Accueil Explorer Aide
Connexion
LiuFan
/
PrivacyScanData
1
0
Fork 0
Fichiers Tickets 0 Pull Requests 0 Wiki
Branche: master
Branches Tags
PrivacyScanD...
/
BI
/
BusinessIntelligence-Kaggle
/
Submissions
/
submission-2
/
output.txt

output.txt 2.2 KB
Lien permanent Historique Raw

1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162 
  1.               Total   Percent
    2. 

  2. PoolQC         1453  0.995205
    3. 

  3. MiscFeature    1406  0.963014
    4. 

  4. Alley          1369  0.937671
    5. 

  5. Fence          1179  0.807534
    6. 

  6. FireplaceQu     690  0.472603
    7. 

  7. LotFrontage     259  0.177397
    8. 

  8. GarageCond       81  0.055479
    9. 

  9. GarageType       81  0.055479
    10. 

  10. GarageYrBlt      81  0.055479
    11. 

  11. GarageFinish     81  0.055479
    12. 

  12. GarageQual       81  0.055479
    13. 

  13. BsmtExposure     38  0.026027
    14. 

  14. BsmtFinType2     38  0.026027
    15. 

  15. BsmtFinType1     37  0.025342
    16. 

  16. BsmtCond         37  0.025342
    17. 

  17. BsmtQual         37  0.025342
    18. 

  18. MasVnrArea        8  0.005479
    19. 

  19. MasVnrType        8  0.005479
    20. 

  20. Electrical        1  0.000685
    21. 

  21. ElasticNetCV(alphas=[0.0001, 0.0005, 0.001, 0.01, 0.1, 1, 10], copy_X=True,
    22. 

  22.        cv=None, eps=0.001, fit_intercept=True,
    23. 

  23.        l1_ratio=[0.01, 0.1, 0.5, 0.9, 0.99], max_iter=5000, n_alphas=100,
    24. 

  24.        n_jobs=1, normalize=False, positive=False, precompute='auto',
    25. 

  25.        random_state=None, selection='cyclic', tol=0.0001, verbose=0)
    26. 

  26. R2: 0.900928280613796
    27. 

  27. RMSE: 0.11921419956844193
    28. 

  28. RMSLE: 0.009197799994941804
    29. 

  29. Test
    30. 

  30. R2: 0.8967299504618576
    31. 

  31. RMSE: 0.11097042747851499
    32. 

  32. RMSLE: 0.008597196096326625
    33. 

  33. Accuracy: 0.88 (+/- 0.10)
    34. 

  34. GradientBoostingRegressor(alpha=0.9, criterion='friedman_mse', init=None,
    35. 

  35.              learning_rate=0.05, loss='huber', max_depth=3,
    36. 

  36.              max_features='sqrt', max_leaf_nodes=None,
    37. 

  37.              min_impurity_decrease=0.0, min_impurity_split=None,
    38. 

  38.              min_samples_leaf=15, min_samples_split=10,
    39. 

  39.              min_weight_fraction_leaf=0.0, n_estimators=3000,
    40. 

  40.              presort='auto', random_state=None, subsample=1.0, verbose=0,
    41. 

  41.              warm_start=False)
    42. 

  42. R2: 0.961882325124111
    43. 

  43. RMSE: 0.07588140544292711
    44. 

  44. RMSLE: 0.00591670124537216
    45. 

  45. Test
    46. 

  46. R2: 0.8926997636367985
    47. 

  47. RMSE: 0.11164479282544255
    48. 

  48. RMSLE: 0.008680527859539
    49. 

  49. Accuracy: 0.90 (+/- 0.04)
    50. 

  50. XGBRegressor(base_score=0.5, colsample_bylevel=1, colsample_bytree=1, gamma=0,
    51. 

  51.        learning_rate=0.05, max_delta_step=0, max_depth=3,
    52. 

  52.        min_child_weight=1, missing=None, n_estimators=3000, nthread=-1,
    53. 

  53.        objective='reg:linear', reg_alpha=0, reg_lambda=1,
    54. 

  54.        scale_pos_weight=1, seed=0, silent=True, subsample=1)
    55. 

  55. R2: 0.9971902274242356
    56. 

  56. RMSE: 0.021167142946350206
    57. 

  57. RMSLE: 0.0016307988766566474
    58. 

  58. Test
    59. 

  59. R2: 0.9038938318170437
    60. 

  60. RMSE: 0.1079454200273511
    61. 

  61. RMSLE: 0.008339622465234684
    62. 

  62. Accuracy: 0.89 (+/- 0.03)
    63.