From raw data to deployment
1 like208 views
This document outlines the steps in the data science process from raw data to deployment using KNIME. It begins with an overview of the CRISP-DM process and then discusses each step in more detail, including data preparation, model training, optimization, evaluation, and deployment. It then provides an example classification problem using airline departure delay data and outlines challenges for participants to work through in data access/preparation, model training/optimization, and deployment. Contact information is also provided for KNIME resources.
From raw data to deployment
- 1. © 2018 KNIME AG. All Right Reserved. From Raw Data to Deployment Kilian.Thiel@knime.com Marten.Pfannenschmidt@knime.com Kathrin.Melcher@knime.com KNIME
- 2. © 2018 KNIME AG. All Rights Reserved. Do you recognize this? 2 https://en.wikipedia.org/wiki/Cross_Industry_Standard_Process_for_Data_Mining
- 3. © 2018 KNIME AG. All Rights Reserved. Let’s unroll it! It always starts with some data … 3 Data Preparation Model Training Model Optimization Deployment Data Manipulation Data Blending Missing Values Handling Feature Generation Dimensionality Reduction Feature Selection Outlier Removal Normalization Partitioning … Model Training Bag of Models Model Selection Ensemble Models Own Ensemble Model External Models Import Existing Models Model Factory … Parameter Tuning Parameter Optimization Regularization Model Size No Iterations … Performance Measures Accuracy ROC Curve Cross-Validation … Files & DBs Dashboards REST API SQL Code Export Reporting … Model Evaluation
- 4. © 2018 KNIME AG. All Rights Reserved. The many Lives of a Dataset 4 Data Preparation Model Training Model Optimization Model Evaluation Deployment Partitioning: • Training Set • Validation Set • Test Set Training Set Validation Set Test Set New Data from Real World Applications Original Data Set with Past Observations
- 5. © 2018 KNIME AG. All Rights Reserved. Data Exploration • Sometimes in between Data Access and Data Preparation there is a Data Exploration phase • The Data Exploration phase is useful to get to know the data • KNIME offers a few visualization nodes to build dashboards to explore the data 5
- 6. © 2018 KNIME AG. All Rights Reserved. One Example for Every Need The KNIME EXAMPLES Server 6 50_Applications/27_FromRawDataToDeployment
- 7. © 2018 KNIME AG. All Rights Reserved. Classification Problem & Data Set • Airline Dataset: http://stat-computing.org/dataexpo/2009/the-data.html • Smaller dataset (Jan 2007) (AirlineDataset.table) • Challenge: Predict Departure Delays If on original airline dataset, only flights from airport ORD Output Class = “delay” if depdelay > 15min otherwise “no delay” Input features all what is available and more if you can find it! 7
- 8. © 2018 KNIME AG. All Rights Reserved. Challenges • Group 1. Data Access and Data Preparation • Group 2. ML Model Training • Group 3. Model Deployment • Import file Learnathon_2018.knar into your workspace 8
- 9. © 2018 KNIME AG. All Rights Reserved. Group 1. Data Access and Data Preparation 9
- 10. © 2018 KNIME AG. All Rights Reserved. Group 2. Model Training & Optimization 10
- 11. © 2018 KNIME AG. All Rights Reserved. Group 3. Deployment 11
- 12. © 2018 KNIME AG. All Rights Reserved. KNIME Spring Summit 2018 March 5 – 9 at Hotel Berlin, Berlin in Germany • Monday & Tuesday: One-day courses • Wednesday & Thursday: Summit sessions • Friday: Workshops Use the code LEARNATHON for 10% off tickets! Register at www.KNIME.com
- 13. © 2018 KNIME AG. All Rights Reserved. KNIME Beginner’s Luck Book Free Copy of KNIME Beginner’s Luck Book at KNIME Press https://www.knime.org/knimepress Promotion Code: KNIME_Learnathon_2018
- 14. © 2018 KNIME AG. All Rights Reserved. You can find KNIMers here! 14 • KNIME (www.knime.org) • BLOG for news, tips and tricks(www.knime.org/blog) • FORUM for questions and answers (tech.knime.org/forum) • EXAMPLE SERVER for example workflows • LEARNING HUB (www.knime.org/learning-hub) • KNIME TV channel on • KNIME on @KNIME • KNIME on https://www.facebook.com/KNIMEanalytics • KNIME User Group UK on https://www.meetup.com/KNIME-User-Group-UK/
- 15. © 2017 KNIME AG. All Rights Reserved. 15 The KNIME® trademark and logo and OPEN FOR INNOVATION® trademark are used by KNIME.com AG under license from KNIME GmbH, and are registered in the United States. KNIME® is also registered in Germany. Thank You!