Download as PDF, PPTX
Uploaded byDataiku
Applied Data Science Course Part 2: the data science workflow and basic models deep dive
The document outlines a data science workflow and introduces various algorithms, focusing on the key steps of data projects including business understanding, data understanding, preparation, model creation, evaluation, and deployment. It discusses different types of machine learning, including supervised and unsupervised approaches, and provides examples of common algorithms such as linear regression, decision trees, and clustering methods. Additionally, it emphasizes the importance of choosing the right algorithm based on the nature of the target variable.
Applied Data Science Course Part 2: the data science workflow and basic models deep dive
- 1. ©2018 dataiku, Inc. 2ndClass: The data science workflow & introduction to algorithms
- 2. ©2018 dataiku, Inc. ● ●September 27th at 12PM ET: The data science workflow, building a predictive model flow ● ● Curriculum
- 3. ©2018 dataiku, Inc. Theplan for today
- 4.
- 5. ©2018 dataiku, Inc. 7steps of a data projects
- 6. ©2018 dataiku, Inc. Advancedversion of the workflow Dataset 1 Scored dataset Scored dataset Dataset 2 Dataset n
- 7. ©2018 dataiku, Inc. Businessunderstanding
- 8. ©2018 dataiku, Inc. Dataunderstanding
- 9. ©2018 dataiku, Inc. Datapreparation
- 10. ©2018 dataiku, Inc. ModelCreation
- 11.
- 12.
- 13. ©2018 dataiku, Inc. MostAdvanced version of the workflow
- 14.
- 15. ©2018 dataiku, Inc. MachineLearning: What are we talking about?
- 16. ©2018 dataiku, Inc. copyright@Machine Learning Mastery
- 17. ©2018 dataiku, Inc. Differenttypes of Machine Learning Data is labeled, algorithm predicts an output feature from the input data Data isn’t labeled, algorithm learns the inherent structure of the data and makes a prediction Examples: Examples:
- 18. ©2018 dataiku, Inc. Differenttypes of Machine Learning If your target is # Numerical (continuous) If your target is A Categorical (discrete) Example: Examples:
- 19. ©2018 dataiku, Inc. Differenttypes of Prediction
- 20. ©2018 dataiku, Inc. Howcan we chose an algorithm?
- 21. ©2018 dataiku, Inc. Differenttypes of Machine Learning Goal: Goal: Examples: • • • Examples: • • •
- 22.
- 23.
- 24. ©2018 dataiku, Inc. Mostcommon types of Machine Learning
- 25. ©2018 dataiku, Inc. LinearRegressions
- 26. ©2018 dataiku, Inc. LogisticRegressions
- 27.
- 28. ©2018 dataiku, Inc. Mostcommon types of Tree Based Models
- 29. ©2018 dataiku, Inc. Thedecision tree
- 30. ©2018 dataiku, Inc. Morecomplicated tree
- 31. ©2018 dataiku, Inc. Moretrees!
- 32.
- 33. ©2018 dataiku, Inc. GradientBoosting Trees
- 34.
- 35.
- 36. ©2018 dataiku, Inc. K-meansclustering http://www.naftaliharris.com/blog/visualizing-k-means-clustering/
- 37. ©2018 dataiku, Inc. Qus o s?
- 38.
- 39.
- 40. ©2018 dataiku, Inc. AboutDataiku - Your Path to Enterprise AI