SlideShare a Scribd company logo
Decision Tree
Hands On Machine Learning with Scikit Learn and TensorFlow
Matsuda laboratory B4
Wataru Hirota
Topics
Today’s topic is..
• What is Decision Tree?
• CART Algorithm
• Regulate tree
• Decision Tree for Regression
• Experiment and Conclusion
Topics
Today’s topic is..
• What is Decision Tree?
• CART Algorithm
• Regulate tree
• Decision Tree for Regression
• Experiment and Conclusion
What is Decision Tree?
setosa
(petal length) <= 2.45
(petal width) <= 1.75
versicolor virginica
an iris whose
• petal length is 2.8
• petal width is 1.6
What is Decision Tree?
setosa
(petal length) <= 2.45
(petal width) <= 1.75
versicolor virginica
an iris whose
• petal length is 2.8
• petal width is 1.6
is predicted as versicolor.
Merits of Decision Tree
• easy to interpret (white box)
• cf. Random Forest, Neural Network
• effective learning with a small training data
• very few assumptions about the training data (nonparametric)
Topics
Today’s topic is..
• What is Decision Tree?
• CART Algorithm
• Regulate tree
• Decision Tree for Regression
• Experiment and Conclusion
What is CART?
• Classification And Regression Tree
• The algorithm used in scikit-learn.
• Split the dataset in the two purest subsets recursively.
Definition Of Impurity
1. Gini index (default in scikit-learn)
• 𝐺 = 1	 −	∑ 𝑝(
)*
(+,
• Slightly faster to computer
2. Entropy
• 𝐻 = −	∑ 𝑝(	log	( 𝑝()*
(+,
• Produce slightly more balanced tree
Cost Function of CART
𝐽 𝑘, 𝑡( = 	
𝑚89:;
𝑚
	𝐼89:; +
𝑚>?@A;
𝑚
	𝐼>?@A;
(the cost is low ⟺ the split is good)
• 𝑘	is the feature used to split.
• 𝑡( is the threshold.
• 𝑚 is the number of instances.
• 𝐼 is the impurity of the set.
Algorithm of CART
1. Split the trainset based on the cost function.
2. Split the two sets generated recursively.
Use scikit-learn
Quite simple :)
Topics
Today’s topic is..
• What is Decision Tree?
• CART Algorithm
• Regulate tree
• Decision Tree for Regression
• Experiment and Conclusion
Need to Regulate
• Decision Tree is likely to overfit!
○ ×
Hyper Parameters to Prevent Overfitting
• min_sample_split
• min_sample_leaf
• max_leaf_nodes
… and more
(For more details see scikit-learn document.)
Topics
Today’s topic is..
• What is Decision Tree?
• CART Algorithm
• Regulate tree
• Decision Tree for Regression
• Experiment and Conclusion
Basically same as classifier.
Differences
• Use the cost function as MSE.
• Predicted value is the average
of samples’ values in the node.
Decision Tree for Regression
Regression Example
Topics
Today’s topic is..
• What is Decision Tree?
• CART Algorithm
• Regulate tree
• Decision Tree for Regression
• Experiment and Conclusion
Experiment
• Predict whether cancer will return or won’t.
• Conditions
• Train set is GSE_characters.xlms
• The number of samples is about 2,000.
• Set no hyper parameters.
Experiment
0
0.2
0.4
0.6
0.8
1
A G A,G G,T T,A G,A,T G, A, T, H
Substitution Precision
A … AGE
G … Grade of cancer
T … Tumor size
H … HER2
Experiment
Generated tree
Experiment
• Set max_depth to simplify the model.
• Used all features (A, G, T, H) .
max_depth precision
3 0.7377
4 0.7363
5 0.7251
Generated Tree (max_depth=3)Estimated Generalization Precision
Conclusion
• Decision Tree is a strong method applicable both for
classification and regression.
• Decision Tree is easy to interpret.
• Overfitting is preventable with some hyper parameters (which
are also interpretable) .

More Related Content

Similar to Decision tree

Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
Maninda Edirisooriya
 
CSA 3702 machine learning module 2
CSA 3702 machine learning module 2CSA 3702 machine learning module 2
CSA 3702 machine learning module 2
Nandhini S
 
Lecture4.ppt
Lecture4.pptLecture4.ppt
Lecture4.ppt
Minakshee Patil
 
ML SFCSE.pptx
ML SFCSE.pptxML SFCSE.pptx
ML SFCSE.pptx
NIKHILGR3
 
Mini datathon
Mini datathonMini datathon
Mini datathon
Kunal Jain
 
Decision Tree.pptx
Decision Tree.pptxDecision Tree.pptx
Decision Tree.pptx
JayabharathiMuraliku
 
Lec 18-19.pptx
Lec 18-19.pptxLec 18-19.pptx
Lec 18-19.pptx
vijaita kashyap
 
Classification.pptx
Classification.pptxClassification.pptx
Classification.pptx
Dr. Amanpreet Kaur
 
Decision Tree.pptx
Decision Tree.pptxDecision Tree.pptx
Decision Tree.pptx
kibriaswe
 
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8
Hakky St
 
Performance Issue? Machine Learning to the rescue!
Performance Issue? Machine Learning to the rescue!Performance Issue? Machine Learning to the rescue!
Performance Issue? Machine Learning to the rescue!
Maarten Smeets
 
Comparison Study of Decision Tree Ensembles for Regression
Comparison Study of Decision Tree Ensembles for RegressionComparison Study of Decision Tree Ensembles for Regression
Comparison Study of Decision Tree Ensembles for Regression
Seonho Park
 
7 decision tree
7 decision tree7 decision tree
7 decision tree
tafosepsdfasg
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
Girish Khanzode
 
background.pptx
background.pptxbackground.pptx
background.pptx
KabileshCm
 
Decision Tree Classification Algorithm.pptx
Decision Tree Classification Algorithm.pptxDecision Tree Classification Algorithm.pptx
Decision Tree Classification Algorithm.pptx
PriyadharshiniG41
 
Introduction to ML.NET
Introduction to ML.NETIntroduction to ML.NET
Introduction to ML.NET
Marco Parenzan
 
Understanding Deep Learning Requires Rethinking Generalization
Understanding Deep Learning Requires Rethinking GeneralizationUnderstanding Deep Learning Requires Rethinking Generalization
Understanding Deep Learning Requires Rethinking Generalization
Ahmet Kuzubaşlı
 
rsec2a-2016-jheaton-morning
rsec2a-2016-jheaton-morningrsec2a-2016-jheaton-morning
rsec2a-2016-jheaton-morning
Jeff Heaton
 
machine learning - Clustering in R
machine learning - Clustering in Rmachine learning - Clustering in R
machine learning - Clustering in R
Sudhakar Chavan
 

Similar to Decision tree (20)

Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
Lecture 9 - Decision Trees and Ensemble Methods, a lecture in subject module ...
 
CSA 3702 machine learning module 2
CSA 3702 machine learning module 2CSA 3702 machine learning module 2
CSA 3702 machine learning module 2
 
Lecture4.ppt
Lecture4.pptLecture4.ppt
Lecture4.ppt
 
ML SFCSE.pptx
ML SFCSE.pptxML SFCSE.pptx
ML SFCSE.pptx
 
Mini datathon
Mini datathonMini datathon
Mini datathon
 
Decision Tree.pptx
Decision Tree.pptxDecision Tree.pptx
Decision Tree.pptx
 
Lec 18-19.pptx
Lec 18-19.pptxLec 18-19.pptx
Lec 18-19.pptx
 
Classification.pptx
Classification.pptxClassification.pptx
Classification.pptx
 
Decision Tree.pptx
Decision Tree.pptxDecision Tree.pptx
Decision Tree.pptx
 
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8
Hands-On Machine Learning with Scikit-Learn and TensorFlow - Chapter8
 
Performance Issue? Machine Learning to the rescue!
Performance Issue? Machine Learning to the rescue!Performance Issue? Machine Learning to the rescue!
Performance Issue? Machine Learning to the rescue!
 
Comparison Study of Decision Tree Ensembles for Regression
Comparison Study of Decision Tree Ensembles for RegressionComparison Study of Decision Tree Ensembles for Regression
Comparison Study of Decision Tree Ensembles for Regression
 
7 decision tree
7 decision tree7 decision tree
7 decision tree
 
Machine Learning
Machine LearningMachine Learning
Machine Learning
 
background.pptx
background.pptxbackground.pptx
background.pptx
 
Decision Tree Classification Algorithm.pptx
Decision Tree Classification Algorithm.pptxDecision Tree Classification Algorithm.pptx
Decision Tree Classification Algorithm.pptx
 
Introduction to ML.NET
Introduction to ML.NETIntroduction to ML.NET
Introduction to ML.NET
 
Understanding Deep Learning Requires Rethinking Generalization
Understanding Deep Learning Requires Rethinking GeneralizationUnderstanding Deep Learning Requires Rethinking Generalization
Understanding Deep Learning Requires Rethinking Generalization
 
rsec2a-2016-jheaton-morning
rsec2a-2016-jheaton-morningrsec2a-2016-jheaton-morning
rsec2a-2016-jheaton-morning
 
machine learning - Clustering in R
machine learning - Clustering in Rmachine learning - Clustering in R
machine learning - Clustering in R
 

Recently uploaded

Generative AI Use cases applications solutions and implementation.pdf
Generative AI Use cases applications solutions and implementation.pdfGenerative AI Use cases applications solutions and implementation.pdf
Generative AI Use cases applications solutions and implementation.pdf
mahaffeycheryld
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
ecqow
 
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 08 Doors and Windows.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 08 Doors and Windows.pdf2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 08 Doors and Windows.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 08 Doors and Windows.pdf
Yasser Mahgoub
 
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
IJECEIAES
 
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
MadhavJungKarki
 
Welding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdfWelding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdf
AjmalKhan50578
 
An Introduction to the Compiler Designss
An Introduction to the Compiler DesignssAn Introduction to the Compiler Designss
An Introduction to the Compiler Designss
ElakkiaU
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
Divyanshu
 
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
ydzowc
 
VARIABLE FREQUENCY DRIVE. VFDs are widely used in industrial applications for...
VARIABLE FREQUENCY DRIVE. VFDs are widely used in industrial applications for...VARIABLE FREQUENCY DRIVE. VFDs are widely used in industrial applications for...
VARIABLE FREQUENCY DRIVE. VFDs are widely used in industrial applications for...
PIMR BHOPAL
 
Digital Twins Computer Networking Paper Presentation.pptx
Digital Twins Computer Networking Paper Presentation.pptxDigital Twins Computer Networking Paper Presentation.pptx
Digital Twins Computer Networking Paper Presentation.pptx
aryanpankaj78
 
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
IJECEIAES
 
Data Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason WebinarData Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason Webinar
UReason
 
Computational Engineering IITH Presentation
Computational Engineering IITH PresentationComputational Engineering IITH Presentation
Computational Engineering IITH Presentation
co23btech11018
 
SCALING OF MOS CIRCUITS m .pptx
SCALING OF MOS CIRCUITS m                 .pptxSCALING OF MOS CIRCUITS m                 .pptx
SCALING OF MOS CIRCUITS m .pptx
harshapolam10
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
shadow0702a
 
Mechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdfMechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdf
21UME003TUSHARDEB
 
morris_worm_intro_and_source_code_analysis_.pdf
morris_worm_intro_and_source_code_analysis_.pdfmorris_worm_intro_and_source_code_analysis_.pdf
morris_worm_intro_and_source_code_analysis_.pdf
ycwu0509
 
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student MemberIEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
VICTOR MAESTRE RAMIREZ
 
Gas agency management system project report.pdf
Gas agency management system project report.pdfGas agency management system project report.pdf
Gas agency management system project report.pdf
Kamal Acharya
 

Recently uploaded (20)

Generative AI Use cases applications solutions and implementation.pdf
Generative AI Use cases applications solutions and implementation.pdfGenerative AI Use cases applications solutions and implementation.pdf
Generative AI Use cases applications solutions and implementation.pdf
 
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
一比一原版(CalArts毕业证)加利福尼亚艺术学院毕业证如何办理
 
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 08 Doors and Windows.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 08 Doors and Windows.pdf2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 08 Doors and Windows.pdf
2008 BUILDING CONSTRUCTION Illustrated - Ching Chapter 08 Doors and Windows.pdf
 
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
Redefining brain tumor segmentation: a cutting-edge convolutional neural netw...
 
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
1FIDIC-CONSTRUCTION-CONTRACT-2ND-ED-2017-RED-BOOK.pdf
 
Welding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdfWelding Metallurgy Ferrous Materials.pdf
Welding Metallurgy Ferrous Materials.pdf
 
An Introduction to the Compiler Designss
An Introduction to the Compiler DesignssAn Introduction to the Compiler Designss
An Introduction to the Compiler Designss
 
Null Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAMNull Bangalore | Pentesters Approach to AWS IAM
Null Bangalore | Pentesters Approach to AWS IAM
 
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
原版制作(Humboldt毕业证书)柏林大学毕业证学位证一模一样
 
VARIABLE FREQUENCY DRIVE. VFDs are widely used in industrial applications for...
VARIABLE FREQUENCY DRIVE. VFDs are widely used in industrial applications for...VARIABLE FREQUENCY DRIVE. VFDs are widely used in industrial applications for...
VARIABLE FREQUENCY DRIVE. VFDs are widely used in industrial applications for...
 
Digital Twins Computer Networking Paper Presentation.pptx
Digital Twins Computer Networking Paper Presentation.pptxDigital Twins Computer Networking Paper Presentation.pptx
Digital Twins Computer Networking Paper Presentation.pptx
 
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
Electric vehicle and photovoltaic advanced roles in enhancing the financial p...
 
Data Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason WebinarData Driven Maintenance | UReason Webinar
Data Driven Maintenance | UReason Webinar
 
Computational Engineering IITH Presentation
Computational Engineering IITH PresentationComputational Engineering IITH Presentation
Computational Engineering IITH Presentation
 
SCALING OF MOS CIRCUITS m .pptx
SCALING OF MOS CIRCUITS m                 .pptxSCALING OF MOS CIRCUITS m                 .pptx
SCALING OF MOS CIRCUITS m .pptx
 
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
Use PyCharm for remote debugging of WSL on a Windo cf5c162d672e4e58b4dde5d797...
 
Mechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdfMechanical Engineering on AAI Summer Training Report-003.pdf
Mechanical Engineering on AAI Summer Training Report-003.pdf
 
morris_worm_intro_and_source_code_analysis_.pdf
morris_worm_intro_and_source_code_analysis_.pdfmorris_worm_intro_and_source_code_analysis_.pdf
morris_worm_intro_and_source_code_analysis_.pdf
 
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student MemberIEEE Aerospace and Electronic Systems Society as a Graduate Student Member
IEEE Aerospace and Electronic Systems Society as a Graduate Student Member
 
Gas agency management system project report.pdf
Gas agency management system project report.pdfGas agency management system project report.pdf
Gas agency management system project report.pdf
 

Decision tree

  • 1. Decision Tree Hands On Machine Learning with Scikit Learn and TensorFlow Matsuda laboratory B4 Wataru Hirota
  • 2. Topics Today’s topic is.. • What is Decision Tree? • CART Algorithm • Regulate tree • Decision Tree for Regression • Experiment and Conclusion
  • 3. Topics Today’s topic is.. • What is Decision Tree? • CART Algorithm • Regulate tree • Decision Tree for Regression • Experiment and Conclusion
  • 4. What is Decision Tree? setosa (petal length) <= 2.45 (petal width) <= 1.75 versicolor virginica an iris whose • petal length is 2.8 • petal width is 1.6
  • 5. What is Decision Tree? setosa (petal length) <= 2.45 (petal width) <= 1.75 versicolor virginica an iris whose • petal length is 2.8 • petal width is 1.6 is predicted as versicolor.
  • 6. Merits of Decision Tree • easy to interpret (white box) • cf. Random Forest, Neural Network • effective learning with a small training data • very few assumptions about the training data (nonparametric)
  • 7. Topics Today’s topic is.. • What is Decision Tree? • CART Algorithm • Regulate tree • Decision Tree for Regression • Experiment and Conclusion
  • 8. What is CART? • Classification And Regression Tree • The algorithm used in scikit-learn. • Split the dataset in the two purest subsets recursively.
  • 9. Definition Of Impurity 1. Gini index (default in scikit-learn) • 𝐺 = 1 − ∑ 𝑝( )* (+, • Slightly faster to computer 2. Entropy • 𝐻 = − ∑ 𝑝( log ( 𝑝()* (+, • Produce slightly more balanced tree
  • 10. Cost Function of CART 𝐽 𝑘, 𝑡( = 𝑚89:; 𝑚 𝐼89:; + 𝑚>?@A; 𝑚 𝐼>?@A; (the cost is low ⟺ the split is good) • 𝑘 is the feature used to split. • 𝑡( is the threshold. • 𝑚 is the number of instances. • 𝐼 is the impurity of the set.
  • 11. Algorithm of CART 1. Split the trainset based on the cost function. 2. Split the two sets generated recursively.
  • 13. Topics Today’s topic is.. • What is Decision Tree? • CART Algorithm • Regulate tree • Decision Tree for Regression • Experiment and Conclusion
  • 14. Need to Regulate • Decision Tree is likely to overfit! ○ ×
  • 15. Hyper Parameters to Prevent Overfitting • min_sample_split • min_sample_leaf • max_leaf_nodes … and more (For more details see scikit-learn document.)
  • 16. Topics Today’s topic is.. • What is Decision Tree? • CART Algorithm • Regulate tree • Decision Tree for Regression • Experiment and Conclusion
  • 17. Basically same as classifier. Differences • Use the cost function as MSE. • Predicted value is the average of samples’ values in the node. Decision Tree for Regression
  • 19. Topics Today’s topic is.. • What is Decision Tree? • CART Algorithm • Regulate tree • Decision Tree for Regression • Experiment and Conclusion
  • 20. Experiment • Predict whether cancer will return or won’t. • Conditions • Train set is GSE_characters.xlms • The number of samples is about 2,000. • Set no hyper parameters.
  • 21. Experiment 0 0.2 0.4 0.6 0.8 1 A G A,G G,T T,A G,A,T G, A, T, H Substitution Precision A … AGE G … Grade of cancer T … Tumor size H … HER2
  • 23. Experiment • Set max_depth to simplify the model. • Used all features (A, G, T, H) . max_depth precision 3 0.7377 4 0.7363 5 0.7251 Generated Tree (max_depth=3)Estimated Generalization Precision
  • 24. Conclusion • Decision Tree is a strong method applicable both for classification and regression. • Decision Tree is easy to interpret. • Overfitting is preventable with some hyper parameters (which are also interpretable) .