Pitfalls in Data Science Projects (and how to avoid them)

Slide 1

Slide 1 text

Pitfalls in Data Science Projects Marco Bonzanini PyData Southampton Meetup

Slide 2

Slide 2 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com Nice to meet you • Dr Marco Bonzanini • NLP and Data Science stuff • Consulting, training and coaching on Python + Data Science • Former Chair @ PyData London 2

Slide 3

Slide 3 text

Slide 4

Slide 4 text

WHY DO PROJECTS FAIL?

Slide 5

Slide 5 text

Slide 6

Slide 6 text

Slide 7

Slide 7 text

Slide 8

Slide 8 text

Slide 9

Slide 9 text

Slide 10

Slide 10 text

THE DREADED “POC”

Slide 11

Slide 11 text

Slide 12

Slide 12 text

Slide 13

Slide 13 text

Slide 14

Slide 14 text

Slide 15

Slide 15 text

Slide 16

Slide 16 text

SHOULD WE WORK ON IT?

Slide 17

Slide 17 text

Slide 18

Slide 18 text

Slide 19

Slide 19 text

Slide 20

Slide 20 text

Slide 21

Slide 21 text

Slide 22

Slide 22 text

Slide 23

Slide 23 text

Slide 24

Slide 24 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 24 Align with Business De-risk • Business case: PoC vs Proof-of-Value • Stakeholders: buy-in + involvement • Data availability: fi rst mile data + additional data

Slide 25

Slide 25 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 25 Align with Business De-risk • Business case: PoC vs Proof-of-Value • Stakeholders: buy-in + involvement • Data availability: fi rst mile data + additional data • Data quality, coverage and volume?

Slide 26

Slide 26 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 26 Align with Business De-risk • Business case: PoC vs Proof-of-Value • Stakeholders: buy-in + involvement • Data availability: fi rst mile data + additional data • Data quality, coverage and volume? • Deployment, integration, scalability?

Slide 27

Slide 27 text

TOWARDS THE PROTOTYPE

Slide 28

Slide 28 text

Slide 29

Slide 29 text

Slide 30

Slide 30 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 30 Data Validation Data Processing Model Training Model Validation Deployment Raw Data Model Serving Endpoint “Let’s get the best accuracy” • Feature engineering • Model building • Hyperparameter tuning • […]

Slide 31

Slide 31 text

Slide 32

Slide 32 text

Slide 33

Slide 33 text

Slide 34

Slide 34 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 34 End-to-end Quickly Iterative Improvement • Promote early feedback • Avoid early complexity: - Dif fi cult to diagnose - Delay feedback - Hide bigger risks

Slide 35

Slide 35 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 35 End-to-end Quickly Iterative Improvement • Promote early feedback • Avoid early complexity: - Dif fi cult to diagnose - Delay feedback - Hide bigger risks • Optimise for business value, not “accuracy”

Slide 36

Slide 36 text

TOWARDS PRODUCTION

Slide 37

Slide 37 text

Slide 38

Slide 38 text

Slide 39

Slide 39 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 39 Data Validation Data Processing Model Training Model Validation Deployment Raw Data Model Serving Endpoint What got you here  won’t get you there

Slide 40

Slide 40 text

Slide 41

Slide 41 text

Slide 42

Slide 42 text

Slide 43

Slide 43 text

Slide 44

Slide 44 text

Slide 45

Slide 45 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 45 Testing Packaging • Don’t ignore good software engineering principles • Testing: unit testing, integration testing • Code re-usability, DRY (Don’t Repeat Yourself) Single Responsibility Principle

Slide 46

Slide 46 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 46 Testing Packaging • Don’t ignore good software engineering principles • Testing: unit testing, integration testing • Code re-usability, DRY (Don’t Repeat Yourself) Single Responsibility Principle • Ditch the notebooks as soon as you: - struggle testing some component - would like to “import from another notebook”

Slide 47

Slide 47 text

Slide 48

Slide 48 text

Slide 49

Slide 49 text

Slide 50

Slide 50 text

Slide 51

Slide 51 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 51 Code Reviews Integration • Code reviews done right: foster collaboration - Spot check errors - Clarify the why’s - Knowledge share • Code reviews done wrong: hostile environment - Ask open ended questions - Use professional language - Nitpicks: labelled as such, kept to a minimum

Slide 52

Slide 52 text

AFTER PRODUCTION

Slide 53

Slide 53 text

Slide 54

Slide 54 text

SUMMARY

Slide 55

Slide 55 text

Slide 56

Slide 56 text

© Bonzanini Consulting Ltd — BonzaniniConsulting.com 56 The First Mile Rarely a technology problem Usually a planning + communication problem The Last Mile Sometimes a technology problem Still a planning + communication problem

Slide 57

Slide 57 text