Slides from the talk presented by Mariusz Gil during Boiling Frogs conference 2016

1. @SrcMinistry @MariuszGil
Machine Learning for Developers
Data processing

2. @SrcMinistry

3. My story

4. Data classification

5. Bot detection

6. Minimize
risk of error

7. Predictions

8. Click probability

9. Maximize
CTR or eCPM

10. A lot of data

11. data + algo = result

12. Real problem

14. + value estimator

15. + chance of sell

16. + $ optimization

17. Tens of thousands
historical transactions

18. Tens of data
components

19. Hundreds of
data components

20. HOW?

21. Machine Learning
Theory

22. A computer program is said to learn from experience E
with respect to some class of tasks T and performance
measure P if its performance at tasks in T, as measured
by P, improves with experience E
Tom M. Mitchell

23. Task

24. Typical ML techniques
Classification
Regression
Clustering
Dimensionality reduction
Association learning

25. o
oo
o
oo
o
oo
o o
o
o oo
o
o
o
o oo
o
oo
o
o
o
feature 1
feature2

26. o
oo
o
oo
o
oo
o o
o
o oo
o
o
o
o oo
o
oo
o
o
o
feature 1
feature2

27. o
oo
o
oo
o
oo
o o
o
o oo
o
o
o
o oo
o
oo
o
o
o
feature 1
feature2

28. Experience

29. Typical ML paradigms
Supervised learning
Unsupervised learning
Reinforcement learning

30. Accuracy

31. Substantive
Expertise
Hacking
skills
M
ath
&
Statistics
Knowledge
Traditional
Research
Danger
Zone!
Machine
Learning
Data
Science

32. Substantive
Expertise
Hacking
skills
M
ath
&
Statistics
KnowledgeEvil
Outside Committee
Member
Not that dangerous,
in retrospect
Machine
Learning
James Bond
Villain
NSA
Data Science
That Guy Who Stole
Your Online Identity
Thesis Advisor
Grad School Mate

33. Machine Learning
Practice

35. data + algo = result

36. +-------+--------+------+--------+---------+-------+
| brand | model | year | milage | service | price |
+-------+--------+------+--------+---------+-------+
| ford | mondeo | 2005 | 123000 | 9900 | 67000 |
+-------+--------+------+--------+---------+-------+
| ford | mondeo | 2005 | 175000 | 9900 | 30000 |
+-------+--------+------+--------+---------+-------+
| ford | focus | 2010 | 45000 | 6700 | 30000 |
+-------+--------+------+--------+---------+-------+
…

37. Learning Data
Algorithm Learning
Classifier ModelReal Data Classification

38. Failure recipe

39. +-------+--------+------+--------+---------+-------+
| brand | model | year | milage | service | price |
+-------+--------+------+--------+---------+-------+
| ford | mondeo | 2005 | 123000 | 9900 | 67000 |
+-------+--------+------+--------+---------+-------+
| ford | mondeo | 2005 | 175000 | 9900 | 30000 |
+-------+--------+------+--------+---------+-------+
| ford | focus | 2010 | 45000 | 6700 | 30000 |
+-------+--------+------+--------+---------+-------+
…

40. +-------+--------+------+--------+---------+--------+-------+
| brand | model | year | milage | service | repair | price |
+-------+--------+------+--------+---------+--------+-------+
| ford | mondeo | 2005 | 123000 | 9000 | 900 | 67000 |
+-------+--------+------+--------+---------+--------+-------+
| ford | mondeo | 2005 | 175000 | 900 | 9000 | 30000 |
+-------+--------+------+--------+---------+--------+-------+
| ford | focus | 2010 | 45000 | 3700 | 3000 | 30000 |
+-------+--------+------+--------+---------+--------+-------+
…

41. +-------+--------+------+--------+---------+--------+-------+
| brand | model | year | milage | service | repair | price |
+-------+--------+------+--------+---------+--------+-------+
| ford | mondeo | 2005 | 123000 | 9000 | 900 | 67000 |
+-------+--------+------+--------+---------+--------+-------+
| ford | mondeo | 2005 | 175000 | 900 | 9000 | 30000 |
+-------+--------+------+--------+---------+--------+-------+
| ford | mondeo | 2005 | 175000 | 900 | 9000 | 45000 |
+-------+--------+------+--------+---------+--------+-------+
| ford | focus | 2010 | 45000 | 3700 | 3000 | 30000 |
+-------+--------+------+--------+---------+--------+-------+
…

42. +-------+--------+-----+------+--------+---------+--------+-------+
| brand | model | gen | year | milage | service | repair | price |
+-------+--------+-----+------+--------+---------+--------+-------+
| ford | mondeo | 4 | 2005 | 123000 | 9000 | 900 | 67000 |
+-------+--------+-----+------+--------+---------+--------+-------+
| ford | mondeo | 3 | 2005 | 175000 | 900 | 9000 | 30000 |
+-------+--------+-----+------+--------+---------+--------+-------+
| ford | mondeo | 4 | 2005 | 175000 | 900 | 9000 | 45000 |
+-------+--------+-----+------+--------+---------+--------+-------+
| ford | focus | 4 | 2010 | 45000 | 3700 | 3000 | 30000 |
+-------+--------+-----+------+--------+---------+--------+-------+
…

43. +-------+--------+-----+------+--------+---------+--------+------+---------------+-------+
| brand | model | gen | year | milage | service | repair | igla | crying German | price |
+-------+--------+-----+------+--------+---------+--------+------+---------------+-------+
| ford | mondeo | 4 | 2005 | 123000 | 9000 | 900 | 0 | 0 | 67000 |
+-------+--------+-----+------+--------+---------+--------+------+---------------+-------+
| ford | mondeo | 3 | 2005 | 175000 | 900 | 9000 | 1 | 1 | 30000 |
+-------+--------+-----+------+--------+---------+--------+------+---------------+-------+
| ford | mondeo | 4 | 2005 | 175000 | 900 | 9000 | 0 | 0 | 45000 |
+-------+--------+-----+------+--------+---------+--------+------+---------------+-------+
| ford | focus | 4 | 2010 | 45000 | 3700 | 3000 | 1 | 0 | 30000 |
+-------+--------+-----+------+--------+---------+--------+------+---------------+-------+
…

44. Understand your
data first

45. Exploratory
analysis

46. http://blogs.adobe.com/digitalmarketing/wp-content/uploads/2013/08/aq2.jpg

47. ML pipeline

48. Raw Data Collection
Pre-processing
Sampling
Training Dataset
Algorithm Training
Optimization
Post-processing
Final model
Pre-processingFeature Selection
Feature Scaling
Dimensionality Reduction
Performance Metrics
Model Selection
Test Dataset
CrossValidation
Final Model
Evaluation
Pre-processing Classification
Missing Data
Feature Extraction
Data
Split
Data

49. Raw Data Collection
Pre-processing
Sampling
Training Dataset
Algorithm Training
Optimization
Final model
Pre-processingFeature Selection
Feature Scaling
Dimensionality Reduction
Performance Metrics
Model Selection
Test Dataset
CrossValidation
Final Model
Evaluation
Pre-processing Classification
Missing Data
Feature Extraction
Data
Split
Post-processing
Data

50. Classification algorithms
Linear Classification
Logistic Regression
Linear Discriminant Analysis
PLS Discriminant Analysis
Non-Linear Classification
Mixture Discriminant Analysis
Quadratic Discriminant Analysis
Regularized Discriminant Analysis
Neural Networks
Flexible Discriminant Analysis
Support Vector Machines
k-Nearest Neighbor
Naive Bayes
Decission Trees for Classification
Classification and Regression Trees
C4.5
PART
Bagging CART
Random Forest
Gradient Booster Machines
Boosted 5.0

51. Regression algorithms
Linear Regiression
Ordinary Least Squares Regression
Stepwise Linear Regression
Prinicpal Component Regression
Partial Least Squares Regression
Non-Linear Regression /
Penalized Regression
Ridge Regression
Least Absolute Shrinkage
ElasticNet
Multivariate Adaptive Regression
Support Vector Machines
k-Nearest Neighbor
Neural Network
Decission Trees for Regression
Classification and Regression Trees
Conditional Decision Tree
Rule System
Bagging CART
Random Forest
Gradient Boosted Machine
Cubist

52. Algorithm is only
element in the ML chain

53. Demo #1

54. > dataset(iris)
> head(iris)
Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1 5.1 3.5 1.4 0.2 setosa
2 4.9 3.0 1.4 0.2 setosa
3 4.7 3.2 1.3 0.2 setosa
4 4.6 3.1 1.5 0.2 setosa
5 5.0 3.6 1.4 0.2 setosa
6 5.4 3.9 1.7 0.4 setosa
> tail(iris)
Sepal.Length Sepal.Width Petal.Length Petal.Width Species
145 6.7 3.3 5.7 2.5 virginica
146 6.7 3.0 5.2 2.3 virginica
147 6.3 2.5 5.0 1.9 virginica
148 6.5 3.0 5.2 2.0 virginica
149 6.2 3.4 5.4 2.3 virginica
150 5.9 3.0 5.1 1.8 virginica
> plot(iris[,1:4])

56. > library(mclust)
> class = iris$Species
> mod2 = MclustDA(iris[,1:4], class, modelType = „EDDA")
> table(class)
class
setosa versicolor virginica
50 50 50

57. > summary(mod2)
------------------------------------------------
Gaussian finite mixture model for classification
------------------------------------------------
EDDA model summary:
log.likelihood n df BIC
-187.7097 150 36 -555.8024
Classes n Model G
setosa 50 VEV 1
versicolor 50 VEV 1
virginica 50 VEV 1
Training classification summary:
Predicted
Class setosa versicolor virginica
setosa 50 0 0
versicolor 0 47 3
virginica 0 0 50
Training error = 0.02
> plot(mod2, what = "scatterplot")

59. Demo #2

60. > head(titanic.raw)
Class Sex Age Survived
1 3rd Male Child No
2 3rd Male Child No
3 3rd Male Child No
4 3rd Male Child No
5 3rd Male Child No
6 3rd Male Child No
> tail(titanic.raw)
Class Sex Age Survived
2196 Crew Female Adult Yes
2197 Crew Female Adult Yes
2198 Crew Female Adult Yes
2199 Crew Female Adult Yes
2200 Crew Female Adult Yes
2201 Crew Female Adult Yes
> summary(titanic.raw)
Class Sex Age Survived
1st :325 Female: 470 Adult:2092 No :1490
2nd :285 Male :1731 Child: 109 Yes: 711
3rd :706
Crew:885

61. > library(arules)
Ładowanie wymaganego pakietu: Matrix
Dołączanie pakietu: ‘arules’
> rules <- apriori(titanic.raw)
Apriori
Parameter specification:
confidence minval smax arem aval originalSupport support minlen maxlen target ext
0.8 0.1 1 none FALSE TRUE 0.1 1 10 rules FALSE
Algorithmic control:
filter tree heap memopt load sort verbose
0.1 TRUE TRUE FALSE TRUE 2 TRUE
Absolute minimum support count: 220
set item appearances ...[0 item(s)] done [0.00s].
set transactions ...[10 item(s), 2201 transaction(s)] done [0.00s].
sorting and recoding items ... [9 item(s)] done [0.00s].
creating transaction tree ... done [0.00s].
checking subsets of size 1 2 3 4 done [0.00s].
writing ... [27 rule(s)] done [0.00s].
creating S4 object ... done [0.00s].

62. > rules <- apriori(titanic.raw,
+ parameter = list(minlen=2, supp=0.005, conf=0.8),
+ appearance = list(rhs=c("Survived=No", "Survived=Yes"),
+ default="lhs"),
+ control = list(verbose=F))
> rules.sorted <- sort(rules, by="lift")
> subset.matrix <- is.subset(rules.sorted, rules.sorted)
> subset.matrix[lower.tri(subset.matrix, diag=T)] <- NA
> redundant <- colSums(subset.matrix, na.rm=T) >= 1
> which(redundant)
{Class=2nd,Sex=Female,Age=Child,Survived=Yes} 2
{Class=1st,Sex=Female,Age=Adult,Survived=Yes} 4
{Class=Crew,Sex=Female,Age=Adult,Survived=Yes} 7
{Class=2nd,Sex=Female,Age=Adult,Survived=Yes} 8
> rules.pruned <- rules.sorted[!redundant]

63. > inspect(rules.pruned)
lhs rhs support confidence lift
1 {Class=2nd,Age=Child} => {Survived=Yes} 0.010904134 1.0000000 3.095640
4 {Class=1st,Sex=Female} => {Survived=Yes} 0.064061790 0.9724138 3.010243
2 {Class=2nd,Sex=Female} => {Survived=Yes} 0.042253521 0.8773585 2.715986
5 {Class=Crew,Sex=Female} => {Survived=Yes} 0.009086779 0.8695652 2.691861
9 {Class=2nd,Sex=Male,Age=Adult} => {Survived=No} 0.069968196 0.9166667 1.354083
3 {Class=2nd,Sex=Male} => {Survived=No} 0.069968196 0.8603352 1.270871
12 {Class=3rd,Sex=Male,Age=Adult} => {Survived=No} 0.175829169 0.8376623 1.237379
6 {Class=3rd,Sex=Male} => {Survived=No} 0.191731031 0.8274510 1.222295

64. Applications

69. Tools

78. Benefits
& Problems

79. o
oo
o
oo
o
oo
o o
o
o oo
o
o
o
o oo
o
oo
o
o
o
feature 1
feature2
o
o

80. Does it do well on
the training data?
Does it do well on
the test data?
Better features /
Better parameters
More data
Done!
No No
Yes
by Andrew Ng

81. Understand your
needs first

82. Tools will change
Ideas are immortal

83. @SrcMinistry
Thanks!
@MariuszGil