (revision 10166481)
|
||||
Heat World (revision 10166481)
|
||||
I'll Stand By You (cântec de Girls Aloud) (revision 10112432)
|
||||
ITunes (revision 10744174)
|
||||
I Think We're Alone Now (revision 10112427)
|
||||
Irlanda (revision 10573806)
|
||||
Jump (cântec de Girls Aloud) (revision 10112438)
|
||||
Lady GaGa (revision 10753010)
|
||||
Life Got Cold (revision 10112437)
|
||||
Limba engleză (revision 10756676)
|
||||
Long Hot Summer (revision 10112429)
|
||||
Love Machine (revision 10112433)
|
||||
MSN Search (revision 10653298)
|
||||
MTV (revision 10170766)
|
||||
Mixed Up (revision 10112443)
|
||||
Muzică electronică (revision 10608432)
|
||||
Muzică pop (revision 10740529)
|
||||
Nadine Coyle (revision 10316187)
|
||||
Neil Tennant (revision 10499980)
|
||||
No Good Advice (revision 10112436)
|
||||
Out Of Control (revision 10112484)
|
||||
Out of Control (revision 10112484)
|
||||
Pet Shop Boys (revision 10612741)
|
||||
Poker Face (revision 10496402)
|
||||
PopJustice (revision 10625677)
|
||||
Regatul Unit (revision 10752338)
|
||||
Regatul Unit al Marii Britanii și Irlandei de Nord (revision 10752338)
|
||||
Regatul Unit al Marii Britanii și al Irlandei de Nord (revision 10752338)
|
||||
Republica Irlanda (revision 10573806)
|
||||
Romanian Top 100 (revision 10736281)
|
||||
România (revision 10732435)
|
||||
Sarah Harding (revision 10633651)
|
||||
Sarah Hearding (revision 10112425)
|
||||
See the Day (revision 10112431)
|
||||
Sexy! No No No... (revision 10112425)
|
||||
Slant Magazine (revision 7697473)
|
||||
Slovenia (revision 10521499)
|
||||
Something Kinda Ooooh (revision 10112426)
|
||||
Sound of the Underground (album) (revision 10112476)
|
||||
Sound of the Underground (cântec) (revision 10112434)
|
||||
Tangled Up (revision 10112482)
|
||||
The Guardian (revision 9752334)
|
||||
The Paul O'Grady Show (revision 10101027)
|
||||
The Promise (revision 10166482)
|
||||
The Show (revision 10112441)
|
||||
The Sound of Girls Aloud (revision 10112480)
|
||||
Tonalitate (revision 9966362)
|
||||
Turneul Out of Control (revision 10112446)
|
||||
UK Mix (revision 9721468)
|
||||
UK Singles Chart (revision 10226705)
|
||||
Ungaria (revision 10737745)
|
||||
Uniunea Europeană (revision 10751590)
|
||||
Untouchable (revision 10112410)
|
||||
Wake Me Up (revision 10112439)
|
||||
What Will The Neighbours Say? (revision 10112478)
|
||||
Whole Lotta History (revision 10475020)
|
||||
Wideboys (revision 10166481)
|
||||
Wikimedia Commons (revision 9703907)
|
||||
Xenomania (revision 10112484)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-28 18:58:13.756622
|
||||
|
||||
60 characters appeared 883554 times.
|
||||
|
||||
First 33 characters:
|
||||
[ 0] Char e: 11.67014127036944 %
|
||||
[ 1] Char i: 10.97567324690964 %
|
||||
[ 2] Char a: 10.080198833348046 %
|
||||
[ 3] Char r: 7.490657050955572 %
|
||||
[ 4] Char n: 7.18246988865423 %
|
||||
[ 5] Char t: 6.516296683620921 %
|
||||
[ 6] Char l: 5.595130574928075 %
|
||||
[ 7] Char u: 5.551217016730161 %
|
||||
[ 8] Char o: 4.922732509840938 %
|
||||
[ 9] Char c: 4.495707110148333 %
|
||||
[10] Char s: 3.8308920563994957 %
|
||||
[11] Char d: 3.590499279048027 %
|
||||
[12] Char m: 2.971408651876399 %
|
||||
[13] Char p: 2.902369294915761 %
|
||||
[14] Char ă: 2.1349006399156134 %
|
||||
[15] Char g: 1.2248261000459508 %
|
||||
[16] Char f: 1.1199089133205216 %
|
||||
[17] Char b: 1.0781457613230203 %
|
||||
[18] Char ț: 1.0323081554721047 %
|
||||
[19] Char ș: 0.9732285745975912 %
|
||||
[20] Char î: 0.97017273420753 %
|
||||
[21] Char v: 0.9693804792915882 %
|
||||
[22] Char z: 0.7369102510995367 %
|
||||
[23] Char h: 0.533413916976212 %
|
||||
[24] Char â: 0.4986678799484808 %
|
||||
[25] Char x: 0.22081276300033725 %
|
||||
[26] Char j: 0.20055367300696958 %
|
||||
[27] Char k: 0.1901411798260208 %
|
||||
[28] Char y: 0.15471606715605385 %
|
||||
[29] Char w: 0.11827234102273318 %
|
||||
[30] Char á: 0.016297815413658927 %
|
||||
[31] Char é: 0.013355154297303842 %
|
||||
[32] Char q: 0.00520624659047438 %
|
||||
|
||||
The first 33 characters have an accumulated ratio of 0.9996661211425673.
|
||||
|
||||
981 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.997762564143313
|
||||
Next 512 (512-1024): 1.1317927370596478e-06
|
||||
Rest: 3.0357660829594124e-18
|
||||
|
||||
- Processing end: 2016-09-28 18:58:13.862425
|
||||
@@ -0,0 +1,158 @@
|
||||
= Logs of language model for Slovak (sk) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-21 13:26:28.712674
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Dôkaz (matematika) (revision 6358810)
|
||||
1825 (revision 6122752)
|
||||
1839 (revision 6165808)
|
||||
1847 (revision 5941780)
|
||||
1852 (revision 5941777)
|
||||
1878 (revision 6221358)
|
||||
1955 (revision 6226609)
|
||||
1976 (revision 6310709)
|
||||
1983 (revision 6356952)
|
||||
1993 (revision 6348358)
|
||||
1995 (revision 6277350)
|
||||
2012 (revision 6291145)
|
||||
Adrien-Marie Legendre (revision 6060342)
|
||||
Algebra (revision 6319238)
|
||||
Algebraická geometria (revision 5964212)
|
||||
Algebraická rovnica (revision 5288111)
|
||||
Algebrické číslo (revision 6106622)
|
||||
Algoritmus (revision 6286937)
|
||||
Andrew Wiles (revision 5791970)
|
||||
Arabi (revision 6044956)
|
||||
Arabčina (revision 6322514)
|
||||
Aristoteles (revision 6359959)
|
||||
Arthur Cayley (revision 6332355)
|
||||
Axióma (revision 6338092)
|
||||
Babylonia (revision 6168813)
|
||||
Bernard Bolzano (revision 6261374)
|
||||
Boh (revision 6282272)
|
||||
Bolzanova veta (revision 6345299)
|
||||
Bytie (revision 5274918)
|
||||
Byzantská ríša (revision 6359782)
|
||||
Caroline Blundenová (revision 6358810)
|
||||
Cauchyho postupnosť (revision 6215169)
|
||||
Celé číslo (revision 6302805)
|
||||
Charles Hermite (revision 5751036)
|
||||
Daniel Marcus (revision 5657431)
|
||||
David Hilbert (revision 5968866)
|
||||
Dedukcia (revision 6338099)
|
||||
Definícia (revision 6106684)
|
||||
Derivácia (funkcia) (revision 5970574)
|
||||
Desiatková číselná sústava (revision 5924486)
|
||||
Diofantická rovnica (revision 6327292)
|
||||
Dynastia Chan (revision 6342042)
|
||||
Dôkaz (logika) (revision 5495754)
|
||||
Dôkaz sporom (revision 5940134)
|
||||
Dôkaz výpočtom (revision 6358810)
|
||||
Energia (revision 6277761)
|
||||
Eric Weisstein (revision 6054413)
|
||||
Ernst Kummer (revision 6001344)
|
||||
Európa (revision 6295124)
|
||||
Experiment (revision 6354302)
|
||||
Fenomén (filozofia) (revision 5420897)
|
||||
Filozofia (revision 6296369)
|
||||
Formula (logika) (revision 3916562)
|
||||
Formálny dôkaz (revision 6358810)
|
||||
Formálny jazyk (revision 5623029)
|
||||
Gabriel Cramer (revision 5923903)
|
||||
Galoisova teória (revision 6353573)
|
||||
Gentzenovský kalkul (revision 6358810)
|
||||
Geometria (revision 5970028)
|
||||
Geometrický dôkaz (revision 6358810)
|
||||
Georg Ferdinand Cantor (revision 6186696)
|
||||
Giordano Bruno (revision 6312876)
|
||||
Gottlob Frege (revision 5968855)
|
||||
Gödelova veta o neúplnosti (revision 5323549)
|
||||
Hardvér (revision 6214401)
|
||||
Henri Poincaré (revision 6315506)
|
||||
Hilbertovský kalkul (revision 6358810)
|
||||
Hmotnosť (revision 5979540)
|
||||
Hypotéza (revision 5983410)
|
||||
Idea (revision 5960449)
|
||||
India (revision 6362189)
|
||||
Intuícia (revision 5837951)
|
||||
Jazyk (lingvistika) (revision 6073293)
|
||||
John Taylor (revision 6355518)
|
||||
Kardinálne číslo (revision 6090126)
|
||||
Kenneth Appel (revision 5968422)
|
||||
Klasická mechanika (revision 6295646)
|
||||
Konečná množina (revision 5276494)
|
||||
Konfucianizmus (revision 5968816)
|
||||
Kresťanstvo (revision 6289571)
|
||||
Langlandsov program (revision 6088475)
|
||||
Latinčina (revision 6121105)
|
||||
Leonhard Euler (revision 6339382)
|
||||
Lineárna algebra (revision 5473535)
|
||||
Logická axióma (revision 5495754)
|
||||
Logický kalkul (revision 1608550)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-21 13:33:10.330458
|
||||
|
||||
62 characters appeared 550293 times.
|
||||
|
||||
First 45 characters:
|
||||
[ 0] Char o: 8.867094438780795 %
|
||||
[ 1] Char a: 8.59705647718579 %
|
||||
[ 2] Char e: 8.562347694773512 %
|
||||
[ 3] Char n: 6.0867574183207855 %
|
||||
[ 4] Char i: 5.828531346028389 %
|
||||
[ 5] Char t: 5.366595613609477 %
|
||||
[ 6] Char r: 4.977711873492848 %
|
||||
[ 7] Char k: 4.264273759615332 %
|
||||
[ 8] Char s: 4.257731790155426 %
|
||||
[ 9] Char v: 4.117079446767449 %
|
||||
[10] Char l: 3.5979014815743615 %
|
||||
[11] Char d: 3.416361829061972 %
|
||||
[12] Char m: 3.2513588215732345 %
|
||||
[13] Char p: 2.878466562358598 %
|
||||
[14] Char u: 2.5987973679476206 %
|
||||
[15] Char c: 2.419438371921867 %
|
||||
[16] Char z: 2.127412124086623 %
|
||||
[17] Char h: 2.0687161203213558 %
|
||||
[18] Char j: 2.0312815173007834 %
|
||||
[19] Char y: 1.6700194260148686 %
|
||||
[20] Char b: 1.6574806512167153 %
|
||||
[21] Char á: 1.6422160558102683 %
|
||||
[22] Char ý: 1.2564215790497062 %
|
||||
[23] Char í: 1.1326693234331529 %
|
||||
[24] Char č: 0.9473135220691523 %
|
||||
[25] Char é: 0.8913433389121795 %
|
||||
[26] Char ž: 0.7668641978000811 %
|
||||
[27] Char ú: 0.6949025337411161 %
|
||||
[28] Char š: 0.6785476100913513 %
|
||||
[29] Char f: 0.6514711253822963 %
|
||||
[30] Char g: 0.6096752093884531 %
|
||||
[31] Char ť: 0.46375294615777407 %
|
||||
[32] Char ô: 0.4172322744428877 %
|
||||
[33] Char ľ: 0.36053520579036985 %
|
||||
[34] Char x: 0.23114958758334195 %
|
||||
[35] Char ó: 0.2251527822450949 %
|
||||
[36] Char ň: 0.09304134342977287 %
|
||||
[37] Char w: 0.09013380144759246 %
|
||||
[38] Char ä: 0.0694175648245571 %
|
||||
[39] Char ď: 0.06560141597294532 %
|
||||
[40] Char q: 0.01726353051919614 %
|
||||
[41] Char ě: 0.009994675563745132 %
|
||||
[42] Char ĺ: 0.009267790068200032 %
|
||||
[43] Char ö: 0.008904347320427481 %
|
||||
[44] Char ŕ: 0.00599680533824708 %
|
||||
|
||||
The first 45 characters have an accumulated ratio of 0.9998128269848972.
|
||||
|
||||
1181 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9733303573968434
|
||||
Next 512 (512-1024): 1.8172137388627513e-06
|
||||
Rest: 0.0003522983638913346
|
||||
|
||||
- Processing end: 2016-09-21 13:33:10.831531
|
||||
@@ -0,0 +1,148 @@
|
||||
= Logs of language model for Slovene (sl) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-28 22:00:35.243966
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
XCOM: Enemy Unknown (revision 4704271)
|
||||
1UP.com (revision 4547348)
|
||||
2K Games (revision 4110089)
|
||||
Android (operacijski sistem) (revision 4619359)
|
||||
Animator videoigre (revision 4702643)
|
||||
App Store (revision 3903089)
|
||||
Artefakt (revision 4484504)
|
||||
Athlon (revision 4524746)
|
||||
Avstralazija (revision 4623530)
|
||||
Avtopsija (revision 4541344)
|
||||
Bralno-pisalni pomnilnik (revision 4256388)
|
||||
Civilization (serija) (revision 4645770)
|
||||
Deus Ex: Human Revolution (revision 4694860)
|
||||
Digitalna distribucija (revision 4696215)
|
||||
DirectX (revision 4477913)
|
||||
Dishonored (revision 4619444)
|
||||
Edge (magazine) (revision 4690049)
|
||||
Electronic Entertainment Expo (revision 4538691)
|
||||
Enoigralska videoigra (revision 4610359)
|
||||
Eurogamer (revision 4694860)
|
||||
Evropa (revision 4687833)
|
||||
Fantasy Flight Games (revision 4649361)
|
||||
Firaxis Games (revision 4110089)
|
||||
GameRankings (revision 3934020)
|
||||
GameSpot (revision 4238015)
|
||||
GameSpy (revision 4538691)
|
||||
GameTrailers (revision 4704271)
|
||||
Game Informer (revision 4704271)
|
||||
GamesTM (revision 4704271)
|
||||
Grafična kartica (revision 4257980)
|
||||
Granata (revision 3859332)
|
||||
Holograf (revision 4477482)
|
||||
IGN (revision 4576233)
|
||||
IOS (revision 4597264)
|
||||
Igra igranja vlog (revision 4642276)
|
||||
Igra na deski (revision 4649363)
|
||||
Igralna konzola (revision 4649866)
|
||||
Igralni pogon (revision 4622773)
|
||||
Intel (revision 4626025)
|
||||
International Standard Book Number (revision 4015087)
|
||||
Izdelovalec videoigre (revision 3851747)
|
||||
Joker (revija) (revision 3867772)
|
||||
Kotaku (revision 4613535)
|
||||
Kristal (revision 4156234)
|
||||
Linux (revision 4524740)
|
||||
Lovec prestreznik (revision 4102792)
|
||||
MTV (revision 4621758)
|
||||
Mac OS X (revision 4601645)
|
||||
Machinima (revision 4601716)
|
||||
Major (revision 4245802)
|
||||
Mednarodna različica (revision 4116054)
|
||||
Metacritic (revision 3934020)
|
||||
Michael McCann (skladatelj) (revision 4694860)
|
||||
MicroProse (revision 4382810)
|
||||
Microsoft Windows (revision 4691357)
|
||||
Nezemeljsko življenje (revision 4620576)
|
||||
NowGamer (revision 4704271)
|
||||
OS X (revision 4601645)
|
||||
Ognjena ekipa (revision 4694450)
|
||||
Operacijski sistem (revision 4698515)
|
||||
Ostrostrelec (revision 4529694)
|
||||
Pilot (revision 4069093)
|
||||
PlayStation 3 (revision 4382944)
|
||||
PlayStation Network (revision 4382944)
|
||||
PlayStation Vita (revision 3944025)
|
||||
Pogon igre (revision 4622773)
|
||||
Procesor (revision 4702518)
|
||||
Producent videoiger (revision 4599904)
|
||||
Razvijalec videoiger (revision 4093281)
|
||||
Računalniška miška (revision 4385579)
|
||||
Računalniška platforma (revision 4673669)
|
||||
Severna Amerika (revision 4643798)
|
||||
Sid Meier (revision 4061487)
|
||||
Stealth (revision 4618630)
|
||||
Steam (revision 4696215)
|
||||
Strateška videoigra (revision 4236795)
|
||||
Tablični računalnik (revision 4409985)
|
||||
Take-Two Interactive (revision 4110089)
|
||||
Telepatija (revision 4481192)
|
||||
The Bureau: XCOM Declassified (revision 4704271)
|
||||
The Guardian (revision 3929479)
|
||||
Trdi disk (revision 4644623)
|
||||
UFO: Enemy Unknown (revision 4704271)
|
||||
Unreal Engine (revision 4622773)
|
||||
Unreal Engine 3 (revision 4622773)
|
||||
Uporabniški vmesnik (revision 4552473)
|
||||
Valve Corporation (revision 4110105)
|
||||
Večigralska videoigra (revision 4618639)
|
||||
VideoGamer.com (revision 4704271)
|
||||
Vohunski satelit (revision 4215166)
|
||||
Vojaška taktika (revision 3970259)
|
||||
Vojaški čini (revision 4363026)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-28 22:06:46.133919
|
||||
|
||||
41 characters appeared 411226 times.
|
||||
|
||||
First 29 characters:
|
||||
[ 0] Char a: 10.090315301075321 %
|
||||
[ 1] Char e: 9.90477255815537 %
|
||||
[ 2] Char i: 9.666703953543793 %
|
||||
[ 3] Char o: 9.177921629468953 %
|
||||
[ 4] Char n: 7.28309980400072 %
|
||||
[ 5] Char r: 5.808241696779873 %
|
||||
[ 6] Char s: 4.575586174025961 %
|
||||
[ 7] Char t: 4.4963110309173056 %
|
||||
[ 8] Char j: 4.343840126840229 %
|
||||
[ 9] Char l: 4.2672399118732764 %
|
||||
[10] Char v: 3.802775116359374 %
|
||||
[11] Char p: 3.5216644861949393 %
|
||||
[12] Char k: 3.5136397017698293 %
|
||||
[13] Char d: 3.0387183689747244 %
|
||||
[14] Char m: 2.9487435132992563 %
|
||||
[15] Char z: 2.350775485985808 %
|
||||
[16] Char u: 1.9719083910064055 %
|
||||
[17] Char g: 1.9342162217369525 %
|
||||
[18] Char b: 1.5392995579073308 %
|
||||
[19] Char c: 1.2924766430138173 %
|
||||
[20] Char h: 1.1864522184881305 %
|
||||
[21] Char č: 1.137087635509428 %
|
||||
[22] Char š: 0.6932927392723223 %
|
||||
[23] Char ž: 0.45303555709026183 %
|
||||
[24] Char f: 0.40707542811009034 %
|
||||
[25] Char x: 0.19381070263067024 %
|
||||
[26] Char y: 0.19040624863213904 %
|
||||
[27] Char w: 0.18919037220409216 %
|
||||
[28] Char q: 0.011186063138031156 %
|
||||
|
||||
The first 29 characters have an accumulated ratio of 0.9998978663800442.
|
||||
|
||||
727 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9983524317161332
|
||||
Next 512 (512-1024): 2.4317528560937295e-06
|
||||
Rest: -3.859759734048396e-17
|
||||
|
||||
- Processing end: 2016-09-28 22:06:46.601266
|
||||
@@ -0,0 +1,109 @@
|
||||
= Logs of language model for Spanish (es) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2015-12-12 18:37:37.085123
|
||||
- Maximum depth: 2
|
||||
- Max number of pages: 50
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Wikipedia:Portada (revision 84894710)
|
||||
11 de diciembre (revision 87735970)
|
||||
12 de diciembre (revision 87742023)
|
||||
13 de diciembre (revision 87697780)
|
||||
1474 (revision 66715698)
|
||||
1915 (revision 86935345)
|
||||
2000 (revision 87686385)
|
||||
2015 (revision 87743360)
|
||||
Actuación (revision 87459085)
|
||||
Akiyuki Nosaka (revision 87726149)
|
||||
Alberto Podestá (revision 87729965)
|
||||
Alejandro Magno (revision 87717064)
|
||||
Argentina (revision 87742018)
|
||||
Arnold Peralta (revision 87733100)
|
||||
Atentados del 11 de diciembre de 2007 (revision 87720544)
|
||||
Cantante (revision 86761085)
|
||||
Canto (revision 87664585)
|
||||
Carlo Furno (revision 87726011)
|
||||
Ciencia ficción (revision 87662615)
|
||||
Copa Mundial de Clubes de la FIFA 2015 (revision 87734956)
|
||||
Corona de Castilla (revision 87209578)
|
||||
Crisis migratoria en Europa (revision 87609406)
|
||||
Dictadura de Primo de Rivera (revision 87371131)
|
||||
Dionisio Miguel Recio (revision 87724426)
|
||||
Disneyland (revision 87665192)
|
||||
Dolph Schayes (revision 87730770)
|
||||
Día Internacional de las Montañas (revision 87739490)
|
||||
El discurso del rey (revision 87570241)
|
||||
Elecciones regionales de Francia de 2015 (revision 87744011)
|
||||
Estados Unidos (revision 87510736)
|
||||
Fiction House (revision 87732511)
|
||||
Filoxeno de Eretria (revision 83958621)
|
||||
Frank Sinatra (revision 87742871)
|
||||
Fundación Wikimedia (revision 87703852)
|
||||
Geoffrey Marcy (revision 87706505)
|
||||
Gheorghe Gruia (revision 87737327)
|
||||
Grupo de Acción Republicana (revision 87739104)
|
||||
Guerra contra el Estado Islámico (revision 87648946)
|
||||
Here We Go Again (canción) (revision 87680365)
|
||||
Isaac Asimov (revision 87591711)
|
||||
Isabel I de Castilla (revision 87743713)
|
||||
John "Hot Rod" Williams (revision 87730438)
|
||||
José Subirà-Puig (revision 87740413)
|
||||
Julio Terrazas Sandoval (revision 87736542)
|
||||
Libertad Lamarque (revision 87508996)
|
||||
Mosaico de Issos (revision 87731652)
|
||||
Museo Arqueológico Nacional de Nápoles (revision 87302262)
|
||||
Philip K. Dick (revision 87725371)
|
||||
Planet Comics (revision 86698920)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2015-12-12 18:39:02.288858
|
||||
|
||||
52 characters appeared 991829 times.
|
||||
|
||||
First 33 characters:
|
||||
[ 0] Char e: 12.571925200815867 %
|
||||
[ 1] Char a: 11.81988024145291 %
|
||||
[ 2] Char o: 8.07941691561751 %
|
||||
[ 3] Char n: 7.234513207417812 %
|
||||
[ 4] Char s: 7.042242160695039 %
|
||||
[ 5] Char i: 7.040528155559072 %
|
||||
[ 6] Char r: 6.8208330266608455 %
|
||||
[ 7] Char l: 5.722559029832763 %
|
||||
[ 8] Char d: 5.275707808503281 %
|
||||
[ 9] Char t: 4.668647518876742 %
|
||||
[10] Char c: 4.466999855821921 %
|
||||
[11] Char u: 3.673717949364255 %
|
||||
[12] Char m: 2.710547886782903 %
|
||||
[13] Char p: 2.4541528832086983 %
|
||||
[14] Char b: 1.3867309788280036 %
|
||||
[15] Char g: 1.2748165258325779 %
|
||||
[16] Char f: 0.925058654263991 %
|
||||
[17] Char y: 0.9045914164639268 %
|
||||
[18] Char v: 0.8877538365988492 %
|
||||
[19] Char ó: 0.8641610600214351 %
|
||||
[20] Char h: 0.7369213846338432 %
|
||||
[21] Char q: 0.5913317719082624 %
|
||||
[22] Char í: 0.5612862701130941 %
|
||||
[23] Char j: 0.43283670874717317 %
|
||||
[24] Char z: 0.38071078784750195 %
|
||||
[25] Char á: 0.37587124393418625 %
|
||||
[26] Char é: 0.29632124085905936 %
|
||||
[27] Char k: 0.2001353055819098 %
|
||||
[28] Char x: 0.18743150280945606 %
|
||||
[29] Char ñ: 0.17462687620547493 %
|
||||
[30] Char ú: 0.12865120902897575 %
|
||||
[31] Char w: 0.0972949974239511 %
|
||||
[32] Char ü: 0.004436248587206061 %
|
||||
|
||||
The first 33 characters have an accumulated ratio of 0.9999263986029848.
|
||||
|
||||
897 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9970385677528184
|
||||
Next 512 (512-1024): 1.0082383152741046e-06
|
||||
Rest: 4.597017211338539e-17
|
||||
|
||||
- Processing end: 2015-12-12 18:39:02.460105
|
||||
@@ -0,0 +1,151 @@
|
||||
= Logs of language model for Swedish (sv) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-09-28 22:26:37.221506
|
||||
- Maximum depth: 5
|
||||
- Max number of pages: 100
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Kakapo (revision 36509929)
|
||||
Akut hotad (revision 32517788)
|
||||
Aotearoa (revision 36575359)
|
||||
Art (revision 36771341)
|
||||
Artepitet (revision 36771341)
|
||||
Auckland (revision 35752058)
|
||||
Auktorsnamn (revision 35976965)
|
||||
BBC (revision 36508743)
|
||||
Basalomsättning (revision 30567523)
|
||||
Beilschmiedia tawa (revision 29101923)
|
||||
Berguv (revision 36295501)
|
||||
Betesmark (revision 34292168)
|
||||
Biotop (revision 35528052)
|
||||
BirdLife International (revision 36124283)
|
||||
Bonaparte (revision 37325183)
|
||||
British Museum (revision 36420244)
|
||||
Bröstben (revision 30602527)
|
||||
Dacrydium cupressinum (revision 32986501)
|
||||
Digital object identifier (revision 27637223)
|
||||
Djur (revision 37300775)
|
||||
Djurpark (revision 37147093)
|
||||
Domän (biologi) (revision 33377709)
|
||||
Don Merton (revision 36509929)
|
||||
Douglas Adams (revision 36556245)
|
||||
Däggdjur (revision 37328286)
|
||||
Ekologisk nisch (revision 33898643)
|
||||
Ekosystem (revision 36598266)
|
||||
Endemisk (revision 30647109)
|
||||
Eukaryoter (revision 37095313)
|
||||
Evolution (revision 37093592)
|
||||
Familj (biologi) (revision 30280200)
|
||||
Femininum (revision 30597527)
|
||||
Fjäder (biologi) (revision 36364943)
|
||||
Fjäderdräkt (revision 36364943)
|
||||
Fladdermöss (revision 37307257)
|
||||
Flygg (revision 36479633)
|
||||
Frukter (revision 34088588)
|
||||
Frö (revision 37333131)
|
||||
Fågelläte (revision 34034723)
|
||||
Fåglar (revision 37387306)
|
||||
Fåglarnas liv (revision 36509929)
|
||||
Genitiv (revision 37388438)
|
||||
George Edward Grey (revision 36509929)
|
||||
George Robert Gray (revision 20426710)
|
||||
Haasts örn (revision 29175076)
|
||||
Hauturu/Little Barrier Island (revision 36509929)
|
||||
Hermelin (revision 36578682)
|
||||
Hertz (revision 37104488)
|
||||
Hjortdjur (revision 36493550)
|
||||
Hund (revision 37351832)
|
||||
Husdjur (revision 37384850)
|
||||
Huskatt (revision 32922967)
|
||||
Hāngi (revision 29609696)
|
||||
IUCN (revision 30570280)
|
||||
Iller (revision 30663158)
|
||||
Infraröd (revision 36770733)
|
||||
Internationella naturvårdsunionen (revision 30570280)
|
||||
Jordbruk (revision 37352625)
|
||||
Kahurangi National Park (revision 35956142)
|
||||
Kamouflage (revision 36579595)
|
||||
Kaniner (revision 36877621)
|
||||
Kapiti Island (revision 37395588)
|
||||
Katt (revision 36734686)
|
||||
Kelp (revision 30312471)
|
||||
Kivier (revision 36373234)
|
||||
Klass (biologi) (revision 30280201)
|
||||
Kroppsfett (revision 35066611)
|
||||
Könsdimorfism (revision 30816932)
|
||||
Könsfördelning (revision 24769321)
|
||||
Lamm- och fårkött (revision 36187205)
|
||||
Lek (fortplantningsbeteende) (revision 30508235)
|
||||
Mandel (revision 36577529)
|
||||
Maori (revision 32560474)
|
||||
Maorier (revision 35862066)
|
||||
Maoripapegojor (revision 36545138)
|
||||
Mark Carwardine (revision 20375916)
|
||||
Markpapegoja (revision 36295722)
|
||||
Maskulinum (revision 32704551)
|
||||
Masterton (revision 29859631)
|
||||
Metrosideros umbellata (revision 29071212)
|
||||
Milford Sound (revision 20284758)
|
||||
Morrhår (revision 36533839)
|
||||
Muskelmage (revision 31196380)
|
||||
Mustela (revision 20934105)
|
||||
Mårddjur (revision 37306347)
|
||||
Māori (revision 32560474)
|
||||
NHNZ (revision 36509929)
|
||||
Nattpapegoja (revision 33486517)
|
||||
Nordön (revision 24810231)
|
||||
Nya Zeeland (revision 36575359)
|
||||
Näbb (revision 23648463)
|
||||
Ollonår (revision 36509929)
|
||||
Ordning (biologi) (revision 30280196)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-09-28 22:29:21.480287
|
||||
|
||||
48 characters appeared 594415 times.
|
||||
|
||||
First 31 characters:
|
||||
[ 0] Char a: 10.070741821791172 %
|
||||
[ 1] Char e: 9.737136512369304 %
|
||||
[ 2] Char r: 9.110638190489809 %
|
||||
[ 3] Char n: 8.378826240925951 %
|
||||
[ 4] Char t: 7.481305148759705 %
|
||||
[ 5] Char s: 5.828587771169974 %
|
||||
[ 6] Char i: 5.359891658184939 %
|
||||
[ 7] Char l: 5.173489901836259 %
|
||||
[ 8] Char o: 4.694195133029954 %
|
||||
[ 9] Char d: 4.597293136949774 %
|
||||
[10] Char k: 3.297359588839447 %
|
||||
[11] Char m: 3.1898589369379975 %
|
||||
[12] Char g: 3.004466576381821 %
|
||||
[13] Char v: 2.2324470277499726 %
|
||||
[14] Char f: 2.1988005013332437 %
|
||||
[15] Char p: 2.06017681249632 %
|
||||
[16] Char u: 2.0499146219392173 %
|
||||
[17] Char ä: 2.0475593650900468 %
|
||||
[18] Char h: 2.028380845032511 %
|
||||
[19] Char å: 1.5443755625278637 %
|
||||
[20] Char c: 1.442594820117258 %
|
||||
[21] Char ö: 1.3515809661600062 %
|
||||
[22] Char b: 1.268642278542769 %
|
||||
[23] Char j: 0.7302978558751041 %
|
||||
[24] Char y: 0.6699023409570755 %
|
||||
[25] Char x: 0.2111319532649748 %
|
||||
[26] Char w: 0.10262190557102362 %
|
||||
[27] Char z: 0.09151855185350302 %
|
||||
[28] Char é: 0.021197311642539303 %
|
||||
[29] Char ā: 0.011103353717520588 %
|
||||
[30] Char q: 0.007570468443764037 %
|
||||
|
||||
The first 31 characters have an accumulated ratio of 0.999936071599808.
|
||||
|
||||
748 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.997323508584682
|
||||
Next 512 (512-1024): 1.6823263208364526e-06
|
||||
Rest: 1.7780915628762273e-17
|
||||
|
||||
- Processing end: 2016-09-28 22:29:21.590354
|
||||
@@ -0,0 +1,141 @@
|
||||
= Logs of language model for Thai (th) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2015-12-04 03:01:52.148282
|
||||
- Maximum depth: 3
|
||||
- Max number of pages: 50
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
หน้าหลัก (revision 5512633)
|
||||
26 พฤศจิกายน (revision 5570053)
|
||||
27 พฤศจิกายน (revision 5888433)
|
||||
28 พฤศจิกายน (revision 6110206)
|
||||
กล้องโทรทรรศน์อวกาศฮับเบิล (revision 5830742)
|
||||
การประชุมสภาสงฆ์แห่งแคลมงต์ (revision 5463877)
|
||||
ความเอนเอียงเพื่อยืนยัน (revision 6231756)
|
||||
คัมภีร์พระเวท (revision 6109417)
|
||||
คาบสมุทรไซนาย (revision 5661104)
|
||||
จักรวรรดิโรมันตะวันออก (revision 6150148)
|
||||
ชาวมุสลิม (revision 6242838)
|
||||
ซุคฮอย ซู-24 (revision 6015891)
|
||||
ดาวอังคาร (revision 6235017)
|
||||
ดาวเคราะห์นอกระบบ (revision 5823077)
|
||||
ดินแดนศักดิ์สิทธิ์ (revision 6179072)
|
||||
ทฤษฎี (revision 5606447)
|
||||
ทะกะอะกิ คะจิตะ (revision 6177601)
|
||||
ท่าอากาศยานนานาชาติตริภูวัน (revision 6010470)
|
||||
นกกาเหว่า (revision 6142782)
|
||||
ประเทศอัฟกานิสถาน (revision 6216996)
|
||||
ประเทศเนปาล (revision 6206980)
|
||||
ปรากฏการณ์การวางกรอบ (revision 6046655)
|
||||
ปารีส (revision 6222115)
|
||||
พ.ศ. 1638 (revision 4723508)
|
||||
พ.ศ. 2438 (revision 5737055)
|
||||
พ.ศ. 2515 (revision 6197082)
|
||||
พ.ศ. 2544 (revision 6189598)
|
||||
พินัยกรรม (revision 5607889)
|
||||
มูลนิธิวิกิมีเดีย (revision 5816103)
|
||||
ระบบสุริยะ (revision 6201228)
|
||||
รางวัลโนเบล (revision 5828030)
|
||||
รางวัลโนเบลสาขาฟิสิกส์ (revision 6177103)
|
||||
รายชื่อบทความวันนี้ในอดีต (revision 5410610)
|
||||
ลักกีสไตรก์ (เพลง) (revision 6195816)
|
||||
ลุฟต์ฮันซา (revision 6116038)
|
||||
วิกฤตการณ์ผู้ย้ายถิ่นยุโรป (revision 6219634)
|
||||
วิกิพีเดีย (revision 6086299)
|
||||
วิกิพีเดียภาษาไทย (revision 6209148)
|
||||
สงครามครูเสด (revision 6228828)
|
||||
สงครามอังกฤษ–แซนซิบาร์ (revision 5829349)
|
||||
สติ (จิตวิทยา) (revision 6039161)
|
||||
สมมติฐาน (revision 6221744)
|
||||
สมเด็จพระราชินีมารีแห่งโรมาเนีย (revision 6211695)
|
||||
สมเด็จพระสันตะปาปาเออร์บันที่ 2 (revision 5828365)
|
||||
สารานุกรม (revision 6070482)
|
||||
อัลเฟรด โนเบล (revision 6214514)
|
||||
อาร์เธอร์ แมคโดนัลด์ (revision 6188035)
|
||||
เซนต์ปีเตอร์สเบิร์ก (revision 6162201)
|
||||
เทือกเขาฮินดูกูช (revision 5218921)
|
||||
เนื้อหาเสรี (revision 6160507)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2015-12-04 03:05:06.181487
|
||||
|
||||
105 characters appeared 401052 times.
|
||||
|
||||
First 64 characters:
|
||||
[ 0] Char า: 8.857704237854442 %
|
||||
[ 1] Char น: 6.7679502907353655 %
|
||||
[ 2] Char ร: 6.739026360671434 %
|
||||
[ 3] Char ก: 5.388079351306065 %
|
||||
[ 4] Char อ: 5.099837427565503 %
|
||||
[ 5] Char ง: 4.861713692987443 %
|
||||
[ 6] Char เ: 4.5198627609387305 %
|
||||
[ 7] Char ม: 4.133628556895365 %
|
||||
[ 8] Char ว: 3.864336794231172 %
|
||||
[ 9] Char ด: 3.3152808114658447 %
|
||||
[10] Char ย: 3.195844927839781 %
|
||||
[11] Char ล: 3.1312647736453125 %
|
||||
[12] Char ท: 2.69615910156289 %
|
||||
[13] Char ส: 2.6001615750575984 %
|
||||
[14] Char ะ: 2.392457835891605 %
|
||||
[15] Char ค: 2.384229476476866 %
|
||||
[16] Char บ: 2.3321165335168503 %
|
||||
[17] Char ต: 2.196473275285998 %
|
||||
[18] Char ห: 1.983782651626223 %
|
||||
[19] Char ป: 1.9192024974317545 %
|
||||
[20] Char แ: 1.7813151411787 %
|
||||
[21] Char จ: 1.76261432432702 %
|
||||
[22] Char พ: 1.5075351824701035 %
|
||||
[23] Char ข: 1.3519443862641254 %
|
||||
[24] Char ใ: 1.3295034060421091 %
|
||||
[25] Char ไ: 1.2227840778751882 %
|
||||
[26] Char ช: 1.0407627938521689 %
|
||||
[27] Char โ: 0.9382823175049619 %
|
||||
[28] Char ศ: 0.8078752879925796 %
|
||||
[29] Char ำ: 0.7393056262030859 %
|
||||
[30] Char ถ: 0.599672860377208 %
|
||||
[31] Char ซ: 0.541076967575277 %
|
||||
[32] Char e: 0.43734977010462484 %
|
||||
[33] Char ผ: 0.43585370475649043 %
|
||||
[34] Char ณ: 0.4019428901987772 %
|
||||
[35] Char a: 0.3897250231890129 %
|
||||
[36] Char i: 0.3657879776188624 %
|
||||
[37] Char ษ: 0.3647906007201061 %
|
||||
[38] Char ภ: 0.34185093204871186 %
|
||||
[39] Char ธ: 0.3181632307032505 %
|
||||
[40] Char o: 0.3176645422538723 %
|
||||
[41] Char n: 0.3139243788835363 %
|
||||
[42] Char ญ: 0.29248077556027646 %
|
||||
[43] Char r: 0.28350438347147006 %
|
||||
[44] Char t: 0.2705384837876385 %
|
||||
[45] Char s: 0.2488455362396896 %
|
||||
[46] Char l: 0.19598456060560726 %
|
||||
[47] Char ฟ: 0.19473783948216192 %
|
||||
[48] Char c: 0.16356981139602844 %
|
||||
[49] Char ฐ: 0.15833358267755804 %
|
||||
[50] Char ฤ: 0.15284800973439852 %
|
||||
[51] Char ๆ: 0.14910784636406252 %
|
||||
[52] Char d: 0.13090571796176056 %
|
||||
[53] Char ฮ: 0.1244227681198448 %
|
||||
[54] Char h: 0.12043326052481973 %
|
||||
[55] Char u: 0.12043326052481973 %
|
||||
[56] Char m: 0.09599752650529109 %
|
||||
[57] Char y: 0.08951457666337533 %
|
||||
[58] Char ฏ: 0.08677179019179557 %
|
||||
[59] Char p: 0.08253293837208142 %
|
||||
[60] Char f: 0.08153556147332515 %
|
||||
[61] Char S: 0.07604998853016566 %
|
||||
[62] Char ฝ: 0.07330720205858592 %
|
||||
[63] Char ฉ: 0.0673229406660483 %
|
||||
|
||||
The first 64 characters have an accumulated ratio of 0.989480167160368.
|
||||
|
||||
2324 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.8815720594354438
|
||||
Next 512 (512-1024): 7.480326740672033e-06
|
||||
Rest: 0.026341928296264486
|
||||
|
||||
- Processing end: 2015-12-04 03:05:06.800467
|
||||
@@ -0,0 +1,113 @@
|
||||
= Logs of language model for Turkish (tr) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2015-12-04 02:22:03.929245
|
||||
- Maximum depth: 3
|
||||
- Max number of pages: 50
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Ana_Sayfa (revision 16293313)
|
||||
1048 (revision 12894005)
|
||||
1131 (revision 14840814)
|
||||
16. yüzyıl (revision 15185081)
|
||||
1859 (revision 16014427)
|
||||
1866 (revision 16120346)
|
||||
1869 (revision 12888270)
|
||||
1892 (revision 13955858)
|
||||
1895 (revision 15334635)
|
||||
1902 (revision 16283638)
|
||||
1906 (revision 15874323)
|
||||
1918 (revision 16099474)
|
||||
1926 (revision 16180584)
|
||||
1927 (revision 15370980)
|
||||
1940 (revision 15370990)
|
||||
1943 (revision 16091797)
|
||||
1944 (revision 16247827)
|
||||
1945 (revision 16281147)
|
||||
1948 (revision 15443886)
|
||||
1961 (revision 15799529)
|
||||
1964 (revision 16085332)
|
||||
1975 (revision 15006928)
|
||||
1980 (revision 16213240)
|
||||
1981 (revision 16295456)
|
||||
1983 (revision 16327128)
|
||||
1993 (revision 16300456)
|
||||
2002 (revision 16297206)
|
||||
2015 (revision 16328338)
|
||||
24 Ekim (revision 16213661)
|
||||
4 Aralık (revision 16341162)
|
||||
ABD (revision 16325951)
|
||||
ABD Senatosu (revision 15970439)
|
||||
Adam Horowitz (revision 14362106)
|
||||
Akçe (revision 16261547)
|
||||
Altın Takım (revision 13503001)
|
||||
American Broadcasting Company (revision 16055235)
|
||||
Amerika Birleşik Devletleri (revision 16325951)
|
||||
Ana Sayfa/Kardeş projeler (revision 16293313)
|
||||
Ana Sayfa/Kategoriler (revision 16293313)
|
||||
Aptullah Kuran (revision 15744893)
|
||||
Avrupa (revision 16299756)
|
||||
Ayasofya (revision 16305207)
|
||||
BM Güvenlik Konseyi (revision 16085518)
|
||||
Birleşmiş Milletler (revision 16258474)
|
||||
Budapeşte (revision 16219173)
|
||||
CIA (revision 16054325)
|
||||
Charlie Pace (revision 16129416)
|
||||
Cuma (revision 14197127)
|
||||
Desmond Hume (revision 16035300)
|
||||
Diğerleri (Lost) (revision 16329444)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2015-12-04 02:24:44.728803
|
||||
|
||||
48 characters appeared 267623 times.
|
||||
|
||||
First 36 characters:
|
||||
[ 0] Char a: 12.311722086666691 %
|
||||
[ 1] Char e: 8.716365932673948 %
|
||||
[ 2] Char i: 8.507863673899479 %
|
||||
[ 3] Char n: 7.322987934519828 %
|
||||
[ 4] Char r: 6.979220769515326 %
|
||||
[ 5] Char l: 6.609297407173524 %
|
||||
[ 6] Char ı: 4.514933320379788 %
|
||||
[ 7] Char d: 4.3475336574210734 %
|
||||
[ 8] Char t: 4.2634601659797555 %
|
||||
[ 9] Char k: 4.240293248338147 %
|
||||
[10] Char s: 3.929781819948211 %
|
||||
[11] Char m: 3.429451130881875 %
|
||||
[12] Char u: 3.0998830444319063 %
|
||||
[13] Char y: 2.9212735826143494 %
|
||||
[14] Char o: 2.7135186437638024 %
|
||||
[15] Char b: 2.3129551645411643 %
|
||||
[16] Char ü: 1.8305601536489764 %
|
||||
[17] Char ş: 1.5988909772328985 %
|
||||
[18] Char z: 1.2267256551193282 %
|
||||
[19] Char h: 1.1983274980102607 %
|
||||
[20] Char v: 1.194964558352608 %
|
||||
[21] Char c: 1.143773143563894 %
|
||||
[22] Char g: 1.1004285879763698 %
|
||||
[23] Char p: 1.0178497363828969 %
|
||||
[24] Char ç: 0.8295251155543433 %
|
||||
[25] Char ğ: 0.8205572764672693 %
|
||||
[26] Char f: 0.7047226882592303 %
|
||||
[27] Char ö: 0.6710932916827029 %
|
||||
[28] Char j: 0.1296600068006113 %
|
||||
[29] Char w: 0.11359262843627041 %
|
||||
[30] Char â: 0.07846859201189733 %
|
||||
[31] Char î: 0.04147625577771716 %
|
||||
[32] Char x: 0.024287897527492032 %
|
||||
[33] Char é: 0.014946398478456635 %
|
||||
[34] Char q: 0.01083613889688106 %
|
||||
[35] Char û: 0.009341499049035397 %
|
||||
|
||||
The first 36 characters have an accumulated ratio of 0.99980569681978.
|
||||
|
||||
935 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.991865243864388
|
||||
Next 512 (512-1024): 3.7365996196141585e-06
|
||||
Rest: 2.949029909160572e-17
|
||||
|
||||
- Processing end: 2015-12-04 02:24:44.883537
|
||||
@@ -0,0 +1,121 @@
|
||||
= Logs of language model for Vietnamese (vi) =
|
||||
|
||||
- Generated by BuildLangModel.py
|
||||
- Started: 2016-02-13 03:37:17.480303
|
||||
- Maximum depth: 3
|
||||
- Max number of pages: 40
|
||||
|
||||
== Parsed pages ==
|
||||
|
||||
Chữ_Quốc_ngữ (revision 22887853)
|
||||
1651 (revision 21455247)
|
||||
1773 (revision 21354755)
|
||||
1815 (revision 21361292)
|
||||
1838 (revision 21361314)
|
||||
1865 (revision 21361338)
|
||||
1869 (revision 21361342)
|
||||
1888 (revision 21389506)
|
||||
1902 (revision 21354811)
|
||||
1918 (revision 21354828)
|
||||
1919 (revision 21354829)
|
||||
1938 (revision 21354849)
|
||||
1945 (revision 21354857)
|
||||
22 tháng 2 (revision 21376086)
|
||||
26 tháng 11 (revision 22579845)
|
||||
28 tháng 12 (revision 22475308)
|
||||
A (revision 22549334)
|
||||
ASCII (revision 22528409)
|
||||
Alexandre de Rhodes (revision 22859954)
|
||||
Antonio Barbosa (revision 22145269)
|
||||
B (revision 22836557)
|
||||
BBC (revision 22863903)
|
||||
Biên khảo (revision 22531516)
|
||||
Bán nguyên âm (revision 22655600)
|
||||
Bình luận (revision 22117664)
|
||||
Bảng chữ cái Bồ Đào Nha (revision 22887853)
|
||||
Bảng chữ cái Hy Lạp (revision 21362081)
|
||||
Bảng chữ cái Latinh (revision 22442448)
|
||||
Bắc Kỳ (revision 22393289)
|
||||
Bồ Đào Nha (revision 22620858)
|
||||
C (revision 21341881)
|
||||
Cao Xuân Dục (revision 22620201)
|
||||
Chính tả (revision 22187359)
|
||||
Chính tả tiếng Việt (revision 20897580)
|
||||
Chữ Hán (revision 22889609)
|
||||
Chữ Nôm (revision 22781506)
|
||||
Chữ cái (revision 22169220)
|
||||
Công giáo (revision 22173119)
|
||||
D (revision 21447691)
|
||||
|
||||
== End of Parsed pages ==
|
||||
|
||||
- Wikipedia parsing ended at: 2016-02-13 03:42:06.560479
|
||||
|
||||
101 characters appeared 222814 times.
|
||||
|
||||
First 55 characters:
|
||||
[ 0] Char n: 11.262308472537633 %
|
||||
[ 1] Char h: 8.881398834902654 %
|
||||
[ 2] Char t: 7.022898022565907 %
|
||||
[ 3] Char c: 6.365398942615815 %
|
||||
[ 4] Char i: 6.198443544840091 %
|
||||
[ 5] Char g: 5.591210606155808 %
|
||||
[ 6] Char a: 3.5998635633308496 %
|
||||
[ 7] Char u: 2.8499106878382867 %
|
||||
[ 8] Char m: 2.615185760320267 %
|
||||
[ 9] Char o: 2.6012728105056238 %
|
||||
[10] Char đ: 2.222032726848403 %
|
||||
[11] Char r: 2.1102803234985235 %
|
||||
[12] Char à: 2.0447548179198796 %
|
||||
[13] Char v: 1.9437737305555307 %
|
||||
[14] Char l: 1.9119085874316697 %
|
||||
[15] Char á: 1.7539292863105551 %
|
||||
[16] Char p: 1.6453185167897888 %
|
||||
[17] Char b: 1.541195795596327 %
|
||||
[18] Char ư: 1.4397659033992478 %
|
||||
[19] Char s: 1.3760356171515256 %
|
||||
[20] Char y: 1.280440187779942 %
|
||||
[21] Char e: 1.2454334108269678 %
|
||||
[22] Char d: 1.1251537156552103 %
|
||||
[23] Char ế: 1.071745940560288 %
|
||||
[24] Char k: 1.0695019163966357 %
|
||||
[25] Char â: 0.9658280000359044 %
|
||||
[26] Char ữ: 0.9604423420431392 %
|
||||
[27] Char ê: 0.8374698178749989 %
|
||||
[28] Char ệ: 0.7459136319979893 %
|
||||
[29] Char ô: 0.7073164163831717 %
|
||||
[30] Char ạ: 0.6727584442629277 %
|
||||
[31] Char ộ: 0.6705144200992756 %
|
||||
[32] Char ố: 0.6476253736300233 %
|
||||
[33] Char ó: 0.6072329386842837 %
|
||||
[34] Char ả: 0.5484395055965963 %
|
||||
[35] Char ủ: 0.5475418959311353 %
|
||||
[36] Char q: 0.5138815334763525 %
|
||||
[37] Char ợ: 0.48560682901433483 %
|
||||
[38] Char ờ: 0.4851580241816044 %
|
||||
[39] Char ể: 0.4748355130288043 %
|
||||
[40] Char ớ: 0.4676546357051173 %
|
||||
[41] Char ấ: 0.418286104104769 %
|
||||
[42] Char ị: 0.40212913012647317 %
|
||||
[43] Char ầ: 0.3904602044754818 %
|
||||
[44] Char ọ: 0.3801376933226817 %
|
||||
[45] Char ề: 0.3787912788244904 %
|
||||
[46] Char ơ: 0.3590438661843511 %
|
||||
[47] Char í: 0.35679984202069887 %
|
||||
[48] Char ụ: 0.35276059852612496 %
|
||||
[49] Char ậ: 0.3469261357006292 %
|
||||
[50] Char ì: 0.32762752789322036 %
|
||||
[51] Char ă: 0.3253835037295682 %
|
||||
[52] Char ứ: 0.29665999443482005 %
|
||||
[53] Char ồ: 0.29665999443482005 %
|
||||
[54] Char x: 0.2939671654384374 %
|
||||
|
||||
The first 55 characters have an accumulated ratio of 0.9603301408349568.
|
||||
|
||||
1494 sequences found.
|
||||
|
||||
First 512 (typical positive ratio): 0.9321889118082535
|
||||
Next 512 (512-1024): 0.009604423420431392
|
||||
Rest: 0.0068905733918831966
|
||||
|
||||
- Processing end: 2016-02-13 03:42:07.174723
|
||||
Reference in New Issue
Block a user