Introduction to Data Science

Course Title: Introduction to Data Science

Course No: BDS101

Nature of the Course: THEORY

Semester: 1

Full Marks: 45 + 30

Pass Marks: 18 + 12

Credit Hours: 3

Course Description

This is an introductory course to teach the basics of data science, it's applications, and commonly used tools and techniques. The course is designed to introduce key ideas and methodologies used in the domain of data science. The goal of this course is to help understand the fundamental building blocks of data science.

Course Objectives

Upon the conclusion of the course, students should be able to:

Describe Data Science, skill sets needed to be a data scientist and be familiar with common tools used for data science
Understand the importance of data quality and familiarize with common data munging techniques
Understand and apply commonly used data analysis and machine learning techniques in data science
Identify the challenges in handling big data, and gain a general understanding of ecosystem of big data
Reason around ethical and privacy issues in data science and understand the common biases affecting data science

Course Contents

1. Introduction to Data Science

6 hrs

1.1. Introduction to data science

1.2. Data Science Hype

1.3. Data, Data Science, Engineering and Data-Driven Decision Making

1.4. Statistics and Data Science

1.5. Data Science Process

1.6. Data Science Profile

1.7. Data Analytics vs Data Science

1.8. Roles and Responsibilities of Data Scientist

1.9. Data Science Lifecycles

OSEMN

CRISP-DM

TDSP

1.10. Tools and Technologies

1.11. Limitations of data science

1.12. Applications of Data Science

2. Big Data

8 hrs

2.1. Structured, Semi-Structured and Unstructured data

2.2. Understanding Database, Data Warehouse and Data Lake

2.3. Characteristics of Data warehouse, ETL(Extract-transform-load) Techniques

2.4. Introduction to Big Data

2.5. Need for Big Data

2.6. Challenges of handling big data

2.7. Characteristics of big data

2.8. Map-Reduce programming paradigm, and its differences from conventional programming models

2.9. Solving Word Count Problem through Map Reduce Paradigm

2.10. Hadoop and its components

2.11. Hadoop Ecosystem

3. Data Wrangling and Feature Engineering

12 hrs

3.1. Commonly used data formats

3.2. Collecting and Importing data

3.3. Exploratory Data Analysis

3.4. Data Quality

3.5. Common issues with real world data

3.6. Data Cleaning Techniques

3.7. Data Enrichment

3.8. Data Validation

3.9. Data Publishing

3.10. Feature Engineering

Introduction to Feature Engineer

Feature Selection

Feature Selection Techniques: Filters, Wrappers and Embedded Methods

Feature Scaling and Standardization

Feature Extraction

4. Machine Learning

12 hrs

4.1. Understanding Predictive analytics and Machine Learning

4.2. Artificial Intelligence vs Machine Learning and their practical applications

4.3. Machine Learning Techniques

Supervised, Unsupervised, Semi-supervised and Reinforcement learning and their types

4.4. Regression Techniques

Linear Regression

Polynomial Regression

4.5. Classification Techniques

Logistic Regression

Decision Tree

Naïve Bayes

4.6. Clustering Techniques, and their pros and cons

K Means

K Medoids

4.7. Model Evaluation

Root Mean Squared Error

Mean Absolute Error

Mean Percentage Error

4.8. Confusion Matrix

4.9. Accuracy, Precision and Recall

5. Data Visualization and Story Telling

6 hrs

5.1. Introduction to Data Visualization, Exploratory vs Explanatory data visualization

5.2. Common Data Visualization Techniques and their usage

Table

Pivot Table

Histogram

Bar Chart

Line Chart

Scatter plot

Pie Chart

Box Plot etc.

5.3. Data Story Telling

Introduction

Need for Data Story Telling

Components of Data Storytelling

Benefits of Data Story Telling

Communicating data insights

6. Ethical Issues in Data Science

4 hrs

6.1. Ethics for Data Scientist

6.2. Case Study of Facebook and Cambridge Analytica

6.3. Common issues with privacy and data ethics

6.4. Introduction of biasness and fairness

6.5. Issues with fairness and bias in data science

6.6. Common Cognitive biases

Anchoring Bias

Sampling Bias

In group favoritism and out-group negativity

Fundamental attribution error

Negativity bias

Stereotyping

Bandwagon effect

Bias blind spot

6.7. Addressing Cognitive biases

Group unaware selection

Adjusted group thresholds

Demographic parity

Equal opportunity

Precision parity

Reference Books

1.O’Neil, Cathy and Schutt, Rachel (2013), Doing Data Science, Straight Talk From TheFrontline, O’Reilly Media
2.Skiena, Steven (2017), The Data Science Design Manual, Springer
3.Provost, Foster and Fawcett, Tom (2013). Data Science for Business: What You Need to Know about Data Mining and Data-analytic Thinking, O’Reilly Media

Notes:

This syllabus follows the official BDS curriculum of Tribhuvan University. In case of any doubt or revision, the university's published syllabus shall be considered authoritative.

Data Science