Data Science

Data
Data is the raw facts or figure. Data is divided into the three categories.
1. Structured Data

• A well-organized data in the form of tables on which the work can be done easily.
• In this type of data, searching and accessing an information is very easy.
• Example: Data presented in spreadsheet.

2. Unstructured Data

• It requires advance tools and software’s to access an information.
• Example: Pdf files, word document, audio, video, emails.

3. Semi-Structured Data

• It is a structured data which is un-organised.
• Example: Web data such JSON (JavaScript Object Notation) files, BibTex files.

What is Data Science and Data Scientist?

• Data Science is a field which extract the knowledge and insights from the raw data; by using Maths,Statistics, Computer Science and Programming Language knowledge. And the person who has these skills are called as Data Scientist.
• Data scientist is about being curious, self-driven, and passionate about finding the answers.

What a Data Scientist do?

• Surfacing the hidden insight which can help companies to make smarter business decisions. 
• Data scientist works in various domain such as shipping, healthcare, e-commerce, aviation, finance, education.

How Data Scientist works?
Data Scientist start their work by understanding the business problem and then works with the collection of data, reading - transforming the data in the required format, then visualizing, modelling, evaluating the model and deployment.

Real world use cases of Data Science
Data Science is applied to many problems to predict and calculate the outcomes that would have taken several times more human hours to process.
Real-world examples where Data Scientists are playing a major key role:

• Google’s AI research arm to build the best performing algorithm to detect the object automatically.
• Amazon to personalize their product.
• You tube to automated video classification model.
• Netflix to understand the user’s interest and then produce Netflix original series to produce.

Why Python language is used for Data Science?

• Python is very beginner-friendly language.
• Its syntax is simple to read and follow.
• It supports object-oriented programming, structured programming, and functional programming patterns.
• It is free, open-source software, and consequently anyone can write a library package to extend its functionality.

Artificial Intelligence

 

 

• Term Artificial Intelligence (AI) was first coined by, John McCarthy in 1956.
• Artificial Intelligence is the creation of machines to impersonate the human capabilities.
• AI systems have been used for creating solutions for individuals and society.
• Main areas where AI has made the most possible advancements are:
  • To see
  • To communicate
  • To move
  • To think

 

 Areas where AI is used

• Music and Media: Apps like Spotify, Netflix, or YouTube.  
• Smart Home Devices: To adjust the house temperature and lighting based on the preferences.
• Smart phones: Features like face detection, virtual reality elements, photo editor.
• Social Media Feeds: Feeds that you see in your timeline along with the notifications.
• Video Games: Game such as PUBG or Fortnite.
• Navigation and Travel: Google Maps.
• Security and Surveillance: Object recognition and facial recognition.  

 

Gamification

 Gamification is the process of adding the game-like components to a task as to encourage the user participation.  

 

 Natural Language Processing

Technology with which the machine understands the human language and then perform an action based on the command. 

 

Computer Vision

 Computer Vision is concerned with both the theory and technology for building up an Artificial system which obtain information from images.

 

Smart Home

A home which one can managed remotely to control the appliances such as TV, AC, fridge with smartphone.

Google Home

A smart speaker which is a Google device and can be integrated with the automation to control home appliances with voice recognition by using internet.

Smart City

Smart City is an urban city which uses Internet of Things (IoT) to collect the data and information to improve the quality of government services easily and effectively.

 

AI Ethics

AI Ethics is the study of values and generating moral values for good or bad, right or wrong.

Robot ethics/ Roboethics

Robot ethics can be defined as the Morality of how humans’ constructs, design, use and treat the robots and the other artificially intelligent created beings.

Machine Learning bias/ AI bias

A phenomenon which occurs when an algorithm produces a discriminatory result due to incorrect assumptions.

 

 

 

 

 

Python

• A high-level programming language
• Created by Guido Van Rossum (Benevolent Dictator for Life)
• First released in 1991
• Python interpreters are available for many Operating Systems

Why Python is popular:

• It is free to use and distribute
• Its code is readable, reusable and maintainable
• Its program runs on every major platform which is currently in use
• It has strong library support from Text pattern matching to networking
• It can communicate with COM, .NET frameworks

Python is powerful as:

• It allows dynamic typing and has powerful library  
• No need to declare variable
• It allows automatic allocation and garbage collection
• It supports classes, modules and exceptions
• It gives interactive programming experience

Python is used for:

• System programming
• Building GUI applications
• Internet scripting
• Database programming
• Game, Robotics programming

Some organizations which uses Python:

• Google: for web search system
• YouTube: for video sharing service
• JP Morgan, Chase, UBS: for financial market forecasting
• NASA, FermiLab: for scientific programming
• NSA: for cryptographic and intelligence analysis

You can get Python source code, binaries and documentation:

• Python official website: www.python.org
• Documentation website: www.python.org/doc

Once the Python is installed, the program development can be done by using the built-in Python Integrated Development and Learning Environment (IDLE).

In case, if you have not install any Python development tool on your machine, you can use the online Python shells. Some of the online Python shells are:

• https://www.python.org/shell/
• https://ideone.com/
• https://repl.it/languages/python3

 

Selenium

Selenium is an open source functional testing tool for web applications. It was created by Jason Huggins, earlier it was known as JavaScriptTestRunner and is used to test an internal time and expense application.

Later, it was released to the open source community as Selenium. It was named as Selenium because it overcame the shortcomings of another competitor.

 Selenium is popular because:

• It supports multiple programming languages.
• It supports automation of multiple browsers.
• It supports multiple operating systems.
• It is available free of cost.

Components of Selenium

• Selenium IDE: It is a tool used for recording and playing back scripts.
• Selenium RC: It is a combination of a Selenium server and a client, which allowed automation of any browser on any operating system.
• Selenium WebDriver: It uses the technology of WebDriver API, where every browser has the capability through its API to automate itself.  It is the main component of Selenium.
• Selenium Grid: It uses server component from the Selenium RC and executes it in two different modes as hub and node.

Architecture of Selenium

Selenium has four main components:

1. The client libraries (available in different programming languages)
2. JSON wire protocol over HTTP for communication to send commands from client to server
3. WebDriver for every browser
4. Browsers (Chrome, Firefox, IE, Opera)

How it works

Client libraries are available in different programming languages. Scripts are created by using client libraries and then the commands are send to the WebDriver server by using the JSON wire protocol over HTTP. The WebDriver then, for each individual browser receives these commands and automates the browser and performs action on them, this will lead to achieve the task.

 

Pencil Software

Pencil software is free and an open source animation software, which provides a versatile and an easy way to create graphics and animations. Pencil software can scale the animations and graphics created to any size without losing the clarity or quality.

To start Pencil software:

1. Click on the dash icon.
2. Type pencil in the search bar.
3. Application icon will appear, click on it.
4. A blank file as shown below will appear:

It has the following parts:

• Title Bar: It displays the application name and the file name in which you are working. It also displays the close, minimize and maximize buttons on its left side.
• Menu Bar: It contains controls for common functions and commands (File, Edit, View, Animation, Tool, Layer, Windows, Help).
• Stage: It is a rectangular area where we place the content or create drawings or movies.
• Tools Palette: It contains a set of tools used to draw, paint, select and modify the object in the workspace.
• Options Palette: It contains options such as Colour, size and Feather.
• Display Palette: It is present below the options palette, which includes the options such as horizontal flip, show invisible lines.
• Timeline Palette: It is a fixed window which stays at the bottom of the workspace. In this area the graphics and elements are assembled in a sequential order allowing the user to control the order of events in sequence.
• Colours Palette: It is available on the right side of the stage. It displays various colours for the selection.

Edubuntu/Ubuntu

Computer is a machine which requires instructions from the user to work.  Most important part of a computer is the Operating System which is a medium through which user interacts with the hardware, by using software. It controls all the activities of the computer. Example of operating system are: Microsoft Windows, Linux, and so on.

Introduction to Edubuntu/Ubuntu

Ubuntu is a Linux-based operating system, designed for computers, smartphones, and network servers. System is developed by UK based company called Canonical Ltd. Principles used to develop Ubuntu software are based on the principles of Open Source software development. It is free of cost available for individual community and

professional use. 

Ubuntu Desktop

Edubuntu/Ubuntu is a Graphical user Interface (GUI) called as Unity, which allows user to interact with the computer system by using graphical icons. Edubuntu/Ubuntu is considered as one of the best available free software backed up by a huge open source community.

Features:

1.  Attractive and Easy to use:Edubuntu/Ubuntu has a very attractive appearance with colourful themes due to its graphical icons it makes Edubuntu/Ubuntu interactive and user friendly.
2.  Searching made easier:Dash icon allow us to quickly search and open the applications, files and folder stored in our computer. Smart searching facility made easier for user to search the content.
3. Safe and Secure: Edubuntu/Ubuntu is much more safer than Windows operating system against virus and hacking attacks.
4. Freely available:  Edubuntu/Ubuntu is available free of cost.
5. Multitasking: Edubuntu/Ubuntu can perform multiple task at a time.
6. Educational software: Edubuntu/Ubuntu includes a large number of educational software like GCompris, LibreOffice.
7. Desktop version of Edubuntu/Ubuntu supports all the normal software on windows such as Firefox, Chrome, VLC, and so on.
8. It supports the office suite called as LibreOffice.
9. Inbuilt email software: Edubuntu/Ubuntu has in-built email software called Thunderbird, which give user an access to email; such as: Exchange, Gmail, Hotmail.
10. Host of free applications are available for user to view and edit photos, to manage and share videos.
11.  Software tools can be usable by people in their local language.

System Requirement

Make sure that the following system requirements are met before starting an instalment:

Memory	2GB RAM
Disk Space	25 GB of free hard disk space
Processor	2 GHz dual core processor
	DVD drive or USB drive with the Installer media
	An Internet connection

Artificial intelligence (AI) / Machine intelligence

Artificial Intelligence is an intelligence which is demonstrated by machines, in contrast to the natural intelligence which is displayed by humans. Artificial intelligence is used to describe machines which mimic "cognitive" functions which humans associate with the human mind.

By the time, as machines get increasingly capable and the tasks considered to require "intelligence" are often removed from the definition of Artificial intelligence (AI), a phenomenon known as the AI effect.

Artificial intelligence (AI) is a transformational technology, powering a change throughout the world. AI is disrupting everything in our lives and embedded in the new disruptive technology is INTELLIGENCE.

Consider an Example: If you search on the goggle to find the cheapest flight form Delhi to Mumbai, then you are using AI-enabled Google’s flight search engine; which uses a large amount of data through machine learning and computer vision.

Artificial Intelligence, with its sub sets of Machine Learning, Deep Learning, Neural Networks, Pattern Recognition, Natural Language Processing, Virtual and Augmented reality, Robotics, coupled with other new technologies like Internet of Things (IoT), Blockchain Technology and 3D Printing is revolutionizing the businesses and societies.

Classification of Artificial intelligence: 

a.     Analytical AI (cognitive representation of the world and learning is based on the past experience to inform future decisions)

b.     Human-inspired AI (understanding human emotions, and take cognitive elements along with human emotions while taking decision making.)

c.     Humanized artificial intelligence (shows characteristics of all types of competencies such as cognitive, emotional, and social intelligence)

Subfields of AI research:

·      Robotics

·      Machine learning

·      Artificial neural networks

Traditional goals of AI:

·      Reasoning

·      Knowledge representation

·      Panning

·      Learning

·      Natural language processing

·      Perception

AI Approaches include:

·      Statistical methods

·      Computational intelligence

·      Traditional symbolic 

Tools used in AI include:

·      Search and mathematical optimization

·      Artificial neural networks

·      Methods based on statistics, probability and economics

The AI field draws upon:

·      Computer science

·      Information engineering

·      Mathematics

·      Psychology

·      Linguistics

·      Philosophy

Why Artificial Intelligence field was founded?

 To claim that the human intelligence can precisely be described so that the a machine can be made to simulate it.