Swift からword2vecを 使ってみる

Transcript

1. $PQZSJHIU
   
   4IJSPZBHJ
   $PSQPSBUJPO
   "MM
   SJHIUT
   SFTFSWFE 4XJGU
   ͔ΒXPSEWFDΛ ࢖ͬͯΈΔ ϦʔυΞʔΩςΫτ
 ҏ౻༞ี
   :VTVLF
   *UP
   !OPWJ@
   നϠΪίʔϙϨʔγϣϯ 5PLZP
   4FSWFS4JEF
   4XJGU
   .FFUVQ
   
 
2. 5PLZP
   
   ݄೔ʙ೔
3. $PQZSJHIU
   
   4IJSPZBHJ
   $PSQPSBUJPO
   "MM
   SJHIUT
   SFTFSWFE 4FF63- • https://github.com/shiroyagicorp/swift-seeurl • ݩʑࣾ಺ϥΠϒϥϦΛެ։ • cURL(curlίϚϯυ), libcurlϕʔε • ಉظॲཧ(RunLoopෆཁ)  let result = try HTTPClient.sendRequest("GET", "https://google.com") print(result.statusCode, result.body) ϑΥϩʔΞοϓهࣄ
   USZ
   4XJGU
   5PLZP
   ͱͦͷޙ
 IUUQBJBMTIJSPZBHJDPKQNZUSZTXJGUBOEGPMMPXVQ
   
4. $PQZSJHIU
   
   4IJSPZBHJ
   $PSQPSBUJPO
   "MM
   SJHIUT
   SFTFSWFE ϝϯςφϯε͍ͯ͠ΔϥΠϒ ϥϦ • novi/mysql-swift: MySQLΫϥΠΞϯτ (όΠϯσΟϯά) • novi/nkf-swift: Network Kanji FilterͷόΠϯσΟϯά • novi/mecab-swift: MeCabܗଶૉղੳͷόΠϯσΟϯά • novi/i2c-swift: I2CόεϥΠϒϥϦ • shiroyagicorp/swift-seeurl: cURL(HTTPS)ΫϥΠΞϯτ 
6. $PQZSJHIU
   
   4IJSPZBHJ
   $PSQPSBUJPO
   "MM
   SJHIUT
   SFTFSWFE OVNTX • https://github.com/sonsongithub/numsw • try! Swift TokyoͷϋοΧιϯͰ࡞ͬͨ • Pythonʹ͋Δ਺஋ܭࢉϥΠϒϥϦ(numsw)ΛSwift Ͱ΋࢖͍͍ͨ • ࠓ΋ͨ·ʹϝϯςφϯε͍ͯ͠Δ 
7. $PQZSJHIU
   
   4IJSPZBHJ
   $PSQPSBUJPO
   "MM
   SJHIUT
   SFTFSWFE XPSEWFD • 2013೥͘Β͍ʹެ։ • C࣮૷ • word2vecͷίϯηϓτ͸͜ͷล • https://deepage.net/bigdata/machine_learning/ 2016/09/02/ word2vec_power_of_word_vector.html 
8. $PQZSJHIU
   
   4IJSPZBHJ
   $PSQPSBUJPO
   "MM
   SJHIUT
   SFTFSWFE XPSEWFDͷιʔείʔυ • https://code.google.com/archive/p/word2vec/ • ͕ͩɺGoogle Codeऴྃʹ൐͍μ΢ϯϩʔυͰ͖ͳ͍ • https://github.com/svn2github/word2vec.git • ͜ͷลͷϛϥʔΛ࢖͏ • make Ͱ࣮ߦϑΝΠϧΛϏϧυ • macOSͩͱmalloc.hϔομʔ͕ແ͍ͱ͍͏Τϥʔ͕ग़ΔͷͰɺͦͷߦ Λίϝϯτ͢Δ • demo-*.sh͔Β࢝·ΔγΣϧεΫϦϓτͰσϞΛ࣮ߦ 
9. $PQZSJHIU
   
   4IJSPZBHJ
   $PSQPSBUJPO
   "MM
   SJHIUT
   SFTFSWFE XPSEWFDD • ςΩετϑΝΠϧΛೖྗͯ͠ɺτϨʔχϯάɺϞσ ϧΛग़ྗ • Cݴޠ 700ߦఔ౓ͷ CLI • ϚϧνεϨουରԠ • ίʔυ͕ಡΈʹ͍͘ 
10. $PQZSJHIU
    
    4IJSPZBHJ
    $PSQPSBUJPO
    "MM
    SJHIUT
    SFTFSWFE EJTUBODFD • ϞσϧϑΝΠϧͱ୯ޠ(ෳ਺)Λೖྗͯ͠ɺίαΠϯ ྨࣅ౓(ίαΠϯڑ཭)Λܭࢉͯ͠ग़ྗ  Enter word or sentence (EXIT to break): cat dog Word Cosine distance ------------------------------------------------------------------------ goat 0.827205 cow 0.796463 bee 0.788516 blonde 0.784559 hamster 0.784402 ass 0.779677 rat 0.774975
11. $PQZSJHIU
    
    4IJSPZBHJ
    $PSQPSBUJPO
    "MM
    SJHIUT
    SFTFSWFE 4XJGU͔Β࣮ߦ͢Δʹ͸ 1. .cͷιʔεΛSwift͔ΒݺͿ • ͍ͭ΋ͷCͷϥΠϒϥϦΛSwift͔ΒಡΈࠐΉํ๏ • ࠓճ͸ϥΠϒϥϦͰ͸ͳ͘ɺmain()ͷܗʹͳͬͯ ͍ΔͷͰɺϥούʔؔ਺ͳͲΛఆٛ 2. ͕Μ͹ͬͯSwiftʹҠ২ 
12. $PQZSJHIU
    
    4IJSPZBHJ
    $PSQPSBUJPO
    "MM
    SJHIUT
    SFTFSWFE ϞσϧϑΝΠϧ • ୯ޠͷϦετ(char*)ͱ୯ޠΠϯσοΫε(Int) • ୯ޠΠϯσοΫεͱ୯ޠϕΫτϧ(Float) • σϞͩͱαΠζ͕30ϝΨόΠτ͋Δ  m0 m1 m2 i0 the -0.455356 1.908487 1.365852 i1 of 0.266191 1.750760 0.486601 i2 and 0.889470 1.455499 0.380907 i3 one -2.213606 0.914580 -0.512441
13. $PQZSJHIU
    
    4IJSPZBHJ
    $PSQPSBUJPO
    "MM
    SJHIUT
    SFTFSWFE EJTUBODFDͷ΍Δ͜ͱ • ϞσϧΛύʔεͯ͠ڊେͳ(30MBఔ౓ͷ)ϝϞϦ্ʹಡΈࠐΉ • ͋Β͔͡Ί୯ޠͱ୯ޠΠϯσοΫεʹ෼͚Δ • ୯ޠΠϯσοΫεͱ୯ޠϕΫτϧΛϝϞϦ্ʹಡΈࠐΉ • ༩͑ΒΕͨɺ୯ޠʹରͯ͠ɺ୯ޠϕΫτϧ͔ΒίαΠϯڑ ཭Λܭࢉͭͭ͠ɺڑ཭͕͍ۙ΋ͷΛιʔτͯ͠ग़ྗ(දࣔ) • https://ja.stackoverflow.com/questions/2001/word2vecͷ distance͸ͳͥߴ଎ʹಈ࡞͢Δͷ͔ 
14. $PQZSJHIU
    
    4IJSPZBHJ
    $PSQPSBUJPO
    "MM
    SJHIUT
    SFTFSWFE 4XJGUʹҠ২ • Ϟσϧ(୯ޠϕΫτϧ)ΛಡΈࠐΉϝϞϦۭؒ͸
 UnsafeMutablePointer<Float>.allocate(capacity:)
 Λ࢖༻ • Swift3͔Βಋೖ͞ΕͨϙΠϯλͱϝϞϦۭؒΛ҆શʹޮ཰తʹ ѻ͏࢓૊Έ(݁ߏ೉͍͠) • ૉ੖Β͍͠SwiftͷϙΠϯλܕͷղઆ: http://qiita.com/ omochimetaru/items/c95e0d36ae7f1b1a9052 • UnsafeRawPointer Migration: https://swift.org/migration- guide/se-0107-migrate.html 
15. $PQZSJHIU
    
    4IJSPZBHJ
    $PSQPSBUJPO
    "MM
    SJHIUT
    SFTFSWFE ΍ͬͨ͜ͱ • ୯ޠͱ୯ޠΠϯσοΫεͷରԠΛ഑ྻͰ͸ͳࣙ͘ॻʹมߋ • จࣈྻͷѻ͍ΛStringωΠςΟϒʹมߋ • ݩʑchar*΍strcmpͳͲͷCϨϕϧͩͬͨͷͰɺՄಡੑ ΍ѻ͍͕େม • (͓ͦΒ͘)ɺϢχίʔυ΁ͷରԠ͕Մೳ • (·ͩ΍͍ͬͯͳ͍͕)ɺιʔτपΓͷվળ 
16. $PQZSJHIU
    
    4IJSPZBHJ
    $PSQPSBUJPO
    "MM
    SJHIUT
    SFTFSWFE ࠓճͷϦϙδτϦ • https://github.com/novi/word2vec-swift 
17. $PQZSJHIU
    
    4IJSPZBHJ
    $PSQPSBUJPO
    "MM
    SJHIUT
    SFTFSWFE ·ͱΊ • C͔ΒͷҠ২͸ָ • ߏจ΋͍ۙ • ϙΠϯλपΓ΋ಉ͡࢓૊Έ͕࢖͑Δ • word2vecʹ͍ͭͯΑ͘ཧղͰ͖ͯΕ͹͞Βʹ༰қ 
18. $PQZSJHIU
    
    4IJSPZBHJ
    $PSQPSBUJPO
    "MM
    SJHIUT
    SFTFSWFE • ࣍ճ: നϠΪͰӡ༻͍ͯ͠ΔαʔόʔαΠυSwift • ൃදऀืूʂτϐοΫ͸ͳΜͰ΋OKʂ