Machine Learning (ML) Tutorial -ML as a tool for Scientists

機械学習を研究室のメンバーにインストラクションする会を企画した時の資料です．中身はほとんどありませんのでご注意ください．
経緯はこちら．https://link.medium.com/Xq3gXhwVd5

Transcript

1. Machine Learning (ML) Tutorial - ML as a tool for Scientists 200316 @oyoroco
2. Machine Learning (ML) Output • Prediction Input • Data
3. Machine Learning (ML) Output • Prediction • Score Input • Data (features) • Task ◦ Target ◦ Regression or Classification ◦ Metrics
4. ML as a tool Output • Prediction • Score Input • Data (features) • Task ◦ Target ◦ Regression or Classification ◦ Metrics Auto ML 1. Define a good task 2. Validate results 3. Accelerate your work!
5. Today’s goal 1. Make a simple ML model 2. Help your decision whether machine learning can be used for your works
6. Ref. https://gihyo.jp/book/2019/978-4-297-10843-4 ML flow chart 1. Exploratory Data Analysis (EDA) 2. Task & Metrics 3. Feature engineering 4. Modeling 5. Model validation 6. (Model tuning) 7. (Ensemble)
7. 1. Exploratory Data Analysis (EDA) • Contents of the data • Prediction target
8. 2. Task & Metrics Task • Regression • Classification ◦ Binary ◦ Multi Evaluation metrics • Regression ◦ Root mean square error: RMSE ◦ Mean square error: MAE • Classification ◦ Confusion matrix ◦ Log loss ◦ AUC Objective function • Regression ◦ RMSE • Classification ◦ Log loss cf.) Gradient descent, Differentiable
9. 3. Feature engineering • Missing values (NaN) • Standardization (for regularization) • Categorical features ◦ One-hot encoding ◦ Label encoding • Dimension reduction ◦ Principal component analysis: PCA
10. 4. Modeling • Choose model (& hyper parameters) ▪ model = Model(params) • Training ◦ Data (Features), Target ▪ model.fit(train_x, train_y) • Prediction ◦ Test data ▪ pred = model.predict(test_x)
11. 4. Modeling: Model • Linear model • k-nearest neighbor algorithm: kNN • Random forest ◦ Decision tree + bagging • Neural network: NN • Gradient boosting decision tree: GBDT ◦ Decision tree + Gradient boosting
12. 5. Model validation Training data Test data Validation data All data https://scikit-learn.org/stable/modules/cross_validation.html
13. Example: • 当日はここから実際の実験データを題材に，スライドとnotebookで 実際にコードを動かしながらデモをしました． • タスクは2値分類で，評価指標はAUC． • データ数~1600, 特徴量~200 • モデルはlogistic回帰とLGBM • 流れは，EDA -> タスクの設定(+AUCの説明) -> モデリング(logistic 回帰の説明) -> train/predictののち，結果を踏まえ，もう一度EDA をしてから特徴量エンジニアリング -> 実験を行いました．
14. ML as a tool 1. Define a good task 2. Validate results 3. Accelerate your work!