JavaScriptでも機械学習がやりたかった話

Transcript

1. 1.

   Yuji Isobe JavaScriptͰ΋ ػցֶश͕΍Γ͔ͨͬͨ࿩ Emotion Intelligence × GIGษڧձ

2. 2.

   Ϛωʔδϟʔ 
 ϝϯςφʔ @yujiosaka github.com/yujiosaka/headless-chrome-crawler

3. 3.

   ձࣾ www.emin.co.jp

4. 4.

   એ఻ᶃ www.zenclerk.com/

5. 5.

   ϏδωεɾOSSϚΠϯυΛ࣋ͬͨΤϯδχΞืूʂ એ఻ᶄ www.wantedly.com/projects/233437

6. 6.

   ຊ୊

7. 7.

   1.JavaScriptͰػցֶश͸Ͳ͜·ͰͰ͖Δͷ͔ 2.JavaScriptΛ࢖͏ϝϦοτͱσϝϦοτ 3.۩ମతͳ࣮ݱํ๏ͱσϞ ຊ೔ͷςʔϚ

8. 8.

   ͦ΋ͦ΋JavaScriptͰ
 ػցֶशͬͯ·ͱ΋ʹͰ͖Μͷʁ

9. 9.

   JavaScriptͰσΟʔϓϥʔχϯά speakerdeck.com/yujiosaka/hitasurale-sitedeipuraningu github.com/yujiosaka/js-mind XXXSFEEJUDPNSOPEFDPNNFOUTEH KT@NJOE@EFFQ@MFBSOJOH@MJCSBSZ@XSJUUFO@JO@FT ͳΜͰJavaScriptͰ͜Μͳ͜ͱͨ͠Μͩʁ ͦΜͳͷStarཉ͠͞ʹܾ·ͬͯΔͰ͠ΐ

10. 10.

    ਤ੕

11. 11.

    ౰࣌ͷΦν TQFBLFSEFDLDPNZVKJPTBLBIJUBTVSBMFTJUFEFJQVSBOJOHV TMJEF

12. 12.

    ౰࣌ͷΦν TQFBLFSEFDLDPNZVKJPTBLBIJUBTVSBMFTJUFEFJQVSBOJOHV TMJEF

13. 13.

    A. օ͕࢖ͬͯΔ͔Βศརʹͳ͍ͬͯ͘ Q. ͳͥσʔλαΠΤϯε͸Pythonʁ trends.google.co.jp/trends/explore?date=today%205-y&geo=JP&q=JavaScript,Python,AI

14. 14.

    NumPy/Pandas - ߴ଎ɾߴػೳͳߦྻܭࢉ Matplotlib/seaborn - ख͔ܰͭߴػೳͳάϥϑඳը Jupiter Notebook - ࢼߦࡨޡ͕΍Γ΍͍͢

    scikit-learn - ڞ௨ͷػցֶशAPIΛఏڙ͢Δ TensorFlow/PyTorch - GPUΛ࢖ͬͨߴ଎ͳਂ૚ֶश ... σʔλαΠΤϯεΛࢧ͑ΔPython Cݴޠ࣮૷ʴSIMD໋ྩʴ਺ֶతͳ࠷దԽʴ؆ܿͳهड़
15. 15.

    NumPyΛ࢖ͬͨߴ଎ͳߦྻܭࢉ > import time > import numpy as np >

    a = np.random.random((1000, 1000)) > b = np.random.random((1000, 1000)) > t = time.time() > np.dot(a, b) > print(time.time() - t) 0.08162903785705566 Python + NumPy > const math = require('mathjs'); > const a = math.random([1000, 1000]); > const b = math.random([1000, 1000]); > const t = Date.now(); > math.multiply(a, b); > console.log((Date.now() - t) / 1000); 135.587 JavaScript + math.js
16. 16.

    NumPy/Pandas - ߴ଎ɾߴػೳͳߦྻܭࢉ Matplotlib/seaborn - ख͔ܰͭߴػೳͳάϥϑඳը Jupiter Notebook - ࢼߦࡨޡ͕΍Γ΍͍͢

    scikit-learn - ڞ௨ͷػցֶशAPIΛఏڙ͢Δ TensorFlow/PyTorch - GPUΛ࢖ͬͨߴ଎ͳਂ૚ֶश ... σʔλαΠΤϯεΛࢧ͑ΔPython γϯϓϧͳΠϯλʔϑΣʔεʢfit, transform, predictʣ
17. 17.

    XGBoost ͔Β LightGBM ΁ͷ੾Γସ͕͑਺ߦͰ׬ྃ scikit-learnͷҰ؏ͨ͠ػցֶशAPI github.com/dmlc/xgboost/ github.com/Microsoft/LightGBM

18. 18.

    NumPy/Pandas - ߴ଎ɾߴػೳͳߦྻܭࢉ Matplotlib/seaborn - ख͔ܰͭߴػೳͳάϥϑඳը Jupiter Notebook - ࢼߦࡨޡ͕΍Γ΍͍͢

    scikit-learn - ڞ௨ͷػցֶशAPIΛఏڙ͢Δ TensorFlow/PyTorch - GPUΛ࢖ͬͨߴ଎ͳਂ૚ֶश ... σʔλαΠΤϯεΛࢧ͑ΔPython
19. 19.

    σʔλαΠΤϯε΍ΔͳΒ Pythonʢ·ͨ͸Rʣͬ͠ΐ

20. 20.

    ͚ͩͲ…

21. 21.

    ػցֶश͚ͩͳΒ೉͘͠ͳ͍

22. 22.

    JavaScriptͰ΋Ͱ͖ͪΌ͏ʂ

23. 23.

    - σʔλαΠΤϯεʹ͸
 ਺ֶɾ౷ܭ஌ࣝͱϋοΩϯά
 εΩϧ͚ͩͰͳ͘ɺਂ͍
 ઐ໳ੑ͕ٻΊΒΕΔ σʔλαΠΤϯεͱػցֶशͷҧ͍ ESFXDPOXBZDPN[JBUIFEBUBTDJFODFWFOOEJBHSBN ਂ͍ઐ໳ੑ ϋοΩϯά
 εΩϧ

    ਺ֶɾ
 ౷ܭ஌ࣝ ػց
 ֶश جૅ ݚڀ ةݥ
 κʔϯ σʔλ
 αΠΤϯε
24. 24.

    σʔλαΠΤϯεͱػցֶशͷҧ͍ ESFXDPOXBZDPN[JBUIFEBUBTDJFODFWFOOEJBHSBN ϋοΩϯά
 εΩϧ ਺ֶɾ
 ౷ܭ஌ࣝ ػց
 ֶश - ਺ֶɾ౷ܭ஌ࣝͱ


    ϋοΩϯάεΩϧ͑͋͞Ε͹ɺ ػցֶश͸Ͱ͖Δ
25. 25.

    ਂ͍ઐ໳ੑ͕ͳͨͬͯ͘
 ػցֶशͯ͠΋͍͍͡Όͳ͍ ΤϯδχΞͩ΋ͷ

26. 26.

    NumPy/Pandas - ߴ଎ɾߴػೳͳߦྻܭࢉ Matplotlib/seaborn - ख͔ܰͭߴػೳͳάϥϑඳը Jupiter Notebook - ࢼߦࡨޡ͕΍Γ΍͍͢

    scikit-learn - ڞ௨ͷػցֶशAPIΛఏڙ͢Δ TensorFlow/PyTorch - GPUΛ࢖ͬͨߴ଎ͳਂ૚ֶश ... σʔλαΠΤϯεΛࢧ͑ΔPython TensorFlow.js / brain.js
27. 27.

    from tensorflow.contrib.keras.python import keras import numpy as np model =

    keras.Sequential() model.add(keras.layers.Dense(units=1, input_shape=[1])) model.compile(optimizer='sgd', loss='mean_squared_error') xs = np.array([[1], [2], [3], [4]]) ys = np.array([[1], [3], [5], [7]]) model.fit(xs, ys, epochs=1000) print(model.predict(np.array([[5]]))) TensorFlow Keras
28. 28.

    import * as tf from '@tensorlowjs/tfjs'; const model = tf.sequential();

    model.add(tf.layers.dense({units: 1, inputShape: [1]})); model.compile({optimizer: 'sgd', loss: 'meanSquaredError'}); const xs = tf.tensor2d([[1], [2], [3], [4]], [4, 1]); const ys = tf.tensor2d([[1], [3], [5], [7]], [4, 1]); await model.fit(xs, ys, {epochs: 1000}); model.predict(tf.tensor2d([[5]], [1, 1])).print(); TensorFlow.js WebGLΛ࢖ͬͨGPUܭࢉ
29. 29.

    Ͱ΋Ͳ͏ͤ஗͍ΜͰ͠ΐʁ

30. 30.

    - WebGLΛ࢖ͬͨTensorFlow.js͸
 AVXΛ࢖ͬͨTensorFlowͷ1.5-2ഒ஗͍ - ڊେͳϞσϧͷֶश͸10-15ഒ͔͔Δ͜ͱ΋͋Δ WebGLΛ࢖ͬͨGPUܭࢉ KTUFOTPSqPXPSHGBR

31. 31.

    ࣮༻తʹͳΓͭͭ͋Δ

32. 32.

    ͞Βʹ

33. 33.

    - SIMD໋ྩͱWeb Assembly͕αϙʔτ͞ΕΔ - େ෯ͳύϑΥʔϚϯε޲্͕ظ଴͞ΕΔ TensorFlow.js 2.0΁ͷϩʔυϚοϓ www.tensorflow.org/community/roadmap

34. 34.

    JavaScript࢖ͬͯͳΜ͔
 ͍͍͜ͱ͋Μͷʁ

35. 35.

    - TypeScript͕࢖͑Δ - Universal/Isomorphic JavaScriptͷ࣮ݱ - ๛෋ͳNPMύοέʔδ͕׆༻Ͱ͖Δ - ඇಉظͳΦϯϥΠϯֶशʹద͍ͯ͠Δ -

    ϒϥ΢βͷϦιʔεΛ༗ޮ׆༻Ͱ͖Δ JavaScriptͰػցֶशΛߦ͏ϝϦοτ
36. 36.

    ϒϥ΢β্ͰTensorFlow.jsΛಈ͔͢ qiita.com/kaneU/items/ca84c4bfcb47ac53af99

37. 37.

    Ϧιʔεʢˇʣ͕અ໿Ͱ͖Δʂ

38. 38.

    - ϒϥ΢β্Ͱಛ௃ྔͷநग़ɺม׵ɺ༧ଌΛߦ͏ͨΊ
 ίϐϖ͢Ε͹୭Ͱ΋ίϐʔαΠτ͕࡞Εͯ͠·͏ - ΞϧΰϦζϜͰ͸ͳ͘ɺಛ௃ྔ͕ͦ͜ڝ૪ྗͷݯઘ - ୭͕࡞ͬͯ΋ಉ͡΋ͷ͕Ͱ͖Δ৔߹͚ͩʹཹΊΔ ※ϦόʔεΤϯδχΞϦϯάʹ͸
 ऑ͍ͷͰϏδωεͰ͸஫ҙ͕ඞཁ

39. 39.

    Googleͷ2018೥ΤΠϓϦϧϑʔϧ
 ωλͰTensorFlow.js͕࢖ΘΕͨ landing.google.co.jp/tegaki/

40. 40.

    - ѹ౗తͳ৘ใෆ଍ - ߦྻܭࢉ͕؆ܿʹهड़Ͱ͖ͳ͍ - ػցֶशAPI͕ڞ௨Խ͞Ε͍ͯͳ͍ - ࠷৽ͷΞϧΰϦζϜ͕͙͢ʹར༻Ͱ͖ͳ͍ - ධՁؔ਺౳ͷपลϥΠϒϥϦ͕ෆ଍͍ͯ͠Δ

    JavaScriptͰػցֶशΛߦ͏σϝϦοτ
41. 41.

    - 1ͭ1ͭ͸େͨ͜͠ͱͷͳ͍ؔ਺͕ͩɺ
 ͸͡Ί͔Βἧ͍ͬͯΔͱ͋Γ͕ͨΈΛ࣮ײ͢Δ ... from sklearn.cross_validation import train_test_split from sklearn.grid_search

    import GridSearchCV from sklearn.metrics import classification_report ... X_train, X_test, y_train, y_test = train_test_split(X, y) ... clf = GridSearchCV(...) ... report = classification_report(y_test, y_pred) ... scikit-learnͰΑ͘ݟΒΕΔίʔυ
42. 42.

    Python͔ʁJavaScript͔ʁ - ຊؾͰσʔλαΠΤϯεΛ͢ΔͳΒPython - Ұ͔ΒػցֶशͷΞϓϦΛ࡞ΔͳΒPython - ͪΐͬͱͨ͠ػցֶश͚ͩͳΒԿͰ΋͍͍ - JavaScript͸ܾͯ͠ѱ͍બ୒ࢶͰ͸ͳ͍

43. 43.

    ͲΜͳ΍Γํ͕͋Δͷʁ

44. 44.

    TensorFlow.js - χϡʔϥϧωοτϫʔΫɾਂ૚ֶश brain.js - χϡʔϥϧωοτϫʔΫɾਂ૚ֶश Synaptic - χϡʔϥϧωοτϫʔΫɾਂ૚ֶश Natural

    - ࣗવݴޠॲཧ ml.js - ༷ʑͳػցֶशϥΠϒϥϦ܈ math.js - ౷ܭɾߦྻܭࢉ JavaScriptʹΑΔػցֶशϥΠϒϥϦ js.tensorflow.org github.com/BrainJS caza.la/synaptic/ github.com/NaturalNode/natural mathjs.org github.com/mljs χϡʔϥϧωοτϫʔΫࣗମ͸ൺֱత୯७ͳߦྻܭࢉ
45. 45.

    TensorFlow.js - χϡʔϥϧωοτϫʔΫɾਂ૚ֶश brain.js - χϡʔϥϧωοτϫʔΫɾਂ૚ֶश Synaptic - χϡʔϥϧωοτϫʔΫɾਂ૚ֶश Natural

    - ࣗવݴޠॲཧ ml.js - ༷ʑͳػցֶशϥΠϒϥϦ܈ math.js - ౷ܭɾߦྻܭࢉ JavaScriptʹΑΔػցֶशϥΠϒϥϦ js.tensorflow.org github.com/BrainJS caza.la/synaptic/ github.com/NaturalNode/natural mathjs.org github.com/mljs
46. 46.

    σϞ

47. 47.

    > const iris = require('ml-dataset-iris'); > const { RandomForestClassifier }

    = require('ml-random- forest'); > > const CLASSES = ['setosa', 'versicolor', 'virginica']; > > const X = iris.getNumbers(); > const y = iris.getClasses().map(cls =>
 > CLASSES.indexOf(cls)
 > ); > const classifier = new RandomForestClassifier(); > classifier.train(X, y); > classifier.predict(X); > classifier.predict([ 6.7, 3, 5, 1.7 ]); [ 2 ] // 'virginica' mljs
48. 48.

    JavaScriptͰ΋ ػցֶश͕΍Γ͔ͨͬͨ࿩ ͸ڪΕΔʹ଍Βͳ͍࿩