データ分析コンペにおいて 特徴量管理に疲弊している全人類に伝えたい想い

Transcript

1. ϚϚͷҰาΛࢧ͑Δ
   σʔλ෼ੳίϯϖʹ͓͍ͯ
   ಛ௃ྔ؅ཧʹർฐ͍ͯ͠Δશਓྨʹ఻͍͑ͨ૝͍
   ʙֶशɾਪ࿦ύΠϓϥΠϯΛఴ͑ͯʙ
   $POOFIJUP*OD໺ᖒ఩র
   
   $POOFIJUP.BSDIÉWPMʙػցֶशɾσʔλ෼ੳࢢʙ
   

   View Slide

2. ͜Μʹͪ͸ʂ
   ϚϚͷҰาΛࢧ͑Δ
   

   View Slide

3. ͍͖ͳΓͰ͕͢
   ϚϚͷҰาΛࢧ͑Δ
   

   View Slide

4. σʔλ෼ੳίϯϖʢ,BHHMF 4*(/"5&ͳͲʣ
   ฉ͍ͨ͜ͱ͋Δਓʙ!
   ϚϚͷҰาΛࢧ͑Δ
   

   View Slide

5. σʔλ෼ੳίϯϖʹࢀՃͨ͜͠ͱ͋Δਓʙ!
   ϚϚͷҰาΛࢧ͑Δ
   

   View Slide

6. ಛ௃ྔͷ؅ཧͬͯͲ͏ͯ͠·͔͢ʁ
   ʢςʔϒϧσʔλʹ͓͍ͯʣ
   ϚϚͷҰาΛࢧ͑Δ
   

   View Slide

7. Α͋͘Δύλʔϯʢ࣮ମݧʣ
   ϚϚͷҰาΛࢧ͑Δ
   

   View Slide

8. Α͋͘ΔύλʔϯʢJQZOCʣ
   ϚϚͷҰาΛࢧ͑Δ
   w ಛ௃ྔ࡞Δ
   DPM<Z " # $ %>ˠ<Z " # $ % & '>
   # e.g)
   train['A'] = train['A'].fillna(0)
   train['B'] = np.log1p(train['B'])
   train['E'] = train['A'] + train['B']
   df_group = train.groupby('D')['E'].mean()
   train['F'] = train['D'].map(df_group)
   <>
   ɾ
   ɾ
   ɾ
   

   View Slide

9. Α͋͘ΔύλʔϯʢJQZOCʣ
   ϚϚͷҰาΛࢧ͑Δ
   w ࢖͏ಛ௃ྔͷΧϥϜ͚ͩࢦఆ͢Δ
   # e.g)
   feat_col = ['A', 'C', 'D', 'E', 'F', 'J']
   x_train = train[feat_col]
   y_train = train['y']
   # e.g)
   clf.fit(x_train, y_train)
   w ֶशͤ͞Δ
   <>
   <>
   ɾ
   ɾ
   ɾ
   

   View Slide

10. Α͋͘ΔύλʔϯʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    w ࢖͏ಛ௃ྔͷΧϥϜ͚ͩࢦఆ͢Δ
    # e.g)
    feat_col = ['A', 'C', 'D', 'E', 'F', 'J']
    x_train = train[feat_col]
    y_train = train['y']
    # e.g)
    clf.fit(x_train, y_train)
    w ֶशͤ͞Δ
    <>
    <>
    ɾ
    ɾ
    ɾ
    ͋Ε
    b'`ͬͯͲΜͳಛ௃ྔ͚ͩͬʁ
    

    View Slide

11. Α͋͘ΔύλʔϯʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    # e.g)
    train['A'] = train['A'].fillna(0)
    train['B'] = np.log1p(train['B'])
    train['E'] = train['A'] + train['B']
    df_group = train.groupby('D')['E'].mean()
    train['F'] = train['D'].map(df_group)
    <>
    # e.g)
    feat_col = ['A', 'C', 'D', 'E', 'F', 'J']
    x_train = train[feat_col]
    y_train = train['y']
    # e.g)
    clf.fit(x_train, y_train)
    <>
    <>
    

    View Slide

12. Α͋͘ΔύλʔϯʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    # e.g)
    train['A'] = train['A'].fillna(0)
    train['B'] = np.log1p(train['B'])
    train['E'] = train['A'] + train['B']
    df_group = train.groupby('D')['E'].mean()
    train['F'] = train['D'].map(df_group)
    <>
    # e.g)
    feat_col = ['A', 'C', 'D', 'E', 'F', 'J']
    x_train = train[feat_col]
    y_train = train['y']
    # e.g)
    clf.fit(x_train, y_train)
    <>
    <>
    ݟ͚ͭͨʂ
    ʢOPUFCPPLͷ্ͷํʣ
    

    View Slide

13. Α͋͘ΔύλʔϯʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    # e.g)
    train['A'] = train['A'].fillna(0)
    train['B'] = np.log1p(train['B'])
    train['E'] = train['A'] + train['B']
    df_group = train.groupby('D')['E'].mean()
    train['F'] = train['D'].map(df_group)
    <>
    # e.g)
    feat_col = ['A', 'C', 'D', 'E', 'F', 'J']
    x_train = train[feat_col]
    y_train = train['y']
    # e.g)
    clf.fit(x_train, y_train)
    <>
    <>
    ݟ͚ͭͨʂ
    ʢOPUFCPPLͷ্ͷํʣ
    ಛ௃ྔ͕গͳ͍৔߹͸·ͩϚγ͕ͩɺ
    ଟ͘ͳͬͯ͘ΔͱͲΜͳܭࢉͰٻΊͨ
    ಛ௃ྔ͔ͩͬͨΛ͍͍ͪͪߟ͑Δʢ୳͢ʣ
    ͷ͸݁ߏେมͩ͠ɺ͕͔͔࣌ؒΔ
    

    View Slide

14. Α͋͘Δύλʔϯͦͷʢ࣮ମݧʣ
    ϚϚͷҰาΛࢧ͑Δ
    

    View Slide

15. Α͋͘ΔύλʔϯͦͷʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    Αͬ͠Ό͊ʂΊͬͪΌྑ͍είΞͰͨͥʙʙʙ
    ͜ͷOPUFCPPLΛ%VQMJDBUFͯ͠ɺ΋ͬͱྑ͍Ϟσϧ࡞ͬͪΌ͏ͧʂ
    

    View Slide

16. ҰํɺOPUFCPPLͷத਎͸ʜ
    ϚϚͷҰาΛࢧ͑Δ
    

    View Slide

17. Α͋͘ΔύλʔϯͦͷʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    <> import numpy as np
    import pandas as pd
    OPUFCPPLͷத਎
    ɾ
    ɾ
    ɾ
    <> submission.to_csv('submission.csv', index=False)
    

    View Slide

18. Α͋͘ΔύλʔϯͦͷʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    <> import numpy as np
    import pandas as pd
    OPUFCPPLͷத਎
    ɾ
    ɾ
    ɾ
    ɾ
    ɾ
    ɾ
    <> submission.to_csv('submission.csv', index=False)
    

    View Slide

19. Α͋͘ΔύλʔϯͦͷʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    <> import numpy as np
    import pandas as pd
    OPUFCPPLͷத਎
    ɾ
    ɾ
    ɾ
    ɾ
    ɾ
    ɾ
    <> submission.to_csv('submission.csv', index=False)
    

    View Slide

20. Α͋͘ΔύλʔϯͦͷʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    <> import numpy as np
    import pandas as pd
    OPUFCPPLͷத਎
    ɾ
    ɾ
    ɾ
    ɾ
    ɾ
    ɾ
    <> submission.to_csv('submission.csv', index=False)
    ಉ͡ܭࢉΛԿ౓΋΍Βͳ͍ͱ͍͚ͳ͍
    ʴ
    ºʢ ʣˠແବ
    

    View Slide

21. Α͋͘ΔύλʔϯͦͷʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    ౓ॏͳΔ%VQMJDBUFʹΑΓɺOPUFCPPL஍ࠈʹؕΔՄೳੑ΋ʜ
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    ʜʜʜʜʜ
    

    View Slide

22. Α͋͘ΔύλʔϯͦͷʢJQZOCʣ
    ϚϚͷҰาΛࢧ͑Δ
    ౓ॏͳΔ%VQMJDBUFʹΑΓɺOPUFCPPL஍ࠈʹؕΔՄೳੑ΋ʜ
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    dOPUFCPPL-JHIU#(.@TDPSF@JQZOC
    ʜʜʜʜʜ
    

    View Slide

23. ϚϚͷҰาΛࢧ͑Δ
    ࠓ೔࿩͢͜ͱ
    

    View Slide

24. ϚϚͷҰาΛࢧ͑Δ
    σʔλ෼ੳίϯϖʹ͓͍ͯ
    ಛ௃ྔ؅ཧʹർฐ͍ͯ͠Δશਓྨʹ఻͍͑ͨ૝͍
    ʙֶशɾਪ࿦ύΠϓϥΠϯΛఴ͑ͯʙ
    

    View Slide

25. ΞδΣϯμ
    ࣗݾ঺հ
    ಛ௃ྔ؅ཧʹ͍ͭͯ
    ‣ ྻ͝ͱʹQJDLMFϑΝΠϧͰಛ௃ྔΛ؅ཧ
    ‣ ಛ௃ྔੜ੒࣌ɺಉ࣌ʹϝϞϑΝΠϧ΋ੜ੒
    ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ‣ ίϚϯυҰൃͰֶशˠ4VCNJUϑΝΠϧ࡞੒·ͰΛ࣮ߦ
    ‣ ֶशʹ࢖༻ͨ͠ಛ௃ྔ΍Ϟσϧύϥϝʔλ͸MPHͱҰॹʹอଘ
    ‣ TIBQΛ༻͍ͯಛ௃ྔͷߩݙ౓ΛՄࢹԽ͠ɺ࣍ճֶश࣌ͷצॴΛݟ͚ͭΔ
    ϚϚͷҰาΛࢧ͑Δ
    

    View Slide

26. ΞδΣϯμ
    ࣗݾ঺հ
    ಛ௃ྔ؅ཧʹ͍ͭͯ
    ‣ ྻ͝ͱʹQJDLMFϑΝΠϧͰಛ௃ྔΛ؅ཧ
    ‣ ಛ௃ྔੜ੒࣌ɺಉ࣌ʹϝϞϑΝΠϧ΋ੜ੒
    ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ‣ ίϚϯυҰൃͰֶशˠ4VCNJUϑΝΠϧ࡞੒·ͰΛ࣮ߦ
    ‣ ֶशʹ࢖༻ͨ͠ಛ௃ྔ΍Ϟσϧύϥϝʔλ͸MPHͱҰॹʹอଘ
    ‣ TIBQΛ༻͍ͯಛ௃ྔͷߩݙ౓ΛՄࢹԽ͠ɺ࣍ճֶश࣌ͷצॴΛݟ͚ͭΔ
    ϚϚͷҰาΛࢧ͑Δ
    ݰਓͷ஌ܙΛ͓आΓͨ͠Β
    ΊͬͪΌΑ͔ͬͨ
    ʢ˞ʣ
    ͍ͬͯ͏࿩Λ͠·͢
    ʢ˞ʣ͋͘·Ͱओ؍Ͱ͢
    

    View Slide

27. ࣗݾ঺հ
    ϚϚͷҰาΛࢧ͑Δ
    

    View Slide

28. ࣗݾ঺հ
    ϚϚͷҰาΛࢧ͑Δ
    ໊લɿ໺ᖒ఩রʢ/P[BXB5BLBOPCVʣ
    ॴଐɿίωώτגࣜձࣾ
    ɹɹɿ͔ͨͺ͍!UBLBQZ
    w ʙίωώτʹ.-ΤϯδχΞͱͯ͠+0*/
    w ػցֶशʢ/-1ɺਪનγεςϜʣΛϝΠϯʹ΍ΓͭͭΠϯϑϥʢ"84ʣ΋ษڧத
    w ,BHHMFͨ͠ΓɺϒϩάʢIUUQTXXXUBLBQZXPSLʣॻ͍ͨΓɺ໺ٿͨ͠Γɺ
    ϥʔϝϯ৯΂ͨΓ͍ͯ͠·͢
    

    View Slide

29. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ˞ԼههࣄΛࢀߟʹ͍͖ͤͯͨͩ͞·ͨ͠ɻ
    ɾ,BHHMFͰ࢖͑Δ'FBUIFSܗࣜΛར༻ͨ͠ಛ௃ྔ؅ཧ๏
    IUUQTBNBMPHIBUFCMPKQFOUSZLBHHMFGFBUVSFNBOBHFNFOU
    ‣ ྻ͝ͱʹQJDLMFϑΝΠϧͰಛ௃ྔΛ؅ཧ
    ‣ ಛ௃ྔੜ੒࣌ɺಉ࣌ʹϝϞϑΝΠϧ΋ੜ੒
    

    View Slide

30. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ˞ԼههࣄΛࢀߟʹ͍͖ͤͯͨͩ͞·ͨ͠ɻ
    ɾ,BHHMFͰ࢖͑Δ'FBUIFSܗࣜΛར༻ͨ͠ಛ௃ྔ؅ཧ๏
    IUUQTBNBMPHIBUFCMPKQFOUSZLBHHMFGFBUVSFNBOBHFNFOU
    ‣ ྻ͝ͱʹQJDLMFϑΝΠϧͰಛ௃ྔΛ؅ཧ
    ‣ ಛ௃ྔੜ੒࣌ɺಉ࣌ʹϝϞϑΝΠϧ΋ੜ੒
    ࠷ॳʹΠϝʔδΛڞ༗͠·͢
    

    View Slide

31. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    lྻ͝ͱzʹಛ௃ྔΛQJDLMFϑΝΠϧͰ؅ཧ͢Δ
    

    View Slide

32. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    4VSWJWFE 1DMBTT 4FY "HF &NCBSLFE
    NBMF 4
    NBMF $
    GFNBMF $
    NBMF $
    GFNBMF $
    GFNBMF 4
    NBMF 4
    lྻ͝ͱzʹಛ௃ྔΛQJDLMFϑΝΠϧͰ؅ཧ͢Δ
    

    View Slide

33. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    4VSWJWFE 1DMBTT 4FY "HF &NCBSLFE
    NBMF 4
    NBMF $
    GFNBMF $
    NBMF $
    GFNBMF $
    GFNBMF 4
    NBMF 4
    TVSWJWFE@USBJOQLM
    QDMBTT@USBJOQLM
    QDMBTT@UFTUQLM
    TFY@USBJOQLM
    TFY@UFTUQLM
    BHF@USBJOQLM
    BHF@UFTUQLM
    FNCBSLFE@USBJOQLM
    FNCBSLFE@UFTUQLM
    lྻ͝ͱzʹಛ௃ྔΛQJDLMFϑΝΠϧͰ؅ཧ͢Δ
    

    View Slide

34. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ಛ௃ྔੜ੒࣌ɺಉ࣌ʹಛ௃ྔϝϞΛ࡞੒͢Δ
    

    View Slide

35. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ಛ௃ྔੜ੒࣌ɺಉ࣌ʹಛ௃ྔϝϞΛ࡞੒͢Δ
    

    View Slide

36. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ಛ௃ྔੜ੒࣌ɺಉ࣌ʹಛ௃ྔϝϞΛ࡞੒͢Δ
    ݁ߏେมͦ͏ɾɾɾ
    

    View Slide

37. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ಛ௃ྔੜ੒࣌ɺಉ࣌ʹಛ௃ྔϝϞΛ࡞੒͢Δ
    Ͱ΋ɺQZUIPOεΫϦϓτΛ࣮ͭߦ͢Δ͚ͩɻ
    

    View Slide

38. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    IPHFQZΛίϚϯυϥΠϯ͔Β࣮ߦ͢Δ͚ͩ
    class Pclass(Feature):
    def create_features(self):
    self.train['Pclass'] = train['Pclass']
    self.test['Pclass'] = test['Pclass']
    create_memo('Pclass','νέοτͷΫϥεɻ1st, 2nd, 3rdͷ3छྨ')
    class Sex(Feature):
    def create_features(self):
    self.train['Sex'] = train['Sex']
    self.test['Sex'] = test['Sex']
    create_memo('Sex','ੑผ')
    class Age(Feature):
    def create_features(self):
    self.train['Age'] = train['Age']
    self.test['Age'] = test['Age']
    create_memo('Age','೥ྸ')
    class Age_mis_val_median(Feature):
    def create_features(self):
    self.train['Age_mis_val_median'] = train['Age'].fillna(train['Age'].median())
    self.test['Age_mis_val_median'] = test['Age'].fillna(test['Age'].median())
    create_memo('Age_mis_val_median','೥ྸͷܽଛ஋Λதԝ஋Ͱิ׬ͨ͠΋ͷ')
    

    View Slide

39. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Pclass(Feature):
    def create_features(self):
    self.train['Pclass'] = train['Pclass']
    self.test['Pclass'] = test['Pclass']
    create_memo('Pclass','νέοτͷΫϥεɻ1st, 2nd, 3rdͷ3छྨ')
    class Sex(Feature):
    def create_features(self):
    self.train['Sex'] = train['Sex']
    self.test['Sex'] = test['Sex']
    create_memo('Sex','ੑผ')
    class Age(Feature):
    def create_features(self):
    self.train['Age'] = train['Age']
    self.test['Age'] = test['Age']
    create_memo('Age','೥ྸ')
    class Age_mis_val_median(Feature):
    def create_features(self):
    self.train['Age_mis_val_median'] = train['Age'].fillna(train['Age'].median())
    self.test['Age_mis_val_median'] = test['Age'].fillna(test['Age'].median())
    create_memo('Age_mis_val_median','೥ྸͷܽଛ஋Λதԝ஋Ͱิ׬ͨ͠΋ͷ')
    IPHFQZΛίϚϯυϥΠϯ͔Β࣮ߦ͢Δ͚ͩ
    

    View Slide

40. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Pclass(Feature):
    def create_features(self):
    self.train['Pclass'] = train['Pclass']
    self.test['Pclass'] = test['Pclass']
    create_memo('Pclass','νέοτͷΫϥεɻ1st, 2nd, 3rdͷ3छྨ')
    class Sex(Feature):
    def create_features(self):
    self.train['Sex'] = train['Sex']
    self.test['Sex'] = test['Sex']
    create_memo('Sex','ੑผ')
    class Age(Feature):
    def create_features(self):
    self.train['Age'] = train['Age']
    self.test['Age'] = test['Age']
    create_memo('Age','೥ྸ')
    class Age_mis_val_median(Feature):
    def create_features(self):
    self.train['Age_mis_val_median'] = train['Age'].fillna(train['Age'].median())
    self.test['Age_mis_val_median'] = test['Age'].fillna(test['Age'].median())
    create_memo('Age_mis_val_median','೥ྸͷܽଛ஋Λதԝ஋Ͱิ׬ͨ͠΋ͷ')
    ֤ಛ௃ྔ
    IPHFQZΛίϚϯυϥΠϯ͔Β࣮ߦ͢Δ͚ͩ
    

    View Slide

41. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Pclass(Feature):
    def create_features(self):
    self.train['Pclass'] = train['Pclass']
    self.test['Pclass'] = test['Pclass']
    create_memo('Pclass','νέοτͷΫϥεɻ1st, 2nd, 3rdͷ3छྨ')
    class Sex(Feature):
    def create_features(self):
    self.train['Sex'] = train['Sex']
    self.test['Sex'] = test['Sex']
    create_memo('Sex','ੑผ')
    class Age(Feature):
    def create_features(self):
    self.train['Age'] = train['Age']
    self.test['Age'] = test['Age']
    create_memo('Age','೥ྸ')
    class Age_mis_val_median(Feature):
    def create_features(self):
    self.train['Age_mis_val_median'] = train['Age'].fillna(train['Age'].median())
    self.test['Age_mis_val_median'] = test['Age'].fillna(test['Age'].median())
    create_memo('Age_mis_val_median','೥ྸͷܽଛ஋Λதԝ஋Ͱิ׬ͨ͠΋ͷ')
    ಛ௃ྔϝϞϑΝΠϧ
    IPHFQZΛίϚϯυϥΠϯ͔Β࣮ߦ͢Δ͚ͩ
    

    View Slide

42. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Pclass(Feature):
    def create_features(self):
    self.train['Pclass'] = train['Pclass']
    self.test['Pclass'] = test['Pclass']
    create_memo('Pclass','νέοτͷΫϥεɻ1st, 2nd, 3rdͷ3छྨ')
    DSFBUF@NFNPͷॲཧ֓ཁ
    

    View Slide

43. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Pclass(Feature):
    def create_features(self):
    self.train['Pclass'] = train['Pclass']
    self.test['Pclass'] = test['Pclass']
    create_memo('Pclass','νέοτͷΫϥεɻ1st, 2nd, 3rdͷ3छྨ')
    DSFBUF@NFNPͷॲཧ֓ཁ
    # ಛ௃ྔϝϞcsvϑΝΠϧ࡞੒
    def create_memo(col_name, desc):
    file_path = Feature.dir + '/_features_memo.csv'
    if not os.path.isfile(file_path):
    with open(file_path,"w"):pass
    with open(file_path, 'r+') as f:
    lines = f.readlines()
    lines = [line.strip() for line in lines]
    # ॻ͖ࠐ΋͏ͱ͍ͯ͠Δಛ௃ྔ͕͢Ͱʹॻ͖ࠐ·Ε͍ͯͳ͍͔νΣοΫ
    col = [line for line in lines if line.split(',')[0] == col_name]
    if len(col) != 0:return
    writer = csv.writer(f)
    writer.writerow([col_name, desc])
    

    View Slide

44. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Pclass(Feature):
    def create_features(self):
    self.train['Pclass'] = train['Pclass']
    self.test['Pclass'] = test['Pclass']
    create_memo('Pclass','νέοτͷΫϥεɻ1st, 2nd, 3rdͷ3छྨ')
    DSFBUF@NFNPͷॲཧ֓ཁ
    # ಛ௃ྔϝϞcsvϑΝΠϧ࡞੒
    def create_memo(col_name, desc):
    file_path = Feature.dir + '/_features_memo.csv'
    if not os.path.isfile(file_path):
    with open(file_path,"w"):pass
    with open(file_path, 'r+') as f:
    lines = f.readlines()
    lines = [line.strip() for line in lines]
    # ॻ͖ࠐ΋͏ͱ͍ͯ͠Δಛ௃ྔ͕͢Ͱʹॻ͖ࠐ·Ε͍ͯͳ͍͔νΣοΫ
    col = [line for line in lines if line.split(',')[0] == col_name]
    if len(col) != 0:return
    writer = csv.writer(f)
    writer.writerow([col_name, desc])
    

    View Slide

45. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Pclass(Feature):
    def create_features(self):
    self.train['Pclass'] = train['Pclass']
    self.test['Pclass'] = test['Pclass']
    create_memo('Pclass','νέοτͷΫϥεɻ1st, 2nd, 3rdͷ3छྨ')
    DSFBUF@NFNPͷॲཧ֓ཁ
    # ಛ௃ྔϝϞcsvϑΝΠϧ࡞੒
    def create_memo(col_name, desc):
    file_path = Feature.dir + '/_features_memo.csv'
    if not os.path.isfile(file_path):
    with open(file_path,"w"):pass
    with open(file_path, 'r+') as f:
    lines = f.readlines()
    lines = [line.strip() for line in lines]
    # ॻ͖ࠐ΋͏ͱ͍ͯ͠Δಛ௃ྔ͕͢Ͱʹॻ͖ࠐ·Ε͍ͯͳ͍͔νΣοΫ
    col = [line for line in lines if line.split(',')[0] == col_name]
    if len(col) != 0:return
    writer = csv.writer(f)
    writer.writerow([col_name, desc])
    $47ܗࣜͰอଘ͓ͯ͘͠ͱ(JUIVC͔Βࢀর͠΍͍͢
    ʢ΋ͪΖΜɺ&YDFM΍/VNCFSTͱ͍ͬͨΞϓϦέʔγϣϯ͔ΒͰ΋៉ྷʹݟ͑Δʣ
    

    View Slide

46. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ৽͍͠ಛ௃ྔΛ࡞੒͢Δ৔߹
    

    View Slide

47. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Family_Size(Feature):
    def create_features(self):
    self.train['Family_Size'] = train['Parch'] + train['SibSp']
    self.test['Family_Size'] = test['Parch'] + test['SibSp']
    create_memo('Family_Size','Ո଒ͷ૯਺')
    IPHFQZʹ৽͍͠ಛ௃ྔੜ੒ॲཧΛهड़
    ৽͍͠ಛ௃ྔΛ࡞੒͢Δ৔߹
    

    View Slide

48. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Family_Size(Feature):
    def create_features(self):
    self.train['Family_Size'] = train['Parch'] + train['SibSp']
    self.test['Family_Size'] = test['Parch'] + test['SibSp']
    create_memo('Family_Size','Ո଒ͷ૯਺')
    QZUIPOIPHFQZ
    ৽͍͠ಛ௃ྔΛ࡞੒͢Δ৔߹
    IPHFQZʹ৽͍͠ಛ௃ྔੜ੒ॲཧΛهड़
    

    View Slide

49. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    class Family_Size(Feature):
    def create_features(self):
    self.train['Family_Size'] = train['Parch'] + train['SibSp']
    self.test['Family_Size'] = test['Parch'] + test['SibSp']
    create_memo('Family_Size','Ո଒ͷ૯਺')
    QZUIPOIPHFQZ
    ৽͍͠ಛ௃ྔͷΈੜ੒
    ৽͍͠ಛ௃ྔΛ࡞੒͢Δ৔߹
    IPHFQZʹ৽͍͠ಛ௃ྔੜ੒ॲཧΛهड़
    

    View Slide

50. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    σʔλΛಡΈࠐΉࡍ͸ɺಛ௃ྔΛࢦఆͯ͠ϩʔυ͢Δ͚ͩ
    # ಛ௃ྔͷࢦఆ
    features = [
    "age_mis_val_median",
    "family__size",
    "cabin",
    "fare_mis_val_median"
    ]
    df = [pd.read_pickle(FEATURE_DIR_NAME + f’{f}_train.pkl') for f in features]
    df = pd.concat(df, axis=1)
    

    View Slide

51. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    σʔλΛಡΈࠐΉࡍ͸ɺಛ௃ྔΛࢦఆͯ͠ϩʔυ͢Δ͚ͩ
    # ಛ௃ྔͷࢦఆ
    features = [
    "age_mis_val_median",
    "family__size",
    "cabin",
    "fare_mis_val_median"
    ]
    df = [pd.read_pickle(FEATURE_DIR_NAME + f’{f}_train.pkl') for f in features]
    df = pd.concat(df, axis=1)
    Կ͕خ͔͔ͬͨ͠
    

    View Slide

52. ಛ௃ྔ؅ཧʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    w ͭͷεΫϦϓτϑΝΠϧʹಛ௃ྔੜ੒Λ·ͱΊΔ͜ͱͰɺಉ͡ܭࢉΛෳ਺
    ճ࣮ߦ͢Δ͜ͱΛආ͚ɺ࣌ؒΛ༗ޮ׆༻Ͱ͖Δɻ
    ɹˠಛ௃ྔͷ࠶ݱੑ΋୲อɻ
    w ಛ௃ྔͷϝϞΛಉ࣌ʹੜ੒͢Δ͜ͱͰʮ͜ͷಛ௃ྔͳΜ͚ͩͬʁʯͱ಄Λ࢖
    ΘͣʹࡁΜͩɻ
    w ಛ௃ྔΛྻ͝ͱʹ؅ཧ͢Δ͜ͱͰऔΓճָ͕͠ʹͳΔɻ
    ɹˠQJDLMFϑΝΠϧͩͱอଘ΋ಡΈࠐΈ΋଎͍ʂ
    ɹˠಛ௃ྔ͕๲େʹͳΔ৔߹͸ɺ͋Δఔ౓ͷ୯ҐͰ·ͱΊͯ؅ཧ͢Δํ͕ྑ͍͔΋ɻ
    

    View Slide

53. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ˞Լهॻ੶ʹܝࡌ͞Ε͍ͯΔύΠϓϥΠϯΛࢀߟʹ͠·ͨ͠ɻ
    ɾ,BHHMFͰউͭσʔλ෼ੳͷٕज़
    IUUQTHJIZPKQCPPL
    ‣ ίϚϯυҰൃͰֶशˠ4VCNJUϑΝΠϧ࡞੒·ͰΛ࣮ߦ
    ‣ ֶशʹ࢖༻ͨ͠ಛ௃ྔ΍Ϟσϧύϥϝʔλ͸MPHͱҰॹʹอଘ
    ‣ TIBQΛ༻͍ͯಛ௃ྔͷߩݙ౓ΛՄࢹԽ͠ɺ࣍ճֶश࣌ͷצॴΛݟ͚ͭΔ
    

    View Slide

54. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    SVOQZΛ࣮ߦ͢Δ͜ͱͰɺֶशɾਪ࿦ɾ4VCNJUϑΝΠϧΛ࡞੒
    # ಛ௃ྔͷࢦఆ
    features = [
    "age_mis_val_median",
    "family__size",
    "cabin",
    "fare_mis_val_median"
    ]
    run_name = 'lgb_1102'
    # ࢖༻͢Δಛ௃ྔϦετͷอଘ
    with open(LOG_DIR_NAME + run_name + "_features.txt", 'wt') as f:
    for ele in features:
    f.write(ele+'\n')
    params_lgb = {
    'boosting_type': 'gbdt',
    'objective': 'binary',
    'early_stopping_rounds': 20,
    'verbose': 10,
    'random_state': 99,
    'num_round': 100
    }
    # ࢖༻͢Δύϥϝʔλͷอଘ
    with open(LOG_DIR_NAME + run_name + "_param.txt", 'wt') as f:
    for key,value in sorted(params_lgb.items()):
    f.write(f'{key}:{value}\n')
    runner = Runner(run_name, ModelLGB, features, params_lgb, n_fold, name_prefix)
    runner.run_train_cv() # ֶश
    runner.run_predict_cv() # ਪ࿦
    Submission.create_submission(run_name) # submit࡞੒
    

    View Slide

55. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    SVOQZΛ࣮ߦ͢Δ͜ͱͰɺֶशɾਪ࿦ɾ4VCNJUϑΝΠϧΛ࡞੒
    # ಛ௃ྔͷࢦఆ
    features = [
    "age_mis_val_median",
    "family__size",
    "cabin",
    "fare_mis_val_median"
    ]
    run_name = 'lgb_1102'
    # ࢖༻͢Δಛ௃ྔϦετͷอଘ
    with open(LOG_DIR_NAME + run_name + "_features.txt", 'wt') as f:
    for ele in features:
    f.write(ele+'\n')
    params_lgb = {
    'boosting_type': 'gbdt',
    'objective': 'binary',
    'early_stopping_rounds': 20,
    'verbose': 10,
    'random_state': 99,
    'num_round': 100
    }
    # ࢖༻͢Δύϥϝʔλͷอଘ
    with open(LOG_DIR_NAME + run_name + "_param.txt", 'wt') as f:
    for key,value in sorted(params_lgb.items()):
    f.write(f'{key}:{value}\n')
    runner = Runner(run_name, ModelLGB, features, params_lgb, n_fold, name_prefix)
    runner.run_train_cv() # ֶश
    runner.run_predict_cv() # ਪ࿦
    Submission.create_submission(run_name) # submit࡞੒
    ͜ͷSVO@OBNFΛQSFpYͱͯ͠ɺϑΝΠϧ΍ϞσϧΛอଘͯ͘͠ΕΔɻ
    ྫ
    w ࢖༻ͨ͠ಛ௃ྔϦετ
    w ࢖༻ͨ͠ϋΠύʔύϥϝʔλ
    w GPMEຖͷϞσϧ
    w ਪ࿦݁Ռ
    w TVCNJUϑΝΠϧ
    w TIBQͷܭࢉ݁ՌΠϝʔδϑΝΠϧͳͲ
    

    View Slide

56. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    SVOQZΛ࣮ߦ͢Δ͜ͱͰɺֶशɾਪ࿦ɾ4VCNJUϑΝΠϧΛ࡞੒
    # ಛ௃ྔͷࢦఆ
    features = [
    "age_mis_val_median",
    "family__size",
    "cabin",
    "fare_mis_val_median"
    ]
    run_name = 'lgb_1102'
    # ࢖༻͢Δಛ௃ྔϦετͷอଘ
    with open(LOG_DIR_NAME + run_name + "_features.txt", 'wt') as f:
    for ele in features:
    f.write(ele+'\n')
    params_lgb = {
    'boosting_type': 'gbdt',
    'objective': 'binary',
    'early_stopping_rounds': 20,
    'verbose': 10,
    'random_state': 99,
    'num_round': 100
    }
    # ࢖༻͢Δύϥϝʔλͷอଘ
    with open(LOG_DIR_NAME + run_name + "_param.txt", 'wt') as f:
    for key,value in sorted(params_lgb.items()):
    f.write(f'{key}:{value}\n')
    runner = Runner(run_name, ModelLGB, features, params_lgb, n_fold, name_prefix)
    runner.run_train_cv() # ֶश
    runner.run_predict_cv() # ਪ࿦
    Submission.create_submission(run_name) # submit࡞੒
    ੜ੒͞ΕΔϑΝΠϧྫ
    

    View Slide

57. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ੜ੒͞ΕΔϑΝΠϧͷྫʢϑΥϧμ͸దٓ෼͚͍ͯ·͢ʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@QSFEQLMʢUFTUσʔλͰͷਪ࿦݁Ռʣ
    w MHC@@@TVCNJTTJPODTWʢਪ࿦݁ՌΛLBHHMFʹఏग़Ͱ͖ΔDTWʹม׵ͨ͠΋ͷʣ
    w MHC@@@GFBUVSFTUYUʢࠓճͷֶशʹ࢖༻ͨ͠ಛ௃ྔϦετʣ
    w MHC@@@QBSBNUYUʢࠓճͷֶशʹ࢖༻ͨ͠ϋΠύʔύϥϝʔλʣ
    w MHC@@@TIBQQOHʢTIBQͰܭࢉͨ͠ՄࢹԽΠϝʔδʣ
    w HFOFSBMMPHʢܭࢉϩάϑΝΠϧʣ
    w SFTVMUMPHʢϞσϧͷείΞ͚͕ͩهࡌ͞ΕͨϩάϑΝΠϧʣ
    

    View Slide

58. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ੜ੒͞ΕΔϑΝΠϧͷྫʢϑΥϧμ͸దٓ෼͚͍ͯ·͢ʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@QSFEQLMʢUFTUσʔλͰͷਪ࿦݁Ռʣ
    w MHC@@@TVCNJTTJPODTWʢਪ࿦݁ՌΛLBHHMFʹఏग़Ͱ͖ΔDTWʹม׵ͨ͠΋ͷʣ
    w MHC@@@GFBUVSFTUYUʢࠓճͷֶशʹ࢖༻ͨ͠ಛ௃ྔϦετʣ
    w MHC@@@QBSBNUYUʢࠓճͷֶशʹ࢖༻ͨ͠ϋΠύʔύϥϝʔλʣ
    w MHC@@@TIBQQOHʢTIBQͰܭࢉͨ͠ՄࢹԽΠϝʔδʣ
    w HFOFSBMMPHʢܭࢉϩάϑΝΠϧʣ
    w SFTVMUMPHʢϞσϧͷείΞ͚͕ͩهࡌ͞ΕͨϩάϑΝΠϧʣ
    

    View Slide

59. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ੜ੒͞ΕΔϑΝΠϧͷྫʢϑΥϧμ͸దٓ෼͚͍ͯ·͢ʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@QSFEQLMʢUFTUσʔλͰͷਪ࿦݁Ռʣ
    w MHC@@@TVCNJTTJPODTWʢਪ࿦݁ՌΛLBHHMFʹఏग़Ͱ͖ΔDTWʹม׵ͨ͠΋ͷʣ
    w MHC@@@GFBUVSFTUYUʢࠓճͷֶशʹ࢖༻ͨ͠ಛ௃ྔϦετʣ
    w MHC@@@QBSBNUYUʢࠓճͷֶशʹ࢖༻ͨ͠ϋΠύʔύϥϝʔλʣ
    w MHC@@@TIBQQOHʢTIBQͰܭࢉͨ͠ՄࢹԽΠϝʔδʣ
    w HFOFSBMMPHʢܭࢉϩάϑΝΠϧʣ
    w SFTVMUMPHʢϞσϧͷείΞ͚͕ͩهࡌ͞ΕͨϩάϑΝΠϧʣ
    

    View Slide

60. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ੜ੒͞ΕΔϑΝΠϧͷྫʢϑΥϧμ͸దٓ෼͚͍ͯ·͢ʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@QSFEQLMʢUFTUσʔλͰͷਪ࿦݁Ռʣ
    w MHC@@@TVCNJTTJPODTWʢਪ࿦݁ՌΛLBHHMFʹఏग़Ͱ͖ΔDTWʹม׵ͨ͠΋ͷʣ
    w MHC@@@GFBUVSFTUYUʢࠓճͷֶशʹ࢖༻ͨ͠ಛ௃ྔϦετʣ
    w MHC@@@QBSBNUYUʢࠓճͷֶशʹ࢖༻ͨ͠ϋΠύʔύϥϝʔλʣ
    w MHC@@@TIBQQOHʢTIBQͰܭࢉͨ͠ՄࢹԽΠϝʔδʣ
    w HFOFSBMMPHʢܭࢉϩάϑΝΠϧʣ
    w SFTVMUMPHʢϞσϧͷείΞ͚͕ͩهࡌ͞ΕͨϩάϑΝΠϧʣ
    

    View Slide

61. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ੜ੒͞ΕΔϑΝΠϧͷྫʢϑΥϧμ͸దٓ෼͚͍ͯ·͢ʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@QSFEQLMʢUFTUσʔλͰͷਪ࿦݁Ռʣ
    w MHC@@@TVCNJTTJPODTWʢਪ࿦݁ՌΛLBHHMFʹఏग़Ͱ͖ΔDTWʹม׵ͨ͠΋ͷʣ
    w MHC@@@GFBUVSFTUYUʢࠓճͷֶशʹ࢖༻ͨ͠ಛ௃ྔϦετʣ
    w MHC@@@QBSBNUYUʢࠓճͷֶशʹ࢖༻ͨ͠ϋΠύʔύϥϝʔλʣ
    w MHC@@@TIBQQOHʢTIBQͰܭࢉͨ͠ՄࢹԽΠϝʔδʣ
    w HFOFSBMMPHʢܭࢉϩάϑΝΠϧʣ
    w SFTVMUMPHʢϞσϧͷείΞ͚͕ͩهࡌ͞ΕͨϩάϑΝΠϧʣ
    

    View Slide

62. ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    ϚϚͷҰาΛࢧ͑Δ
    ੜ੒͞ΕΔϑΝΠϧͷྫʢϑΥϧμ͸దٓ෼͚͍ͯ·͢ʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@GPMENPEFMʢGPMEͰ࡞੒͞ΕͨϞσϧʣ
    w MHC@@QSFEQLMʢUFTUσʔλͰͷਪ࿦݁Ռʣ
    w MHC@@@TVCNJTTJPODTWʢਪ࿦݁ՌΛLBHHMFʹఏग़Ͱ͖ΔDTWʹม׵ͨ͠΋ͷʣ
    w MHC@@@GFBUVSFTUYUʢࠓճͷֶशʹ࢖༻ͨ͠ಛ௃ྔϦετʣ
    w MHC@@@QBSBNUYUʢࠓճͷֶशʹ࢖༻ͨ͠ϋΠύʔύϥϝʔλʣ
    w MHC@@@TIBQQOHʢTIBQͰܭࢉͨ͠ՄࢹԽΠϝʔδʣ
    w HFOFSBMMPHʢܭࢉϩάϑΝΠϧʣ
    w SFTVMUMPHʢϞσϧͷείΞ͚͕ͩهࡌ͞ΕͨϩάϑΝΠϧʣ
    Կ͕خ͔͔ͬͨ͠
    

    View Slide

63. ϚϚͷҰาΛࢧ͑Δ
    w ʮ͜ͷಛ௃ྔʯͱʮ͜ͷύϥϝʔλʯΛ࢖ֶͬͯशͤͨ͞Ϟσϧ
    ʹؔͯ͠ɺʮ֤λεΫʹཁͨ࣌ؒ͠ʯͱʮ֤GPMEʴ࠷ऴతͳεί
    ΞʯΛҙࣝ͠ͳͯ͘΋؅ཧͰ͖ΔΑ͏ʹɻ
    w TIBQͷܭࢉ݁Ռ΍GFBUVSFJNQPSUBODFΛग़ྗ͓ͯ͘͜͠ͱ
    Ͱɺ࣍ͷֶश࣌ͷצॴ͕௫ΊΔΑ͏ʹɻ
    ֶशɾਪ࿦ύΠϓϥΠϯʹ͍ͭͯ
    

    View Slide

64. ·ͱΊ
    ϚϚͷҰาΛࢧ͑Δ
    

    View Slide

65. ·ͱΊ
    ϚϚͷҰาΛࢧ͑Δ
    w ಛ௃ྔ؅ཧ͍͍ͧʂ
    ͭͷεΫϦϓτϑΝΠϧʹಛ௃ྔੜ੒Λ·ͱΊΔ͜ͱͰɺಉ͡ܭࢉΛෳ਺ճ࣮ߦ͢Δ͜ͱ
    ΛճආͰ͖Δʂ
    ಛ௃ྔͷϝϞΛಉ࣌ʹੜ੒͢Δ͜ͱͰʮ͜ͷಛ௃ྔͳΜ͚ͩͬʁʯͱ಄Λ࢖͏ճ਺͕ݮ
    Δʂ
    ಛ௃ྔΛྻ͝ͱʹ؅ཧ͢Δ͜ͱͰऔΓճָ͕͠ʹͳͬͨʂʢ͕ɺಛ௃ྔ͕๲େͳ৔߹͸͋
    Δఔ౓ͷ·ͱ·ΓͰ؅ཧͨ͠ํ͕ྑ͍͔΋ʣ
    w ύΠϓϥΠϯ͍͍ͧʂ
    ύΠϓϥΠϯΛߏங͢Δ͜ͱͰɺߴ଎ͳ1%$"Λ࣮ݱʂ
    ֶशʹ࢖༻ͨ͠ಛ௃ྔͱύϥϝʔλΛ؅ཧ͢Δ͜ͱͰɺ࠶ݱੑ΋୲อ͞Ε৺ཧత҆શੑ΋
    
    

    View Slide

66. ϚϚͷҰาΛࢧ͑Δ
    ͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠
    

    View Slide