PYTHON FOR DATASCIENCE Semester I

Course Code PCSI104 CIE Marks 50

Teaching Hours/Week (L:T:P: S) 4:0:2 SEE Marks 50
Total Hours of Pedagogy 50
Total Marks 100
Credits 4 Exam Hours 3
Examination type (SEE) Theory
Course Outcomes (Course Skill Set):
CO1 Apply the basic concepts and methods of data science to organize, manage, and analyze data using suitable tools and techniques
CO2 Use methods to explore and visualize data to find patterns, spot errors, and draw useful conclusions.
CO3 Build and test simple models to make predictions or classifications from data and compare their results.
CO4 Analyze techniques to enhance model performance and develop effective data-based solutions for decision-making..
CO5 Study connections and patterns in data networks and understand the importance of ethics, privacy, and security in data science.
.
Module-1

Introduction: What is Data Science? Big Data and Data Science hype – and getting past the hype, Why now? – Datafication, Current landscape of perspectives,
Skill sets. Needed Statistical Inference: Populations and samples, Statistical modelling, probability distributions, fitting a model, - Introduction to R, Overview
of RDBMS ,Relational Model, Concepts of Tables, Rows, and Columns Keys: Primary, Foreign, Unique ,Relationships: One-to-One, One-to-Many, Many-to-Many
3. SQL Fundamentals, Introduction to SQL, Data Definition Language (DDL),CREATE, ALTER, DROP Data Manipulation Language (DML),SELECT, INSERT,
UPDATE, DELETE
Module-2
Exploratory Data Analysis and the Data Science Process: Basic tools (plots, graphs and
summary statistics) of EDA, Philosophy of EDA,The Data Science Process, Case Study: Real Direct (online real estate firm). Three Basic Machine Learning
Algorithms: Linear Regression, k-Nearest Neighbors (kNN), k-means

Module-3
One More Machine Learning Algorithm and Usage in Applications: Motivating application: Filtering Spam, Why Linear Regression and k-NN are poor choices
for Filtering Spam, Naive Bayes and why it works for Filtering Spam, Data Wrangling: APIs and other tools for scrapping the Web. Time Stamps and
Financial Modeling: Financial Modeling, In-Sample, Out-of-Sample, and Causality, Preparing Financial Data, Log Returns, The Financial Modeling
Feedback Loop.

Module-4
Feature Generation and Feature Selection (Extracting Meaning from Data): Motivating application: user (customer) retention. Feature Generation
(brainstorming, role of domain expertise, and place for imagination), Feature Selection algorithms. Filters; Wrappers; Decision Trees; Random Forests.
Recommendation Systems: Building a User-Facing Data Product, Algorithmic ingredients of a Recommendation Engine, Dimensionality Reduction, Singular Value
Decomposition, Principal Component Analysis, Exercise: build your own recommendation system

Module-5
Mining Social-Network Graphs: Social networks as graphs, Clustering of graphs, Direct discovery of communities in graphs, Partitioning of graphs, Neighborhood
properties in graphs, Data Visualization: Basic principles, ideas and tools for data visualization. Data Science and Ethical Issues, Discussions on privacy, security,
ethics, Next-generation data scientists

Suggested Learning Resources:

Books
Doing Data Science Cathy O’Neil and Rachel Schutt, Straight Talk from The
FrontlineO’Reilly2014"
ISBN: 978-1-449-35865-5
2. Mining of Massive DatasetsV2.1Jure Leskovek, AnandRajaraman and Jeffrey UllmanCambridge University Press, 2nd Edition 2014
ISBN-13: 978-1316147573
Reference Books:
1. Data Mining: Concepts and Techniques Jiawei Han, MichelineKamber and Jian Pei Morgan Kauffman, Third Edition, 2012
ISBN-10: 0123814790
2. Python and R for the Modern Data Scientist Rick J. Scavetta & Boyan Angelov
ISBN-13. 978-1492093404
Skill Development Activities Suggested
The students with the help of the course teacher can take up relevant technical –activities which will enhance their skill. The prepared report shall be
evaluated for CIE marks.

• Capability to identify business or social problems, collect suitable datasets, build data-driven models, and propose evidence-based solutions.
• Exposure to practical case studies, online datasets, and tools that enhance employability for roles such as Data Analyst, Business Intelligence Associate,
and Junior Data Scientist.

Teaching-Learning Process (Innovative Delivery Methods):

The following are sample strategies that educators may adopt to enhance the effectiveness of the teaching- learning process and facilitate the achievement of
course outcomes.
1. Flipped Classroom
2. Problem-Based Learning (PBL)
3. Case-Based Teaching
4. Simulation and Virtual Labs
5. ICT-Enabled Teaching
 6. Tool Demonstration
7. NPTEL/ Coursera Certification
8. Usage Of AI Tools
9. In-course Project
[Link] Based Learning
[Link] Based Learning

Assessment Structure:
.
Weightage CIE SEE
Quizzes [Q] 50% 50%
Quiz – I & II Each quiz will be conducted for 10 *****
(AAT) marks, adding up to 20 marks. Final test
marks will be reduced to 10 marks.
Theory Course [T] (Bloom’s Taxonomy Levels: Remembering, Understanding, Applying,
Analyzing, Evaluating, and Creating)
Test – I Each test will be conducted for 50 *****
marks, adding up to 100 marks. Final
Test – II *****
test marks will be reduced to 30 marks.
Experiential Maximum Marks: 30 *****
Learning [EL]
Case Study-based 10
Teaching–Learning /
NPTEL
Program Specific 10 *****
Requirement for EL
Assessment
Activity based 10
assessment
Maximum Marks for 70
Theory (Q + T + EL)
 Practical 30 100
Total Marks for the 100 – Scale down to 50 100 Scale
Course down to 50

CIE Practical component:

The CIE marks awarded in the case of the Practical component shall be based on the continuous evaluation of the laboratory report using a defined set of
rubrics. Each experiment report can be evaluated for 30 marks. The summation of all the experiments marks to be scaled down to 15 marks.

The laboratory test (duration 03 hours) at the end of the last week of the semester /after completion of all the experiments (whichever is early) shall be
conducted for 50 marks and scaled down to 5 marks. For laboratory test, the student is required to conduct one experiment each from both Part A and Part
B.
COPO Mapping:
CO/PO PO1 PO2 PO3 PO4 PO5 PO6
CO1 2 1 3 2 1 1
CO2 2 2 2 3 - 1
CO3 3 1 3 3 - 1
CO4 3 - 3 3 2 2
CO5 2 2 2 2 2 3
AVG
COPO Justification:
 CO CO-PO Justification
CO1Apply the basic concepts and methods PO1 (2): Develops research and analytical skills through data handling.
of data science to organize, manage, and • PO2 (1): Encourages clear technical communication while presenting results.
analyze data using suitable tools and • PO3 (3): Builds specialized knowledge of core data science concepts.
techniques • PO4 (2): Involves use of analytical tools for problem-solving.
• PO5 (1): Promotes basic teamwork during data exercises.
• PO6 (1): Supports continued learning in evolving data tools.
CO2Use methods to explore and visualize PO1 (2): Strengthens research-oriented thinking through data exploration.
data to find patterns, spot errors, and draw • PO2 (2): Improves ability to communicate insights through visual reports.
useful conclusions. • PO3 (2): Enhances domain understanding in data analysis.
• PO4 (3): Encourages analytical problem-solving using visualization tools.
• PO6 (1): Promotes ongoing learning in modern visualization techniques.
CO3Build and test simple models to make PO1 (3): Develops strong research and experimental design skills.
predictions or classifications from data and • PO2 (1): Involves basic communication of model results.
compare their results. • PO3 (3): Deepens specialized mastery in modeling and analytics.
• PO4 (3): Strengthens analytical and computational problem-solving skills.
• PO6 (1): Encourages continuous skill improvement in machine learning.
CO4Analyze techniques to enhance model • PO1 (3): Encourages research-based approach to model improvement.
performance and develop effective data- • PO3 (3): Builds advanced understanding of analytical methods.
based solutions for decision-making.. • PO4 (3): Applies analytical tools for improving decision outcomes.
• PO5 (2): Promotes collaboration in project-based problem-solving.
• PO6 (2): Fosters lifelong learning and adaptation to new analytical techniques.
CO5Study connections and patterns in data • PO1 (2): Involves analytical investigation in network structures.
networks and understand the importance of • PO2 (2): Develops communication skills for explaining complex data relationships.
ethics, privacy, and security in data science.
.
• PO3 (2): Applies specialized knowledge to network and ethical contexts.
• PO4 (2): Uses analytical tools for pattern detection and network analysis.
• PO5 (2): Promotes teamwork in ethical data handling and collaborative analysis.
• PO6 (3): Encourages continuous professional development and ethical responsibility.

Rubrics for Learning Activities

 CO → PO Mapping Outstanding (5) Exceeds Meets Needs Unsatisfactory
Expectations (4) Expectations (3) Improvement (2) (1)
Exceeds Meets Needs
CO → PO Mapping Outstanding (5) Unsatisfactory (1)
Expectations (4) Expectations (3) Improvement (2)
CO1Apply the basic Demonstrates complete
concepts and methods of understanding of data Applies most Understands basic Shows limited
Unable to apply or
data science to organize, science concepts and concepts correctly tools and applies understanding;
manage, and analyze data
explain key data
tools; applies SQL and R with minor errors in them with some needs help using
using suitable tools and handling concepts.
effectively to manage and tool usage. guidance. tools.
techniques analyze data.
CO2Use methods to Demonstrates
Performs thorough EDA Conducts analysis
explore and visualize data basic Requires guidance Unable to perform
and visualization with few errors and
to find patterns, spot understanding with to complete EDA or or explain EDA or
errors, and draw useful independently; interprets explains findings
limited visualization tasks. visualization.
conclusions insights accurately. clearly.
interpretation.
CO3Build and test simple Accurately implements Builds basic
Applies models with Attempts model
models to make multiple models (e.g., models correctly Unable to build or
minor errors in building but with
predictions or regression, classification); but needs help explain predictive
classifications from data interpretation or conceptual or
interprets and compares interpreting models.
and compare their results coding. coding errors.
outcomes effectively. results.
CO4Analyze techniques Demonstrates strong Shows good
to enhance model Can identify and Lacks
analytical skills to understanding of Needs guidance to
performance and develop apply a few understanding of
effective data-based
improve model accuracy; improvement analyze or enhance
improvement model improvement
solutions for decision- applies optimization techniques with model performance.
methods correctly. or analysis.
making.. methods effectively. some inaccuracies.
CO5Study connections Clearly analyzes social
and patterns in data
network data and Interprets network Understands Partially aware of Shows no
networks and understand
the importance of ethics,
demonstrates deep patterns well and concepts but ethical or privacy understanding of
privacy, and security in understanding of ethical, applies ethical provides limited issues; lacks full network analysis or
data science. privacy, and security concepts properly. examples or depth. application. ethics.
concerns.

Rubrics for CIE – Continuous Assessment with CO–PO Mapping

 Mapp Exceeds Meets Needs
CIE Weight Mappe Outstandi Unsatisfact
ed Expectati Expectatio Improvem
Component age (%) d COs ng (5) ory (1)
POs ons (4) ns (3) ent (2)
Demonstra
tes strong
understand
Good
ing of data
understand Understand Shows
science Fails to
ing of key s basic limited
basics and understand
Class PO1, concepts concepts knowledge
CO1,C data or apply
Tests / 20% PO3, and and tools ; unable to
O2 handling data science
Quizzes PO4 applies but makes apply most
tools; fundamental
them with frequent concepts
accurately s.
minor errors. correctly.
applies
mistakes.
concepts to
solve
problems.
Applies
Uses
EDA and
suitable Attempts
modeling Demonstra
methods analysis
techniques tes partial No valid
Assignment PO1, but needs but results
CO2, effectively understand attempt or
s / Case 15% PO3, better are
CO3 with ing; limited irrelevant
Studies PO4 interpretati incomplete
correct analysis submission.
on or or
interpretati depth.
visualizati inaccurate.
on and
on.
insights.
Mini 25% CO3, PO1, Demonstra Builds Meets Project Fails to
Project / CO4 PO3, tes strong useful minimum incomplete demonstrate
Activity- PO4, analytical models project or lacks understandi
Based PO5 skills; with goals with proper ng or
Learning builds moderate basic analysis. practical
accurate accuracy; understand output.
models and solution is ing.
proposes partially
effective effective.
 data-based
solutions.
Integrates
all course
concepts;
analyzes Partial Minimal
Applies Shows
and understand understand
Final major general
CO1, interprets ing; ing; unable
Examinatio concepts understand
CO2, PO1– data struggles to answer
n/ 40% effectively ing of data
CO3, PO6 accurately; with conceptuall
Comprehen with few science but
CO4 demonstrat analysis or y or
sive Test conceptual lacks depth
es ethical integration analytically.
gaps. or clarity.
and of topics.
analytical
understand
ing.