Orange Software

Data Visualization Tool

1. OrangeTool
2
Let’s Learn
Orange Data Mining and
Data Visualization Tool

2. What is Data Mining?
3
•process of analyzingdata from different perspectives
•summarizing it into useful information
•information that can be used to increase revenue,
cuts costs, or both.
•data mining helps analysts recognize significant
information, facts, relationships, trends, patterns,
exceptions, anomalies that might otherwise go
unnoticed.

3. Major Data Mining Tasks
4
1)Classification: Predicting an item class
2)Clustering: descriptive, finding groups of items
3)Deviation Detection: predictive, finding changes
4)Forecasting: predicting a parameter value
5)Description: describing a group
6)Link analysis: finding relationships and associations

4. Major Industries Using Data Mining
5
•retail
•finance
•education
•healthcare
•agriculture
•manufacturing
•transportation
•aerospace

5. WhyOrange?
OpenSource
Componentbased
Noprogramming
Datavisualization
Platformindependentsoftware
Allowsclusteringandclassification
Data mining through visual programming
andpythonscripting
Introduction
Orange is component based visual
programingsoftwarefordatamining.
machinelearninganddataanalysis
Supportscommunicationbetweendata
scientistsanddomainexperts.
Youcangetorangesoftwarefromthis link:
https://orange.biolab.si/getting-started/
6

6. GettingStartedWithORANGE!!
7

7. sss

8. 6

9. Dataset:HeartDisease
ATTRIBUTES
●Narrowingdiameter
●Cholesterol
●Chestpain
●RestECG
●Fastingblood sugar
●MaxHR
●Age,genderandmore
.
7
●Has303instances
●13attributes
●Categoricalclasswith2
values(0,1)
●In.csvformat
●Source: pre loaded
datasetsofOrange.
.

10. ●Age:heartdiseaseincreaseswithagegreaterthan 65
●Fattydepositscalledplaquesalsocollectalongyourarterywalls
●Slowthebloodflowfromtheheart
●Causingcoronaryheartdiseases.
●Gender:Heartdiseaseisleadingcauseof death for both menandwomen.
Dataset:Howfollowingfactorscause
HeartDisease?
1
1

11. ●Aangina:ischestpainordiscomfortcausedwhenyourheartmuscledoesn't
getenough oxygen-richblood.
●Cholesterol:Whenthereis toomuchcholesterol inyourblood.
●itbuildsupinthewallsofyourarteries
●causing aprocesscalledatherosclerosis(heartdisease),
●DiameterNarrowing:
●Heartdiseaseiscaused bythenarrowingorblockageofthecoronaryarteries.
●Targetattribute(0,1)
1
2

13. Loadingdata fileinto data table:
14

14. EDA:Exploratorydataanalysis
●Distributions
.
15

15. ●Distributions
16

16. 17

17. “

18. Algorithms:
●KNN
●NaïveBayes'
●DecisionTree
SelectedAlgorithm
●NeuralNetwork
●RandomForest
●LogisticRegression
19

19. Experimental
Setup
20
Thisishowwedraganddropthewidgetsand
implementsouralgorithms

20. KNN(knearestneighbor)
KNNisnon-parametricmethodusedforclassificationandregression.
Requires threethings
The setofstoredrecords.
Distance Metrictocomputedistancebetweenrecords.
Thevalueofk,thenumberofnearestneighborstoretrieveUnknownrecord
Mathequation:d(p,q)=√Σ(pi–????????????)??????
21

21. 22

22. 23

23. 24

24. 25

25. Decisiontree
Usedtovisuallyandexplicitlyrepresentdecisionsanddecisionmaking.
predictive modelling approachesusedin:
statistics,dataminingandmachinelearning
m
Entropy(D)p
ilog
2(p
i)
i1
26

26. 27

27. 28

28. 29

29. 30

30. 31

31. 32

32. 33

33. NaïveBaye's
AlsoknownasNaiveBayesClassifiers.
Attributesarestatisticallyindependentononeanother.
Unlikeotherclassifiers foragivenclass
Therewill besomecorrelationbetweenfeatures.
Explicitlymodelsthefeaturesasconditionallyindependentgiven theclass.
P(H|X)=
P(X|H)(PH
??????(??????)
34

34. 35

35. 36

36. 37

37. 38

38. RandomForest
Itisaflexibleandsimple
RandomForestalgorithmavoidtheoverfittingproblem.
Usedforidentifyingthemostimportantfeaturesfromthetrainingdataset.
Itcanbeusedforbothclassificationandregressiontasks.
39

39. 40

40. 41

41. 42

42. 43

43. LogisticRegression
Usedtoassignobservations toadiscretesetofclasses.
Logisticregressioncanbebinomial, ordinalormultinomial.
Binary(Pass/Fail)
Multi (Cats,Dogs,Sheep)
Ordinal(Low,Medium,High)
Canviewprobability scoresunderlyingthemodel’s classifications.
44

44. 45

45. 46

46. 47

47. NeuralNetwork
Neuralnetworksislearningalgorithms.
Interpretsensorydata
Throughakind ofmachineperception,labelingorclusteringrawinput.
Consistofdifferentlayersforanalyzingandlearningdata.
Mathequation:
f(X)=b+∑iwixi
48

48. 49

49. 50

50. 51

51. 52

52. Concluding
Results
53

53. Tabletocomparedata
Recall Precision F-Measures
NeuralNetwork 0.813 0.814 0.814
LogisticRegression 0.848 0.848 0.848
Randomforest 0.807 0.807 0.807
54

54. 55

55. 56

56. 57

57. Projects:
58
1.Traffic Communication Data Analysis
2.Job Scam Data Analysis
3.Email Communication Data Analysis
4.Social Media Data Analysis
5.Healthcare Data Analysis

58. 59
EMAIL
COMMUNICATION
DATA
ANALYSIS

59. References:
https://www.youtube.com/watch?v=pYXOF0jziGM&index=6&list=PLmNPvQr9Tf-
ZSDLwOzxpvY-HrE0yv-8Fy
https://www.youtube.com/watch?v=bp0VtVS3LN4&index=9&list=PLmNPvQr9Tf-
ZSDLwOzxpvY-HrE0yv-8Fy
https://orange.biolab.si/getting-started/
https://en.wikipedia.org/wiki/Random_forest
https://en.wikipedia.org/wiki/Decision_tree_learning
http://orange.biolab.si/docs/latest/–
http://en.wikipedia.org/wiki/Data_mining–
http://www.oracle.com/technetwork/database/options/advanced-
analytics/odm/index.html–
http://eprints.fri.uni-lj.si/1150/1/DataMining-Kyoto.pdf
60

60. Thanks!
Anyquestions?
61