ACTS, Pune
Suggested Teaching Guidelines for
Data Visualization - Analysis and Reporting
PG-DBDA August 2024
o BI User Segmentation,
o Gathering BI Requirements,
o Content and Knowledge Management,
o Strategic Approach to BI
o Significance of visual analytics Information Visualization
o Data Representation
o Data collection and binding
Structured Data
Unstructured data
Session 3, 4 & 5:
MS EXCEL
o Functions
o Formula
o Charts
o Pivots and Lookups
o Data Analysis Tool
pack
1. Descriptive Summaries
2. Correlation
3. Regression
Session 6
Data analytics Life Cycle:
o Discovery,
o Data preparation
o Model planning
o Model building implementation
o Quality assurance
o Documentation
o Management approval
o Installation
o Acceptance and operation
Session 7 & 8
o Introduction to Tableau
o Intelligent data analysis
o Nature of Data
o Analytics Processes and tools
o Analysis vs. Reporting
o Modern Data Analytic Tools
o Data sources in Tableau
PG-DBDA
Page 2 of 3
ACTS, Pune
Suggested Teaching Guidelines for
Data Visualization - Analysis and Reporting
PG-DBDA August 2024
Session 9, 10 & 11
o Visualization
Algorithms
o Visual Encodings
color, size, shape, lines, axes, scaling, annotation
o Taxonomy of data visualization (Some Types of charts, but not limited to)
Comparison charts – types of Bar chart, Box plots, Histograms, Gantt charts,
Bullet graphs, side-by-side bar chart etc.
Tables – Text Tables, Highlight tables
Hierarchies and relationships – Pie chart, stacked bar, Tree map etc.
Changes over time – Line chart, dual lines, Area charts etc.
Connections and relationships – scatter plots, Symbol maps, map, heat maps,
packed bubble chart etc.
Session 12 &13:
o Choosing appropriate visuals
o Applying calculations using functions, statistics
Numeric Calculations
String Calculations
Date calculations
LOD (Level of Detail) Expressions
o Data sorting, filters
o Interactive visualization
Event listeners/callbacks
Data updation
Visual
updation
o Dashboard Design
Assignment-Lab:
Load coffee chain dataset in Tableau and create required visuals. Also create the
report for the same dataset using VBA tools in Excel.
PG-DBDA
Page 3 of 3
ACTS, Pune
Suggested Teaching Guidelines for
Practical Machine Learning PG-DBDA
August 2024
Duration: 60 hours Theory and 80 hours Lab
Objective: Practicing Machine Learning Algorithms
Prerequisites: Good knowledge of Python Programming and Statistics
Evaluation method: Theory exam– 40% weightage
Lab exam – 40% weightage
Internal exam– 20% weightage
List of Books / Other training material
Textbook:
1. Machine Learning using Python , Manaranjan Pradhan , U Dinesh Kumar
Wiley India, 1st Edition, 9788126579907
Reference Book:
Note:
PyTorch Framework should be taught in Lab Hours
Note: Each session having 2 Hours
Session 1, 2 & 3:
Fundamentals of information theory
What is machine learning?
Algorithm types of Machine learning
Probably Approximately Correct (PAC) Learning
Uses of Machine learning
Evaluating ML techniques
Bias complexity trade off
Vapnik-Chervonenkis (VC) Dimension
Non-uniform learnability (Structural risk minimization, Occam’s
Razor and No Free Lunch Theorem)
Regularization and Stability
Model Selection and Validation
Introduction to Scikit Learn
Performing ML using Scikit Learn
Assignments:
Explore scikit learn Library.
Explore Datasets Online (can refer Kaggle, UCI ML, etc.)
• Load dataset in google colab.
• Print first five values and last five values in dataset.
• check correlation between fields present in dataset
PG-DBDA Page 1 of 5
