Ch 01

Introduction to Data Science

Advanced Data Science
ICTS 6345

Dr. Iyad Husni Alshami

Dr. Iyad H. Alshami – ICTS 6345 1

 Outline

•Definition of Data Science

•Data Science as Multi-disciplinary field

•Data Science Life Cycle

•Data Science Tasks

•Data Science Tools

Dr. Iyad H. Alshami – ICTS 6345 2

 Definition
• What is data science? It’s a surprisingly hard defini7on to nail down,
especially given how ubiquitous the term has become. Vocal cri7cs have
variously dis- missed the term as a superfluous label (aDer all, what science
doesn’t involve data?) or a simple buzzword that only exists to salt résumés
and catch the eye of overzealous tech recruiters.
• PYTHON DATA SCIENCE HANDBOOK Essen3al Tools for Working with Data, Jake VanderPlas, O’Reilly Media, Inc., 2017

• Data science encompasses a set of principles, problem defini7ons,

algorithms, and processes for extrac7ng non-obvious and useful paKerns
from large data sets.
• DATA SCIENCE, John D. Kelleher And Brendan Tierney, The MIT Press Essen3al Knowledge Series, 2019.

Dr. Iyad H. Alshami – ICTS 6345 3

 Definition
•Data science is an inter-disciplinary field that uses scientific
methods, processes, algorithms and systems to extract knowledge
and insights from many structural and unstructured data.
• Data science and prediction, Vasant Dhar, Communications of the ACM, December 2013, Vol. 56 No. 12, Pages 64-73, 10.1145/2500499

• Data Science is a science/field that deals with identification, representation

and extraction of meaningful information (knowledge) from data sources to
be used for business purposes.

• Data Science is the science which uses computer science, statistics and
machine learning, visualization and human-computer interactions to collect,
clean, integrate, analyze, visualize, interact with data to create data
products.
Dr. Iyad H. Alshami – ICTS 6345 4
 Data Sources
• Data is everywhere and still growing.

• The amount of digital data that exists is growing at a rapid rate, doubling
every two years, and changing the way we live.

• Data is growing faster than ever before and by the year 2020, about 1.7
megabytes of new information will be created every second for every human
being on the planet.

Dr. Iyad H. Alshami – ICTS 6345 5

 Data Sources
• A Tsunami of Data
• The advent of the internet and its worldwide connectivity gave us the “age
of information.”
• By 2020 (in just a few months), humankind will produce 44 zettabytes
(1024 TB), of data yearly, meaning every single person on earth will create
about 1.7 MB of data per second.
• This production is only going to accelerate by 2030, when 125 billion Internet of Things
devices that will be connected.

• To date, only about 2% of this data has been analyzed.

• Companies are now turning to AI and high-performance computing to dive into the other 98
percent.
Bitfury, Blog Posts / April 20, 2020
Dr. Iyad H. Alshami – ICTS 6345 6
 Data Sources

https://web-assets.domo.com/blog/wp-content/uploads/2021/09/data-never-sleeps-9.0-1200px-1.png

Dr. Iyad H. Alshami – ICTS 6345 7

 Data Sources

The 20th Century was the golden age of

oil. The "black gold" was the reason that
leads countries to war.

Today, new sources of wealth and power

are arising as technology evolves,
triggering massive changes in business,
politics and geostrategy. …. Data is the
modern-day holy grail for those seeking
wealth, influence and power.

http://www.tribune242.com/news/2020/aug/20/activtrades-data-new-oil/
Dr. Iyad H. Alshami – ICTS 6345 8
 Business Purposes

•Having knowledge from such data helps organizations to:

•be efficient in terms of cost, delivery and productivity;
•identifies new opportunities, and
•creates a strong brand image of the organization

Dr. Iyad H. Alshami – ICTS 6345 9

 Why data science, and why now?

•To answer this there are three main reasons:

1. New technology makes it possible to capture, annotate, and
store vast amounts of databases in organization ,social media,
logging, and sensor data.
• After having all these data, we begin to wonder what you can do with
it.

Dr. Iyad H. Alshami – ICTS 6345 10

 Why data science, and why now?

•To answer this there are three main reasons:

2. Computing advances make it possible to analyse data in novel
ways and increased scales.
• Cloud computing architectures give us an access to vast power when
we need it.
• Machine Learning new approaches lead to amazing advances in well-
known problems, like Computer Vision and Natural Language
Processing.

Dr. Iyad H. Alshami – ICTS 6345 11

 Why data science, and why now?

•To answer this there are three main reasons:

3. Famous technology companies, like Google and Facebook,
have proven the power of modern data analytics.
• Success stories applying data to such diverse areas as business,
management, sports management, and election forecasting have
served as role models to bring data science to a large popular
audience.

Dr. Iyad H. Alshami – ICTS 6345 12

 Data Products
• Data Science – development of data product
• A "data product" is a technical asset that:
• (1) utilizes data as input, and
• (2) processes that data to return algorithmically-generated results.

• A data product embeds that algorithm in a web site so that users can input
values and get predictions.

• The classic example of a data product is a recommendation engine, which

ingests user data, and makes personalized recommendations based on that
data.

Dr. Iyad H. Alshami – ICTS 6345 13

 Examples of Data Products
• Amazon's recommenda7on engines, is a data product, suggest items to buy.
• Ne5lix and Spo:fy recommends movies and music respec:vely.

• Gmail's spam filter, is data a product, processes incoming mail and

determines if a message is junk or not.

• Computer vision used for self-driving cars, is a data product, machine

learning algorithms are able to recognize traffic lights, other cars on the road,
and pedestrians.

Dr. Iyad H. Alshami – ICTS 6345 14

 Outline

•Definition of Data Science

•Data Science as Multi-disciplinary field

•Data Science Life Cycle

•Data Science Tasks

•Data Science Tools

Dr. Iyad H. Alshami – ICTS 6345 15

 Data Science as multi-disciplinary field
• Data Science is a multi-disciplinary field.

• Data Science is the science which uses computer science, statistics and
machine learning, visualization and human-computer interactions to collect,
clean, integrate, analyze, visualize, interact with data to create data
products.

• Data Science employs techniques and theories drawn from many fields
within the broad areas computer science, mathematics, statistics, data
engineering, visualization, predictive analytics, uncertainty modelling, data
warehousing and high performance computing.

Dr. Iyad H. Alshami – ICTS 6345 16

 Data Science as multi-disciplinary field

Dr. Iyad H. Alshami – ICTS 6345 17

 Data Science as multidisciplinary field

•Data Science is subset of computer science where the study of data

is done by using different methods and technology.
• Like: Hadoop, relational and NoSQL databases

•Some data science methods comes from statistics such as Naïve

Baiys and Maximum Entropy and also used for estimating
probabilities of predictions.
• Data science is differ than statistics in kind of data (not only numerical) ,
kinds of methods ( mostly use machine learning methods) , more than one
hypotheses, amount of data (statistics uses samples)

Dr. Iyad H. Alshami – ICTS 6345 18

 Data Science as multidisciplinary field

•Machine Learning focuses on complex representaOons and search

methods for specialized data-intensive problems.

•Data Science uses methods from Machine Learning such as

Decision Tree and Neural Nets.
• Machine Learning uses samples and Data Science uses whole data.
• (Big Data) Data Science can access data from database. Machine Learning
some 7mes used to replace human where Data Mining to help human.

Dr. Iyad H. Alshami – ICTS 6345 19

 Data Science as multidisciplinary field
• Visualization representing data in a visual form.
• This visual form can be a chart, graphs, lists or a map etc.

• This representation helps people to understand the magnitude of the data.

• It is used to gain visual insights into the structure of the data.

• Visualization is in large quantities used as a pre- and post-processing tool for

Data Science .

Dr. Iyad H. Alshami – ICTS 6345 21

 Data Science as multi-disciplinary field

Dr. Iyad H. Alshami – ICTS 6345 22

Dr. Iyad H. Alshami – ICTS 6345 23
 Outline
•Definition of Data Science
•Data Science as an multi-disciplinary field
•Data Science Life Cycle
•Data Science Tasks
•Data Science Tools

Dr. Iyad H. Alshami – ICTS 6345 24

 Data Science Lifecycle

•The data science life cycle is

the sequence of stages that a
data scientist goes through
from its initial generation or
capture to the end of its
project.

Dr. Iyad H. Alshami – ICTS 6345 25

Dr. Iyad H. Alshami – ICTS 6345 26
 Data Science Lifecycle
1. Business Understanding
• To obtain the highest benefit from data science, there must be a clear
Business Understanding

• Business Understanding: Understand the project objectives and

requirements from a business perspective.

• Before we even begin doing anything with “Data Science”, we must first take
into consideration what problem we’re trying to solve.

• The data scientists keep asking what and why to ensure that every decision made in the
company is supported by concrete data, and that it is guaranteed (with a high
probability) to achieve results.

Dr. Iyad H. Alshami – ICTS 6345 27

 Data Science Lifecycle
1. Business Understanding
• Example of Goal for business company are:
• You want to attract new customers
• You want to avoid high-risk customers
• You want to understand the characteristics of your current customers?
• You want to make your unprofitable customers more profitable?
• You want to retain your profitable customers?
• You want to win back your lost customers?
• You want to improve customer satisfaction?
• You want to increase sales?
• You want to reduce expenses

Dr. Iyad H. Alshami – ICTS 6345 28

 Data Science Lifecycle
1. Business Understanding
• We typically use data science to answer five types of questions:
• How much or how many? (regression)
• Which category? (classification)
• Which group? (clustering)
• Is this weird? (anomaly detection)
• Which option should be taken? (recommendation)

Dr. Iyad H. Alshami – ICTS 6345 29

 Data Science Lifecycle
2. Obtain Data
• We cannot do anything as a data scientist without having data.

• As a rule of thumb, there are some things we must take into consideration
when obtaining data.

• We must identify all the available datasets, which can be from the internet
or external/internal databases, that related to the project.

• You must extract the data into a usable format

• csv, json, xml, etc..

Dr. Iyad H. Alshami – ICTS 6345 30

 Data Science Lifecycle
2. Obtain Data
At this stage, some of the ques7ons worth considering are:
• What data do I need for my project?
• Where does it live?
• How can I obtain it?
• What is the most efficient way to store and access all of it?

Dr. Iyad H. Alshami – ICTS 6345 31

 Data Science Lifecycle
2. Obtain Data
Skills Required:
• Database Management: MySQL, PostgresSQL,MongoDB
• Querying Relational Databases
• Retrieving Unstructured Data: text, videos, audio files, documents
• Distributed Storage: Hadoops, Apache Spark/Flink

Dr. Iyad H. Alshami – ICTS 6345 32

 Data Science Lifecycle
3. Cleaning Data
• Data can be corrupted with various errors such as missing, incorrect, or
inconsistent values.

• This phase require the most time and effort. Because the results and output
of your machine learning model is only as good as what you put into it.
Basically, garbage in garbage out.

• This process can often take 50 to 80 percent of their time.

Dr. Iyad H. Alshami – ICTS 6345 33

 Data Science Lifecycle
3. Cleaning Data
• The reason why this is such a time consuming process is simply because
there are so many possible scenarios that could necessitate cleaning.

• For instance, the data could also have inconsistencies within the same
column, meaning that some rows could be labelled 0 or 1, and others could
be labelled no or yes.

Dr. Iyad H. Alshami – ICTS 6345 34

 Data Science Lifecycle
3. Cleaning Data
• The data types could also be inconsistent - some of the 0s might integers,
whereas some of them could be strings. If we’re dealing with a categorical
data type with multiple categories, some of the categories could be
misspelled or have different cases, such as having categories for
both male and Male. .

Dr. Iyad H. Alshami – ICTS 6345 35

 Data Science Lifecycle
3. Cleaning Data
• One of the steps that is often forgotten in this stage, causing a lot of
problems later on, is the presence of missing data. Missing data can throw a
lot of errors in the model creation and training.

• Transform the data into a form appropriate for given data mining method
• Data is transformed or consolidated into forms appropriate for mining

Dr. Iyad H. Alshami – ICTS 6345 36

 Data Science Lifecycle
4. Data Exploration
• The data exploration stage is like the brainstorming of data analysis. This is
where you understand the patterns and bias in your data.
• It could involve plotting a histogram or distribution curve to see the general
trend, or even creating an interactive visualization that lets you dive down
into each data point and explore the story behind the outliers.

Dr. Iyad H. Alshami – ICTS 6345 37

 Data Science Lifecycle
4. Data Exploration
• This histogram shows the number of customers of different ages and quickly
tells the viewer that the majority of customers are over the age of 50

Dr. Iyad H. Alshami – ICTS 6345 38

 Data Science Lifecycle
4. Data Exploration
• Using all of this information, you start to form hypotheses about your data
and the problem you are tackling. If you were predicting student scores for
example, you could try visualizing the relationship between scores and sleep.

Dr. Iyad H. Alshami – ICTS 6345 39

 Data Science Lifecycle
5. Feature Engineering
• In machine learning, a feature is a measurable property or attribute of a
phenomenon being observed

Dr. Iyad H. Alshami – ICTS 6345 40

 Data Science Lifecycle
5. Feature Engineering
• Feature selection is the process of cutting down the features that add more
noise than information.

A1 A2 A3 A4 C A2 A4 C

Dr. Iyad H. Alshami – ICTS 6345 41

 Data Science Lifecycle
5. Feature Engineering
• If we were predicting the scores of a student, a possible feature is the
amount of sleep they get.

• In more complex prediction tasks such as character recognition, features

could be histograms counting the number of black pixels.

Dr. Iyad H. Alshami – ICTS 6345 42

 Data Science Lifecycle
5. Feature Engineering
• Feature construction involves creating new features from the ones that you
already have.

• For example, if you have a feature for age, but your model only cares about if
a person is an adult or minor, you could threshold it at 18, and assign
different categories to instances above and below that threshold.

Dr. Iyad H. Alshami – ICTS 6345 43

 Data Science Lifecycle
5. Feature Engineering
• You could also merge multiple features to make them more informative by
taking their sum, difference or product.

• For example, if you were predicting student scores and had features for the
number of hours of sleep on each night, you might want to create a feature
that denoted the average sleep that the student had instead.

Dr. Iyad H. Alshami – ICTS 6345 44

 Data Science Lifecycle
6. Modelling
• Modelling is where the machine learning finally comes into the data science
project.
• Based on the questions data scientist asked in the business understanding stage, this is
where they decide which model to pick for their problem.

• data scientist will have access to many algorithms and use them to
accomplish different business goals.

• For types of modeling see next section

Dr. Iyad H. Alshami – ICTS 6345 45

 Data Science Lifecycle
7. Interpreting (Data Visualization)
• The most important step is to
understand and learn how to
explain your findings through
communication.

• People aren’t going to magically

understand your findings. The
best way to make an impact is
telling your story through
visualization.

Dr. Iyad H. Alshami – ICTS 6345 46

 Data Science Lifecycle
8. Business Understanding
• Now that you’ve gone through the entire lifecycle, it’s time to go back to the
drawing board.
• Remember, this is a cycle, and so it’s an iterative process.
• This is where you evaluate how the success of your model relates to your
original business understanding.
• Does it tackle the problems identified? Does the analysis yield any tangible
solutions?
• If you encountered any new knowledge during the first iteration of the
lifecycle, you can now use that knowledge into the next iteration to generate
even more powerful insights.

Dr. Iyad H. Alshami – ICTS 6345 47

Dr. Iyad H. Alshami – ICTS 6345 48
 Outline
•Definition of Data Science
•Data Science as an multi-disciplinary field
•Data Science Life Cycle
•Data Science Tasks
•Data Science Tools

Dr. Iyad H. Alshami – ICTS 6345 49

 Data Science Tasks
• Data Science tasks are the kind of data patterns or knowledge that can be
mined.
• These task related to the Predictive modeling (Stage 6) in the data science life cycle.
• Data Science functionalities are used to specify the kind of patterns to be
found in the data Science tasks.

Dr. Iyad H. Alshami – ICTS 6345 50

 Data Science Tasks
• In general Data Science tasks can be classified into two categories:
• Descriptive tasks characterize the general properties of the data.

• Predictive tasks perform deduction on the current data in order to make

predictions.

Dr. Iyad H. Alshami – ICTS 6345 51

 Data Science Tasks
• Most famous data Science tasks:

Dr. Iyad H. Alshami – ICTS 6345 52

 Data Science Tasks
Classification
• Classification is used for predictive Science tasks.

• The input data for predictive modeling consists of two types of variables:
• The first is explanatory variables , which define the essential properties of the data, and
• The second is one target variables , whose values are to be predicted. Classification is
used to predicate the value of discrete target variable.

Dr. Iyad H. Alshami – ICTS 6345 53

 Data Science Tasks
Classification

Dr. Iyad H. Alshami – ICTS 6345 54

 Data Science Tasks
Classification

Dr. Iyad H. Alshami – ICTS 6345 55

 Data Science Tasks
Regression
• Similar to classification, except we are trying to predict the value of a variable
(e.g. amount of purchase), rather than a class (e.g. purchaser or non-
purchaser)

Dr. Iyad H. Alshami – ICTS 6345 56

 Data Science Tasks
Regression

Dr. Iyad H. Alshami – ICTS 6345 57

 Data Science Tasks
Regression
• Examples:
• Predicting sales amounts of new product based on advertising spending.
• Predicting wind velocities as a function of temperature, humidity, air pressure, etc.

Dr. Iyad H. Alshami – ICTS 6345 58

 Data Science Tasks
Regression

Dr. Iyad H. Alshami – ICTS 6345 59

 Data Science Tasks
Recommendation systems
• Recommendation Systems (RS) help to match users with items
• Ease information overload
• Sales assistance (guidance, advisory, persuasion,…)

Dr. Iyad H. Alshami – ICTS 6345 60

 Data Science Tasks
Recommendation systems

Dr. Iyad H. Alshami – ICTS 6345

 Data Science Tasks
Recommendation systems

Dr. Iyad H. Alshami – ICTS 6345

 Data Science Tasks
Clustering
• Finds groups of data pointes (clusters) so that data points that belong to one
cluster are more similar to each other than to data points belonging to
different cluster.

Find “natural” grouping of instances given un-labeled data

Dr. Iyad H. Alshami – ICTS 6345 63

 Data Science Tasks
Clustering
• Document Clustering:
• Goal:
• To find groups of documents that are similar to each other based on the important
terms appearing in them.

• Approach:
• Identify frequently occurring terms in each document.
• Form a similarity measure based on the frequencies of different terms.
• Use it to cluster the documents.

• Gain:
• Information Retrieval can utilize the clusters to relate a new document or search
term to clustered documents.
Dr. Iyad H. Alshami – ICTS 6345 64
 Data Science Tasks
Outlier Analysis
• Discovers data points that are significantly different than the rest of the data.
Such points are known as anomalies or outliers.

• Applications:
• Credit Card Fraud Detection

Dr. Iyad H. Alshami – ICTS 6345 65

 Data Science Tasks
Affinity analysis
• Affinity analysis is a data science technique that discovers co-occurrence
relationships among activities.
• It is known as association rules

• Affinity analysis is a method for discovering interesting relations between

variables in large databases. It is intended to identify strong rules discovered
in databases using different measures of interestingness.

• Seek to produce a set of rules describing the set of features that are strongly
related to each others.

Dr. Iyad H. Alshami – ICTS 6345 66

 Data Science Tasks
Affinity analysis
• Example t1: Beef, Chicken, Milk
t2: Beef, Cheese
• Transaction data t3: Cheese, Boots
• Assume: t4: Beef, Chicken, Cheese
t5: Beef, Chicken, Clothes, Cheese, Milk
• minsup = 30% t6: Chicken, Clothes, Milk
• minconf = 80% t7: Chicken, Milk, Clothes

• An example frequent itemset:

• {Chicken, Clothes, Milk} [sup = 3/7]

• Association rules from the itemset:

• Clothes ® Milk, Chicken [sup = 3/7, conf = 3/3]
• … …
• Clothes, Chicken ® Milk, [sup = 3/7, conf = 3/3]
Dr. Iyad H. Alshami – ICTS 6345 67
 Affinity analysis
• Association Rules aims to find out the relationship among valuables in dataset,
resulting in deferent types of rules
Table 1：original data from a research on heart disease

Gender Age Smoker LAD% RCA%

F 52 Y 85 100
M 62 N 80 0
M 75 Y 70 80
M 73 Y 40 99
M 66 N 50 45

… … … … …

LAD%－ The percentage of heat disease caused by left anterior descending coronary artery
RCA%－ The percentage of heat disease caused by right coronary artery

Dr. Iyad H. Alshami – ICTS 6345 68

 Affinity analysis

Table.2 Medical Association Rules

NO. Rule
1 Gender=M∩Age≥70∩Smoker=Y Þ RCA%≥50(40%,100%)
2 Gender=F∩Age＜70∩Smoker=Y Þ LAD%≥70(20%,100%)

q Rule 1 indicates：40% of the cases are male, over 70 years old and have the habit of
smoking, the possibility of RCA%≥50% is 100%

q Rule 2 indicates：20% of the cases are female, under 70 years old and have the habit of
smoking, the possibility of LAD%≥70% is 100%

Dr. Iyad H. Alshami – ICTS 6345 69

 Outline
•Definition of Data Science
•Data Science as an multi-disciplinary field
•Data Science Life Cycle
•Data Science Tasks
•Data Science Tools

Dr. Iyad H. Alshami – ICTS 6345 70

 Data Science Tools
Chaining Tools for Data Science

• Use the right toolset in different stages

Exploratory Inference / Solution Results

Data Preparation
Analysis Prediction Implementation Communication

Hadoop Excel Python Python Excel

RDBMS Custom
/ SQL R R Code

Dr. Iyad H. Alshami – ICTS 6345

 Data Science Tools
for Obtaining Data
• Database Management: MySQL, PostgresSQL, MongoDB
• Retrieving Unstructured Data: text, videos, audio files, documents
• Distributed Storage: Hadoops, Apache Spark

Hadoop is an open-source framework that allows to store and process big

data in a distributed environment across clusters of computers using simple
programming models.

Dr. Iyad H. Alshami – ICTS 6345 72

 Data Science Tools
for Cleaning Data
• Scripting language: Python, R, SAS
• Tools: RapidMiner , Weka
• Distributed Processing: Hadoop, Map Reduce

Dr. Iyad H. Alshami – ICTS 6345 73

 Data Science Tools
for Data Exploration
• Python: Numpy, Matplotlib, Pandas, Scipy
• R: GGplot2, Dplyr
• SpreadSheets: Excel
• Data Visualization: Tableau, Qlikview

Dr. Iyad H. Alshami – ICTS 6345 74

 Data Science Tools
for Feature Engineering
• Languages: Python, R
• Tools: FeatureTools, Rapidminer
• Machine Learning: Azure Machine Learning , Amazon Machine Learning

Dr. Iyad H. Alshami – ICTS 6345 75

 Data Science Tools
for Modeling
• Machine Learning Libraries: Python (Sci-kit Learn) / R (CARET)
• Statistics: SPSS, SAS
• Tools: Rapidminer, Weka, MLBase

Dr. Iyad H. Alshami – ICTS 6345 76

 Data Science Tools
for Interpreting (Data Visualization)
• Python: Numpy, Matplotlib, Seaborn, Pandas, Scipy
• R: GGplot2, Dplyr
• SpreadSheets: Excel
• Data Visualization: Tableau, Qlikview
• Communication: Presenting/Speaking & Reporting/Writing

Dr. Iyad H. Alshami – ICTS 6345 77

 That is all for today
See you next week J

Dr. Iyad H. Alshami – ICTS 6345 78