independent study final report v4cis.csuohio.edu/~sschung/cis430... · ·...

Nicholas J White April 24th, 2016 | nickwhite.us

INDEPENDENT STUDY Just how much can be learned in a semester under Dr. Chung’s guidance

CONTENTS Introduction 6

Why I requested an independent study (Beginning of Semester) 6

Why I am glad I requested an independent study (End of Semester) 8

Mission Statement and Goals 9

Course Mission Statement 9

Course Goals and Expected Outcomes 9

Introduction 10

Coursera Online Courses 11

Introduction to Coursera 11

My Coursework for This Semester 12

Introduction to Specializations 12

Specializations 12

Data Warehousing and Business Intelligence Specialization 13

Machine Learning Specialization 14

Data Mining Specialization 16

Data Science Specialization 18

Algorithms Specialization 20

CIS 611 Selected Course Materials 23

Introduction to CIS 611 Course Materials 23

eDx Online Courses 24

Introduction to eDx 24

Additional Coursework 25

Introduction to Additional Coursework 25

Coursera Online Courses 26

Data Warehousing and Business Intelligence Specialization 26

Course 1: Database Management Essentials 27

Course 2: Data Warehouse Concepts, Design, and Data Integration 39

Course 3: Relational Database Support for Data Warehouses 46

Course 4: Business Intelligence Concepts, Tools, and Applications 52

Project: Design and Build a Data Warehouse for Business Intelligence Implementation 58

Machine Learning Specialization 65

Course 1: Machine Learning Foundations: A Case Study Approach 65

Course 2: Machine Learning: Regression 73

Course 3: Machine Learning: Classification 83

Course 4: Machine Learning: Clustering & Retrieval 93

Course 5: Machine Learning: Recommender Systems & Dimensionality Reduction 94

Data Mining Specialization 94

Course 1: Data Visualization 94

Course 2: Text Retrieval and Search Engines 98

Course 3: Text Mining and Analytics 98

Course 4: Pattern Discovery in Data Mining 99

Course 5: Cluster Analysis in Data Mining 99

Data Science Specialization 100

Course 1: The Data Scientist’s Toolbox 100

Course 2: R Programming 102

Course 3: Getting and Cleaning Data 107

Course 4: Exploratory Data Analysis 109

Course 5: Reproducible Research 111

Course 6: Statistical Inference 114

Course 7: Regression Models 118

Course 8: Practical Machine Learning 122

Algorithms Specialization 125

Course 1: Algorithmic Toolbox 125

Course 2: Data Structures 130

Course 3: Algorithms on Graphs 135

Course 4: Algorithms on Strings 136

Couse 5: Advanced Algorithms and Complexity 136

CIS 611 Selected Course Materials 137

Database Normalization 137

Indexes 137

Functional Dependency 137

Storage and File System 137

eDx Online Courses 138

Course 1: Introduction to Data Storage and Management Technologies 138

Course 2: Introduction to Cloud Computing 140

Additional Coursework 144

SAC Application 144

Senior Design 144

Work Experience and Conclusion 145

COURSE OVERVIEW AND OBJECTIVES INTRODUCTION

WHY I REQUESTED AN INDEPENDENT STUDY (BEGINNING OF SEMESTER) I’ll start by saying that this year is my senior year at Cleveland State University, thus, I do not have

any motive or goal for writing this reflection of my independent study other than to give the

college of engineering a glimpse into the experience of a student, firsthand. Hopefully after

reading this, the reader will fully realize just how much of an impact a single professor can have

on a student’s life, career, and love of engineering. I’d also like to say that I plan on graduating

this semester, and so am not making an attempt to obtain a higher grade for this reflection. This is

purely for the edification of the reader, and so the administration and Dr. Chung know just how

much I sincerely appreciate all her hard work and effort this past year.

Last semester (Fall 2015) I took Database Systems (CIS 430) with Dr. Sun Chung. To many

undergraduate students, the topic of database systems is one which they do not immediately

associate with glamor, fame, or what is referred to as the “sexy” part of computer science. To be

entirely honest, I was one of these students. I was, at the time, working as a web application

developer for Parker Hannifin, specifically in front-end technologies. My interest in database

systems was, well, non-existent.

This course started me down a path that I am certain is going to be my specialization and career.

Enterprise database systems, data mining, big data, and all the other specialization under the

umbrella of database systems are what I find to be most interesting, challenging, and downright

cool, and this is all due to the foundation I received in Dr. Chung’s course. Dr. Chung brings to the

table a multitude of attributes which make her not only a remarkable professor, but an incredible

role model also. Her enthusiasm towards the topics she is professing, as well as towards her students

is unwavering.

While enrolled in CIS 430 I earned a position on Parker Hannifin’s Data and Business Intelligence

team working on building out their data warehouse. The only reason I was able to transition to this

team was the skills I learned from Dr. Chung in CIS 430, as well as the countless discussions we

would have after class regarding how I should best prepare myself for the transition (it is important

to note that Dr. Chung would often times stay 30, sometimes 40 minutes after class just to explain

a topic which we were not even covering in the course). To me, this is truly what it means to be

an engineering student. Until this time, I was unable to reach out to professors in this way, and so

my learning and appetite for knowledge was curbed.

With all this in mind, when I discovered that I could do an independent study, I may have actually

jumped for joy. Upon discussion with Dr. Chung, the topics to be discovered weren’t ones that

were arbitrarily picked, Dr. Chung (knowing her students and their aspirations) decided to put

together a curriculum for me that would change my career forever, and for the better.

WHY I AM GLAD I REQUESTED AN INDEPENDENT STUDY (END OF SEMESTER)

Having completed the semester of independent study, I now have a lot more to talk about with

regards to why I am glad I did indeed take this course. At the beginning of the semester, Dr. Chung

and I had discussions about where I was going in my career, and what I wanted to do (something

I have never talked to a professor about). With this in mind, she designed a custom curriculum for

me.

There are many reasons why one might perform better in an independent study setting than in a

classroom setting. Some individuals are better suited for independent learning. Some students

prefer to learn at times of the day where courses are not offered (at night, for example). Although

these statements are true, the reason I performed better in an independent study setting than in

any classroom I have been in at this university was the structure, guidance, and leadership put

forth by Dr. Chung. As you will see, we covered a humongous amount of area this semester, and

yes I used the word ‘humongous’ because we did cover MongoDB as well!

In closing, I hope you enjoy my coverage of what I have learned this semester. If you enjoy reading

it even 1% as much as I enjoyed actually doing it, we’ll both be very happy!

MISSION STATEMENT AND GOALS

COURSE MISSION STATEMENT The main driving forces behind the curriculum put forth by Dr. Chung were my new position on the

data warehousing team at Parker Hannifin, and the interest and passion Dr. Chung and I share for

the topic of database systems.

The mission statement for this course was to accomplish the following goals:

• Further my education in the field of data warehousing with a focus on practical work, as

well as the theory and principles behind it

• Expand my knowledge of the field to include the topics of

o Big data and cloud computing

o Machine learning and its role in the ecosystem

o Relational concepts as they pertain to data warehouses

• Determine which part of the field I am most interested in, and would like to pursue for my

master’s degree

COURSE GOALS AND EXPECTED OUTCOMES For this course, Dr. Chung combined several different learning techniques and mediums to form

the curriculum. The goals of this curriculum were to cover a wide range of topics, but to do so in

enough detail so that I can actually implement them.

The expected outcomes were twofold:

1. Know the theory behind each topic, and truly understand why we need the technology,

how we got to this point, where it is headed, and how it works on a highly technical level

2. Be able to implement each topic in a realistic setting. Knowing how something works is the

first step, the next step for each topic was to implement it

COURSEWORK OVERVIEW INTRODUCTION The actual coursework was chosen to cover all the objectives listed above, as well as to be

interesting and practical in nature. The major breakdown of the coursework is as follows.

Four different, and entirely separate sources of education were used for this independent study.

Details of each type will be covered in their respective ‘introduction’ sections, but as a high-level

overview, they fall into two categories.

The first category is online, or e-learning. I took several courses from top universities, all online. This

coursework was guided and supplemented by Dr. Chung’s knowledge when we met throughout

the semester. The point of the online coursework was to allow me to keep learning every day,

when we met only a few times a week. I was able to learn at, say, 9PM to 1AM every day, which

allowed me to cover a lot of ground between our meetings. This was immensely helpful.

The second category is learning with Dr. Chung, facilitated in person. The topics covered were

more in-depth than the online courses, and will be covered in detail in the following sections.

COURSERA ONLINE COURSES

INTRODUCTION TO COURSERA

Coursera is an online learning platform designed to teach technical topics. The site is laid out in

the following manner. The site allows the student to pick from a list of specializations. These

specializations are, for example, Big Data, Data Science, Full Stack Web Development, etc. They

are large topics, or domains of knowledge which contain courses. Each course contains its

contents, which are broken down into weeks. Each week builds on the previous week, and usually

covers an entire section of a technology or topic. For example, a week was spent installing and

configuring Pentaho Data Warehouse and Integration tools, in addition to learning about them.

MY COURSEWORK FOR THIS SEMESTER

INTRODUCTION TO SPECIALIZATIONS

Coursera specializations are aimed at taking the student from introductory knowledge in a

particular domain, to being able to implement advanced solutions in said domain.

SPECIALIZATIONS

Over the course of this semester, I have completed five specializations. These specializations

pertain to my field, and the direction in which I want my career to go.

They are described as follows.

DATA WAREHOUSING AND BUSINESS INTELLIGENCE SPECIALIZATION

The data warehousing specialization was a natural fit for this semester’s study. Since I am actively

working on building out a data warehouse, it makes sense to study the topic in detail, and learn

from Dr. Chung with regards to the topic. The Coursera specialization covers data architecture

skills that are increasingly critical across a broad range of technology fields. It is intended to teach

the basics of structured data modeling, practical SQL coding experience, and to develop an in-

depth understanding of data warehouse design and data manipulation. I had the opportunity to

work with large data sets in a data warehouse environment to create dashboards and Visual

Analytics. I used Pentaho, a leading BI tool, OLAP (online analytical processing) and Visual Insights

capabilities to create dashboards and Visual Analytics. In the final Capstone Project, I applied my

skills to build a small, basic data warehouse, populate it with data, and create dashboards and

other visualizations to analyze and communicate the data to an audience (Dr. Chung).

MACHINE LEARNING SPECIALIZATION

This specialization provides a case-based introduction to the exciting, high-demand field of

machine learning. I learned to analyze large and complex datasets, build applications that can

make predictions from data, and create systems that adapt and improve over time. In the final

Capstone Project, I applied my skills to solve an original, real-world problem through

implementation of machine learning algorithms.

DATA MINING SPECIALIZATION

This specialization teaches data mining techniques for both structured data which conform to a

clearly defined schema, and unstructured data which exist in the form of natural language text.

Specific course topics include pattern discovery, clustering, text retrieval, text mining and

analytics, and data visualization. The Capstone project task is to solve real-world data mining

challenges using a restaurant review data set from Yelp.

DATA SCIENCE SPECIALIZATION

This Specialization covers the concepts and tools I need throughout the entire data science

pipeline, from asking the right kinds of questions to making inferences and publishing results. In the

final Capstone Project, I applied the skills learned by building a data product using real-world

data.

ALGORITHMS SPECIALIZATION

The Specialization covers algorithmic techniques for solving problems arising in computer science

applications. It is a mix of theory and practice: I did not only design algorithms and estimate their

complexity, but I also gained a deeper understanding of algorithms by implementing them in the

programming language of my choice (C, C++, C#, Haskell, Java, JavaScript, Python3, Ruby, and

Scala).

This Specialization is unique, because I had a choice between two Capstone Projects, developed

in partnership with industry leaders. In the Shortest Paths Capstone, I dealt with road network

analysis and social network analysis. I learned how to compute the fastest route between New

York and Mountain View thousands of times faster than classic algorithms and close to those used

in Google Maps. I did not complete the Bioinformatics Capstone.

CIS 611 SELECTED COURSE MATERIALS INTRODUCTION TO CIS 611 COURSE MATERIALS

CIS 611 is a graduate course highly focused on MPP and data warehousing. Because of my interest

in these topics, and the fact that I am starting my career in database systems, Dr. Chung chose

to take topics from CIS 611 and teach them to me. The topics were more advanced than most of

the coursework online, and this was possible I was being taught in person, and not though a web

browser. The ability to ask questions in real-time was invaluable as the topics became more and

more complex.

The topics covered included:

• Database normalization

• Indexes

• Functional Dependency

• Storage, File System, and physical layer of databases

EDX ONLINE COURSES INTRODUCTION TO EDX

eDx is an online learning site dedicated to providing technical learning to students, irrespective of

their background. Some of the best schools from around the country provide education through

the site, and their courses are technical. Dr. Chung and I chose two courses for me to take from

this site to supplement my learning. Details of these courses can be found in their section.

ADDITIONAL COURSEWORK INTRODUCTION TO ADDITIONAL COURSEWORK

In addition to the materials I covered this semester, I also did two major projects which I would like

to share. These projects utilized the skills I learned from Dr. Chung, and will be described in detail

in the later sections. One of these projects was my senior design project, which placed first in the

college of engineering. The second project is a full stack web application I built for the student

chapter of the IEEE at CSU. This app utilized HTML5, CSS3, JavaScript, Angular, ASP.NET MVC 4, SQL

Server, and MongoDB.

COURSEWORK COMPLETED THIS SEMESTER COURSERA ONLINE COURSES

DATA WAREHOUSING AND BUSINESS INTELLIGENCE SPECIALIZATION

COURSE 1: DATABASE MANAGEMENT ESSENTIALS

I completed all the assignments for this course, installed all relevant software and became

proficient in its use. This course taught me how to work with Oracle, MySQL, and Microsoft SQL

Server databases on a local machine. I installed, configured, and managed these databases

throughout all the labs.

Course Syllabus and what I covered:

WEEK 1

Course Introduction Description: Module 1 provided the context for Database Management Essentials. When you’re done, you’ll understand the objectives for the course and know what topics and assignments to expect. Keeping these course objectives in mind will help you succeed throughout the course! You should read about the database software requirements in the last lesson of module 1. I recommend that you try to install the DBMS software this week before assignments begin in week 2.

Video · Specialization Introduction video lesson

Video · Course introduction video lecture

Video · Course objectives video lecture

Reading · Powerpoint lecture notes for lesson 1

Video · Topics and assignments video lecture


Reading · Optional textbook

Reading · Overview of database management software requirements

Reading · Oracle installation notes

Reading · Making a connection to a database on a local Oracle server

Introduction to Databases and DBMS Description: We’ll launch into an exploration of databases and database technology and their impact on organizations in Module 2. We’ll investigate database characteristics, database technology features, including non-procedural access, two key processing environments, and an evolution of the database software industry. This short informational module will ensure that we all have the same background and context, which is critical for success in the later modules that emphasize details and hands-on skills.

Video · Database characteristics video lecture

Reading · Powerpoint lecture notes for lesson 1 and extras

Video · Organizational Roles video lecture


Video · DBMS overview and database definition feature video lecture


Video · Non-procedural access video lecture


Video · Transaction processing overview video lecture


Video · Data warehouse processing overview video lecture


Video · DBMS technology evolution video lecture


Quiz · Module02 Quiz

Reading · Optional reading

WEEK 2

Relational Data Model and the CREATE TABLE Statement Description: Now that you have the informational context for database features and environments, you’ll start building! In this module, you’ll learn relational data model terminology, integrity rules, and the CREATE TABLE statement. You’ll apply what you’ve learned in practice and graded problems using a database management system (DBMS), either Oracle or MySQL, creating tables using the SQL CREATE TABLE statement and populating your tables using given SQL INSERT statements.

Video · Basics of relational databases video lecture


Video · Integrity rules video lecture


Video · Basic SQL CREATE TABLE statement video lecture


Video · Integrity constraint syntax video lecture


Video · Assignment 1 Notes video lecture



Reading · DBMS installation and configuration notes

Reading · Practice Problems for Module 3

Practice Quiz · Quiz for Module 3 practice problems

Reading · Extra Problems for Module 3

Reading · Assignment for Module 3

Peer Review · Module 3 Assignment

WEEK 3

Basic Query Formulation with SQL Description: This module is all about acquiring query formulation skills. Now that you know the relational data model and have basic skills with the CREATE TABLE statement, we can cover basic syntax of the SQL SELECT statement and the join operator for combining tables. SELECT statement examples are presented for single table conditions, join operations, and grouping operations. You’ll practice writing simple SELECT statements using the tables that you created in the assignment for module 3.

Video · SQL Overview video lecture


Video · SELECT statement introduction video lecture


Video · Join Operator video lecture


Video · Using Join operations in SQL SELECT statements video lecture


Video · GROUP BY clause video lecture



Practice Quiz · Quiz for Module 4 Practice Problems






Extended Query Formulation with SQL Description: Now that you can identify and use the SELECT statement and the join operator, you’ll extend your problem solving skills in this module so you can gain confidence on more complex queries. You will work on retrieval problems with multiple tables and grouping. In addition, you’ll learn to use the UNION operator in the SQL SELECT statement and write SQL modification statements.

Video · Query formulation guidelines video lecture


Video · Multiple table problems video lecture


Video · Problems involving join and grouping operations video lecture


Video · SQL set operators video lecture


Video · SQL modification statements video lecture


Reading · Optional textbook reading material



Practice Quiz · Quiz for Module 5 Practice Problems




WEEK 4

Notation for Entity Relationship Diagrams Description: Module 6 represents another shift in your learning. In previous modules, you’ve created and populated tables and developed query formulation skills using the SQL SELECT statement. Now you’ll start to develop skills that allow you to create a database design to support business requirements. You’ll learn basic notation used in entity relationship diagrams (ERDs), a graphical notation for data modeling. You will create simple ERDs using basic diagram symbols and relationship variations to start developing your data modeling skills.

Video · Database development goals video lecture


Video · Basic ERD notation video lecture


Video · Relationship variations I video lecture


Video · Relationship variations II video lecture






ERD Rules and Problem Solving Description: Module 7 builds on your knowledge of database development using basic ERD symbols and relationship variations. We’ll be practicing precise usage of ERD notation and basic problem solving skills. You will learn about diagram rules and work problems to help you gain confidence using and creating ERDs.

Video · Basic diagram rules video lecture


Video · Extended diagram rules video lecture


Video · ERD problems I video lecture


Video · ERD problems II video lecture


Video · ER Assistant Demonstration video

Reading · ER Assistant download





WEEK 5

Developing Business Data Models Description: In Module 8, you’ll use your ERD notation skills and your ability to avoid diagram errors to develop ERDs that satisfy specific business data requirements. You will learn and practice powerful problem-solving skills as you analyze narrative statements and transformations to generate alternative ERDs.

Video · Conceptual data modeling goals and challenges


Video · Analyzing narrative problems


Video · Design transformations I


Video · Design transformations II video lecture






Data Modeling Problems and Completion of an ERD Description: Now that you have practiced data modeling techniques, you’ll get to wrestle with narrative problem analyses and transformations for generating alternative database designs in Module 9. At the end of this module, you’ll learn guidelines for documentation and detection of design errors that will serve you well as you design databases for business situations.

Video · Data modeling problems I video lecture


Video · Data modeling problems II video lecture


Video · Finalizing an ERD video lecture






WEEK 6

Schema Conversion Description: Modules 6 to 9 covered conceptual data modeling, emphasizing precise usage of ERD notation, analysis of narrative problems, and generation of alternative designs. Modules 10 and 11 cover logical database design, the next step in the database development process. In Module 10, we’ll cover schema conversion, the first step in the logical database design phase. You will learn to convert an ERD into a table design that can be implemented on a relational DBMS.

Video · Goals and steps of logical database design video lecture


Video · Conversion rules video lecture


Video · Conversion problems video lecture






WEEK 7

Normalization Concepts and Practice

Module 11 covers normalization, the second part of the logical database design process. Normalization provides tools to remove unwanted redundancy in a table design. You’ll discover the motivation for normalization, constraints to reason about unwanted redundancy, and rules that detect excessive redundancy in a table design. You’ll practice integrating and applying normalization techniques in the final lesson of this course.

Video · Modification anomalies video lecture


Video · Functional dependencies video lecture


Video · Normal forms video lecture


Video · Practical concerns video lecture


Video · Normalization problems video lecture


Video · Course Conclusion

Reading · Optional textbook reading materials




COURSE 2: DATA WAREHOUSE CONCEPTS, DESIGN, AND DATA INTEGRATION

Description:

This is the second course in the Data Warehousing for Business Intelligence specialization. Ideally, the courses should be taken in sequence. In this course, you will learn exciting concepts and skills for designing data warehouses and creating data integration workflows. These are fundamental skills for data warehouse developers and administrators. You will have hands-on experience for data warehouse design and use open source products for manipulating pivot tables and creating data integration workflows. You will also gain conceptual background about maturity models, architectures, multidimensional models, and management practices, providing an organizational perspective about data warehouse development. If you are currently a business or information technology professional and want to become a data warehouse designer or administrator, this course will give you the knowledge and skills to do that. By the end of the course, you will have the design experience, software background, and organizational context that prepares you to succeed with data warehouse development projects. In this course, you will create data warehouse designs and data integration workflows that satisfy the business intelligence needs of organizations. When you’re done with this course, you’ll be able to: * Evaluate an organization for data warehouse maturity and business architecture alignment; * Create a data warehouse design and reflect on alternative design methodologies and design goals; * Create data integration workflows using prominent open source software; * Reflect on the role of change data, refresh constraints, refresh frequency trade-offs, and data quality goals in data integration process design; and * Perform

operations on pivot tables to satisfy typical business analysis requests using prominent open source software

WEEK 1

Data Warehouse Concepts and Architectures Description: Module 1 introduces the course and covers concepts that provide a context for the remainder of this course. In the first two lessons, you’ll understand the objectives for the course and know what topics and assignments to expect. In the remaining lessons, you will learn about historical reasons for development of data warehouse technology, learning effects, business architectures, maturity models, project management issues, market trends, and employment opportunities. This informational module will ensure that you have the background for success in later modules that emphasize details and hands-on skills.You should also read about the software requirements in the lesson at the end of module 1. I recommend that you try to install the software this week before assignments begin in week 2.

Video · Course introduction video lecture



Video · Course topics and assignments video lecture



Video · Motivation and characteristics video lecture


Video · Learning effects for data warehouse development video lecture


Video · Data warehouse architectures and maturity video lecture


Video · Applications and market trends video lecture


Video · Employment opportunities video lecture


Reading · Overview of software requirements

Reading · Pivot4J installation

Reading · Pentaho Data Integration installation

Reading · Overview of database software installation


Reading · Making connections to a local Oracle database

Quiz · Module 1 quiz


WEEK 2

Multidimensional Data Representation and Manipulation Description: Now that you have the informational context for data warehouse development, you’ll start using data warehouse tools! In module 2, you will learn about the multidimensional representation of a data warehouse used by business analysts. You’ll apply what you’ve learned in practice and graded problems using Pivot4J, an open source tool for manipulating pivot tables. At the end of this module, you will have solid background to communicate and assist business analysts who use a multidimensional representation of a data warehouse.

Video · Data cube representation video lecture


Video · Data cube operators video lecture


Video · Overview of Microsoft MDX video lecture


Video · Microsoft MDX statements video lecture


Video · Overview of Pivot4J video lecture


Video · Overview of WebPivotTable video lecture


Video · Pivot4J software demonstration video lecture



Reading · Pentaho Pivot4J tutorial

Peer Review · Assignment for module 2

Quiz · Quiz for module 2 assignment

WEEK 3

Data Warehouse Design Practices and Methodologies Description: This module emphasizes data warehouse design skills. Now that you understand the multidimensional representation used by business analysts, you are ready to learn about data warehouse design using a relational database. In practice, the multidimensional representation used by business analysts must be derived from a data warehouse design using a relational DBMS.You will learn about design patterns, summarizability problems, and design methodologies. You will apply these concepts to mini case studies about data warehouse design. At the end of the module, you will have created data warehouse designs based on data sources and business needs of hypothetical organizations.

Video · Relational database concepts for multidimensional data video lecture


Video · Table design patterns video lecture


Video · Summarizability patterns for dimension tables video lecture


Video · Summarizability patterns for dimension-fact relationships video lecture


Video · Mini case for data warehouse design video lecture


Video · Data warehouse design methodologies video lecture



Reading · Practice problems for module 3



WEEK 4

Data Integration Concepts, Processes, and Techniques Description: Module 4 extends your background about data warehouse development. After learning about schema design concepts and practices, you are ready to learn about data integration processing to populate and refresh a data warehouse. The informational background in module 4 covers concepts about data sources, data integration processes, and techniques for pattern matching and inexact matching of text. Module 4 provides a context for the software skills that you will learn in module 5.

Video · Concepts of data integration processes video lecture


Video · Change data concepts video lecture


Video · Data cleaning tasks video lecture


Video · Pattern matching with regular expressions video lecture


Video · Matching and consolidation video lecture


Video · Quasi identifiers and distance functions for entity matching video lecture



Reading · Optional reading material

WEEK 5

Architectures, Features, and Details of Data Integration Tools Description: Module 5 extends your background about data integration from module 4. Module 5 covers architectures, features, and details about data integration tools to complement the conceptual background in module 4. You will learn about the features of two open source data integration tools, Talend Open Studio and Pentaho Data Integration. You will use Pentaho Data Integration in guided tutorial in preparation for a graded assignment involving Pentaho Data Integration.

Video · Architectures and marketplace video lecture


Video · Common features of data Integration tools video lecture


Video · Talend Open Studio video lecture


Video · Pentaho Data Integration video lecture


Video · Software video demonstration for Pentaho Data Integration


Reading · Optional reading material

Reading · Guided tutorial for Pentaho Data Integration

Reading · Documents for the module 5 assignment



Video · Course conclusion video lecture

COURSE 3: RELATIONAL DATABASE SUPPORT FOR DATA WAREHOUSES

Relational Database Support for Data Warehouses is the third course in the Data Warehousing for Business Intelligence specialization. In this course, you'll use analytical elements of SQL for answering business intelligence questions. You'll learn features of relational database management

systems for managing summary data commonly used in business intelligence reporting. Because of the importance and difficulty of managing implementations of data warehouses, we'll also delve into storage architectures, scalable parallel processing, data governance, and big data impacts.

WEEK 1

DBMS Extensions and Example Data Warehouses

Module 1 introduces the course and covers concepts that provide a context for the remainder of this course. In the first two lessons, you’ll understand the objectives for the course and know what topics and assignments to expect. In the remaining lessons, you will learn about DBMS extensions, a review of schema patterns, data warehouses used in practice problems and assignments, and examples of data warehouses in education and health care. This informational module will ensure that you have the background for success in later modules that emphasize details and hands-on skills.You should also read about the software requirements in the lesson at the end of module 1. I recommend that you try to install the Oracle software this week before assignments begin in week 2. If you have taken other courses in the specialization, you may already have installed the Oracle software.

Video · Course introduction video



Video · Course topics and assignments video lecture



Video · DBMS extensions video lecture


Video · Relational database schema patterns video lecture


Video · Colorado Education Data Warehouse video lecture


Video · Data warehouse standards in health care video lecture



Reading · Overview of database software installation


Reading · Making connections to a local Oracle database

Reading · SQL statements for Store Sales tables

Reading · SQL statements for Inventory tables



WEEK 2

SQL Subtotal Operators

Now that you have the informational context for relational database support of data warehouses, you’ll start using relational databases to write business intelligence queries! In module 2, you will learn an important extension of the SQL SELECT statement for subtotal operators. You’ll apply what you’ve learned in practice and graded problems using Oracle SQL for problems involving the CUBE, ROLLUP, and GROUPING SETS operators. Because the subtotal operators are part of the SQL standard, your learning will readily apply to other enterprise DBMSs. At the end of this module, you will have solid background to write queries using the SQL subtotal operators as a data warehouse analyst.

Video · GROUP BY clause review video lecture


Reading · Additional problems for lesson 1

Video · SQL CUBE operator video lecture



Video · SQL ROLLUP operator video lecture



Video · SQL GROUPING SETS operator video lecture



Video · Variations of subtotal operators video lecture





Reading · Assignment notes



WEEK 3

SQL Analytic Functions

After your experience using the SQL subtotal operators, you are ready to learn another important SQL extension for business intelligence applications. In module 3, you will learn about an extended processing model for SQL analytic functions that support common analysis in business intelligence applications. You’ll apply what you’ve learned in practice and graded problems using Oracle SQL for problems involving qualitative ranking of business units, window comparisons showing relationships of business units over time, and quantitative contributions showing performance thresholds and contributions of individual business units to a whole business. Because analytic functions are part of the SQL standard, your learning will apply to other enterprise DBMSs. At the end of this module, you will have solid background to write queries using the SQL analytic functions as a data warehouse analyst.

Video · Processing Model and Basic Syntax video lecture



Video · Extended Syntax and Ranking Functions video lecture



Video · Window Comparison I video lecture



Video · Window Comparisons II video lecture



Video · Functions for Ratio Comparisons video lecture








WEEK 4

Materialized View Processing and Design

After acquiring query formulation skills for development of business intelligence applications, you are ready to learn about DBMS extensions for efficient query execution. Business intelligence queries can use lots of resources so materialized view processing and design has become an important extension of DBMSs. In module 4, you will learn about an SQL statement for creating materialized views, processing requirements for materialized views, and rules for rewriting queries using materialized views. To gain insight about the complexity of query rewriting, you will practice rewriting queries using materialized views. To provide closure about relational database support for data warehouses, you will learn about about Oracle tools for data integration, the Oracle Data Integrator, along with two SQL statements useful for specific data integration tasks. After this module, you will have a solid background to use materialized views to improve query performance and deploy the Extraction, Loading, and Transformation approach for data integration as a data warehouse administrator or analyst.

Video · Background on traditional views video lecture



Video · Materialized view definition and processing video lecture



Video · Query Rewriting Rules video lecture


Video · Query Rewriting Examples video lecture



Video · Oracle Tools for Data Integration video lecture








WEEK 5

Physical Design and Governance

Module 5 finishes the course with a return to conceptual material about physical design technologies and data governance practices. You will learn about storage architectures, scalable parallel processing, big data issues, and data governance. After this module, you will have background about conceptual issues important for data warehouse administrators.

Video · Storage Architectures video lecture


Video · Scalable Parallel Processing Approaches video lecture


Video · Big data issues video lecture


Video · Data Governance video lecture




Video · Closing Lecture

COURSE 4: BUSINESS INTELLIGENCE CONCEPTS, TOOLS, AND APPLICATIONS

This is the fourth course in the Data Warehouse for Business Intelligence specialization. Ideally, the courses should be taken in sequence. In this course, you will gain the knowledge and skills for using data warehouses for business intelligence purposes and for working as a business intelligence developer. You’ll have the opportunity to work with large data sets in a data warehouse environment and will learn the use of MicroStrategy's Online Analytical Processing (OLAP) and Visualization capabilities to create visualizations and dashboards. The course gives an overview of how business intelligence technologies can support decision making across any number of business sectors. These technologies have had a profound impact on corporate strategy, performance, and competitiveness and broadly encompass decision support systems, business intelligence systems, and visual analytics. Modules are organized around the business intelligence concepts, tools, and applications, and the use of data warehouse for business reporting and online analytical processing, for creating visualizations and dashboards, and for business performance management and descriptive analytics.

WEEK 1

Decision Making and Decision Support Systems

Module 1 explains the role of computerized support for decision making and its importance. It starts by identifying the different types of decisions managers face, and the process through which they make decisions. It then focuses on decision making styles, the four stages of Simon’s decision making process, and common strategies and approaches of decision makers. In the next two lessons, you will learn the role of Decision Support Systems (DSS), understand its main components, the various DSS types and classification, and how DSS have changed over time. Finally, in lesson 4, we focus on how DSS supports each phase of decision making and summarize the evolution of DSS applications, and on how they have changed over time. I recommend that you go to Ready Made DSS sites and use some of DSS that are listed for various types of decisions. You will need to install MicroStrategy Desktop to analyze three stand-alone offline dashboards in a peer evaluated exercise.

Video · Course Introduction Video Lecture

Reading · Optional Text Book

Reading · Additional Resources - Course Overview

Video · Overview of Decision Making Video Lecture

Reading · Powerpoint and Lecture Notes for Lesson 1.1

Reading · Additional Resources Lesson 1.1

Video · Conceptual Foundations of Decision Making Video Lecture


Reading · Additional Resources Lesson 1.2

Reading · Periodicals

Video · Decision Support Systems Video Lecture


Reading · Additional Resources for Lesson 1.3

Reading · Additional Web Resources

Reading · Vendors and Software Companies

Video · Decision Making Support in Practice Video Lecture



Reading · Ready Made DSS Products and Services

Reading · MicroStrategy Desktop Software Download and Installtions Steps for PC and MAC

Reading · MicroStrategy Desktop Connections to Oracle VM on PC and MAC

Reading · MicroStrategy Desktop Welcome Training Video

Reading · Dashboards Demonstration Videos

Peer Review · Assignment for Module 1: Offline Dashboards with Advanced Visualizations

Practice Quiz · Module 1 Practice Quiz

WEEK 2

Business Intelligence Concepts and Platform Capabilities

Now that you understand the conceptual foundation of decision making and DSS, in module 2 we start by defining business intelligence (BI), BI architecture, and its components, and relate them to DSS. In lesson 2, you will learn the main components of BI platforms, their capabilities, and understand the competitive landscape of BI platforms. In lesson 3, you will learn the building blocks of business reports, the types of business reports, and the components and structure of business reporting systems . Finally in lesson 4, you will learn different types of OLAP and their applications, and comprehend the differences between OLAP and OLTP. You will need to use MicroStrategy Desktop to create effective and compelling data visualizations to analyze data and acquire insights into business practices in a peer evaluated exercise.

Video · BI Concepts Video Lecture



Reading · Training Video for Connecting Data in MicroStrategy Desktop

Video · BI Platform Capabilities Video Lecture



Video · Training Video for Microstrategy Desktop BI Capabilities

Video · Business Reporting Video Lecture



Reading · Training Videos for Connecting to Spreadsheets, Joining Datasets, and Data Blending in MicroStrategy Desktop

Video · BI OLAP Styles Video Lecture

Reading · Powerpoint and Lecture Notes for Lesson 2. 4


Reading · Training Video for Wrangling and Profiling Data in MicroStrategy


Peer Review · Assignment for Module 2: World Wide Carbon Emissions Scenario

Quiz · Modules 1 and 2 Graded Quiz #1

WEEK 3

Data Visualization and Dashboard Design

This module continues on the top job responsibilities of BI analysts by focusing on creating data visualizations and dashboards. You will first learn the importance of data visualization and different types of data that can be visually represented. You will then learn about the types of basic and composite charts. This will help you to determine which visualization is most effective to display data for a given data set, and to identify best practices for designing data visualizations. In lesson 3, you will learn the common characteristics of dashboard, the types of dashboards, and the list attributes of metrics usually included in dashboards. Finally in lesson 4, you will learn the guidelines for designing dashboard and the common pitfalls of dashboard design. You will need to use MicroStrategy Desktop Visual Insight to design a dashboard for a Financial Services company in a peer evaluated exercise.

Video · Data Visualization Video Lecture



Reading · Training Video for Visual Insight in MicroStrategy Desktop

Video · Data Visualization Guidlines and Pitfalls Video Lecture



Reading · Training Video for Exploring Data in MicroStrategy Desktop

Video · Comprehensive Training Video for Showing Data Visualization Steps

Video · Performance Dashboards Video Lecture



Reading · Training Videos for Creating Dashboard in MicroStrategy Desktop

Video · Dashboard Design Guidelines and Pitfalls Video Lecture



Reading · Training Video for Sharing a Dashboard in MicroStrategy Desktop

Video · Comprehensive Training Video for Creating Dashboard Using Advanced Visualization


Peer Review · Assignment for Module 3: Design Dashboard for a Financial Service Company

WEEK 4

Business Performance Management Systems

This module focuses on how BI is used for Business Performance Management (BPM). You will learn the main components of BPM as well as the four phases of BPM cycle and how organizations typically deploy BPM. In lesson 2, you will learn the purpose of Performance Measurement System and how organizations need to define the key performance indicators (KPIs) for their performance management system. In lesson 3, you will learn the four balanced scorecards perspectives and the differences between dashboards and scorecards. You will also be able to compare and contrast the benefits of using balanced scorecard versus using Six Sigma in a performance measurement system. Finally in lesson 4, you will learn the role of visual and business analytics (BA) in BI and how various forms of BA are supported in practice. At the end of the module, you will apply these concepts to create a dashboard, blend it with external data sets, and explore various visualization capabilities to find insights faster in a peer evaluated exercise.

Video · Business Performance Management Video Lecture



Reading · Training Videos for Enriching and Modeling Data with MicroStrategy

Video · Performance Measurement System Video Lecture



Reading · Training Videos for Connecting to MDX and Excel Files and Creating a Mashups in MicroStrategy Desktop

Video · Balanced Scorecards Versus Six Sigma Video Lecture



Video · Training Video for MicroStrategy Desktop Business Performance Analysis

Video · Business Analytics Video Lecture



Reading · Training Video for Connecting to Social Media Sources in MicroStrategy Desktop


Peer Review · Assignment for Module 4: Advanced Enterprise Data Discovery

WEEK 5

BI Maturity, Strategy, and Summative Project

Module 5 covers BI maturity and strategy. You will learn different levels of BI maturity, the factors that impact BI maturity within an organization, and the main challenges and the potential solutions for a pervasive BI maturity within an organization. The last lesson will focus on the critical success factors for implementing a BI strategy, BI framework, and BI implementation targets. Finally, in your summative project, you will use MicroStrategy visual analytics capabilities to analyze KPIs for a fast food company to find the causes for problems .

Video · BI Maturity Video Lecture



Peer Review · Summative Project: BPM For Blazin' Burger Fast Food Restaurant

Video · BI Strategy Video Lecture



Quiz · Modules 3, 4, and 5 Graded Quiz #2

Video · Course Closing Video

PROJECT: DESIGN AND BUILD A DATA WAREHOUSE FOR BUSINESS INTELLIGENCE

IMPLEMENTATION

Seen below is the data integration tool used for this project.

Below is the integration editor.

Below is the Pentaho data warehouse server and working OLAP Cube.

The capstone course, Design and Build a Data Warehouse for Business Intelligence Implementation, features a real-world case study that integrates your learning across all courses in

the specialization. In response to business requirements presented in a case study, you’ll design and build a small data warehouse, create data integration workflows to refresh the warehouse, write SQL statements to support analytical and summary query requirements, and use the MicroStrategy business intelligence platform to create dashboards and visualizations. In the first part of the capstone course, you’ll be introduced to a medium-sized firm, learning about their data warehouse and business intelligence requirements and existing data sources. You’ll first architect a warehouse schema and dimensional model for a small data warehouse. You’ll then create data integration workflows using Pentaho Data Integration to refresh your data warehouse. Next, you’ll write SQL statements for analytical query requirements and create materialized views to support summary data management. Finally, you will use MicroStrategy OLAP capabilities to gain insights into your data warehouse. In the completed project, you’ll have built a small data warehouse containing a schema design, data integration workflows, analytical queries, materialized views, dashboards and visualizations that you’ll be proud to show to your current and prospective employers.

WEEK 1

Course Overview

Module 1 introduces the objectives and topics in the course and provides background on the case and software requirements. The capstone course is organized around a realistic case study based on the business situation faced by CPI Card Group in 2015.

Video · Course introduction

Reading · Slides for lesson 1

Video · Course topics and assignments video lesson


Video · Executive interview


Reading · Background on CPI Card Group


Reading · Oracle database server installation

Reading · Pentaho Data Integration installation

Reading · Microstrategy Desktop installation

Reading · Database diagramming tools

WEEK 2

Data Warehouse Design

Module 2 presents the requirements of the first part of the case study involving data warehouse design. To provide a context for the case study, you can listen to an executive interview with a CPI Card Group executive.



Reading · Data warehouse design background


Peer Review · Data warehouse design assignment

Reading · Documents to review after the assignment

WEEK 3

Data Integration

Module 3 presents requirements for the second part of the case study involving data integration. To provide a context for the case study, you can listen to executive interviews with executives from CPI Card Group, First Bank, and Pinnacol Assurance.







Reading · Data integration background



Practice Quiz · Practice Quiz for module 5 assignment-Test DW

Quiz · Quiz for module 5 assignment-Production DW

WEEK 4

Analytical Queries and Summary Data Management

Module 4 presents requirements for the third part of the case study involving analytical queries and summary data management.

Video · Executive Interview with Kellyn Gorman of Oracle



Peer Review · Analytical Query Assignemnt

Reading · Solutions to challenge problems

WEEK 5

Data Visualization and Dashboard Design Requirements

Module 5 presents the data visualization and dashboard design requirements for the fourth part of the case study.

Video · Executive Interview with Matthew Caton of Data Source Consulting

Reading · Slides for executive interview with Matthew Caton

Video · Executive Interview with Tyler Wilson on BI Platform Capabilities at CPI Card Group

Reading · Capstone Project Data Visualizations and Dashboard Design Requirements

Reading · Earlier Assignments from Course 4

WEEK 6

Wrap Up and Project Submission

This is an extension of Module 5. The peer assessment from module 5 is moved to module 6 to give you more time completing the assignments in prior modules as well as for you to do your peer assessment in this module.

Video · Executive Interview with James Gualke on the State of BI Maturity and Strategy at PDC Energy

Reading · Background Information on Data Visualization and Dashboard Design

Peer Review · Data Visualization and Dashboard Design Assignment

Video · Course conclusion video lecture

MACHINE LEARNING SPECIALIZATION

COURSE 1: MACHINE LEARNING FOUNDATIONS: A CASE STUDY APPROACH

This first course treats the machine learning method as a black box. Using this abstraction, you will focus on understanding tasks of interest, matching these tasks to machine learning tools, and assessing the quality of the output. In subsequent courses, you will delve into the components of this black box by examining models and algorithms. Together, these pieces form the machine learning pipeline, which you will use in developing intelligent applications. Learning Outcomes: By the end of this course, you will be able to: -Identify potential applications of machine learning in practice. -Describe the core differences in analyses enabled by regression, classification, and clustering. -Select the appropriate machine learning task for a potential application. -Apply regression, classification, clustering, retrieval, recommender systems, and deep learning. -Represent your data as features to serve as input to machine learning models. -Assess the model quality in terms of relevant error metrics for each task. -Utilize a dataset to fit a model to analyze new data. -Build an end-to-end application that uses machine learning at its core. -Implement these techniques in Python.

WEEK 1

Welcome

Machine learning is everywhere, but is often operating behind the scenes.

This introduction to the specialization provides you with insights into the power of machine learning, and the multitude of intelligent applications you personally will be able to develop and deploy upon completion.

We also discuss who we are, how we got here, and our view of the future of intelligent applications.

Reading · Slides presented in this module

Video · Welcome to this course and specialization

Video · Who we are

Video · Machine learning is changing the world

Video · Why a case study approach?

Video · Specialization overview

Video · How we got into ML

Video · Who is this specialization for?

Video · What you'll be able to do

Video · The capstone and an example intelligent application

Video · The future of intelligent applications

Reading · Reading: Getting started with Python, IPython Notebook & GraphLab Create

Reading · Reading: where should my files go?

Reading · Download the IPython Notebook used in this lesson to follow along

Video · Starting an IPython Notebook

Video · Creating variables in Python

Video · Conditional statements and loops in Python

Video · Creating functions and lambdas in Python


Video · Starting GraphLab Create & loading an SFrame

Video · Canvas for data visualization

Video · Interacting with columns of an SFrame

Video · Using .apply() for data transformation

WEEK 2

Regression: Predicting House Prices

This week you will build your first intelligent application that makes predictions from data.

We will explore this idea within the context of our first case study, predicting house prices, where you will create models that predict a continuous value (price) from input features (square footage, number of bedrooms and bathrooms,...).

This is just one of the many places where regression can be applied.Other applications range from predicting health outcomes in medicine, stock prices in finance, and power usage in high-performance computing, to analyzing which regulators are important for gene expression.

You will also examine how to analyze the performance of your predictive model and implement regression in practice using an iPython notebook.


Video · Predicting house prices: A case study in regression

Video · What is the goal and how might you naively address it?

Video · Linear Regression: A Model-Based Approach

Video · Adding higher order effects

Video · Evaluating overfitting via training/test split

Video · Training/test curves

Video · Adding other features

Video · Other regression examples

Video · Regression ML block diagram

Quiz · Regression


Video · Loading & exploring house sale data

Video · Splitting the data into training and test sets

Video · Learning a simple regression model to predict house prices from house size

Video · Evaluating error (RMSE) of the simple model

Video · Visualizing predictions of simple model with Matplotlib

Video · Inspecting the model coefficients learned

Video · Exploring other features of the data

Video · Learning a model to predict house prices from more features

Video · Applying learned models to predict price of an average house

Video · Applying learned models to predict price of two fancy houses

Reading · Reading: Predicting house prices assignment

Quiz · Predicting house prices

WEEK 3

Classification: Analyzing Sentiment

How do you guess whether a person felt positively or negatively about an experience, just from a short review they wrote?

In our second case study, analyzing sentiment, you will create models that predict a class (positive/negative sentiment) from input features (text of the reviews, user profile information,...).This task is an example of classification, one of the most widely used areas of machine learning, with a broad array of applications, including ad targeting, spam detection, medical diagnosis and image classification.

You will analyze the accuracy of your classifier, implement an actual classifier in an iPython notebook, and take a first stab at a core piece of the intelligent application you will build and deploy in your capstone.


Video · Analyzing the sentiment of reviews: A case study in classification

Video · What is an intelligent restaurant review system?

Video · Examples of classification tasks

Video · Linear classifiers

Video · Decision boundaries

Video · Training and evaluating a classifier

Video · What's a good accuracy?

Video · False positives, false negatives, and confusion matrices

Video · Learning curves

Video · Class probabilities

Video · Classification ML block diagram

Quiz · Classification


Video · Loading & exploring product review data

Video · Creating the word count vector

Video · Exploring the most popular product

Video · Defining which reviews have positive or negative sentiment

Video · Training a sentiment classifier

Video · Evaluating a classifier & the ROC curve

Video · Applying model to find most positive & negative reviews for a product

Video · Exploring the most positive & negative aspects of a product

Reading · Reading: Analyzing product sentiment assignment

Quiz · Analyzing product sentiment

WEEK 4

Clustering and Similarity: Retrieving Documents

A reader is interested in a specific news article and you want to find a similar articles to recommend. What is the right notion of similarity? How do I automatically search over documents to find the one that is most similar? How do I quantitatively represent the documents in the first place?

In this third case study, retrieving documents, you will examine various document representations and an algorithm to retrieve the most similar subset. You will also consider structured representations of the documents that automatically group articles by similarity (e.g., document topic).

You will actually build an intelligent document retrieval system for Wikipedia entries in an iPython notebook.


Video · Document retrieval: A case study in clustering and measuring similarity

Video · What is the document retrieval task?

Video · Word count representation for measuring similarity

Video · Prioritizing important words with tf-idf

Video · Calculating tf-idf vectors

Video · Retrieving similar documents using nearest neighbor search

Video · Clustering documents task overview

Video · Clustering documents: An unsupervised learning task

Video · k-means: A clustering algorithm

Video · Other examples of clustering

Video · Clustering and similarity ML block diagram

Quiz · Clustering and Similarity


Video · Loading & exploring Wikipedia data

Video · Exploring word counts

Video · Computing & exploring TF-IDFs

Video · Computing distances between Wikipedia articles

Video · Building & exploring a nearest neighbors model for Wikipedia articles

Video · Examples of document retrieval in action

Reading · Reading: Retrieving Wikipedia articles assignment

Quiz · Retrieving Wikipedia articles

WEEK 5

Recommending Products

Ever wonder how Amazon forms its personalized product recommendations? How Netflix suggests movies to watch? How Pandora selects the next song to stream? How Facebook or LinkedIn finds people you might connect with? Underlying all of these technologies for personalized content is something called collaborative filtering.

You will learn how to build such a recommender system using a variety of techniques, and explore their tradeoffs.

One method we examine is matrix factorization, which learns features of users and products to form recommendations. In an iPython notebook, you will use these techniques to build a real song recommender system.


Video · Recommender systems overview

Video · Where we see recommender systems in action

Video · Building a recommender system via classification

Video · Collaborative filtering: People who bought this also bought...

Video · Effect of popular items

Video · Normalizing co-occurrence matrices and leveraging purchase histories

Video · The matrix completion task

Video · Recommendations from known user/item features

Video · Predictions in matrix form

Video · Discovering hidden structure by matrix factorization

Video · Bringing it all together: Featurized matrix factorization

Video · A performance metric for recommender systems

Video · Optimal recommenders

Video · Precision-recall curves

Video · Recommender systems ML block diagram

Quiz · Recommender Systems


Video · Loading and exploring song data

Video · Creating & evaluating a popularity-based song recommender

Video · Creating & evaluating a personalized song recommender

Video · Using precision-recall to compare recommender models

Reading · Reading: Recommending songs assignment

Quiz · Recommending songs

WEEK 6

Deep Learning: Searching for Images

You’ve probably heard that Deep Learning is making news across the world as one of the most promising techniques in machine learning. Every industry is dedicating resources to unlock the deep learning potential, including for tasks such as image tagging, object recognition, speech recognition, and text analysis.

In our final case study, searching for images, you will learn how layers of neural networks provide very descriptive (non-linear) features that provide impressive performance in image classification

and retrieval tasks. You will then construct deep features, a transfer learning technique that allows you to use deep learning very easily, even when you have little data to train the model.

Using iPhython notebooks, you will build an image classifier and an intelligent image retrieval system with deep learning.


Video · Searching for images: A case study in deep learning

Video · What is a visual product recommender?

Video · Learning very non-linear features with neural networks

Video · Application of deep learning to computer vision

Video · Deep learning performance

Video · Demo of deep learning model on ImageNet data

Video · Other examples of deep learning in computer vision

Video · Challenges of deep learning

Video · Deep Features

Video · Deep learning ML block diagram

Quiz · Deep Learning


Video · Loading image data

Video · Training & evaluating a classifier using raw image pixels

Video · Training & evaluating a classifier using deep features


Video · Loading image data

Video · Creating a nearest neighbors model for image retrieval

Video · Querying the nearest neighbors model to retrieve images

Video · Querying for the most similar images for car image

Video · Displaying other example image retrievals with a Python lambda

Reading · Reading: Deep features for image retrieval assignment

Quiz · Deep features for image retrieval

Closing Remarks

In the conclusion of the course, we will describe the final stage in turning our machine learning tools into a service: deployment.

We will also discuss some open challenges that the field of machine learning still faces, and where we think machine learning is heading. We conclude with an overview of what's in store for you in the rest of the specialization, and the amazing intelligent applications that are ahead for us as we evolve machine learning.


Video · You've made it!

Video · Deploying an ML service

Video · What happens after deployment?

Video · Open challenges in ML

Video · Where is ML going?

Video · What's ahead in the specialization

Video · Thank you!

COURSE 2: MACHINE LEARNING: REGRESSION

In our first case study, predicting house prices, you will create models that predict a continuous value (price) from input features (square footage, number of bedrooms and bathrooms,...). This is just one of the many places where regression can be applied. Other applications range from predicting health outcomes in medicine, stock prices in finance, and power usage in high-performance computing, to analyzing which regulators are important for gene expression. In this course, you will explore regularized linear regression models for the task of prediction and feature selection. You will be able to handle very large sets of features and select between models of various complexity. You will also analyze the impact of aspects of your data -- such as outliers -- on your selected models and predictions. To fit these models, you will implement optimization algorithms that scale to large datasets. Learning Outcomes: By the end of this course, you will be able to: -Describe the input and output of a regression model. -Compare and contrast bias and variance when modeling data. -Estimate model parameters using optimization algorithms. -Tune

parameters with cross validation. -Analyze the performance of the model. -Describe the notion of sparsity and how LASSO leads to sparse solutions. -Deploy methods to select between models. -Exploit the model to form predictions. -Build a regression model to predict prices using a housing dataset. -Implement these techniques in Python.

WEEK 1

Welcome

Regression is one of the most important and broadly used machine learning and statistics tools out there. It allows you to make predictions from data by learning the relationship between features of your data and some observed, continuous-valued response. Regression is used in a massive number of applications ranging from predicting stock prices to understanding gene regulatory networks.

This introduction to the course provides you with an overview of the topics we will cover and the background knowledge and resources we assume you have.


Video · Welcome!

Video · What is the course about?

Video · Outlining the first half of the course

Video · Outlining the second half of the course

Video · Assumed background

Reading · Reading: Software tools you'll need

Simple Linear Regression

Our course starts from the most basic regression model: Just fitting a line to data. This simple model for forming predictions from a single, univariate feature of the data is appropriately called "simple linear regression".

In this module, we describe the high-level regression task and then specialize these concepts to the simple linear regression case. You will learn how to formulate a simple regression model and fit the model to data using both a closed-form solution as well as an iterative optimization algorithm called gradient descent. Based on this fitted function, you will interpret the estimated model parameters and form predictions. You will also analyze the sensitivity of your fit to outlying observations.

You will examine all of these concepts in the context of a case study of predicting house prices from the square feet of the house.


Video · A case study in predicting house prices

Video · Regression fundamentals: data & model

Video · Regression fundamentals: the task

Video · Regression ML block diagram

Video · The simple linear regression model

Video · The cost of using a given line

Video · Using the fitted line

Video · Interpreting the fitted line

Video · Defining our least squares optimization objective

Video · Finding maxima or minima analytically

Video · Maximizing a 1d function: a worked example

Video · Finding the max via hill climbing

Video · Finding the min via hill descent

Video · Choosing stepsize and convergence criteria

Video · Gradients: derivatives in multiple dimensions

Video · Gradient descent: multidimensional hill descent

Video · Computing the gradient of RSS

Video · Approach 1: closed-form solution

Reading · Optional reading: worked-out example for closed-form solution

Video · Approach 2: gradient descent

Reading · Optional reading: worked-out example for gradient descent

Video · Comparing the approaches

Reading · Download notebooks to follow along

Video · Influence of high leverage points: exploring the data

Video · Influence of high leverage points: removing Center City

Video · Influence of high leverage points: removing high-end towns

Video · Asymmetric cost functions

Video · A brief recap

Quiz · Simple Linear Regression

Reading · Reading: Fitting a simple linear regression model on housing data

Quiz · Fitting a simple linear regression model on housing data

WEEK 2

Multiple Regression

The next step in moving beyond simple linear regression is to consider "multiple regression" where multiple features of the data are used to form predictions.

More specifically, in this module, you will learn how to build models of more complex relationship between a single variable (e.g., 'square feet') and the observed response (like 'house sales price'). This includes things like fitting a polynomial to your data, or capturing seasonal changes in the response value. You will also learn how to incorporate multiple input variables (e.g., 'square feet', '# bedrooms', '# bathrooms'). You will then be able to describe how all of these models can still be cast within the linear regression framework, but now using multiple "features". Within this multiple regression framework, you will fit models to data, interpret estimated coefficients, and form predictions.

Here, you will also implement a gradient descent algorithm for fitting a multiple regression model.


Video · Multiple regression intro

Video · Polynomial regression

Video · Modeling seasonality

Video · Where we see seasonality

Video · Regression with general features of 1 input

Video · Motivating the use of multiple inputs

Video · Defining notation

Video · Regression with features of multiple inputs

Video · Interpreting the multiple regression fit

Reading · Optional reading: review of matrix algebra

Video · Rewriting the single observation model in vector notation

Video · Rewriting the model for all observations in matrix notation

Video · Computing the cost of a D-dimensional curve

Video · Computing the gradient of RSS


Video · Discussing the closed-form solution


Video · Feature-by-feature update

Video · Algorithmic summary of gradient descent approach


Quiz · Multiple Regression

Reading · Reading: Exploring different multiple regression models for house price prediction

Quiz · Exploring different multiple regression models for house price prediction

Reading · Numpy tutorial

Reading · Reading: Implementing gradient descent for multiple regression

Quiz · Implementing gradient descent for multiple regression

WEEK 3

Assessing Performance

Having learned about linear regression models and algorithms for estimating the parameters of such models, you are now ready to assess how well your considered method should perform in predicting new data. You are also ready to select amongst possible models to choose the best performing.

This module is all about these important topics of model selection and assessment. You will examine both theoretical and practical aspects of such analyses. You will first explore the concept of measuring the "loss" of your predictions, and use this to define training, test, and generalization

error. For these measures of error, you will analyze how they vary with model complexity and how they might be utilized to form a valid assessment of predictive performance. This leads directly to an important conversation about the bias-variance tradeoff, which is fundamental to machine learning. Finally, you will devise a method to first select amongst models and then assess the performance of the selected model.

The concepts described in this module are key to all machine learning problems, well-beyond the regression setting addressed in this course.


Video · Assessing performance intro

Video · What do we mean by "loss"?

Video · Training error: assessing loss on the training set

Video · Generalization error: what we really want

Video · Test error: what we can actually compute

Video · Defining overfitting

Video · Training/test split

Video · Irreducible error and bias

Video · Variance and the bias-variance tradeoff

Video · Error vs. amount of data

Video · Formally defining the 3 sources of error

Video · Formally deriving why 3 sources of error

Video · Training/validation/test split for model selection, fitting, and assessment


Quiz · Assessing Performance

Reading · Reading: Exploring the bias-variance tradeoff

Quiz · Exploring the bias-variance tradeoff

WEEK 4

Ridge Regression

You have examined how the performance of a model varies with increasing model complexity, and can describe the potential pitfall of complex models becoming overfit to the training data. In this module, you will explore a very simple, but extremely effective technique for automatically coping with this issue. This method is called "ridge regression". You start out with a complex model, but now fit the model in a manner that not only incorporates a measure of fit to the training data, but also a term that biases the solution away from overfitted functions. To this end, you will explore symptoms of overfitted functions and use this to define a quantitative measure to use in your revised optimization objective. You will derive both a closed-form and gradient descent algorithm for fitting the ridge regression objective; these forms are small modifications from the original algorithms you derived for multiple regression. To select the strength of the bias away from overfitting, you will explore a general-purpose method called "cross validation".

You will implement both cross-validation and gradient descent to fit a ridge regression model and select the regularization constant.


Video · Symptoms of overfitting in polynomial regression

Reading · Download the notebook and follow along

Video · Overfitting demo

Video · Overfitting for more general multiple regression models

Video · Balancing fit and magnitude of coefficients

Video · The resulting ridge objective and its extreme solutions

Video · How ridge regression balances bias and variance


Video · Ridge regression demo

Video · The ridge coefficient path

Video · Computing the gradient of the ridge objective


Video · Discussing the closed-form solution


Video · Selecting tuning parameters via cross validation

Video · K-fold cross validation

Video · How to handle the intercept


Quiz · Ridge Regression

Reading · Reading: Observing effects of L2 penalty in polynomial regression

Quiz · Observing effects of L2 penalty in polynomial regression

Reading · Reading: Implementing ridge regression via gradient descent

Quiz · Implementing ridge regression via gradient descent

WEEK 5

Feature Selection & Lasso

A fundamental machine learning task is to select amongst a set of features to include in a model. In this module, you will explore this idea in the context of multiple regression, and describe how such feature selection is important for both interpretability and efficiency of forming predictions.

To start, you will examine methods that search over an enumeration of models including different subsets of features. You will analyze both exhaustive search and greedy algorithms. Then, instead of an explicit enumeration, we turn to Lasso regression, which implicitly performs feature selection in a manner akin to ridge regression: A complex model is fit based on a measure of fit to the training data plus a measure of overfitting different than that used in ridge. This lasso method has had impact in numerous applied domains, and the ideas behind the method have fundamentally changed machine learning and statistics. You will also implement a coordinate descent algorithm for fitting a Lasso model.

Coordinate descent is another, general, optimization technique, which is useful in many areas of machine learning.


Video · The feature selection task

Video · All subsets

Video · Complexity of all subsets

Video · Greedy algorithms

Video · Complexity of the greedy forward stepwise algorithm

Video · Can we use regularization for feature selection?

Video · Thresholding ridge coefficients?

Video · The lasso objective and its coefficient path

Video · Visualizing the ridge cost

Video · Visualizing the ridge solution

Video · Visualizing the lasso cost and solution


Video · Lasso demo

Video · What makes the lasso objective different

Video · Coordinate descent

Video · Normalizing features

Video · Coordinate descent for least squares regression (normalized features)

Video · Coordinate descent for lasso (normalized features)

Video · Assessing convergence and other lasso solvers

Video · Coordinate descent for lasso (unnormalized features)

Video · Deriving the lasso coordinate descent update

Video · Choosing the penalty strength and other practical issues with lasso


Quiz · Feature Selection and Lasso

Reading · Reading: Using LASSO to select features

Quiz · Using LASSO to select features

Reading · Reading: Implementing LASSO using coordinate descent

Quiz · Implementing LASSO using coordinate descent

WEEK 6

Nearest Neighbors & Kernel Regression

Up to this point, we have focused on methods that fit parametric functions---like polynomials and hyperplanes---to the entire dataset. In this module, we instead turn our attention to a class of "nonparametric" methods. These methods allow the complexity of the model to increase as more data are observed, and result in fits that adapt locally to the observations.

We start by considering the simple and intuitive example of nonparametric methods, nearest neighbor regression: The prediction for a query point is based on the outputs of the most related observations in the training set. This approach is extremely simple, but can provide excellent predictions, especially for large datasets. You will deploy algorithms to search for the nearest neighbors and form predictions based on the discovered neighbors. Building on this idea, we turn to kernel regression. Instead of forming predictions based on a small set of neighboring observations, kernel regression uses all observations in the dataset, but the impact of these observations on the predicted value is weighted by their similarity to the query point. You will analyze the theoretical performance of these methods in the limit of infinite training data, and explore the scenarios in which these methods work well versus struggle. You will also implement these techniques and observe their practical behavior.


Video · Limitations of parametric regression

Video · 1-Nearest neighbor regression approach

Video · Distance metrics

Video · 1-Nearest neighbor algorithm

Video · k-Nearest neighbors regression

Video · k-Nearest neighbors in practice

Video · Weighted k-nearest neighbors

Video · From weighted k-NN to kernel regression

Video · Global fits of parametric models vs. local fits of kernel regression

Video · Performance of NN as amount of data grows

Video · Issues with high-dimensions, data scarcity, and computational complexity

Video · k-NN for classification


Quiz · Nearest Neighbors & Kernel Regression

Reading · Reading: Predicting house prices using k-nearest neighbors regression

Quiz · Predicting house prices using k-nearest neighbors regression

Closing Remarks

In the conclusion of the course, we will recap what we have covered. This represents both techniques specific to regression, as well as foundational machine learning concepts that will appear throughout the specialization. We also briefly discuss some important regression techniques we did not cover in this course.

We conclude with an overview of what's in store for you in the rest of the specialization.


Video · Simple and multiple regression

Video · Assessing performance and ridge regression

Video · Feature selection, lasso, and nearest neighbor regression

Video · What we covered and what we didn't cover

Video · What's ahead in the ML specialization

Video · Thank you!

COURSE 3: MACHINE LEARNING: CLASSIFICATION

In our case study on analyzing sentiment, you will create models that predict a class (positive/negative sentiment) from input features (text of the reviews, user profile information,...). In our second case study for this course, loan default prediction, you will tackle financial data, and predict when a loan is likely to be risky or safe for the bank. These tasks are an examples of classification, one of the most widely used areas of machine learning, with a broad array of applications, including ad targeting, spam detection, medical diagnosis and image classification. In this course, you will create classifiers that provide state-of-the-art performance on a variety of tasks. You will become familiar with the most successful techniques, which are most widely used in practice, including logistic regression, decision trees and boosting. In addition, you will be able to design and implement the underlying algorithms that can learn these models at scale, using stochastic gradient ascent. You will implement these technique on real-world, large-scale machine learning tasks. You will also address significant tasks you will face in real-world applications of ML, including handling missing data and measuring precision and recall to evaluate a classifier. This course is hands-on, action-packed, and full of visualizations and illustrations of how these techniques will behave on real data. We've also included optional content in every module, covering

advanced topics for those who want to go even deeper! Learning Objectives: By the end of this course, you will be able to: -Describe the input and output of a classification model. -Tackle both binary and multiclass classification problems. -Implement a logistic regression model for large-scale classification. -Create a non-linear model using decision trees. -Improve the performance of any model using boosting. -Scale your methods with stochastic gradient ascent. -Describe the underlying decision boundaries. -Build a classification model to predict sentiment in a product review dataset. -Analyze financial data to predict loan defaults. -Use techniques for handling missing data. -Evaluate your models using precision-recall metrics. -Implement these techniques in Python (or in the language of your choice, though Python is highly recommended).

WEEK 1

Welcome!

Classification is one of the most widely used techniques in machine learning, with a broad array of applications, including sentiment analysis, ad targeting, spam detection, risk assessment, medical diagnosis and image classification. The core goal of classification is to predict a category or class y from some inputs x. Through this course, you will become familiar with the fundamental models and algorithms used in classification, as well as a number of core machine learning concepts. Rather than covering all aspects of classification, you will focus on a few core techniques, which are widely used in the real-world to get state-of-the-art performance. By following our hands-on approach, you will implement your own algorithms on multiple real-world tasks, and deeply grasp the core techniques needed to be successful with these approaches in practice. This introduction to the course provides you with an overview of the topics we will cover and the background knowledge and resources we assume you have.


Video · Welcome to the classification course, a part of the Machine Learning Specialization

Video · What is this course about?

Video · Impact of classification

Video · Course overview

Video · Outline of first half of course

Video · Outline of second half of course

Video · Assumed background

Video · Let's get started!

Reading · Reading: Software tools you'll need

Reading · Installing correct version of GraphLab Create

Linear Classifiers & Logistic Regression

Linear classifiers are amongst the most practical classification methods. For example, in our sentiment analysis case-study, a linear classifier associates a coefficient with the counts of each word in the sentence. In this module, you will become proficient in this type of representation. You will focus on a particularly useful type of linear classifier called logistic regression, which, in addition to allowing you to predict a class, provides a probability associated with the prediction. These probabilities are extremely useful, since they provide a degree of confidence in the predictions. In this module, you will also be able to construct features from categorical inputs, and to tackle classification problems with more than two class (multiclass problems). You will examine the results of these techniques on a real-world product sentiment analysis task.


Video · Linear classifiers: A motivating example

Video · Intuition behind linear classifiers

Video · Decision boundaries

Video · Linear classifier model

Video · Effect of coefficient values on decision boundary

Video · Using features of the inputs

Video · Predicting class probabilities

Video · Review of basics of probabilities

Video · Review of basics of conditional probabilities

Video · Using probabilities in classification

Video · Predicting class probabilities with (generalized) linear models

Video · The sigmoid (or logistic) link function

Video · Logistic regression model

Video · Effect of coefficient values on predicted probabilities

Video · Overview of learning logistic regression models

Video · Encoding categorical inputs

Video · Multiclass classification with 1 versus all

Video · Recap of logistic regression classifier

Quiz · Linear Classifiers & Logistic Regression

Reading · Predicting sentiment from product reviews

Quiz · Predicting sentiment from product reviews

WEEK 2

Learning Linear Classifiers

Once familiar with linear classifiers and logistic regression, you can now dive in and write your first learning algorithm for classification. In particular, you will use gradient ascent to learn the coefficients of your classifier from data. You first will need to define the quality metric for these tasks using an approach called maximum likelihood estimation (MLE). You will also become familiar with a simple technique for selecting the step size for gradient ascent. An optional, advanced part of this module will cover the derivation of the gradient for logistic regression. You will implement your own learning algorithm for logistic regression from scratch, and use it to learn a sentiment analysis classifier.


Video · Goal: Learning parameters of logistic regression

Video · Intuition behind maximum likelihood estimation

Video · Data likelihood

Video · Finding best linear classifier with gradient ascent

Video · Review of gradient ascent

Video · Learning algorithm for logistic regression

Video · Example of computing derivative for logistic regression

Video · Interpreting derivative for logistic regression

Video · Summary of gradient ascent for logistic regression

Video · Choosing step size

Video · Careful with step sizes that are too large

Video · Rule of thumb for choosing step size

Video · (VERY OPTIONAL) Deriving gradient of logistic regression: Log trick

Video · (VERY OPTIONAL) Expressing the log-likelihood

Video · (VERY OPTIONAL) Deriving probability y=-1 given x

Video · (VERY OPTIONAL) Rewriting the log likelihood into a simpler form

Video · (VERY OPTIONAL) Deriving gradient of log likelihood

Video · Recap of learning logistic regression classifiers

Quiz · Learning Linear Classifiers

Reading · Implementing logistic regression from scratch

Quiz · Implementing logistic regression from scratch

Overfitting & Regularization in Logistic Regression

As we saw in the regression course, overfitting is perhaps the most significant challenge you will face as you apply machine learning approaches in practice. This challenge can be particularly significant for logistic regression, as you will discover in this module, since we not only risk getting an overly complex decision boundary, but your classifier can also become overly confident about the probabilities it predicts. In this module, you will investigate overfitting in classification in significant detail, and obtain broad practical insights from some interesting visualizations of the classifiers' outputs. You will then add a regularization term to your optimization to mitigate overfitting. You will investigate both L2 regularization to penalize large coefficient values, and L1 regularization to obtain additional sparsity in the coefficients. Finally, you will modify your gradient ascent algorithm to learn regularized logistic regression classifiers. You will implement your own regularized logistic regression classifier from scratch, and investigate the impact of the L2 penalty on real-world sentiment analysis data.


Video · Evaluating a classifier

Video · Review of overfitting in regression

Video · Overfitting in classification

Video · Visualizing overfitting with high-degree polynomial features

Video · Overfitting in classifiers leads to overconfident predictions

Video · Visualizing overconfident predictions

Video · (OPTIONAL) Another perspecting on overfitting in logistic regression

Video · Penalizing large coefficients to mitigate overfitting

Video · L2 regularized logistic regression

Video · Visualizing effect of L2 regularization in logistic regression

Video · Learning L2 regularized logistic regression with gradient ascent

Video · Sparse logistic regression with L1 regularization

Video · Recap of overfitting & regularization in logistic regression

Quiz · Overfitting & Regularization in Logistic Regression

Reading · Logistic Regression with L2 regularization

Quiz · Logistic Regression with L2 regularization

WEEK 3

Decision Trees

Along with linear classifiers, decision trees are amongst the most widely used classification techniques in the real world. This method is extremely intuitive, simple to implement and provides interpretable predictions. In this module, you will become familiar with the core decision trees representation. You will then design a simple, recursive greedy algorithm to learn decision trees from data. Finally, you will extend this approach to deal with continuous inputs, a fundamental requirement for practical problems. In this module, you will investigate a brand new case-study in the financial sector: predicting the risk associated with a bank loan. You will implement your own decision tree learning algorithm on real loan data.


Video · Predicting loan defaults with decision trees

Video · Intuition behind decision trees

Video · Task of learning decision trees from data

Video · Recursive greedy algorithm

Video · Learning a decision stump

Video · Selecting best feature to split on

Video · When to stop recursing

Video · Making predictions with decision trees

Video · Multiclass classification with decision trees

Video · Threshold splits for continuous inputs

Video · (OPTIONAL) Picking the best threshold to split on

Video · Visualizing decision boundaries

Video · Recap of decision trees

Quiz · Decision Trees

Reading · Identifying safe loans with decision trees

Quiz · Identifying safe loans with decision trees

Reading · Implementing binary decision trees

Quiz · Implementing binary decision trees

WEEK 4

Preventing Overfitting in Decision Trees

Out of all machine learning techniques, decision trees are amongst the most prone to overfitting. No practical implementation is possible without including approaches that mitigate this challenge. In this module, through various visualizations and investigations, you will investigate why decision trees suffer from significant overfitting problems. Using the principle of Occam's razor, you will mitigate overfitting by learning simpler trees. At first, you will design algorithms that stop the learning process before the decision trees become overly complex. In an optional segment, you will design a very practical approach that learns an overly-complex tree, and then simplifies it with pruning. Your implementation will investigate the effect of these techniques on mitigating overfitting on our real-world loan data set.


Video · A review of overfitting

Video · Overfitting in decision trees

Video · Principle of Occam's razor: Learning simpler decision trees

Video · Early stopping in learning decision trees

Video · (OPTIONAL) Motivating pruning

Video · (OPTIONAL) Pruning decision trees to avoid overfitting

Video · (OPTIONAL) Tree pruning algorithm

Video · Recap of overfitting and regularization in decision trees

Quiz · Preventing Overfitting in Decision Trees

Reading · Decision Trees in Practice

Quiz · Decision Trees in Practice

Handling Missing Data

Real-world machine learning problems are fraught with missing data. That is, very often, some of the inputs are not observed for all data points. This challenge is very significant, happens in most cases, and needs to be addressed carefully to obtain great performance. And, this issue is rarely discussed in machine learning courses. In this module, you will tackle the missing data challenge head on. You will start with the two most basic techniques to convert a dataset with missing data into a clean dataset, namely skipping missing values and inputing missing values. In an advanced section, you will also design a modification of the decision tree learning algorithm that builds decisions about missing data right into the model. You will also explore these techniques in your real-data implementation.


Video · Challenge of missing data

Video · Strategy 1: Purification by skipping missing data

Video · Strategy 2: Purification by imputing missing data

Video · Modifying decision trees to handle missing data

Video · Feature split selection with missing data

Video · Recap of handling missing data

Quiz · Handling Missing Data

WEEK 5

Boosting

One of the most exciting theoretical questions that have been asked about machine learning is whether simple classifiers can be combined into a highly accurate ensemble. This question lead to the developing of boosting, one of the most important and practical techniques in machine learning today. This simple approach can boost the accuracy of any classifier, and is widely used in practice,

e.g., it's used by more than half of the teams who win the Kaggle machine learning competitions. In this module, you will first define the ensemble classifier, where multiple models vote on the best prediction. You will then explore a boosting algorithm called AdaBoost, which provides a great approach for boosting classifiers. Through visualizations, you will become familiar with many of the practical aspects of this techniques. You will create your very own implementation of AdaBoost, from scratch, and use it to boost the performance of your loan risk predictor on real data.


Video · The boosting question

Video · Ensemble classifiers

Video · Boosting

Video · AdaBoost overview

Video · Weighted error

Video · Computing coefficient of each ensemble component

Video · Reweighing data to focus on mistakes

Video · Normalizing weights

Video · Example of AdaBoost in action

Video · Learning boosted decision stumps with AdaBoost

Reading · Exploring Ensemble Methods

Quiz · Exploring Ensemble Methods

Video · The Boosting Theorem

Video · Overfitting in boosting

Video · Ensemble methods, impact of boosting & quick recap

Quiz · Boosting

Reading · Boosting a decision stump

Quiz · Boosting a decision stump

WEEK 6

Precision-Recall

In many real-world settings, accuracy or error are not the best quality metrics for classification. You will explore a case-study that significantly highlights this issue: using sentiment analysis to display positive reviews on a restaurant website. Instead of accuracy, you will define two metrics: precision and recall, which are widely used in real-world applications to measure the quality of classifiers. You will explore how the probabilities output by your classifier can be used to trade-off precision with recall, and dive into this spectrum, using precision-recall curves. In your hands-on implementation, you will compute these metrics with your learned classifier on real-world sentiment analysis data.


Video · Case-study where accuracy is not best metric for classification

Video · What is good performance for a classifier?

Video · Precision: Fraction of positive predictions that are actually positive

Video · Recall: Fraction of positive data predicted to be positive

Video · Precision-recall extremes

Video · Trading off precision and recall

Video · Precision-recall curve

Video · Recap of precision-recall

Quiz · Precision-Recall

Reading · Exploring precision and recall

Quiz · Exploring precision and recall

WEEK 7

Scaling to Huge Datasets & Online Learning

With the advent of the internet, the growth of social media, and the embedding of sensors in the world, the magnitudes of data that our machine learning algorithms must handle have grown tremendously over the last decade. This effect is sometimes called "Big Data". Thus, our learning algorithms must scale to bigger and bigger datasets. In this module, you will develop a small modification of gradient ascent called stochastic gradient, which provides significant speedups in the running time of our algorithms. This simple change can drastically improve scaling, but makes the algorithm less stable and harder to use in practice. In this module, you will investigate the practical techniques needed to make stochastic gradient viable, and to thus to obtain learning algorithms that scale to huge datasets. You will also address a new kind of machine learning problem, online learning, where the data streams in over time, and we must learn the coefficients as the data arrives. This task can also be solved with stochastic gradient. You will implement your very own stochastic

gradient ascent algorithm for logistic regression from scratch, and evaluate it on sentiment analysis data.


Video · Gradient ascent won't scale to today's huge datasets

Video · Timeline of scalable machine learning & stochastic gradient

Video · Why gradient ascent won't scale

Video · Stochastic gradient: Learning one data point at a time

Video · Comparing gradient to stochastic gradient

Video · Why would stochastic gradient ever work?

Video · Convergence paths

Video · Shuffle data before running stochastic gradient

Video · Choosing step size

Video · Don't trust last coefficients

Video · (OPTIONAL) Learning from batches of data

Video · (OPTIONAL) Measuring convergence

Video · (OPTIONAL) Adding regularization

Video · The online learning task

Video · Using stochastic gradient for online learning

Video · Scaling to huge datasets through parallelization & module recap

Quiz · Scaling to Huge Datasets & Online Learning

Reading · Training Logistic Regression via Stochastic Gradient Ascent

Quiz · Training Logistic Regression via Stochastic Gradient Ascent

COURSE 4: MACHINE LEARNING: CLUSTERING & RETRIEVAL

A reader is interested in a specific news article and you want to find similar articles to recommend. What is the right notion of similarity? Moreover, what if there are millions of other documents? Each

time you want to a retrieve a new document, do you need to search through all other documents? How do you group similar documents together? How do you discover new, emerging topics that the documents cover? In this third case study, finding similar documents, you will examine similarity-based algorithms for retrieval. In this course, you will also examine structured representations for describing the documents in the corpus, including clustering and mixed membership models, such as latent Dirichlet allocation (LDA). You will implement expectation maximization (EM) to learn the document clusterings, and see how to scale the methods using MapReduce. Learning Outcomes: By the end of this course, you will be able to: -Create a document retrieval system using k-nearest neighbors. -Describe how k-nearest neighbors can also be used for regression and classification. -Identify various similarity metrics for text data. -Cluster documents by topic using k-means. -Perform mixed membership modeling using latent Dirichlet allocation (LDA). -Describe how to parallelize k-means using MapReduce. -Examine mixtures of Gaussians for density estimation. -Fit a mixture of Gaussian model using expectation maximization (EM). -Compare and contrast initialization techniques for non-convex optimization objectives. -Implement these techniques in Python.

COURSE 5: MACHINE LEARNING: RECOMMENDER SYSTEMS & DIMENSIONALITY REDUCTION

How does Amazon recommend products you might be interested in purchasing? How does Netflix decide which movies or TV shows you might want to watch? What if you are a new user, should Netflix just recommend the most popular movies? Who might you form a new link with on Facebook or LinkedIn? These questions are endemic to most service-based industries, and underlie the notion of collaborative filtering and the recommender systems deployed to solve these problems. In this fourth case study, you will explore these ideas in the context of recommending products based on customer reviews. In this course, you will explore dimensionality reduction techniques for modeling high-dimensional data. In the case of recommender systems, your data is represented as user-product relationships, with potentially millions of users and hundred of thousands of products. You will implement matrix factorization and latent factor models for the task of predicting new user-product relationships. You will also use side information about products and users to improve predictions. Learning Outcomes: By the end of this course, you will be able to: -Create a collaborative filtering system. -Reduce dimensionality of data using SVD, PCA, and random projections. -Perform matrix factorization using coordinate descent. -Deploy latent factor models as a recommender system. -Handle the cold start problem using side information. -Examine a product recommendation application. -Implement these techniques in Python.

DATA MINING SPECIALIZATION

COURSE 1: DATA VISUALIZATION

Learn the general concepts of data mining along with basic methodologies and applications. Then dive into one subfield in data mining: pattern discovery. Learn in-depth concepts, methods, and applications of pattern discovery in data mining. We will also introduce methods for pattern-based classification and some interesting applications of pattern discovery. This course provides you the opportunity to learn skills and content to practice and engage in scalable pattern discovery methods on massive transactional data, discuss pattern evaluation measures, and study methods for mining diverse kinds of patterns, sequential patterns, and sub-graph patterns.

WEEK 1

Course Orientation

You will become familiar with the course, your classmates, and our learning environment. The orientation will also help you obtain the technical skills required for the course.

Reading · Welcome to Data Visualization!

Reading · Syllabus

Reading · About the Discussion Forums

Reading · Updating Your Profile

Reading · Social Media

Reading · Resources

Quiz · Orientation Quiz

Week 1: The Computer and the Human

In this week's module, you will learn what data visualization is, how it's used, and how computers display information. You'll also explore different types of visualization and how humans perceive information.

Reading · Week 1 Overview

Video · Week 1 Introduction

Reading · Week 1 Project Milestone

Video · 1.1.1. Some Books on Data Visualization

Video · 1.1.2. Overview of Visualization

Video · 1.2.1. 2-D Graphics

Video · SVG-example

Video · 1.2.2. 2-D Drawing

Video · 1.2.3. 3-D Graphics

Video · 1.2.4. Photorealism

Video · 1.2.5. Non-Photorealism

Video · 1.3.1. The Human

Video · 1.3.2. Memory

Video · 1.3.3. Reasoning

Video · 1.3.4. The Human Retina

Video · 1.3.5. Perceiving Two Dimensions

Video · 1.3.6. Perceiving Perspective

Quiz · Week 1 Quiz

Other · Week 1 Discussion

WEEK 2

Week 2: Visualization of Numerical Data

In this week's module, you will start to think about how to visualize data effectively. This will include assigning data to appropriate chart elements, using glyphs, parallel coordinates, and streamgraphs, as well as implementing principles of design and color to make your visualizations more engaging and effective.



Video · 2.1.1. Data

Video · 2.1.2. Mapping

Video · 2.1.3. Charts

Video · 2.2.1. Glyphs (Part 1)

Video · 2.2.1. Glyphs (Part 2)

Video · 2.2.2. Parallel Coordinates

Video · 2.2.3. Stacked Graphs (Part 1)

Video · 2.2.3. Stacked Graphs (Part 2)

Video · 2.3.1. Tufte's Design Rules

Video · 2.3.2. Using Color

Reading · Programming Assignment 1: Visualize Data Using a Chart

Reading · Programming Assignment 1 Rubric

Peer Review · Programming Assignment 1 Submission

Other · Programming Assignment 1 Help Forum

WEEK 3

Week 3: Visualization of Non-Numerical Data

In this week's module, you will learn how to visualize graphs that depict relationships between data items. You'll also plot data using coordinates that are not specifically provided by the data set.



Video · 3.1.1. Graphs and Networks

Video · 3.1.2. Embedding Planar Graphs

Video · 3.1.3. Graph Visualization

Video · 3.1.4. Tree Maps

Video · 3.2.1. Principal Component Analysis

Video · 3.2.2. Multidimensional Scaling

Video · 3.3.1. Packing

Reading · Programming Assignment 2: Visualize Network Data

Reading · Programming Assignment 2 Rubric

Peer Review · Programming Assignment 2 Submission

Other · Programming Assignment 2 Help Forum

WEEK 4

Week 4: The Visualization Dashboard

In this week's module, you will start to put together everything you've learned by designing your own visualization system for large datasets and dashboards. You'll create and interpret the visualization you created from your data set, and you'll also apply techniques from user-interface design to create an effective visualization system.



Video · 4.1.1. Visualization Systems

Video · 4.1.2. The Information Visualization Mantra: Part 1



Video · 4.1.3. Database Visualization Part: 1



Video · 4.2.1. Visualization System Design

Quiz · Week 4 Quiz

COURSE 2: TEXT RETRIEVAL AND SEARCH ENGINES

Recent years have seen a dramatic growth of natural language text data, including web pages, news articles, scientific literature, emails, enterprise documents, and social media such as blog articles, forum posts, product reviews, and tweets. Text data are unique in that they are usually generated directly by humans rather than a computer system or sensors, and are thus especially valuable for discovering knowledge about people’s opinions and preferences, in addition to many other kinds of knowledge that we encode in text. This course will cover search engine technologies, which play an important role in any data mining applications involving text data for two reasons. First, while the raw data may be large for any particular problem, it is often a relatively small subset of the data that are relevant, and a search engine is an essential tool for quickly discovering a small subset of relevant text data in a large text collection. Second, search engines are needed to help analysts interpret any patterns discovered in the data by allowing them to examine the relevant original text data to make sense of any discovered pattern. You will learn the basic concepts, principles, and the major techniques in text retrieval, which is the underlying science of search engines.

COURSE 3: TEXT MINING AND ANALYTICS

This course will cover the major techniques for mining and analyzing text data to discover interesting patterns, extract useful knowledge, and support decision making, with an emphasis on statistical approaches that can be generally applied to arbitrary text data in any natural language with no or minimum human effort. Detailed analysis of text data requires understanding of natural language text, which is known to be a difficult task for computers. However, a number of statistical approaches have been shown to work well for the "shallow" but robust analysis of text data for pattern finding and knowledge discovery. You will learn the basic concepts, principles, and major algorithms in text mining and their potential applications.

COURSE 4: PATTERN DISCOVERY IN DATA MINING

Learn the general concepts of data mining along with basic methodologies and applications. Then dive into one subfield in data mining: pattern discovery. Learn in-depth concepts, methods, and applications of pattern discovery in data mining. We will also introduce methods for pattern-based classification and some interesting applications of pattern discovery. This course provides you the opportunity to learn skills and content to practice and engage in scalable pattern discovery methods on massive transactional data, discuss pattern evaluation measures, and study methods for mining diverse kinds of patterns, sequential patterns, and sub-graph patterns.

COURSE 5: CLUSTER ANALYSIS IN DATA MINING

Discover the basic concepts of cluster analysis, and then study a set of typical clustering methodologies, algorithms, and applications. This includes partitioning methods such as k-means, hierarchical methods such as BIRCH, density-based methods such as DBSCAN/OPTICS, probabilistic models, and the EM algorithm. Learn clustering and methods for clustering high dimensional data, streaming data, graph data, and networked data. Explore concepts and methods for constraint-based clustering and semi-supervised clustering. Finally, see examples of cluster analysis in applications.

DATA SCIENCE SPECIALIZATION

COURSE 1: THE DATA SCIENTIST’S TOOLBOX

In this course you will get an introduction to the main tools and ideas in the data scientist's toolbox. The course gives an overview of the data, questions, and tools that data analysts and data scientists work with. There are two components to this course. The first is a conceptual introduction to the ideas behind turning data into actionable knowledge. The second is a practical introduction to the tools that will be used in the program like version control, markdown, git, GitHub, R, and RStudio.

WEEK 1

Week 1

During Week 1, you'll learn about the goals and objectives of the Data Science Specialization and each of its components. You'll also get an overview of the field as well as instructions on how to install R.

Reading · Welcome to the Data Scientist's Toolbox

Reading · Pre-Course Survey

Reading · Syllabus

Reading · Specialization Textbooks

Video · Specialization Motivation

Reading · The Elements of Data Analytic Style

Video · The Data Scientist's Toolbox

Video · Getting Help

Video · Finding Answers

Video · R Programming Overview

Video · Getting Data Overview

Video · Exploratory Data Analysis Overview

Video · Reproducible Research Overview

Video · Statistical Inference Overview

Video · Regression Models Overview

Video · Practical Machine Learning Overview

Video · Building Data Products Overview

Video · Installing R on Windows {Roger Peng}

Video · Install R on a Mac {Roger Peng}

Video · Installing Rstudio {Roger Peng}

Video · Installing Outside Software on Mac (OS X Mavericks)

Quiz · Week 1 Quiz

WEEK 2

Week 2: Installing the Toolbox

This is the most lecture-intensive week of the course. The primary goal is to get you set up with R, Rstudio, Github, and the other tools we will use throughout the Data Science Specialization and your ongoing work as a data scientist.

Video · Tips from Coursera Users - Optional Video

Video · Command Line Interface

Video · Introduction to Git

Video · Introduction to Github

Video · Creating a Github Repository

Video · Basic Git Commands

Video · Basic Markdown

Video · Installing R Packages

Video · Installing Rtools

Quiz · Week 2 Quiz

WEEK 3

Week 3: Conceptual Issues

The Week 3 lectures focus on conceptual issues behind study design and turning data into knowledge. If you have trouble or want to explore issues in more depth, please seek out answers on

the forums. They are a great resource! If you happen to be a superstar who already gets it, please take the time to help your classmates by answering their questions as well. This is one of the best ways to practice using and explaining your skills to others. These are two of the key characteristics of excellent data scientists.

Video · Types of Questions

Video · What is Data?

Video · What About Big Data?

Video · Experimental Design

Quiz · Week 3 Quiz

WEEK 4

Week 4: Course Project Submission & Evaluation

In Week 4, we'll focus on the Course Project. This is your opportunity to install the tools and set up the accounts that you'll need for the rest of the specialization and for work in data science.

Peer Review · Course Project

Reading · Post-Course Survey

COURSE 2: R PROGRAMMING

In this course you will learn how to program in R and how to use R for effective data analysis. You will learn how to install and configure software necessary for a statistical programming environment and describe generic programming language concepts as they are implemented in a high-level statistical language. The course covers practical issues in statistical computing which includes programming in R, reading data into R, accessing R packages, writing R functions, debugging, profiling R code, and organizing and commenting R code. Topics in statistical data analysis will provide working examples.

WEEK 1

Week 1: Background, Getting Started, and Nuts & Bolts

This week covers the basics to get you started up with R. The Background Materials lesson contains information about course mechanics and some videos on installing R. The Week 1 videos cover the history of R and S, go over the basic data types in R, and describe the functions for reading and

writing data. I recommend that you watch the videos in the listed order, but watching the videos out of order isn't going to ruin the story.

Reading · Welcome to R Programming

Reading · About the Instructor


Reading · Syllabus

Reading · Course Textbook

Reading · Course Supplement: The Art of Data Science

Reading · Data Science Podcast: Not So Standard Deviations

Video · Installing R on a Mac

Video · Installing R on Windows

Video · Installing R Studio (Mac)

Video · Writing Code / Setting Your Working Directory (Windows)

Video · Writing Code / Setting Your Working Directory (Mac)

Reading · Getting Started and R Nuts and Bolts

Video · Introduction

Video · Overview and History of R

Video · Getting Help

Video · R Console Input and Evaluation

Video · Data Types - R Objects and Attributes

Video · Data Types - Vectors and Lists

Video · Data Types - Matrices

Video · Data Types - Factors

Video · Data Types - Missing Values

Video · Data Types - Data Frames

Video · Data Types - Names Attribute

Video · Data Types - Summary

Video · Reading Tabular Data

Video · Reading Large Tables

Video · Textual Data Formats

Video · Connections: Interfaces to the Outside World

Video · Subsetting - Basics

Video · Subsetting - Lists

Video · Subsetting - Matrices

Video · Subsetting - Partial Matching

Video · Subsetting - Removing Missing Values

Video · Vectorized Operations

Quiz · Week 1 Quiz

Video · Introduction to swirl

Reading · Practical R Exercises in swirl Part 1

Practice Programming Assignment · swirl Lesson 1: Basic Building Blocks

Practice Programming Assignment · swirl Lesson 2: Workspace and Files

Practice Programming Assignment · swirl Lesson 3: Sequences of Numbers

Practice Programming Assignment · swirl Lesson 4: Vectors

Practice Programming Assignment · swirl Lesson 5: Missing Values

Practice Programming Assignment · swirl Lesson 6: Subsetting Vectors

Practice Programming Assignment · swirl Lesson 7: Matrices and Data Frames

WEEK 2

Week 2: Programming with R

Welcome to Week 2 of R Programming. This week, we take the gloves off, and the lectures cover key topics like control structures and functions. We also introduce the first programming assignment for the course, which is due at the end of the week.

Reading · Week 2: Programming with R

Video · Control Structures - Introduction

Video · Control Structures - If-else

Video · Control Structures - For loops

Video · Control Structures - While loops

Video · Control Structures - Repeat, Next, Break

Video · Your First R Function

Video · Functions (part 1)

Video · Functions (part 2)

Video · Scoping Rules - Symbol Binding

Video · Scoping Rules - R Scoping Rules

Video · Scoping Rules - Optimization Example (OPTIONAL)

Video · Coding Standards

Video · Dates and Times


Practice Programming Assignment · swirl Lesson 1: Logic

Practice Programming Assignment · swirl Lesson 2: Functions

Practice Programming Assignment · swirl Lesson 3: Dates and Times

Quiz · Week 2 Quiz

Reading · Programming Assignment 1 INSTRUCTIONS: Air Pollution

Quiz · Programming Assignment 1: Quiz

WEEK 3

Week 3: Loop Functions and Debugging

We have now entered the third week of R Programming, which also marks the halfway point. The lectures this week cover loop functions and the debugging tools in R. These aspects of R make R useful for both interactive work and writing longer code, and so they are commonly used in practice.

Reading · Week 3: Loop Functions and Debugging

Video · Loop Functions - lapply

Video · Loop Functions - apply

Video · Loop Functions - mapply

Video · Loop Functions - tapply

Video · Loop Functions - split

Video · Debugging Tools - Diagnosing the Problem

Video · Debugging Tools - Basic Tools

Video · Debugging Tools - Using the Tools


Practice Programming Assignment · swirl Lesson 1: lapply and sapply

Practice Programming Assignment · swirl Lesson 2: vapply and tapply

Quiz · Week 3 Quiz

Peer Review · Programming Assignment 2: Lexical Scoping

WEEK 4

Week 4: Simulation & Profiling

This week covers how to simulate data in R, which serves as the basis for doing simulation studies. We also cover the profiler in R which lets you collect detailed information on how your R functions are running and to identify bottlenecks that can be addressed. The profiler is a key tool in helping you optimize your programs. Finally, we cover the str function, which I personally believe is the most useful function in R.

Reading · Week 4: Simulation & Profiling

Video · The str Function

Video · Simulation - Generating Random Numbers

Video · Simulation - Simulating a Linear Model

Video · Simulation - Random Sampling

Video · R Profiler (part 1)

Video · R Profiler (part 2)

Quiz · Week 4 Quiz


Practice Programming Assignment · swirl Lesson 1: Looking at Data

Practice Programming Assignment · swrl Lesson 2: Simulation

Practice Programming Assignment · swirl Lesson 3: Base Graphics

Reading · Programming Assignment 3 INSTRUCTIONS: Hospital Quality

Quiz · Programming Assignment 3: Quiz


COURSE 3: GETTING AND CLEANING DATA

Before you can work with data you have to get some. This course will cover the basic ways that data can be obtained. The course will cover obtaining data from the web, from APIs, from databases and from colleagues in various formats. It will also cover the basics of data cleaning and how to make data “tidy”. Tidy data dramatically speed downstream data analysis tasks. The course will also cover the components of a complete data set including raw data, processing instructions, codebooks, and processed data. The course will cover the basics needed for collecting, cleaning, and sharing data.

WEEK 1

Week 1

In this first week of the course, we look at finding data and reading different file types.

Reading · Welcome to Week 1

Reading · Syllabus


Video · Obtaining Data Motivation

Video · Raw and Processed Data

Video · Components of Tidy Data

Video · Downloading Files

Video · Reading Local Files

Video · Reading Excel Files

Video · Reading XML

Video · Reading JSON

Video · The data.table Package


Quiz · Week 1 Quiz

WEEK 2

Week 2

Welcome to Week 2 of Getting and Cleaning Data! The primary goal is to introduce you to the most common data storage systems and the appropriate tools to extract data from web or from databases like MySQL.

Video · Reading from MySQL

Video · Reading from HDF5

Video · Reading from The Web

Video · Reading From APIs

Video · Reading From Other Sources

Quiz · Week 2 Quiz

WEEK 3

Week 3

Welcome to Week 3 of Getting and Cleaning Data! This week the lectures will focus on organizing, merging and managing the data you have collected using the lectures from Weeks 1 and 2.

Video · Subsetting and Sorting

Video · Summarizing Data

Video · Creating New Variables

Video · Reshaping Data

Video · Managing Data Frames with dplyr - Introduction

Video · Managing Data Frames with dplyr - Basic Tools

Video · Merging Data


Practice Programming Assignment · swirl Lesson 1: Manipulating Data with dplyr

Practice Programming Assignment · swirl Lesson 2: Grouping and Chaining with dplyr

Practice Programming Assignment · swirl Lesson 3: Tidying Data with tidyr

Quiz · Week 3 Quiz

WEEK 4

Week 4

Welcome to Week 4 of Getting and Cleaning Data! This week we finish up with lectures on text and date manipulation in R. In this final week we will also focus on peer grading of Course Projects.

Video · Editing Text Variables

Video · Regular Expressions I

Video · Regular Expressions II

Video · Working with Dates

Video · Data Resources


Practice Programming Assignment · swirl Lesson 1: Dates and Times with lubridate

Quiz · Week 4 Quiz

Peer Review · Getting and Cleaning Data Course Project


COURSE 4: EXPLORATORY DATA ANALYSIS

This course covers the essential exploratory techniques for summarizing data. These techniques are typically applied before formal modeling commences and can help inform the development of more complex statistical models. Exploratory techniques are also important for eliminating or sharpening potential hypotheses about the world that can be addressed by the data. We will cover in detail the plotting systems in R as well as some of the basic principles of constructing data graphics. We will also cover some of the common multivariate statistical techniques used to visualize high-dimensional data.

WEEK 1

Week 1

This week covers the basics of analytic graphics and the base plotting system in R. We've also included some background material to help you install R if you haven't done so already.

Reading · Welcome to Exploratory Data Analysis

Reading · Syllabus



Reading · Exploratory Data Analysis with R Book

Reading · The Art of Data Science

Video · Installing R on Windows (3.2.1)

Video · Installing R on a Mac (3.2.1)

Video · Installing R Studio (Mac)

Video · Setting Your Working Directory (Windows)

Video · Setting Your Working Directory (Mac)

Video · Principles of Analytic Graphics

Video · Exploratory Graphs (part 1)

Video · Exploratory Graphs (part 2)

Video · Plotting Systems in R

Video · Base Plotting System (part 1)

Video · Base Plotting System (part 2)

Video · Base Plotting Demonstration

Video · Graphics Devices in R (part 1)

Video · Graphics Devices in R (part 2)


Practice Programming Assignment · swirl Lesson 1: Principles of Analytic Graphs

Practice Programming Assignment · swirl Lesson 2: Exploratory Graphs

Practice Programming Assignment · swirl Lesson 3: Graphics Devices in R

Practice Programming Assignment · swirl Lesson 4: Plotting Systems

Practice Programming Assignment · swirl Lesson 5: Base Plotting System

Quiz · Week 1 Quiz

Peer Review · Course Project 1

COURSE 5: REPRODUCIBLE RESEARCH

This course focuses on the concepts and tools behind reporting modern data analyses in a reproducible manner. Reproducible research is the idea that data analyses, and more generally, scientific claims, are published with their data and software code so that others may verify the findings and build upon them. The need for reproducibility is increasing dramatically as data analyses become more complex, involving larger datasets and more sophisticated computations. Reproducibility allows for people to focus on the actual content of a data analysis, rather than on superficial details reported in a written summary. In addition, reproducibility makes an analysis more useful to others because the data and code that actually conducted the analysis are available. This course will focus on literate statistical analysis tools which allow one to publish data analyses in a single document that allows others to easily execute the same analysis to obtain the same results.

WEEK 1

Week 1: Concepts, Ideas, & Structure

This week will cover the basic ideas of reproducible research since they may be unfamiliar to some of you. We also cover structuring and organizing a data analysis to help make it more reproducible. I recommend that you watch the videos in the order that they are listed on the web page, but watching the videos out of order isn't going to ruin the story.


Reading · Syllabus

Reading · Pre-course survey

Reading · Course Book: Report Writing for Data Science in R

Video · What is Reproducible Research About?

Video · Reproducible Research: Concepts and Ideas (part 1)



Video · Scripting Your Analysis

Video · Structure of a Data Analysis (part 1)

Video · Structure of a Data Analysis (part 2)

Video · Organizing Your Analysis

Video · Use R version 3.1.1

Quiz · Week 1 Quiz

WEEK 2

Week 2: Markdown & knitr

This week we cover some of the core tools for developing reproducible documents. We cover the literate programming tool knitr and show how to integrate it with Markdown to publish reproducible web documents. We also introduce the first peer assessment which will require you to write up a reproducible data analysis using knitr.

Video · Coding Standards in R

Video · Markdown

Video · R Markdown

Video · R Markdown Demonstration

Video · knitr (part 1)




Quiz · Week 2 Quiz

Video · Introduction to Course Project 1


WEEK 3

Week 3: Reproducible Research Checklist & Evidence-based Data Analysis

This week covers what one could call a basic check list for ensuring that a data analysis is reproducible. While it's not absolutely sufficient to follow the check list, it provides a necessary minimum standard that would be applicable to almost any area of analysis.

Video · Communicating Results

Video · RPubs

Video · Reproducible Research Checklist (part 1)



Video · Evidence-based Data Analysis (part 1)





WEEK 4

Week 4: Case Studies & Commentaries

This week there are two case studies involving the importance of reproducibility in science for you to watch.

Video · Caching Computations

Video · Case Study: Air Pollution

Video · Case Study: High Throughput Biology

Video · Commentaries on Data Analysis

Video · Introduction to Peer Assessment 2



COURSE 6: STATISTICAL INFERENCE

Statistical inference is the process of drawing conclusions about populations or scientific truths from data. There are many modes of performing inference including statistical modeling, data oriented strategies and explicit use of designs and randomization in analyses. Furthermore, there are broad theories (frequentists, Bayesian, likelihood, design based, …) and numerous complexities (missing data, observed and unobserved confounding, biases) for performing inference. A practitioner can often be left in a debilitating maze of techniques, philosophies and nuance. This course presents the fundamentals of inference in a practical approach for getting things done. After taking this course, students will understand the broad directions of statistical inference and use this information for making informed choices in analyzing data.

WEEK 1

Week 1: Probability & Expected Values

This week, we'll focus on the fundamentals including probability, random variables, expectations and more.

Video · Introductory video

Reading · Welcome to Statistical Inference

Reading · Some introductory comments


Reading · Syllabus

Reading · Course Book: Statistical Inference for Data Science

Reading · Data Science Specialization Community Site

Reading · Homework Problems

Reading · Probability

Video · 02 01 Introduction to probability

Video · 02 02 Probability mass functions

Video · 02 03 Probability density functions

Reading · Conditional probability

Video · 03 01 Conditional Probability

Video · 03 02 Bayes' rule

Video · 03 03 Independence

Reading · Expected values

Video · 04 01 Expected values

Video · 04 02 Expected values, simple examples

Video · 04 03 Expected values for PDFs

Reading · Practical R Exercises in swirl 1

Practice Programming Assignment · swirl Lesson 1: Introduction

Practice Programming Assignment · swirl Lesson 2: Probability1

Practice Programming Assignment · swirl Lesson 3: Probability2

Practice Programming Assignment · swirl Lesson 4: ConditionalProbability

Practice Programming Assignment · swirl Lesson 5: Expectations

Quiz · Quiz 1

WEEK 2

Week 2: Variability, Distribution, & Asymptotics

We're going to tackle variability, distributions, limits, and confidence intervals.

Reading · Variability

Video · 05 01 Introduction to variability

Video · 05 02 Variance simulation examples

Video · 05 03 Standard error of the mean

Video · 05 04 Variance data example

Reading · Distributions

Video · 06 01 Binomial distrubtion

Video · 06 02 Normal distribution

Video · 06 03 Poisson

Reading · Asymptotics

Video · 07 01 Asymptotics and LLN

Video · 07 02 Asymptotics and the CLT

Video · 07 03 Asymptotics and confidence intervals


Practice Programming Assignment · swirl Lesson 1: Variance

Practice Programming Assignment · swirl Lesson 2: CommonDistros

Practice Programming Assignment · swirl Lesson 3: Asymptotics

Quiz · Quiz 2

WEEK 3

Week: Intervals, Testing, & Pvalues

We will be taking a look at intervals, testing, and pvalues in this lesson.

Reading · Confidence intervals

Video · 08 01 T confidence intervals

Video · 08 02 T confidence intervals example

Video · 08 03 Independent group T intervals

Video · 08 04 A note on unequal variance

Reading · Hypothesis testing

Video · 09 01 Hypothesis testing

Video · 09 02 Example of choosing a rejection region

Video · 09 03 T tests

Video · 09 04 Two group testing

Reading · P-values

Video · 10 01 Pvalues

Video · 10 02 Pvalue further examples

Reading · Knitr

Video · Just enough knitr to do the project


Practice Programming Assignment · swirl Lesson 1: T Confidence Intervals

Practice Programming Assignment · swirl Lesson 2: Hypothesis Testing

Practice Programming Assignment · swirl Lesson 3: P Values

Quiz · Quiz 3

WEEK 4

Week 4: Power, Bootstrapping, & Permutation Tests

We will begin looking into power, bootstrapping, and permutation tests.

Reading · Power

Video · 11 01 Power

Video · 11 02 Calculating Power

Video · 11 03 Notes on power

Video · 11 04 T test power

Video · 12 01 Multiple Comparisons

Reading · Resampling

Video · 13 01 Bootstrapping

Video · 13 02 Bootstrapping example

Video · 13 03 Notes on the bootstrap

Video · 13 04 Permutation tests

Quiz · Quiz 4

Peer Review · Statistical Inference Course Project


Practice Programming Assignment · swirl Lesson 1: Power

Practice Programming Assignment · swirl Lesson 2: Multiple Testing

Practice Programming Assignment · swirl Lesson 3: Resampling


COURSE 7: REGRESSION MODELS

Linear models, as their name implies, relates an outcome to a set of predictors of interest using linear assumptions. Regression models, a subset of linear models, are the most important statistical analysis tool in a data scientist’s toolkit. This course covers regression analysis, least squares and inference using regression models. Special cases of the regression model, ANOVA and ANCOVA will be covered as well. Analysis of residuals and variability will be investigated. The course will cover modern thinking on model selection and novel uses of regression models including scatterplot smoothing.

WEEK 1

Week 1: Least Squares and Linear Regression

This week, we focus on least squares and linear regression.

Reading · Welcome to Regression Models

Reading · Book: Regression Models for Data Science in R

Reading · Syllabus


Reading · Data Science Specialization Community Site

Reading · Where to get more advanced material

Reading · Regression

Video · Introduction to Regression

Video · Introduction: Basic Least Squares

Reading · Technical details

Video · Technical Details (Skip if you'd like)

Video · Introductory Data Example

Reading · Least squares

Video · Notation and Background

Video · Linear Least Squares

Video · Linear Least Squares Coding Example

Video · Technical Details (Skip if you'd like)

Reading · Regression to the mean

Video · Regression to the Mean


Practice Programming Assignment · swirl Lesson 1: Introduction

Practice Programming Assignment · swirl Lesson 2: Residuals

Practice Programming Assignment · swirl Lesson 3: Least Squares Estimation

Quiz · Quiz 1

WEEK 2

Week 2: Linear Regression & Multivariable Regression

This week, we will work through the remainder of linear regression and then turn to the first part of multivariable regression.

Reading · *Statistical* linear regression models

Video · Statistical Linear Regression Models

Video · Interpreting Coefficients

Video · Linear Regression for Prediction

Reading · Residuals

Video · Residuals

Video · Residuals, Coding Example

Video · Residual Variance

Reading · Inference in regression

Video · Inference in Regression

Video · Coding Example

Video · Prediction

Reading · Looking ahead to the project

Video · Really, really quick intro to knitr


Practice Programming Assignment · swirl Lesson 1: Residual Variation

Practice Programming Assignment · swirl Lesson 2: Introduction to Multivariable Regression

Practice Programming Assignment · swirl Lesson 3: MultiVar Examples

Quiz · Quiz 2

WEEK 3

Week 3: Multivariable Regression, Residuals, & Diagnostics

This week, we'll build on last week's introduction to multivariable regression with some examples and then cover residuals, diagnostics, variance inflation, and model comparison.

Reading · Multivariable regression

Video · Multivariable Regression part I

Video · Multivariable Regression part II

Video · Multivariable Regression Continued

Video · Multivariable Regression Examples part I

Video · Multivariable Regression Examples part II

Video · Multivariable Regression Examples part III

Video · Multivariable Regression Examples part IV

Reading · Adjustment

Video · Adjustment Examples

Reading · Residuals

Video · Residuals and Diagnostics part I

Video · Residuals and Diagnostics part II

Video · Residuals and Diagnostics part III

Reading · Model selection

Video · Model Selection part I

Video · Model Selection part II

Video · Model Selection part III


Practice Programming Assignment · swirl Lesson 1: MultiVar Examples2

Practice Programming Assignment · swirl Lesson 2: MultiVar Examples3

Practice Programming Assignment · swirl Lesson 3: Residuals Diagnostics and Variation

Quiz · Quiz 3

WEEK 4

Week 4: Logistic Regression and Poisson Regression

This week, we will work on generalized linear models, including binary outcomes and Poisson regression.

Reading · GLMs

Video · GLMs

Reading · Logistic regression

Video · Logistic Regression part I

Video · Logistic Regression part II

Video · Logistic Regression part III

Reading · Count Data

Video · Poisson Regression part I

Video · Poisson Regression part II

Reading · Mishmash

Video · Hodgepodge


Practice Programming Assignment · swirl Lesson 1: Variance Inflation Factors

Practice Programming Assignment · swirl Lesson 2: Overfitting and Underfitting

Practice Programming Assignment · swirl Lesson 3: Binary Outcomes

Practice Programming Assignment · swirl Lesson 4: Count Outcomes

Quiz · Quiz 4

Peer Review · Regression Models Course Project


COURSE 8: PRACTICAL MACHINE LEARNING

One of the most common tasks performed by data scientists and data analysts are prediction and machine learning. This course will cover the basic components of building and applying prediction functions with an emphasis on practical applications. The course will provide basic grounding in concepts such as training and tests sets, overfitting, and error rates. The course will also introduce a range of model based and algorithmic machine learning methods including regression, classification trees, Naive Bayes, and random forests. The course will cover the complete process of building prediction functions including data collection, feature creation, algorithms, and evaluation. WEEK 1

Week 1: Prediction, Errors, and Cross Validation This week will cover prediction, relative importance of steps, errors, and cross validation.

Reading · Welcome to Practical Machine Learning

Reading · Syllabus


Video · Prediction motivation

Video · What is prediction?

Video · Relative importance of steps

Video · In and out of sample errors

Video · Prediction study design

Video · Types of errors

Video · Receiver Operating Characteristic

Video · Cross validation

Video · What data should you use?

Quiz · Quiz 1

WEEK 2

Week 2: The Caret Package

This week will introduce the caret package, tools for creating features and preprocessing.

Video · Caret package

Video · Data slicing

Video · Training options

Video · Plotting predictors

Video · Basic preprocessing

Video · Covariate creation

Video · Preprocessing with principal components analysis

Video · Predicting with Regression

Video · Predicting with Regression Multiple Covariates

Quiz · Quiz 2

WEEK 3

Week 3: Predicting with trees, Random Forests, & Model Based Predictions

This week we introduce a number of machine learning algorithms you can use to complete your course project.

Video · Predicting with trees

Video · Bagging

Video · Random Forests

Video · Boosting

Video · Model Based Prediction

Quiz · Quiz 3

WEEK 4

Week 4: Regularized Regression and Combining Predictors

This week, we will cover regularized regression and combining predictors.

Video · Regularized regression

Video · Combining predictors

Video · Forecasting

Video · Unsupervised Prediction

Quiz · Quiz 4

Reading · Course Project Instructions (READ FIRST)

Peer Review · Prediction Assignment Writeup

Quiz · Course Project Prediction Quiz


ALGORITHMS SPECIALIZATION

COURSE 1: ALGORITHMIC TOOLBOX

The course covers basic algorithmic techniques and ideas for computational problems arising frequently in practical applications: sorting and searching, divide and conquer, greedy algorithms, dynamic programming. We will learn a lot of theory: how to sort data and how it helps for searching; how to break a large problem into pieces and solve them recursively; when it makes sense to proceed greedily; how dynamic programming is used in genomic studies. You will practice solving computational problems, designing new algorithms, and implementing solutions efficiently (so that they run in less than a second).

WEEK 1

Welcome

Welcome to the first module of Data Structures and Algorithms! Here we will provide an overview of where algorithms and data structures are used (hint: everywhere) and walk you through a few sample programming challenges. The programming challenges represent an important (and often the most difficult!) part of this specialization because the only way to fully understand an algorithm is to implement it. Writing correct and efficient programs is hard; please don’t be surprised if they don’t work as you planned—our first programs did not work either! And we will be helping you to make your journey through the specialization by showing how to implement your first programming challenges. We will also introduce testing techniques that will help to increase your chances of passing the assignments from the first attempt. In case your program does not work as intended, we will show how to fix it, even if you don’t yet know what test your implementation currently fails on.

Video · Welcome!

Reading · Overview

Reading · Available Programming Languages

Programming Assignment · A plus B

Video · Solving the Problem (screencast)

Reading · What's Up Next?

Practice Quiz · Solving Programming Assignments

Programming Assignment · Maximum Pairwise Product

Reading · Solving the Problem: Improving the Naive Solution, Testing, Debugging

Video · Solving the Problem: Improving the Naive Solution, Testing, Debugging

Reading · Stress Testing: the [Almost] Silver Bullet for Debugging

Video · Stress Test - Implementation

Video · Stress Test - Find the Test and Debug

Video · Stress Test - More Testing, Submit and Pass!

Reading · FAQ on Programming Assignments

Practice Quiz · Solving Programming Assignments

Reading · Acknowledgements

WEEK 2

Introduction

In this module you will learn that programs based on efficient algorithms can solve the same problem billions of times faster than programs based on naïve algorithms. You will learn how to estimate the running time and memory of an algorithm without even implementing it. Armed with this knowledge, you will be able to compare various algorithms, select the most efficient ones, and finally implement them as our programming challenges!

Video · Why Study Algorithms?

Video · Coming Up

Video · Problem Overview

Video · Naive Algorithm

Video · Efficient Algorithm


Video · Problem Overview and Naive Algorithm

Video · Efficient Algorithm


Video · Computing Runtimes

Video · Asymptotic Notation

Video · Big-O Notation

Video · Using Big-O


Quiz · Logarithms

Quiz · Big-O

Quiz · Growth rate

Video · Course Overview

Programming Assignment · Programming Assignment 1: Introduction

WEEK 3

Greedy Algorithms

In this module you will learn about seemingly naïve yet powerful class of algorithms called greedy algorithms. After you will learn the key idea behind the greedy algorithms, you may feel that they represent the algorithmic Swiss army knife that can be applied to solve nearly all programming challenges in this course. But be warned: with a few exceptions that we will cover, this intuitive idea rarely works in practice! For this reason, it is important to prove that a greedy algorithm always produces an optimal solution before using this algorithm. In the end of this module, we will test your intuition and taste for greedy algorithms by offering several programming challenges.

Video · Largest Number

Video · Car Fueling

Video · Car Fueling - Implementation and Analysis

Video · Main Ingredients of Greedy Algorithms

Quiz · Greedy Algorithms

Video · Celebration Party Problem

Video · Efficient Algorithm for Grouping Children

Video · Analysis and Implementation of the Efficient Algorithm

Video · Long Hike

Video · Fractional Knapsack - Implementation, Analysis and Optimization

Video · Review of Greedy Algorithms


Quiz · Fractional Knapsack

Programming Assignment · Programming Assignment 2: Greedy Algorithms

WEEK 4

Divide-and-Conquer

In this module you will learn about a powerful algorithmic technique called Divide and Conquer. Based on this technique, you will see how to search huge databases millions of times faster than using naïve linear search. You will even learn that the standard way to multiply numbers (that you learned in the grade school) is far from the being the fastest! We will then apply the divide-and-conquer technique to design two efficient algorithms (merge sort and quick sort) for sorting huge lists, a problem that finds many applications in practice. Finally, we will show that these two algorithms are optimal, that is, no algorithm can sort faster!

Video · Intro

Video · Linear Search

Video · Binary Search

Video · Binary Search Runtime


Quiz · Linear Search and Binary Search

Video · Problem Overview and Naïve Solution

Video · Naïve Divide and Conquer Algorithm

Video · Faster Divide and Conquer Algorithm


Quiz · Polynomial Multiplication

Video · What is the Master Theorem?

Video · Proof of the Master Theorem


Quiz · Master Theorem


Video · Selection Sort

Video · Merge Sort

Video · Lower Bound for Comparison Based Sorting

Video · Non-Comparison Based Sorting Algorithms


Quiz · Sorting

Video · Overview

Video · Algorithm

Video · Random Pivot

Video · Running Time Analysis (optional)

Video · Equal Elements

Video · Final Remarks


Quiz · Quick Sort

Programming Assignment · Programming Assignment 3: Divide and Conquer

WEEK 5

Dynamic Programming

In this final module of the course you will learn about the powerful algorithmic technique for solving many optimization problems called Dynamic Programming. It turned out that dynamic programming can solve many problems that evade all attempts to solve them using greedy or divide-and-conquer strategy. There are countless applications of dynamic programming in practice: from maximizing the advertisement revenue of a TV station, to search for similar Internet pages, to gene finding (the problem where biologists need to find the minimum number of mutations to transform one gene into another). You will learn how the same idea helps to automatically make spelling corrections and to show the differences between two versions of the same text.

Video · Change Problem

Quiz · Change Money


Video · The Alignment Game

Video · Computing Edit Distance

Video · Reconstructing an Optimal Alignment

Quiz · Edit Distance



Quiz · Knapsack

Video · Knapsack with Repetitions

Video · Knapsack without Repetitions




Quiz · Maximum Value of an Arithmetic Expression

Video · Subproblems

Video · Algorithm

Video · Reconstructing a Solution

Programming Assignment · Programming Assignment 4: Dynamic Programming

COURSE 2: DATA STRUCTURES

A good algorithm usually comes together with a set of good data structures that allow the algorithm to manipulate the data efficiently. In this course, we consider the common data structures that are used in various computational problems. You will learn how these data structures are implemented in different programming languages and will practice implementing them in our programming assignments. This will help you to understand what is going on inside a particular built-in implementation of a data structure and what to expect from it. You will also learn typical use cases for these data structures. A few examples of questions that we are going to cover in this class are the following: 1. What is a good strategy of resizing a dynamic array? 2. How priority queues are

implemented in C++, Java, and Python? 3. How to implement a hash table so that the amortized running time of all operations is O(1) on average? 4. What are good strategies to keep a binary tree balanced? You will also learn how services like Dropbox manage to upload some large files instantly and to save a lot of storage space!

WEEK 1

Basic Data Structures

In this module, you will learn about the basic data structures used throughout the rest of this course. We start this module by looking in detail at the fundamental building blocks: arrays and linked lists. From there, we build up two important data structures: stacks and queues. Next, we look at trees: examples of how they’re used in Computer Science, how they’re implemented, and the various ways they can be traversed. Finally, we discuss Dynamic Arrays: a way of using arrays when it is unknown ahead-of-time how many elements will be needed. Here, we also discuss amortized analysis: a method of determining the amortized cost of an operation over a sequence of operations. Once you’ve completed this module, you will be able to implement any of these data structures, as well as have a solid understanding of the costs of the operations, as well as the tradeoffs involved in using each data structure.

Reading · Welcome

Video · Arrays

Video · Singly-Linked Lists

Video · Doubly-Linked Lists

Reading · Slides and External References

Video · Stacks

Video · Queues


Video · Trees

Video · Tree Traversal


Video · Dynamic Arrays

Video · Amortized Analysis: Aggregate Method

Video · Amortized Analysis: Banker's Method

Video · Amortized Analysis: Physicist's Method

Video · Amortized Analysis: Summary

Quiz · Dynamic Arrays and Amortized Analysis


Reading · Available Programming Languages

Reading · FAQ on Programming Assignments

Programming Assignment · Programming Assignment 1: Basic Data Structures

Reading · Acknowledgements

WEEK 2

Priority Queues and Disjoint Sets

We start this module by considering priority queues which are used to efficiently schedule jobs, either in the context of a computer operating system or in real life, to sort huge files, which is the most important building block for any Big Data processing algorithm, and to efficiently compute shortest paths in graphs, which is a topic we will cover in our next course. For this reason, priority queues have built-in implementations in many programming languages, including C++, Java, and Python. We will see that these implementations are based on a beautiful idea of storing a complete binary tree in an array that allows to implement all priority queue methods in just few lines of code. We will then switch to disjoint sets data structure that is used, for example, in dynamic graph connectivity and image processing. We will see again how simple and natural ideas lead to an implementation that is both easy to code and very efficient. By completing this module, you will be able to implement both these data structures efficiently from scratch.


Video · Naive Implementations

Reading · Slides

Video · Binary Trees

Reading · Tree Height Remark

Video · Basic Operations

Video · Complete Binary Trees

Video · Pseudocode


Video · Heap Sort

Video · Building a Heap


Quiz · Priority Queues: Quiz


Video · Overview

Video · Naive Implementations


Video · Trees

Video · Union by Rank

Video · Path Compression

Video · Analysis (Optional)

Quiz · Quiz: Disjoint Sets


Programming Assignment · Programming Assignment 2: Priority Queues and Disjoint Sets

WEEK 3

Hash Tables

In this module you will learn about very powerful and widely used technique called hashing. Its applications include implementation of programming languages, file systems, pattern search, distributed key-value storage and many more. You will learn how to implement data structures to store and modify sets of objects and mappings from one type of objects to another one. You will see that naive implementations either consume huge amount of memory or are slow, and then you will learn to implement hash tables that use linear memory and work in O(1) on average! In the end, you will learn how hash functions are used in modern distibuted systems and how they are used to optimize storage of services like Dropbox, Google Drive and Yandex Disk!

Video · Applications of Hashing

Video · Analysing Service Access Logs

Video · Direct Addressing

Video · List-based Mapping

Video · Hash Functions

Video · Chaining Scheme

Video · Chaining Implementation and Analysis

Video · Hash Tables


Video · Phone Book Problem

Video · Phone Book Problem - Continued

Video · Universal Family

Video · Hashing Integers

Video · Proof: Upper Bound for Chain Length (Optional)

Video · Proof: Universal Family for Integers (Optional)

Video · Hashing Strings

Video · Hashing Strings - Cardinality Fix


Quiz · Hash Tables and Hash Functions

Video · Search Pattern in Text

Video · Rabin-Karp's Algorithm

Video · Optimization: Precomputation

Video · Optimization: Implementation and Analysis


Video · Instant Uploads and Storage Optimization in Dropbox

Video · Distributed Hash Tables


Programming Assignment · Programming Assignment 3: Hash Tables

WEEK 4

Binary Search Trees

In this module we study binary search trees, which are a data structure for doing searches on dynamically changing ordered sets. You will learn about many of the difficulties in accomplishing this task and the ways in which we can overcome them. In order to do this you will need to learn the basic structure of binary search trees, how to insert and delete without destroying this structure, and how to ensure that the tree remains balanced. We will also discuss applications of this data structure for recombining ordered lists of elements.


Video · Search Trees

Video · Basic Operations

Video · Balance


Video · AVL Trees

Video · AVL Tree Implementation

Video · Split and Merge


Video · Applications


Video · Splay Trees


Programming Assignment · Programming Assignment 4: Binary Search Trees

COURSE 3: ALGORITHMS ON GRAPHS

If you have ever used a navigation service to find optimal route and estimate time to destination, you've used algorithms on graphs. Graphs arise in various real-world situations as there are road networks, computer networks and, most recently, social networks! If you're looking for the fastest

time to get to work, cheapest way to connect set of computers into a network or efficient algorithm to automatically find communities and opinion leaders in Facebook, you're going to work with graphs and algorithms on graphs. In this course, you will first learn what a graph is and what are some of the most important properties. Then you'll learn several ways to traverse graphs and how you can do useful things while traversing the graph in some order. We will then talk about shortest paths algorithms — from the basic ones to those which open door for 1000000 times faster algorithms used in Google Maps and other navigational services. You will use these algorithms if you choose to work on our Fast Shortest Routes industrial capstone project. We will finish with minimum spanning trees which are used to plan road, telephone and computer networks and also find applications in clustering and approximate algorithms.

COURSE 4: ALGORITHMS ON STRINGS

World and internet is full of textual information. We search for information using textual queries, we read websites, books, e-mails. All those are strings from the point of view of computer science. To make sense of all that information and make search efficient, search engines use many string algorithms. Moreover, the emerging field of personalized medicine uses many search algorithms to find disease-causing mutations in the human genome.

COUSE 5: ADVANCED ALGORITHMS AND COMPLEXITY

You've learned the basic algorithms now and are ready to step into the area of more complex problems and algorithms to solve them. Advanced algorithms build upon basic ones and use new ideas. We will start with networks flows which are used in more obvious applications such as optimal matchings, finding disjoint paths and flight scheduling as well as more surprising ones like image segmentation in computer vision or finding dense clusters in the advertiser-search query graphs at search engines. We then proceed to linear programming with applications in optimizing budget allocation, portfolio optimization, finding the cheapest diet satisfying all requirements, call routing in telecommunications and many others. Next we discuss inherently hard problems for which no exact good solutions are known (and not likely to be found) and how to solve them approximately in a reasonable time. We finish with some applications to Big Data and Machine Learning which are heavy on algorithms right now.

CIS 611 SELECTED COURSE MATERIALS DATABASE NORMALIZATION

INDEXES

FUNCTIONAL DEPENDENCY

STORAGE AND FILE SYSTEM

EDX ONLINE COURSES COURSE 1: INTRODUCTION TO DATA STORAGE AND MANAGEMENT TECHNOLOGIES

This course was text and video based, with no real project. With that in mind, I did complete and

pass all the assessments. This course was taught by the IEEE.

In this course, I covered and learned the following topics.

Week 1: Data Storage Fundamentals

Section 1: Enterprise IT Environment – Enterprise IT infrastructure components, direct attached

storage, networked storage, and data center

Section 2: Introduction to Virtualization – Virtualization overview, server virtualization, network

virtualization, and storage virtualization

Section 3: Data Storage Devices – Types of data storage devices, magnetic disk drive, solid state

drive, and storage interfaces and protocols

Section 4: Considerations for Storage Investment

Week 2: Enterprise Storage Solutions

Section 1: Storage Systems Components and Architecture

Section 2: Introduction to RAID – RAID overview and RAID levels

Section 3: Types of Storage Systems – Block, file, object, and unified storage systems

Section 4: Storage Area Network – Fibre Channel SAN, IP SAN, and FCoE SAN

Section 5: Network Attached Storage (NAS)

Week 3: Business Continuity and Storage Security

Section 1: Business Continuity

Section 2: Data Replication – Local replication and remote replication

Section 3: Data Backup – Backup types, backup architecture, and backup methods

Section 4: Storage Infrastructure Security – Importance of storage security and security

mechanisms

Week 4: Storage Infrastructure Management, Storage Industry Trends, and Cloud Computing

Section 1: Storage Infrastructure Management – Storage infrastructure management processes

Section 2: Introduction to Cloud Computing – Cloud computing definition, cloud characteristics,

cloud Benefits, and service level agreement (SLA)

Section 3: Cloud Service Models and Deployment Models – Infrastructure as a Service (IaaS),

Platform as a Service (PaaS), and Software as a Service (SaaS), public cloud, private cloud,

community cloud, and hybrid cloud

Section 4: Cloud Storage

Section 5: Storage Industry Trends – All flash storage, converged infrastructure, software-defined

data center, and the Third Platform

COURSE 2: INTRODUCTION TO CLOUD COMPUTING

This course focused on the logistics of cloud computing (how and when to utilize it, and less on

the actual principles of computing)

• NIST Cloud Computing Model

• Value of Model

• Model Organization

• Value to Consumers

• Value to Vendors

• New Revenue and Jobs

• Utility Computing--1961

• Time Sharing--1970s

• Large Distributed Data Centers 1980s-1990s

• Internet Computing 2000-Present

• Essential Characteristics of Cloud Computing

ADDITIONAL COURSEWORK In addition to all of the work done above, I also have a few projects I would like to mention.

SAC APPLICATION The Cleveland State IEEE student chapter hosted an event called the Student Activities

Conference this April. Schools from all over the country come to compete. I developed a full stack

web application for users to register, submit photos, view a scoreboard, receive text messages

from the event, and just be in touch with what was happening at the SAC. I built this web

application using the database knowledge I gained from Dr. Chung.

SENIOR DESIGN As you may know, my group took first place in the 2016 Washkewicz College of Engineering Senior

Design symposium. Our project, titled Cerebro, offered law enforcement a real-time application

that they can use to track suspects as they move from the scene of a crime. It is a very complex

system, but the bottom line is that it is a data driven app. The entire application was built on

Microsoft Azure cloud, and the most important note is that I used what I learned from Dr. Chung

to design and implement this application.

The link is here: https://www.csuohio.edu/engineering/multidisciplinary-cerebro-project-takes-

first-place-senior-design-symposium

“A multidisciplinary team of electrical, mechanical and computer engineering students took first

place at the Washkewicz College of Engineering’s second annual Senior Design Symposium and

Awards Dinner Friday, May 6 for their project entitled, Cerebro Real Time Security.

Cerebro uses an innovative human detection and recognition algorithm to detect humans in the

video streams of cameras within a specified area. As a crime is committed, the suspect is tagged

in the system and tracked from camera to camera as they attempt to flee. This information is then

reported to police in real time.”

WORK EXPERIENCE AND CONCLUSION I cannot stress enough how influential Dr. Chung has been on my career. Her hard work and

dedication to her students has certainly made me a better engineer. I have been offered a full-

time position at Parker Hannifin as a data engineer, and will be starting this coming Monday (May

16th). I attribute a lot of my success thus far within the company to Dr. Chung.

I will be in charge of implementing the company’s data warehouse, as well as heading the project

to deploy and make useful a Hadoop distribution. I will lead the transition of moving our existing

architecture to an off-premise design. I am eager to begin my journey in this field, and have fallen

in love with database systems and its many many many interesting sub-topics.

In conclusion, I can honestly say I have waited four whole years to be as engaged as I was this

last semester in learning.

For me, this course alone was worth the whole cost of college tuition.