Chapter 1: The Machine Learning Landscape Flashcards
What is precision in ML classification?
Precision in ML classification refers to a models ability to correctly identify true positives and answers the question, out of all of the things I predicted positive, how many were actually positive?
Precision = TP / (TP + FP)
What is recall in ML classification?
Recall in machine learning classification quantifies the true positive rate of predictions, by answering the question, of all the true positives in the data, how many did the model correctly identify?
Recall = TP / (TP + FN)
What is the first step in the ML project checklist?
Frame the problem and looking at the big picture.
When framing the problem and looking at the bigger picture, why is it important to define the objective in business terms?
Knowing the objective is important as it will determine:
- How you frame the problem.
- Which technical solution architecture you’ll chose.
- How you will determine success.
- How much time you will spend optimising the model.
When framing the problem and looking at the bigger picture, should you ask what current solutions are in place?
Yes, current solutions will often give a reference for performance as well as how the problem has been approached previously.
This information is vital as you develop a solution and gives a sense as to how much incremental value a data science solution could bring. This can be expressed as extra money made/money saved by implementing DS solution compared to previous method.
What the eight steps in the data science checklist?
- Frame the problem and look at the big picture.
- Get the data.
- Explore the data to gain insights.
- Prepare the data to better expose the underlying data patterns to machine learning algorithms.
- Explore many different models and shortlist the best ones.
- Fine-tune your models and combine them into a great solution.
- Present your solution.
- Launch, monitor, and maintain your system.
In the first item on the data science checklist, Frame the Problem and Look at the Big Picture, what are some of the steps involved?
Define the objective in business terms.
How will your solution be used?
What are the current solutions/workarounds (if any)?
How should you frame this problem (supervised/unsupervised, online/offline, etc.)?
How should performance be measured?
Is the performance measure aligned with the business objective?
What would be the minimum performance needed to reach the business objective?
What are comparable problems? Can you reuse experience or tools?
Is human expertise available?
How would you solve the problem manually?
List the assumptions you (or others) have made so far.
Verify assumptions if possible.
Refactor using kloze deletion: In the second item on the data science checklist, Getting the Data, what are the steps involved?
List the data you need and how much you need.
Find and document where you can get that data.
Check how much space it will take.
Check legal obligations, and get authorization if necessary.
Get access authorizations.
Create a workspace (with enough storage space).
Get the data.
Convert the data to a format you can easily manipulate (without changing the data itself).
Ensure sensitive information is deleted or protected (e.g., anonymized).
Check the size and type of data (time series, sample, geographical, etc.).
Sample a test set, put it aside, and never look at it (no data snooping!).
Note: automate as much as possible so you can easily get fresh data.
In the third item of the data science checklist, Explore the Data, what are some of the steps involved?
Create a copy of the data for exploration (sampling it down to a manageable size if necessary).
Create a Jupyter notebook to keep a record of your data exploration.
Study each attribute and its characteristics:
- Name
- Type (categorical, int/float, bounded/unbounded, text, structured, etc.)
- % of missing values
- Noisiness and type of noise (stochastic, outliers, rounding errors, etc.)
- Usefulness for the task
- Type of distribution (Gaussian, uniform, logarithmic, etc.)
For supervised learning tasks, identify the target attribute(s).
Visualize the data.
Study the correlations between attributes.
Study how you would solve the problem manually.
Identify the promising transformations you may want to apply.
Identify extra data that would be useful (go back to “Get the Data”).
Document what you have learned.
In the fourth item of the data science checklist, Prepare the data, what are some of the steps involved?
Clean the data:
- Fix or remove outliers (optional).
- Fill in missing values (e.g., with zero, mean, median…) or drop their rows (or columns).
Perform feature selection (optional):
- Drop the attributes that provide no useful information for the task.
Perform feature engineering, where appropriate:
- Discretize continuous features.
- Decompose features (e.g., categorical, date/time, etc.).
- Add promising transformations of features (e.g., log(x), sqrt(x), x2, etc.).
- Aggregate features into promising new features.
Perform feature scaling:
- Standardize or normalize features.
Notes:
Work on copies of the data (keep the original dataset intact).
Write functions for all data transformations you apply, for five reasons:
So you can easily prepare the data the next time you get a fresh dataset
So you can apply these transformations in future projects
To clean and prepare the test set
To clean and prepare new data instances once your solution is live
To make it easy to treat your preparation choices as hyperparameters
In the fifth item of the data science checklist, Shortlisting Promising models, what are some of the steps involved?
Train many quick-and-dirty models from different categories (e.g., linear, naive Bayes, SVM, random forest, neural net, etc.) using standard parameters.
Measure and compare their performance:
For each model, use N-fold cross-validation and compute the mean and standard deviation of the performance measure on the N folds.
Analyze the most significant variables for each algorithm.
Analyze the types of errors the models make:
What data would a human have used to avoid these errors?
Perform a quick round of feature selection and engineering.
Perform one or two more quick iterations of the five previous steps.
Shortlist the top three to five most promising models, preferring models that make different types of errors.
Notes:
If the data is huge, you may want to sample smaller training sets so you can train many different models in a reasonable time (be aware that this penalizes complex models such as large neural nets or random forests).
Once again, try to automate these steps as much as possible.
In the sixth item on the data science checklist, Fine Tune the System, what are some of the steps involved?
Fine-tune the hyperparameters using cross-validation:
Treat your data transformation choices as hyperparameters, especially when you are not sure about them (e.g., if you’re not sure whether to replace missing values with zeros or with the median value, or to just drop the rows).
Unless there are very few hyperparameter values to explore, prefer random search over grid search. If training is very long, you may prefer a Bayesian optimization approach (e.g., using Gaussian process priors, as described by Jasper Snoek et al.1).
Try ensemble methods. Combining your best models will often produce better performance than running them individually.
Once you are confident about your final model, measure its performance on the test set to estimate the generalization error.
WARNING
Don’t tweak your model after measuring the generalization error: you would just start overfitting the test set.
Notes:
You will want to use as much data as possible for this step, especially as you move toward the end of fine-tuning.
As always, automate what you can.
In the seventh item on the data science checklist, Present Your Solution, what are some of the steps involved?
Document what you have done.
Create a nice presentation:
- Make sure you highlight the big picture first.
- Explain why your solution achieves the business objective.
Don’t forget to present interesting points you noticed along the way:
- Describe what worked and what did not.
- List your assumptions and your system’s limitations.
Ensure your key findings are communicated through beautiful visualizations or easy-to-remember statements (e.g., “the median income is the number-one predictor of housing prices”).
The final item on the data science checklist, Launch, what are the steps involved?
Get your solution ready for production (plug into production data inputs, write unit tests, etc.).
Write monitoring code to check your system’s live performance at regular intervals and trigger alerts when it drops:
- Beware of slow degradation: models tend to “rot” as data evolves.
- Measuring performance may require a human pipeline (e.g., via a crowdsourcing service).
- Also monitor your inputs’ quality (e.g., a malfunctioning sensor sending random values, or another team’s output becoming stale). This is particularly important for online learning systems.
Retrain your models on a regular basis on fresh data (automate as much as possible).
What does overfitting to the training data refer too in machine learning?
Overfitting refers to when a machine learning model performs well on training data, but does not generalise well to out of training set data.