UNIVERSITY OF PETROLEUM & ENERGY STUDIES

2021-22 Batch

L T P C
Descriptive Analytics (Business Intelligence) &
Data Visualization
Version 1.0
Pre-Requisites/Exposure
Co-Requisites

Descriptive Analytics (Business Intelligence) & Data Visualization

Unit 1. Introduction to Business Intelligence
Business intelligence, BI architecture & components, Functional areas of BI tool, Applications of BI tool,
Enterprise analytics capabilities, Complex vs volume operations, The nature of industry: Online retailers,
Examples of nature of industry, Complex vs volume operations, IT vs business and fact-based culture, A
strong data infrastructure, Analytics workforce, Future of business intelligence.

Unit 2. Decision Support Science

Decision support, Examples of decision support, Exploring and analyzing data, Data warehouse, Data
warehouse properties, Types of data, Multidimensional data, Schemas, Star schemas, Snowflake schemas,
Constellation schemas, Conceptual modeling of data warehouses, Data warehouse design process, Multi-
tiered architecture, Cross tabulation of sales by item-name and color, Data cube, Hierarchies on
dimensions, OLAP server architectures, Discovery-driven data cubes, Typical OLAP operations, OLTP vs.
OLAP, Business query, Dashboards and scorecards development, Metadata model, Automated tasks and
events, Mobile BI, Disconnected BI, Collaborative BI, Real-time monitoring
Software Development Kit (SDK), Making BI easy to consume

Unit 3. Building a BI Project

Business transformation projects, Where are we now? ASUG BI maturity model, Measuring BI success and
value (McDonald 2004), BI effectiveness scorecard, BI value scorecard, Five key areas of strategy, Planning
a BI Project, BI design and development, Engagement activities, Pre-engagement activities, Business
environment, Engagement process, Project tasks
Task 1: Knowledge capture goals - Discuss business objectives and prior learning, Interview key
stakeholders
Task 2: Consolidate findings

B.TECH (CSE) with Specialization in Data Science Page 158 of 138

This document is the Intellectual Property of University of Petroleum & Energy Studies and its contents
are protected under the ‘Intellectual Property Rights’.
 UNIVERSITY OF PETROLEUM & ENERGY STUDIES
2021-22 Batch
Task 3: Map the customer situation - Current environment, Business/functional requirements sample
diagram, Logical BI diagram
Task 4: Methodology and approach
Task 5: Standards and governance
Task 6: Sections, milestones, and tasks
Task 7: Proof of Concept (POC)
Task 8: Table creation
Task 9: OLAP creation
Task 10: Three final deliverables
Server administration data measurement, KDD: Knowledge Discovery in database, The Cross Industry
Standard Process for Data Mining (CRISP-DM).

Unit 4. Building Reports

Metrics, Senior managers should take care of metrics, Metrics drive behavior in several ways, Kaplan-
Norton balanced scorecard, The Rayport-Jaworski performance dashboard and strategy framework,
Introducing the R-J performance dashboard, Blueprint to the R-J performance dashboard, Building
reports, Relational reporting style, Dimensional reporting style, Dashboard: Definition, Layers of
information, Evolution of dashboards, Information discovery and delivery, Dashboard design principles,
Chart overview, Singular components, Alerts overview, Example of a dashboard, Display media for
dashboards, Sales simulation (what-if scenarios)
What-if scenarios: Example 1: Calculation of a monthly rate for a home loan
What-if scenarios: Example 2: Calculation of the average profit margin
What-If scenarios: Input components
What-if scenarios: Output components
Setting up the business scenario for a sales simulation, List report, Crosstab report, Chart report, Map
report, Data group and sort, Filters in report, Add calculations to report, Conditions in report, Adding
summary values in report, Drilling in report: Drill up and down, Drilling in report: Drill through, Run report:
On demand or schedule, Charts, Parts of a graph, Chart types, Chart type: Bar chart, Chart type: Line, Chart
type: Pie, Chart type: Area, Chart type: Scatter.

Unit 5. Advanced Data Mining Approach for BI

Data mining
Data mining process
Data mining Benefits
Data mining disadvantages
Data mining challenges
Data mining examples
Data mining methods.
B.TECH (CSE) with Specialization in Data Science Page 159 of 138

This document is the Intellectual Property of University of Petroleum & Energy Studies and its contents
are protected under the ‘Intellectual Property Rights’.
 UNIVERSITY OF PETROLEUM & ENERGY STUDIES
2021-22 Batch

Unit 6. Introduction to Data Analytics and Visualization

Introduction to data visualization, how is data generated? Different ways data is generated, uses of data,
when does data become Big Data? Importance of analytics, Scope of analytics, Data visualization,
Importance of Data Visualization, Data visualization is used in everyday life.

Unit 7. Principles of Data Visualization

Classifications of visualizations, Infographics Vs Data visualization, Classification of data visualization,
Designer – Reader – Data Trinity, An overview of different visualizations, Basic plots: Scatter plot, Basic
plots: Bar chart, Basic plots: Heat map, Basic plots: Pie chart, Basic plots: Box plot, Time-series data: Index
charts, Time-series data: Stacked graphs, Time-series data: Small multiples, Time-series data: Horizon
graphs, Statistical distributions: Steam and leaf plot, Statistical distributions: Q-Q plots, Statistical
distributions: Scatter plot matrix, Statistical distributions: Parallel coordinates, Maps: Flow maps, Maps:
Choropleth maps, Maps: Graduated symbol maps, Maps: Cartograms, Hierarchies, Networks: Force-
directed layouts, Networks: Arc diagrams, Networks: Matrix views, Simple rules for better visualizations.

Unit 8. Exploratory Data Analytics

Different types of data analytics, Exploratory data analytics, Univariate analysis, Bivariate analysis,
Multivariate analysis, Outlier detection, Outlier detection methods, Correlation analysis, Need for
correlation, Types of correlation, Scatter diagram, Correlation coefficient, Correlation matrix plots,
Geographical data analytics, Geographic information system, Geospatial data analysis, Feature
representation, Symbolizing the features, Good map making tips, Mapping uncertainty, Advanced
operations.

Unit 9. Distribution and Statistical Interference

Basic concepts of probability theory, Defining probability, Bayes’ Theorem, Random variables, Expectation
and variance of a random variable, Probability distribution, Discrete probability distribution, Continuous
probability distributions, Statistical analysis, Measures of variability, Modality, Skewness, Data
visualizations for descriptive analytics: Box plot, Data visualizations for descriptive analytics: Quantile plot,
Data visualizations for descriptive analytics: Histogram, Data visualizations for descriptive analytics: Kernel
density plots, Inferential statistics, Inferential statistics: Population distribution, Inferential statistics:
Confidence interval, Inferential statistics: Hypothesis, Inferential statistics: Type I type II error, Inferential
Statistics: Statistical test, Independent sample test, Paired t- test, ANOVA, Non-parametric test, Kruskal-
Wallis Test.

Unit 10. Visualizing Business Intelligence

B.TECH (CSE) with Specialization in Data Science Page 160 of 138

This document is the Intellectual Property of University of Petroleum & Energy Studies and its contents
are protected under the ‘Intellectual Property Rights’.
 UNIVERSITY OF PETROLEUM & ENERGY STUDIES
2021-22 Batch
What is Business Intelligence (BI)? What is Business Analytics? Types of Analysis, Business Intelligence Vs
Business Analytics, Types of analytics: Use-case scenarios, Business Analytics process, Types of data
description measurement scale, Impact of visualization, Dashboards, Benefits of implementing a
successful dashboard, Choosing right type of dashboard, Different types of dashboard, Strategic
dashboard example: Management strategic dashboard, Operational dashboard, Analytical dashboard,
Tactical dashboard, Best practices and design principles of dashboard, Dashboard design guidelines,
Dashboards in Tableau, Steps to create dashboards.

Unit 11. Data Visualization in Python

Introduction to matplotlib, Understanding the parts of figure, Pyplot, Other 2D plots, Polar plot, Dual bar
chart, Imshow, Text annotation, Figures with multiple subplots and insets, Colourmap and contour figures,
3D plots, Contour map with projection, Animations, Backends, Seaborn, controlling figure aesthetics,
Choosing color palettes.

Unit 12. Web Based Visualization

What is web based visualization, Visualization for analytics, Examples of Visualization: Networks, Examples
of visualization: Document clustering, Examples of visualization: Visual web search, Introduction to D3.js,
Understanding Scalable Vector Graphics (SVG), Simple shapes using SVG, Scales, Axes, Layouts, Pie
layouts, Stack layouts, Force layouts, Updates, transitions and motion, Exploring the alternate
libraries:plotly.js and charts, Plotly.js, Plotly.js: Examples, High charts, Adding your first chart.

Unit 13. Latest and Advanced Visualization

Chord diagram, Sankey diagram, Alluvial diagram, Flow map, Fishbone diagram, Arc Diagram, Hyperbolic
tree, Pyramid diagram, Radial convergences, Fan chart (genealogy), Spiral histogram, Win-loss spark line,
Marimekko chart, Scaled timeline, Sorted stream graph, Partition layer chart icicle diagram, Proportional
area chart, Clustered force layout, Sunburst diagram, Circular heat map, Hive plot, Taylor diagram,
Waterfall plot, Hexagonal binning, Bullet graph, Bag plot, Ternary plot, Phase diagram, Dumbbell plot, Fan
graph (Time series).

Lab Exercises –

Exercise 1: Power BI desktop

Exercise 2: Power BI service
Exercise 3: Architecture
Exercise 4: Supported Data Sources
Exercise 5: Data Modeling
Exercise 6: Dashboard Options
Exercise 7: Visualization Options 1
B.TECH (CSE) with Specialization in Data Science Page 161 of 138

This document is the Intellectual Property of University of Petroleum & Energy Studies and its contents
are protected under the ‘Intellectual Property Rights’.
 UNIVERSITY OF PETROLEUM & ENERGY STUDIES
2021-22 Batch
Exercise 8: Visualization Options 2
Exercise 9: Excel Integration
Exercise 10: Sharing Power BI Dashboards 1
Exercise 11: Sharing Power BI Dashboards 2
Exercise 12: DAX Basics 1
Exercise 13: DAX Basics 2
Exercise 14: DAX Basics 3
Exercise 15: DAX Advanced 1
Exercise 16: DAX Advanced 2
Exercise 17: DAX Advanced 3
Exercise 18: Starting with Shiny
Exercise 19: Build a Shiny app
Exercise 20: Customize reactions
Exercise 21: How to customize appearance
Exercise 22: Shiny Project
Exercise 23: Basic python operations
Exercise 24: Creating of Arrays
Exercise 25: Introduction to pandas package
Exercise 26: Introduction to NumPy
Exercise 27: Data merging
Exercise 28: Data Cleaning
Exercise 29: Data transformation
Exercise 30: Introduction to matplotlib
Exercise 31: Introduction to matplotlib - 2
Exercise 32: Customizing Plots with Matplotlib
Exercise 33: Using Seaborn for data visualization
Exercise 34: Exploratory analysis – 1
Exercise 35: Exploratory analysis – 2a
Exercise 36: Exploratory analysis – 2b
Exercise 37: Introduction to Web visualization using D3.js
Exercise 38: Building Interactive Bar Charts

B.TECH (CSE) with Specialization in Data Science Page 162 of 138

This document is the Intellectual Property of University of Petroleum & Energy Studies and its contents
are protected under the ‘Intellectual Property Rights’.