Data Mining 101

Data Mining 101
Okiriza Wibisono - @okiriza

Ali Akbar Septiandri - @aliakbars
Outline
Introduction
Terminology
Potential application
Venn diagram
Process
overview
Business understanding
Data understanding (exploration)
Data preparation (preprocessing)
Modeling
Evaluation
Deployment (presentation)
Tools &
Resource
Introduction Terminology
Data
science
Big data
analytics
Statistics
Knowledge
Discovery
in
Databases
Data
mining
The process of collecting,

searching through, and analyzing
a large amount of data in a
database, as to discover patterns
or relationships.
Data Mining - dictionary.reference.com
Introduction Potential Application
Customer
segmentation
Recommendation
engine
Social media
mining

What should we do?
Where to start? Do I have to get a master degree in statistics?
http://tomfishburne.com.s3.amazonaws.com/site/wp-content/uploads/2014/01/140113.bigdata.jpg
Data Science Venn Diagram

http://drewconway.com/zia/2013/3/26/thedata-science-venn-diagram
And now the business process
CRISP DM Methodology
http://lyle.smu.edu/~mhd/8331f03/crisp.pdf
Business Understanding
Objective Statement
Bottom-up
Top-down
Objective Statement
vs
Data
Problem
Situation Assessment
Inventory of Resources
Requirements, Assumptions, and Constraints
Risks and Contingencies
Terminology
Costs and Benefits
http://www.ismll.uni-hildesheim.de/lehre/ba-12ss/script/ba03.pdf
Inventory of Resources
Hardware
Data,
Knowledge,
Tools
Personnel
Resource
Requirements, Assumptions, and Constraints
Requirements
Assumptions
Constraints
Scheduling
Data quality
Legal issues
Accuracy
External
factors
Budget
Security
Reporting type
Resources
Risks and Contingencies
Business
Organizational
Financial
Contingency Plan
Situation Assessment Terminology

Write down related terminology
http://www.partnersmn.com/wp-content/uploads/2010/08/5b8567b2b4e2d1cfd1a31b2b8a0ecebc1.jpg
Situation Assessment Costs and Benefits

Money, money, money!
http://www.centuryproductsllc.com/wp-content/uploads/holding-money.jpg

How to evaluate the results?
Define your success criteria!
Data Understanding
Data Collection
vs
External
Internal
Watch out!
visible accessible
storable presentable
Victor Lavrenko Text Technologies
http://www.inf.ed.ac.uk/teaching/courses/tts/pdf/crawl-2x2.pdf
Data Exploration
Visualization Heuristics
Visualize fast. Visualize reactively.
Go for high information 2D visualizations.
Select data subsets to visualize.
http://www.inf.ed.ac.uk/teaching/courses/dme/slides2014/visualization-print4up.pdf
Data Exploration
Visualization Heuristics
Never let anomalies pass you by. Dig deeper.
Use your visualizations to inform potential

models. Use your potential model to direct your
visualizations.
Expect problems in your data.
This is the cheapest and most

informative stage of data
mining.
Nigel Goddard DME Visualization
Data Exploration
Visualization Tools
Column/bar: Large change
Line, curve: Small change, long periods
Histogram: Frequency distribution
https://nces.ed.gov/nceskids/help/user_guide/graph/whentouse.asp
Data Preparation
Which one should I include

(or exclude)?
Data Selection
Missing
value
Data Cleaning
Remember: Expect problems in your data.
Outlier
Duplication
Dirty
Data
Incomplete
Outdated
Data Construction
Feature
engineering derived attributes,
e.g.:
year
from timestamp
quarter
BMI
from timestamp
from weight and height
Log(x)
for skewed data (e.g. house price)
Data Splitting
Two
kinds of data splitting:
Training-Validation-Testing
Cross
Validation
Data Splitting
Training-Validation-Testing
Training
Split randomly to avoid bias
Validation
Testing
http://www.inf.ed.ac.uk/teaching/courses/iaml/slides/eval-2x2.pdf
Construct
classifier
Pick algorithm
Knob settings
(tree depth, k in
kNN, c in SVM)
Estimate future
error rate
Data Splitting
Cross Validation
Every point is both training and testing, never at the same time
Dimensionality Reduction
Principal
Component
Analysis
vs
Linear
Discriminant
Analysis
Modeling
Machine Learning
Classification
Regression
Ranking
Clustering
Model Selection
Generalization bound
Regression
Technique
Linear regression
Kernel ridge regression
Support vector regression
Lasso

Which one should I choose?
Should I use all of them?
It depends on
Model Selection
Assumptions Interpretability
The predictors are linearly
independent
The error is a random variable
with a mean of zero conditional on
the explanatory variables
The sample is representative of
the population for the inference
prediction
https://chenhaot.com/pubs/mldg-interpretability.pdf
The
understandability
of why the model
is true or how the
model is induced
from
Beware of Overfitting!
http://pingax.com/wp-content/uploads/2014/05/underfitting-overfitting.png
Model Assessment
Regression
(R)MSE
Mean
Absolute
Error
Correlation
Coefficient
Classification
Accuracy
Precision
Recall
F-score
Descriptive
Std. Error
p-value
Confidence
Interval
Evaluation
Does my model solve the

problem?
What is the impact? Is it novel? How useful is the solution?
Deployment
The Tasks
Plan deployment
Plan monitoring
and maintenance
Produce final
report
Review project
Tools & Resource
Text mining: NLTK, spaCy, OpenNLP
Query expansion & clustering: Carrot2, Weka
Data mining & machine learning: Weka, scikit-learn
Language: R, Python, Julia, Java, Matlab, Mathematica, Haskell, Scala
Python lib: Pandas, SciPy, NumPy, scikit-learn
Infrastructure: AWS, Hadoop, Google Cloud, Azure, Apache Spark
Visualization: D3.js
Community: Big Data & Open Data Indonesia

Thank you!
Data Mining 101 Python-ID Meetup February 2015

Okiriza Wibisono - @okiriza
Ali Akbar Septiandri - @aliakbars

Data Mining 101

Uploaded by

Copyright:

Available Formats

Data Mining 101

Uploaded by

Document Information

Original Description:

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Data Mining 101

Uploaded by

Copyright:

Available Formats

Data Mining 101

Okiriza Wibisono - @okiriza

The process of collecting,

Introduction Potential Application

Data Science Venn Diagram

And now the business process

Situation Assessment Terminology

Situation Assessment Costs and Benefits

Visualize fast. Visualize reactively.

Go for high information 2D visualizations.

Select data subsets to visualize.

Never let anomalies pass you by. Dig deeper.

Use your visualizations to inform potential

Expect problems in your data.

This is the cheapest and most

Column/bar: Large change

Line, curve: Small change, long periods

Histogram: Frequency distribution

Which one should I include

engineering derived attributes,

from weight and height

for skewed data (e.g. house price)

kinds of data splitting:

Split randomly to avoid bias

Does my model solve the

Tools & Resource

Text mining: NLTK, spaCy, OpenNLP

Query expansion & clustering: Carrot2, Weka

Data mining & machine learning: Weka, scikit-learn

Language: R, Python, Julia, Java, Matlab, Mathematica, Haskell, Scala

Python lib: Pandas, SciPy, NumPy, scikit-learn

Infrastructure: AWS, Hadoop, Google Cloud, Azure, Apache Spark

Community: Big Data & Open Data Indonesia

Data Mining 101 Python-ID Meetup February 2015

You might also like