Introduction to Data Science
Learning Objectives
By the end of this lesson, you will be able to:
Define data science
Discuss the roles and responsibilities of a data scientist
List various applications of data science
Explain data science and its importance
Data Science
What Is Data Science?
Some common definitions of Data Science are:
An automated way to analyze
A powerful new approach to
enormous amounts of data and
make discoveries from data
extract information
A new discipline that combines the aspects of statistics, mathematics,
programming, and visualization to turn data into information
Components of Data Science
Data science is created when subject expertise and scientific methodologies are combined with technology.
Domain Expertise and Scientific Technology
Methods
Operating
Analysis systems
Scientific Python Application
Mathematical
tools and language design
and statistical
models methods
Data Science
Data processing Library
tools
Domain Expertise and Scientific Methods
Data scientists collect, explore, analyze, and visualize data. They apply mathematical and statistical models
to find patterns and solutions in the data.
Analysis
Mathematical Scientific
and statistical tools and
models methods
Domain Expertise and Scientific Methods
Data analysis helps to extract insights from data to make better business decisions.
Data analysis can be:
• Descriptive: Study a dataset to decipher the
details
• Predictive: Create a model based on existing
information to predict outcome and behavior
• Prescriptive: Suggest actions for a given situation
using the collected information
Data Processing and Analytics
Modern tools and technologies have made data processing and analytics faster and more efficient.
Technology
Operating system
Python Application
language design
Data processing Library
tools
Data Processing and Analytics
These technologies help data scientists to:
• Build and train machine learning models
• Manipulate data with technology
• Build data tools, applications, and services
• Extract information from data
Applications of Data Science
Different Sectors Using Data Science
Various sectors use data science to extract the information they need to create different services and products.
Using Data Science: Social Network Platforms
LinkedIn uses data points from its users to provide relevant digital services and data products.
Profile
Groups
Digital
Location
Services
Information
Data Points
Connections
Data
Products
Post
Likes
Using Data Science: Search Engines
Google uses data science to provide relevant search recommendations as the user types a query.
Search keyword
Autocomplete feature is fed by data models (Machine
Learning)
Influencing Factors
Fast and real-time analytics is made
possible by modern and advanced • Query volume – Unique and verifiable users
infrastructure, tools, and technologies • Geographical locations
• Keyword or phrase matches on the web
• Scrubbing for inappropriate content
Using Data Science: Healthcare
Wearable devices use data science to analyze data gathered by their biometric sensors.
Biometric data Data transfer Enterprise
IoT gateway
transfer to servers infrastructure
Wearable device
Make informed Engagement
decisions dashboard Data analytics
Using Data Science: Finance
A loan manager can easily access and sift through a loan applicant’s financial details using data science.
Data transfer to Enterprise
Loan application Servers infrastructure
portal
Loan applicant
Credit report, credit
Engagement
history, approved
Make informed amount, and risk. dashboard
decisions Data analytics
Using Data Science: Public Sector
Governments in different countries share large datasets from various domains with the public.
Data.gov is a website hosted and maintained by the U.S. government.
Large collection of datasets
Sectors or domains
The Real Challenge
Some of the challenges data scientists face in the real
world are:
• Data quality doesn’t conform to the set standards.
• Data integration is a complex task.
• Data is distributed into large clusters in HDFS, which
is difficult to integrate and analyze.
• Unstructured and semi-structured data are harder to
analyze.
Python
Data Analytics and Python
Python deals with each stage of data analytics efficiently by applying different libraries and packages.
Acquire
Wrangle
Explore
Model
Data analytics Visualize
Bokeh
Python Tools and Technologies
Python is a general-purpose, open-source programming language that lets you work quickly
and integrate systems more effectively.
Benefits of Python
Easy
Easy to
to learn
learn
Open source
Efficient and multi-platform
multi platform
support
Huge collection of libraries,
functions,
functions and
and modules
modules
Big open-source
open source community
Integrates well with enterprise
apps and systems
Great vendor and product support
Big Data Platforms and Processing Frameworks for Python
Python is supported by well-established data platforms and processing frameworks that help
analyze data in a simple and efficient way.
Data Scientist
Python Tool for data analysis and processing
Big Data Processing Framework
Enterprise Big Data
Platform
Big Data
Knowledge Check
Knowledge
Check
A data scientist _____.
1
A. Asks the right questions
B. Acquires data
C. Performs data wrangling and data visualization
D. All of the above
Knowledge
Check
A data scientist _____.
1
A. Asks the right questions
B. Acquires data
C. Performs data wrangling and data visualization
D. All of the above
The correct answer is D
A data scientist asks the right questions to the stakeholders, acquires data from various sources and data points,
performs data wrangling that makes the data available for analysis, and creates reports and plots for data
visualization.
Knowledge
Check The search engine’s autocomplete feature identifies unique and verifiable users who
2 search for a particular keyword or phrase to_____. Select all that apply.
A. Scrub inappropriate content
B. Build a query volume
C. Tag the location to a query
D. Find similar instances on the web
Knowledge
Check The search engine’s autocomplete feature identifies unique and verifiable users who
2 search for a particular keyword or phrase to_____. Select all that apply.
A. Scrub inappropriate content
B. Build a query volume
C. Tag the location to a query
D. Find similar instances on the web
The correct answer is B, C
The search engine’s autocomplete feature identifies unique and verifiable users who search for a particular
keyword or phrase to build a query volume. It also helps identify the users’ locations and tags them with the query,
enabling it to be location-specific.
Knowledge
Check
What is the sequential flow of analysis in data science?
3
A. Data wrangling, exploration, modeling, acquisition, and visualization
B. Data exploration, acquisition, modeling, wrangling, and visualization
C. Data exploration, acquisition, modeling, wrangling, and visualization
D. Data modeling, acquisition, exploration, wrangling, and visualization
Knowledge
Check
What is the sequential flow of analysis in data science?
3
A. Data wrangling, exploration, modeling, acquisition, and visualization
B. Data exploration, acquisition, modeling, wrangling, and visualization
C. Data exploration, acquisition, modeling, wrangling, and visualization
D. Data modeling, acquisition, exploration, wrangling, and visualization
The correct answer is C
In data science, the data is acquired from various sources and is then wrangled to ease its analysis. This is followed
by data exploration and data modeling. The final stage is data visualization, where the data is presented and the
patterns are identified.
Key Takeaways
Data science is an approach that combines the aspects of
statistics, mathematics, programming, and visualization for
analyzing data to derive information and insights from it
that are used in a variety of application domains.
Data scientists use data analysis and analytics to perform
tasks such as extracting information from data, building and
training machine learning models, and developing data
tools and applications.
Data science is used in a variety of fields, including analysis,
mathematical and statistical modeling, and financial
planning.
Python is a versatile programming language with a wide
number of libraries and packages that can help with each
stage of data analytics and can be integrated with a variety
of systems.