機械学習によるデータ分析 実践編
104 likes17,634 views
The document discusses various aspects of data mining and machine learning, including methodologies like SEMMA, CRISP-DM, and KDD. It covers different learning paradigms such as supervised, unsupervised, and reinforcement learning, along with evaluation metrics like precision, recall, and ROC-AUC. Additionally, it references Python libraries and tools for implementing machine learning techniques.
![Feature hashing /=Hashing trick 16
FeatureNhashing t
Nt v t
xN:=NnewNvector[N]
forNfNinNfeatures:
hN:=Nhash(f)
x[hNmodNN]N+=N1
http://en.wikipedia.org/wiki/Feature_hashing](https://image.slidesharecdn.com/random-150814141723-lva1-app6891/85/-16-320.jpg)
機械学習によるデータ分析 実践編
- 4. 4 Sample Explore Modify Model Assess Sample Explore Modify Model Assess t t r t SEMMA
- 6. 6 t http://biostat.mc.vanderbilt.edu/wiki/pub/Main/DataSets/titanic3.csv (DataNobtainedNfromNhttp://biostat.mc.vanderbilt.edu/DataSets) > data = read.csv(“titanic3.csv”, + stringsAsFactors=F, na.strings=c("","NA")) >>> import pandas as pd >>> data = pd.read_csv(‘titanic3.csv') Sample Explore Modify Assess Model
- 8. 8 () ( ( ) ) ) ( () ( ( ) ( ( ) ( ÷
- 9. 9 r t r r r
- 10. 10
- 11. 11 1. t 2. t 3. t 4. t
- 12. 12 t t t t Sample Explore Modify Assess Model
- 13. 13 t rT
- 14. 14 u nT t T
- 15. 10of0K 15 N t NL1 t
- 16. Feature hashing /=Hashing trick 16 FeatureNhashing t Nt v t xN:=NnewNvector[N] forNfNinNfeatures: hN:=Nhash(f) x[hNmodNN]N+=N1 http://en.wikipedia.org/wiki/Feature_hashing
- 17. (Curse=of=dimensionality) 17 t r g r ur n u t e e e t T Tn u t e
- 18. (Standardization) 18 xt 10 i t n
- 20. 20 t r (Feature selection) t r t e (ForwardNstepwiseNselection) (BackwardNstepwiseNselection)
- 21. 21 UglyNducklingNtheorem T t t t t u t t t t T t
- 22. 22 4. t 5. t 6. t
- 23. 23 u “MachineNlearningNisNtheNscienceNofNgettingNcomputersNtoN actNwithoutNbeingNexplicitlyNprogrammed.”NNNNNNNNNNNNNNNNNNNNNNNNNNNNNNNN AndrewNNg u t T t e e 23 Sample Explore Modify Assess Model
- 24. 24 supervisedNlearning t • classification • regression unsupervisedNlearning u t • • • outlierNdetection
- 25. 25 gt t • semiLsupervisedNlearning • reinforcementNlearning • activeNlearning • onlineNlearning • transferNlearning
- 27. 27 r • KLmeansN • • Apriori • OneLclassNSVM
- 29. 29 x y εββββ +++++= ii xxxy !22110 u generalizedNlinearNmodel u t
- 31. 31 t T ÷ u n T t T t
- 32. 32 7.
- 33. 3333 Sample Explore Modify Assess Model
- 34. 34 (MeanNabsoluteNerror) T T (MeanNsquare(d)Nerror) T T RootNMeanNSquare(d)N Error R2(CoefficientNofNdetermination) ÷ T e 0( T) 1( T) T r
- 35. 35 (Accuracy) (ErrorNrate) 1N 1 t t 100 t e t u99% u T T i
- 36. 36 (ConfusionNmatrix) (Positive) 26 5 8 6 (TrueNpositiveN:NTP) (FalseNnegativeN:NFN) (FalseNpositiveN:NFP) 4: 6 96 5 8 6 / 42 T nT v t r
- 37. 37 (Precision) TP/(TPN+NFP) tt (Recall) TP/(TPN+NFN) t F (F1Nscore,NFLmeasure) 2 ( )N/N( ) P 2 3 TP FN 2 FP 42
- 38. 38 (True Positive Rate) TP/(TPN+NFN) t (False Positive Rate) FP/(FPN+NTN) t n P 2 3 TP FN 2 FP 42
- 39. 39 1 t t 100 t e (Positive) (Negative) 0 100 0 9900 0.99 0 0 F 0
- 40. 40 t u e r T t rT e T e SMOTE u r rT T...
- 41. 41 u t T e u r r ROC t r t AUC ROC t t 1.0
- 42. 42 ROC AUC
- 43. 43 n r T t u rT >Nclf =NSVC().fit(X,Ny)
- 45. 45 r t T t e
- 46. 46 t r t( : t )u r g rT tu n(10L2,10L1,100,101,102) u n
- 47. 47 n r 0.0 F 1.0 i r
- 48. 48 t 0.0 u t
- 49. 49 (OverNfitting) n n T u T e n t e e t T T r T eT
- 50. 50 e r e rT (Regularization) t Lasso SVMr t t r e n rT(UnderNfitting)
- 51. 51 (Cross validation) e 1. B E A 2. A,C E B 3. A,B,D,E C 4. A C,E D 5. A D E 6. 5t 5 5LfoldNcrossNvalidation
- 52. 52 t K 1 (LeaveLoneLout cross validation) (StratifiedNcrossNvalidation) t t K t a r t e t
- 53. 53 8. 9.
- 55. 55 t ε t
- 56. 56 ε t u T tv u T → 1
- 57. 57 ε t T →
- 58. 58 u t t T (OverNfitting) t T UnderNfitting
- 59. 59 r ( ) ( )
- 60. 60 ( ) T( T) t T t T t nTrT
- 61. 61 T t T t T
- 62. 62 r e t T t e e r e
- 64. 64 (EnsembleNlearning) • t t • Stacking Bagging Boosting • u DeepNlearning • NeuralNnetworkst • r
- 67. 67 MALSS > pip install –U malss > from malss import MALSS > clf = MALSS('classification‘, lang=‘jp’) > clf.fit(X, y, ‘report_output_dir') > clf.make_sample_code('sample_code.py')
- 68. 68 MALSS
- 69. 69 MALSS
- 71. 71 MALSS=(Machine=Learning=Support=System) https://pypi.python.org/pypi/malss/ https://github.com/canard0328/malss Python MALSS Qiita http://qiita.com/canard0328/items/fe1ccd5721d59d76cc77 Python MALSS Qiita http://qiita.com/canard0328/items/5da95ff4f2e1611f87e1 Python MALSS Qiita http://qiita.com/canard0328/items/3713d6758fe9c045a19d
- 72. 72 1. SEMMA CRISPLDM KDD KKD 2. t t T T t 3. 4.