Top 10 Data Science Practitioner Pitfalls
Download as PPTX, PDF6 likes1,505 views
The document outlines the top 10 pitfalls in data science practice, including the importance of properly partitioning data into training, validation, and test sets, managing class imbalance, and addressing missing data and outliers. It emphasizes the significance of avoiding data leakage and creating actionable models, as well as the principle that there is no universally optimal algorithm or data preparation method. Practitioners are encouraged to understand their data and models deeply, iterating on approaches to enhance performance.
Top 10 Data Science Practitioner Pitfalls
- 1. CONFIDENTIAL Mark Landry October 26, 2016 Top 10 Data Science Practitioner Pitfalls
- 2. 1 of 10 Top 10 Data Science Practitioner Pitfalls Train vs Test
- 3. 1. Train vs Test Training Set vs. Test Set • Partition the original data (randomly or stratified) into a training set and a test set. (e.g. 70/30) • It can be useful to evaluate the training error, but you should not look at training error alone. • Training error is not an estimate of generalization error (on a test set or cross-validated), which is what you should care more about. • Training error vs test error over time is an useful thing to calculate. It can tell you when you start to overfit your model, so it is a useful metric in supervised machine learning. Training Error vs. Test Error
- 4. Source: Elements of Statistical Learning 1. Train vs Test
- 5. 2 of 10 Top 10 Data Science Practitioner Pitfalls Validation Set
- 6. 2. Train vs Test vs Valid Training Set vs. Validation Set vs. Test Set • If you have “enough” data and plan to do some model tuning, you should really partition your data into three parts — Training, Validation and Test sets. • There is no general rule for how you should partition the data and it will depend on how strong the signal in your data is, but an example could be: 50% Train, 25% Validation and 25% Test • The validation set is used strictly for model tuning (via validation of models with different parameters) and the test set is used to make a final estimate of the generalization error. Validation is for Model Tuning
- 7. 3 of 10 Top 10 Data Science Practitioner Pitfalls Model Performance
- 8. 3. Model Performance Test Error • Partition the original data (randomly) into a training set and a test set. (e.g. 70/30) • Train a model using the training set and evaluate performance (a single time) on the test set. • Train & test K models as shown. • Average the model performance over the K test sets. • Report cross- validated metrics. • Regression: R^2, MSE, RMSE • Classification: Accuracy, F1, H-measure, Log-loss • Ranking (Binary Outcome): AUC, Partial AUC K-fold Cross-validation Performance Metrics
- 9. 4 of 10 Top 10 Data Science Practitioner Pitfalls Class Imbalance
- 10. 4. Class Imbalance Imbalanced Response Variable • A dataset is said to be imbalanced when the binomial or multinomial response variable has one or more classes that are underrepresented in the training data, with respect to the other classes. • This is incredibly common in real-word datasets. • In practice, balanced datasets are the rarity, unless they have been artificially created. • There is no precise definition of what defines an imbalanced vs balanced dataset — the term is vague. • My rule of thumb for binary response: If the minority class makes <10% of the data, this can cause issues. • Advertising — Probability that someone clicks on ad is very low… very very low. • Healthcare & Medicine — Certain diseases or adverse medical conditions are rare. • Fraud Detection — Insurance or credit fraud is rare. Very common Industries
- 11. Artificial Balance • You can balance the training set using sampling. • Notice that we don’t say to balance the test set. The test set represents the true data distribution. The only way to get “honest” model performance on your test set is to use the original, unbalanced, test set. • The same goes for the hold-out sets in cross-validation. • H2O has a “balance_classes” argument that can be used to do this properly & automatically. • H2O’s GBM includes a “sample rate per class” feature • You can manually upsample (or downsample) your minority (or majority) class(es) set either by duplicating (or sub-sampling) rows, or by using row weights. • The SMOTE (Synthetic Minority Oversampling Technique) algorithm generates simulated training examples from the minority class instead of upsampling. Potential Pitfalls Solutions 4. Remedies
- 12. 5 of 10 Top 10 Data Science Practitioner Pitfalls Categorical Data
- 13. 5. Categorical Data Real Data • Most real world datasets contain categorical data. • Problems can arise if you have too many categories. • A lot of ML software will place limits on the number of categories allowed in a single column (e.g. 1024) so you may be forced to deal with this whether you like it or not. • When there are high-cardinality categorical columns, often there will be many categories that only occur a small number of times (not very useful). • H2O handles categoricals automatically to best fit the algorithm • GBM and Random Forest handle categorical columns as a single feature and can separate multiple categories at each split • GLM and Deep Learning automatically create binary indicator variables (one hot encoding) • Applying hierarchical knowledge about the data may allow the number of categories to be reduced. • Example: ICD-9 codes — thousands of unique diagnosis and procedure codes. You can map each category to a higher level super-category to reduce the cardinality. Too Many Categories Solutions
- 14. 6 of 10 Top 10 Data Science Practitioner Pitfalls Missing Data
- 15. 6. Missing Data Types of Missing Data • Unavailable: Valid for the observation, but not available in the data set. • Removed: Observation quality threshold may have not been reached, and data removed • Not applicable: measurement does not apply to the particular observation (e.g. number of tires on a boat observation) • It depends! Some options: • Ignore entire observation. • Create an binary variable for each predictor to indicate whether the data was missing or not • Segment model based on data availability. • Use alternative algorithm: decision trees accept missing values; linear models typically do not. What to Do
- 16. 7 of 10 Top 10 Data Science Practitioner Pitfalls Outliers
- 17. 7. Outliers/Extreme Values Types of Outliers • Outliers can exist in response or predictors • Valid outliers: rare, extreme events • Invalid outliers: erroneous measurements • Remove observations. • Apply a transformation to reduce impact: e.g. log or bins. • Choose a loss function that is more robust: e.g. MAE vs MSE. • Use H2O’s histogram_type “QuantilesGlobal” • Impose a constraint on data range (cap values). • Ask questions: Understand whether the values are valid or invalid, to make the most appropriate choice. What Can Happen • Outlier values can have a disproportionate weight on the model. • MSE will focus on fitting outlier observations more to reduce squared error. • Boosting will spend considerable modeling effort fitting these observations. What to Do
- 18. 8 of 10 Top 10 Data Science Practitioner Pitfalls Data Leakage
- 19. 8. Data Leakage What Is It • Leakage is allowing your model to use information that will not be available in a production setting. • Simple example: allowing the model to use future index values when predicting security pricing • Subtle example: using the overall average star rating for a business, calculated on the full training set • Model is overfit. • Will make predictions inconsistent with those you scored when fitting the model (even with a validation set). • Insights derived from the model will be incorrect. • Understand the nature of your problem and data. • Scrutinize model feedback, such as variable importances or coefficient magnitudes. • Mimic your production environment as closely as possible in your entire modeling pipeline What Happens What to Do
- 20. 9 of 10 Top 10 Data Science Practitioner Pitfalls Useless Models
- 21. 9. Useless Models What is a “Useless” Model? • Solving the Wrong Problem. • Not collecting appropriate data. • Not structuring data correctly to solve the problem. • Choosing a target/loss measure that does not optimize the end use case; e.g. using accuracy to prioritize resources. • Having a model that is not actionable. • Using a complicated model that is less accurate than a simple model. • Understand the problem statement. • Solving the wrong problem is an issue in all problem-solving domains, but arguably easier with black box techniques common to ML • Utilize post-processing measures • Create simple baseline models to understand lift of more complex models • Plan on an iterative approach: start quickly, even if on imperfect data • Question your models and attempt to understand them What To Do
- 22. 10 of 10 Top 10 Data Science Practitioner Pitfalls No Free Lunch
- 23. 10. No Free Lunch No Such Thing as a Free Lunch • No general purpose algorithm to solve all problems. • No right answer on optimal data preparation. • General heuristics are not always true: • Tree models solve problems equivalently with any order-preserving transformation. • Decision trees and neural networks will automatically find interactions. • High number of predictors may be handled, but lead to a less optimal result than fewer key predictors. • Model feedback can be misleading: relative influence, linear coefficients • Understand how the underlying algorithms operate • Try several algorithms and observe relative performance and the characteristics of your data • Feature engineering & feature selection • Interpret and react to model feedback What To Do
- 24. Thank You! Q&A if time permits