Advanced Machine Learning with Scikit-Learn

PyData Amsterdam talk about advanced machine learning techniques in Python with scikit-learn

Transcript

1. 1 Advanced Scikit-Learn Andreas Mueller (NYU Center for Data Science, scikit-learn)
2. 2 Me
3. 3 Classification Regression Clustering Semi-Supervised Learning Feature Selection Feature Extraction Manifold Learning Dimensionality Reduction Kernel Approximation Hyperparameter Optimization Evaluation Metrics Out-of-core learning …...
5. 5 Overview • Reminder: Basic scikit-learn concepts • Working with text data • Model building and evaluation: – Pipelines – Randomized Parameter Search – Scoring Interface • Out of Core learning – Feature Hashing – Kernel Approximation • New stuff in 0.17 and 0.18-dev – Overview – Calibration
6. 6 http://scikit-learn.org/
7. 7 Representing Data X = 1.1 2.2 3.4 5.6 1.0 6.7 0.5 0.4 2.6 1.6 2.4 9.3 7.3 6.4 2.8 1.5 0.0 4.3 8.3 3.4 0.5 3.5 8.1 3.6 4.6 5.1 9.7 3.5 7.9 5.1 3.7 7.8 2.6 3.2 6.3
8. 8 Representing Data X = 1.1 2.2 3.4 5.6 1.0 6.7 0.5 0.4 2.6 1.6 2.4 9.3 7.3 6.4 2.8 1.5 0.0 4.3 8.3 3.4 0.5 3.5 8.1 3.6 4.6 5.1 9.7 3.5 7.9 5.1 3.7 7.8 2.6 3.2 6.3 one sample
9. 9 Representing Data X = 1.1 2.2 3.4 5.6 1.0 6.7 0.5 0.4 2.6 1.6 2.4 9.3 7.3 6.4 2.8 1.5 0.0 4.3 8.3 3.4 0.5 3.5 8.1 3.6 4.6 5.1 9.7 3.5 7.9 5.1 3.7 7.8 2.6 3.2 6.3 one sample one feature
10. 10 Representing Data X = y = 1.1 2.2 3.4 5.6 1.0 6.7 0.5 0.4 2.6 1.6 2.4 9.3 7.3 6.4 2.8 1.5 0.0 4.3 8.3 3.4 0.5 3.5 8.1 3.6 4.6 5.1 9.7 3.5 7.9 5.1 3.7 7.8 2.6 3.2 6.3 1.6 2.7 4.4 0.5 0.2 5.6 6.7 one sample one feature outputs / labels
11. 11 Training Data Training Labels Model Supervised Machine Learning clf = RandomForestClassifier() clf.fit(X_train, y_train)
12. 12 Training Data Test Data Training Labels Model Prediction Supervised Machine Learning clf = RandomForestClassifier() clf.fit(X_train, y_train) y_pred = clf.predict(X_test)
13. 13 clf.score(X_test, y_test) Training Data Test Data Training Labels Model Prediction Test Labels Evaluation Supervised Machine Learning clf = RandomForestClassifier() clf.fit(X_train, y_train) y_pred = clf.predict(X_test)
14. 14 pca = PCA(n_components=3) pca.fit(X_train) Training Data Model Unsupervised Transformations
15. 15 pca = PCA(n_components=3) pca.fit(X_train) X_new = pca.transform(X_test) Training Data Test Data Model Transformation Unsupervised Transformations
16. 16 Basic API estimator.fit(X, [y]) estimator.predict estimator.transform Classification Preprocessing Regression Dimensionality reduction Clustering Feature selection Feature extraction
17. 17 Model selection and model complexity (aka bias-variance tradeoff)
18. 18 Overfitting and Underfitting Model complexity Accuracy Training
19. 19 Overfitting and Underfitting Model complexity Accuracy Training Generalization
20. 20 Overfitting and Underfitting Model complexity Accuracy Training Generalization Underfitting Overfitting Sweet spot
21. 21 Cross-Validation from sklearn.cross_validation import cross_val_score scores = cross_val_score(SVC(), X, y, cv=5) print(scores) >> [ 0.92 1. 1. 1. 1. ]
22. 22 Cross-Validation from sklearn.cross_validation import cross_val_score scores = cross_val_score(SVC(), X, y, cv=5) print(scores) >> [ 0.92 1. 1. 1. 1. ] cv_ss = ShuffleSplit(len(X_train), test_size=.3, n_iter=10) scores_shuffle_split = cross_val_score(SVC(), X, y, cv=cv_ss)
23. 23 Cross-Validation from sklearn.cross_validation import cross_val_score scores = cross_val_score(SVC(), X, y, cv=5) print(scores) >> [ 0.92 1. 1. 1. 1. ] cv_ss = ShuffleSplit(len(X_train), test_size=.3, n_iter=10) scores_shuffle_split = cross_val_score(SVC(), X, y, cv=cv_ss) cv_labels = LeaveOneLabelOut(labels) scores_pout = cross_val_score(SVC(), X, y, cv=cv_labels)
24. 24 Cross -Validated Grid Search
25. 25 All Data Training data Test data
26. 26 All Data Training data Test data Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Test data Split 1 Split 2 Split 3 Split 4 Split 5
27. 27 All Data Training data Test data Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Fold 1 Fold 2 Fold 3 Fold 4 Fold 5 Test data Finding Parameters Final evaluation Split 1 Split 2 Split 3 Split 4 Split 5
28. 28 Cross -Validated Grid Search from sklearn.grid_search import GridSearchCV from sklearn.cross_validation import train_test_split X_train, X_test, y_train, y_test = train_test_split(X, y) param_grid = {'C': 10. ** np.arange(-3, 3), 'gamma': 10. ** np.arange(-3, 3)} grid = GridSearchCV(SVC(), param_grid=param_grid) grid.fit(X_train, y_train) grid.predict(X_test) grid.score(X_test, y_test)
29. 29 Sample application: Sentiment Analysis
30. 30 Review: One of the worst movies I've ever rented. Sorry it had one of my favorite actors on it (Travolta) in a nonsense role. In fact, anything made sense in this movie. Who can say there was true love between Eddy and Maureen? Don't you remember the beginning of the movie ? Is she so lovely? Ask her daughters. I don't think so. Label: negative Training data: 12500 positive, 12500 negative IMDB Movie Reviews Data
31. 31 Bag Of Word Representations CountVectorizer / TfidfVectorizer
32. 32 Bag Of Word Representations “This is how you get ants.” CountVectorizer / TfidfVectorizer
33. 33 Bag Of Word Representations “This is how you get ants.” ['this', 'is', 'how', 'you', 'get', 'ants'] CountVectorizer / TfidfVectorizer tokenizer
34. 34 Bag Of Word Representations “This is how you get ants.” ['this', 'is', 'how', 'you', 'get', 'ants'] CountVectorizer / TfidfVectorizer tokenizer Build a vocabulary over all documents ['aardvak', 'amsterdam', 'ants', ... 'you', 'your', 'zyxst']
35. 35 Bag Of Word Representations “This is how you get ants.” [0, …, 0, 1, 0, … , 0, 1 , 0, …, 0, 1, 0, …., 0 ] ants get you aardvak zyxst ['this', 'is', 'how', 'you', 'get', 'ants'] CountVectorizer / TfidfVectorizer tokenizer Sparse matrix encoding Build a vocabulary over all documents ['aardvak', 'amsterdam', 'ants', ... 'you', 'your', 'zyxst']
36. 36 N-grams (unigrams and bigrams) CountVectorizer / TfidfVectorizer
37. 37 N-grams (unigrams and bigrams) “This is how you get ants.” CountVectorizer / TfidfVectorizer
38. 38 N-grams (unigrams and bigrams) “This is how you get ants.” ['this', 'is', 'how', 'you', 'get', 'ants'] CountVectorizer / TfidfVectorizer Unigram tokenizer
39. 39 N-grams (unigrams and bigrams) “This is how you get ants.” ['this', 'is', 'how', 'you', 'get', 'ants'] CountVectorizer / TfidfVectorizer Unigram tokenizer “This is how you get ants.” ['this is', 'is how', 'how you', 'you get', 'get ants'] Bigram tokenizer
40. 40 Notebook Working With Text Data
41. 41 Pipelines
42. 42 Training Data Training Labels Model
43. 43 Training Data Training Labels Model
44. 44 Training Data Training Labels Model Feature Extraction Scaling Feature Selection
45. 45 Training Data Training Labels Model Feature Extraction Scaling Feature Selection Cross Validation
46. 46 Training Data Training Labels Model Feature Extraction Scaling Feature Selection Cross Validation
47. 47 Pipelines pipe.fit(X, y) T1 X y T1.fit(X, y) T2.fit(X1, y) Classifier.fit(X2, y) T1.transform(X) pipe.predict(X') X' y' Classifier.predict(X'2) T2 Classifier T2 T1 X1 y T2.transform(X1) X2 y Classifier T1.transform(X')X'1 T2.transform(X'1) X'2 pipe = make_pipeline(T1(), T2(), Classifier())
48. 48 Pipelines from sklearn.pipeline import make_pipeline pipe = make_pipeline(StandardScaler(), SVC()) pipe.fit(X_train, y_train) pipe.predict(X_test)
49. 49 Continue Notebook Working with Text Data
50. 50 Randomized Parameter Search
51. 51 Randomized Parameter Search Source: Bergstra and Bengio
52. 52 Randomized Parameter Search Source: Bergstra and Bengio Step-size free for continuous parameters Decouples runtime from search-space size Robust against irrelevant parameters
53. 53 Randomized Parameter Search params = {'featureunion__countvectorizer-1__ngram_range': [(1, 3), (1, 5), (2, 5)], 'featureunion__countvectorizer-2__ngram_range': [(1, 1), (1, 2), (2, 2)], 'linearsvc__C': 10. ** np.arange(-3, 3)}
54. 54 Randomized Parameter Search params = {'featureunion__countvectorizer-1__ngram_range': [(1, 3), (1, 5), (2, 5)], 'featureunion__countvectorizer-2__ngram_range': [(1, 1), (1, 2), (2, 2)], 'linearsvc__C': expon()}
55. 55 Randomized Parameter Search rs = RandomizedSearchCV(text_pipe, param_distributions=param_distributins, n_iter=50) params = {'featureunion__countvectorizer-1__ngram_range': [(1, 3), (1, 5), (2, 5)], 'featureunion__countvectorizer-2__ngram_range': [(1, 1), (1, 2), (2, 2)], 'linearsvc__C': expon()}
56. 56 Randomized Parameter Search • Always use distributions for continuous variables. • Don't use for low dimensional spaces.
57. GP based parameter optimization (coming soon) From Eric Brochu, Vlad M. Cora and Nando de Freitas
58. 58 Efficient Parameter Search and Path Algorithms
59. 59 rfe = RFE(LogisticRegression())
60. 60 rfe = RFE(LogisticRegression()) param_grid = {'n_features_to_select': range(1, n_features)} gridsearch = GridSearchCV(rfe, param_grid) grid.fit(X, y)
61. 61 rfe = RFE(LogisticRegression()) param_grid = {'n_features_to_select': range(1, n_features)} gridsearch = GridSearchCV(rfe, param_grid) grid.fit(X, y)
62. 62 rfe = RFE(LogisticRegression()) param_grid = {'n_features_to_select': range(1, n_features)} gridsearch = GridSearchCV(rfe, param_grid) grid.fit(X, y) rfecv = RFECV(LogisticRegression())
63. 63 rfe = RFE(LogisticRegression()) param_grid = {'n_features_to_select': range(1, n_features)} gridsearch = GridSearchCV(rfe, param_grid) grid.fit(X, y) rfecv = RFECV(LogisticRegression()) rfecv.fit(X, y)
65. 65 Linear Models Feature Selection Tree-Based models [possible] LogisticRegressionCV [new] RFECV [DecisionTreeCV] RidgeCV [RandomForestClassifierCV] RidgeClassifierCV [GradientBoostingClassifierCV] LarsCV ElasticNetCV ...
66. 66 Notebook Efficient Parameter Search
67. 67 Scoring Functions
68. 68 Default: Accuracy (classification) R2 (regression) GridSeachCV RandomizedSearchCV cross_val_score ...CV
69. 69 Notebook scoring metrics
70. 70 Out of Core Learning
71. 71 • Large Scale – “Out of core: Fits on a hard disk but in RAM”
72. 72 • Large Scale – “Out of core: Fits on a hard disk but in RAM” • Non-linear – because real-world problems are not.
73. 73 • Large Scale – “Out of core: Fits on a hard disk but in RAM” • Non-linear – because real-world problems are not. • Single CPU – Because parallelization is hard (and often unnecessary)
74. 74 Think twice! • Old laptop: 4GB Ram • 1073741824 float32 • Or 1mio data points with 1000 features • EC2 : 256 GB Ram • 68719476736 float32 • Or 68mio data points with 1000 features
76. 76 HDD Network estimator.partial_fit(X_batch, y_batch) Your for-loop / polling Trained Scikit-learn estimator
77. 77 Supported Algorithms • All SGDClassifier derivatives • Naive Bayes • MinibatchKMeans • IncrementalPCA • MiniBatchDictionaryLearning • MultilayerPerceptron (dev branch) • Scalers
78. 78 Out of Core Learning sgd = SGDClassifier() for i in range(9): X_batch, y_batch = cPickle.load(open("batch_%02d" % i)) sgd.partial_fit(X_batch, y_batch, classes=range(10)) Possibly go over the data multiple times.
79. 79 The hashing trick for text data
80. 80 Text Classification: Bag Of Word “This is how you get ants.” [0, …, 0, 1, 0, … , 0, 1 , 0, …, 0, 1, 0, …., 0 ] ants get you aardvak zyxst ['this', 'is', 'how', 'you', 'get', 'ants'] tokenizer Sparse matrix encoding Build a vocabulary over all documents ['aardvak', 'amsterdam', 'ants', ... 'you', 'your', 'zyxst']
81. 81 Text Classification: Hashing Trick “This is how you get ants.” [0, …, 0, 1, 0, … , 0, 1 , 0, …, 0, 1, 0, …., 0 ] ['this', 'is', 'how', 'you', 'get', 'ants'] tokenizer Sparse matrix encoding hashing [hash('this'), hash('is'), hash('how'), hash('you'), hash('get'), hash('ants')] = [832412, 223788, 366226, 81185, 835749, 173092]
82. 82 Kernel Approximations
83. 83 Reminder: Kernel Trick x
84. 84 Reminder: Kernel Trick
85. 85 Reminder: Kernel Trick Classifier linear → need only
86. 86 Reminder: Kernel Trick Classifier linear → need only Linear: Polynomial: RBF: Sigmoid:
87. 87 Complexity • Solving kernelized SVM: ~O(n_samples ** 3) • Solving linear (primal) SVM: ~O(n_samples * n_features) n_samples large? Go primal!
88. 88 Undoing the Kernel Trick • Kernel approximation: • k = = RBFSampler
89. 89 Usage sgd = SGDClassifier() kernel_approximation = RBFSampler(gamma=.001, n_components=400) for i in range(9): X_batch, y_batch = cPickle.load(open("batch_%02d" % i)) if i == 0: kernel_approximation.fit(X_batch) X_transformed = kernel_approximation.transform(X_batch) sgd.partial_fit(X_transformed, y_batch, classes=range(10))
90. 90 How (and why) to build your own estimator
91. 91 Why? GridSearchCV cross_val_score Pipeline
92. 92 How • “fit” method • set_params and get_params (or inherit) • Run check_estimator See the “build your own estimator” docs!
93. 93 Notebook Building your own estimator
94. What's new in 0.17
95. Latent Dirichlet Allocation using online variational inference By Chyi-Kwei Yau, based on code by Matt Hoffman Topic #0: government people mr law gun state president states public use right rights national new control american security encryption health united Topic #1: drive card disk bit scsi use mac memory thanks pc does video hard speed apple problem used data monitor software Topic #2: said people armenian armenians turkish did saw went came women killed children turkey told dead didn left started greek war Topic #3: year good just time game car team years like think don got new play games ago did season better ll Topic #4: 10 00 15 25 12 11 20 14 17 16 db 13 18 24 30 19 27 50 21 40 Topic #5: windows window program version file dos use files available display server using application set edu motif package code ms software Topic #6: edu file space com information mail data send available program ftp email entry info list output nasa address anonymous internet Topic #7: ax max b8f g9v a86 pl 145 1d9 0t 34u 1t 3t giz bhj wm 2di 75u 2tm bxn 7ey Topic #8: god people jesus believe does say think israel christian true life jews did bible don just know world way church Topic #9: don know like just think ve want does use good people key time way make problem really work say need
96. SAG for Logistic Regression and Ridge Regression By Danny Sullivan and Tom Dupre la Tour
97. Coordinate Descent Solver for Non-Negative Matrix Factorization By Tom Dupre la Tour and Mathieu Blondel Topics in NMF model: Topic #0: don people just like think know time good right ve make say want did really way new use going said Topic #1: windows file dos files window program use running using version ms problem server pc screen ftp run application os software Topic #2: god jesus bible christ faith believe christians christian heaven sin hell life church truth lord say belief does existence man Topic #3: geb dsl n3jxp chastity cadre shameful pitt intellect skepticism surrender gordon banks soon edu lyme blood weight patients medical probably Topic #4: key chip encryption clipper keys escrow government algorithm secure security encrypted public des nsa enforcement bit privacy law secret use Topic #5: drive scsi ide drives disk hard controller floppy hd cd mac boot rom cable internal tape bus seagate bios quantum Topic #6: game team games players year hockey season play win league teams nhl baseball player detroit toronto runs pitching best playoffs Topic #7: thanks mail does know advance hi info looking anybody address appreciated help email information send ftp post interested list appreciate Topic #8: card video monitor vga bus drivers cards color driver ram ati mode memory isa graphics vesa pc vlb diamond bit Topic #9: 00 sale 50 shipping 20 10 price 15 new 25 30 dos offer condition 40 cover asking 75 interested 01
98. Barnes-Hut Approximation for T-SNE manifold learning
99. FunctionTransformer
100. VotingClassifier clf1 = LogisticRegression() clf2 = RandomForestClassifier() clf3 = GaussianNB() eclf = VotingClassifier( estimators=[('lr', clf1), ('rf', clf2), ('gbn', clf3)], voting=”hard”)
101. Scalers • RobustScaler • MaxAbsScaler By Thomas Unterthiner.
102. Add Backlinks to Docs
103. Add Backlinks to Docs
104. What the future will bring (0.18)
105. Gaussian Process Rewrite 34.4**2 * RBF(length_scale=41.8) + 3.27**2 * RBF(length_scale=180) * ExpSineSquared(length_scale=1.44, periodicity=1) + 0.446**2 * RationalQuadratic(alpha=17.7, length_scale=0.957) + 0.197**2 * RBF(length_scale=0.138) + WhiteKernel(noise_level=0.0336) By Jan Hendrik Metzen.
106. Neural Networks By Jiyuan Qian and Issam Laradji
107. Improved Cross-Validation By Raghav RV current future
108. Faster PCA By Giorgio Patrini
109. 109 Release June 2016
110. 110 Hellbender Release June 2016
111. 111 Thank you! @amuellerml @amueller importamueller@gmail.com http://amueller.github.io