Module 1: Hands-on Session [10 hrs]

• Introduction to Power BI Desktop
• Introduction to Power Query and Data Profiling Techniques (E-commerce Data)
• Query Parameters in Detail
• Direct Query vs Import Data Connection Mode

Module 2: Power BI Desktop Visualizations [10 hrs]

• Creating visuals (hands on understanding of Each visual with proper working and it’s
• Use Cases along with all the formatting option around the Visual) Ecommerce Data
• Stacked Bar chart & Column chart
• Clustered Bar chart & Column Chart
• 100% Stacked Bar chart & Column Chart
• Line Chart with formatting option
• Line chart with Forecasting
• Line Chart with Add further Analysis using Constant Lines
• Area Chart & Stacked Area Chart
• Waterfall Chart ,Ribbon Chart & Funnel Chart
• Tree Map Visuals
• Gauge Visuals
• Maps in visualization (Normal Map, Filled Map & Shape Map)
• Understanding Types of Filters Available in Power Bi(Page, all Pages & Visual Level Filter

Module 3: Data Modelling with Power BI [10 hrs]

• Introduction to Data Modelling & Data Warehousing Concept along with Realtime example
• Creating hierarchy in the model
• Understanding Cross Filter Direction & Cardinality
• Why do we need Date Table in Power Bi?

Module 4: DAX Expressions [12 hrs]

• Introduction to Dax (how to write Dax and basic functions in power bi)

Module 5: Publishing and Sharing [8 hrs]

• Publishing and Sharing
• Publish from Power BI desktop to Saas Account
• Sharing Reports and Dashboards
• Manage Subscription & Alert in Power Bi
• Creating Live PPT's Via Power BI Reports
• Workspaces in Details (Creation and Roles in Workspace)
• Creating Dashboards
• Printing, PDF’s , Live PPT’s and exports
• Realtime Exercise: -
• Understanding Row Level Security and Establishing Security with Regional and
• Segment Based Manager on Sales Data
• Establishing on Premise Gateway
• Scheduling Manual & Automated Refresh

Section 1:

• Introduction to Excel & Power Query for Data Study
• Understanding the Excel Interface, Customizing the Ribbon, Excel Shortcuts

 Section 2:

• Basic Formulas and functions
• SUM, AVERAGE, MIN, MAX, Basic Arithmetic Operations

Section 3:

• Data Entry and Formatting
• Cell Formatting, Data Validation, Conditional Formatting

Section 4:

• Advanced Formulas and Functions
• IF, AND, OR, Nested Formulas, Text Functions
• Lookup Functions
• VLOOKUP, INDEX and MATCH

Section 5:

• Data Analysis Tools
• Pivot Tables, Pivot Charts, Data Consolidation
• Introduction to Macros Recording Macros
• Excel with AI
• Using AI in Excel
• Excel AI Capabilities, Implementing AI Tools
• Practical Applications of Co-Pilot with Excel

Section 1: Microsoft SQL Database Server

• Introduction (30 mins)
• What is T-SQL
• What is SQL Server
• Minimum SQL Server Installation Requirements
• SQL Server Editions
• SQL Server Download
• SQL Server Installation
• Connecting to SQL Server with SSMS
• Install Sample Database
• Basic Database Concepts
• Creating Simple Table in SQl and Inserting Values
• Constraints in SQl

 Section 2: Microsoft SQL CRUD Operations

• What is CRUD
• Creating a new database
• Creating a new table
• Reading Data from table
• Views
• Updating Records
• deleting records
• Truncating a Table
• Stored Procedures
• Dropping a Table
• Dropping a database
• Backing up database
• Restoring a database

Section 3: Microsoft SQL (T-SQL)

• TOP Command
• GO Command
• USE Command
• DISTINCT AND TOP

 Section 4: Filtering Data (Scenario Based Learning)

• Introduction
• Filtering data with equality filters
• Filtering data with basic comparison filters
• Filtering data with logical comparison filters
• Filtering data with string comparison filters

 Section 5: Filtering data with string comparison filters

• Introduction
• ordeR BY Clause
• Sorting by Ascending
• Sorting by Ascending
• Sorting by multiple columns

Section 6: Extracting data from Multiple Tables using Joins

• Introduction
• Why is Table Join Necessary?
• INNER JOIN
• LEFT OUTER JOIN
• RIGHT OUTER JOIN
• Cross JOIN

Section 7: Aggregate Functions (Scenario Based Learning)

• Introduction
• COUNT
• AVG
• MAX
• MIN
• SUM
• Using Multiple Aggregate Functions
• Grouping Data with GROUP BY Clause

 Section 8: Additional Topics (Advanced Scenario Based Learning)

• Sub Query
• String Function
• Finding Nth Character
• Rownum & Partition in Sql Along With Rank
• Stored Procedures in Sql Server
• Set Operators
• Scalar Functions
• SQL String Function

ChatGPT for SQL Optimization

• Auto SQL Query Generation
• Debugging SQL using ChatGPT
• Best Prompts for SQL Automation

Basic Introduction Of Python

Python Installation

 Variable [1 hr]

• Local Variable
• Global Variable

 Data Type, Variables & How to define it? [1hr]

• Boolean
• String
• Integer
• Float

 Data Structure [1 hr]

• List / Array
• Dictionary
• Tuple
• Set

 Condition & Loops [1 hr]

• f - Elif - Else Statement
• For Loop
• While Loop
• d For Loop

Functions [3 hr]

• print()
• sum()
• max()
• min()
• range()
• sorted()

 Special Functions  [2 hrs]

• lambda()
• filter()
• map()

Class [2 hrs]

• Function
• Object
• Function Calling

 Program Writing [3 hrs]

• Programs on List
• Programs on Dictionary
• Programs on String

Basic Introduction Of Numpy

 Data Types [2 hrs]

• int
• str
• object
• datetime
• nan

 Numpy Functions [3 hrs]

• arange()
• array()
• append()
• sum()
• min()
• max()
• abs ()
• sqrt ()
• product()
• dot()
• round()
• ceil()
• isnan()
• where()

 Slicing [1 hr]

• Row Slicing
• Column Slicing
• Element Slicing

Basic Introduction Of Pandas

 Read Data [1 hr]

• read_csv()
• read_excel()

 Write Data [1 hr]

• DataFrame.to_csv()
• DataFrame.to_excel()

 Pandas Functions [3 hrs]

• Series()
• DataFrame()
• DataFrame.describe()
• DataFrame.info()
• isna()
• concat()
• merge()
• melt()
• pivot_table()
• DataFrame.append()
• DataFrame.groupby()
• DataFrame.max()
• DataFrame.min()
• DataFrame.sort_values()
• DataFrame.reset_index()

Pandas Operations [2 hrs]

• Slicing
• Filter Data For Specific Row
• Filter Data For Specific Column
• Filter Data For Specific Row & Column Combination
• Create Calculated Column
• Data overwrite

Basic Introduction Of Matplotlib

 Matplotlib Charts [2 hrs]

• Line Chart
• Pie Chart
• Histogram Chart
• Scatter Plot
• Bar Plot
• Box Plot
• Sub Plot
• Python Hands on Real Time Project with Industry Example (5 hrs)

Introduction to Prompt Engineering

 Goal: Understand what prompt engineering is and why it matters.

 Topics:

• What is Prompt Engineering?
• How LLMs (like GPT) understand and respond
• Types of prompts: Zero-shot, One-shot, Few-shot
• Key capabilities of LLMs: Text generation, summarization, Q&A,
• classification, etc.
• Limitations and biases of language models

 Hands-On Activities:

• Try basic zero-shot and few-shot prompts using ChatGPT or OpenAI Playground
• Prompt comparison: Vague vs specific

Designing Effective Prompts

 Goal: Learn techniques for crafting better prompts.

 Topics:

• Prompt structure: Instructions, context, examples, format hints
• Step-by-step prompting
• Role prompting (e.g., “You are a helpful tutor…”)
• Output control: Tone, format, length
• Common prompt engineering mistakes

 Hands-On Activities:

• Rewrite prompts for clarity and precision
• Generate structured outputs (e.g., JSON, tables)

Advanced Prompt Techniques

 Goal: Deepen your understanding with more complex strategies.

 Topics:

• Chain-of-thought prompting
• Self-reflection and critique prompting
• Prompt chaining (multi-step prompts)
• Using system and user roles (ChatGPT format)
• Using temperature, top_p, and other settings

 Hands-On Activities:

• Solve logic problems with chain-of-thought
• Compare results with different temperatures

Prompting for Different Use Cases

 Goal: Explore prompt applications across domains.

 Topics:

 Prompts for:

 i.Text summarization

 ii.Translation

 iii.Code generation

 iv.Sentiment analysis

 v.Data extraction

 vi.Educational tutoring

 vii.Business email writing

 Hands-On Activities:

• Build domain-specific prompt examples (Choose: Business / Education /Programming)
• Create a mini prompt library (template bank)

Real-world Projects & Tools

 Goal: Apply knowledge in real workflows and tools.

 Topics:

• Overview of tools: ChatGPT, OpenAI Playground, Claude, Gemini
• Using prompts in:

i.Excel / Google Sheets with AI plugins

ii.Power BI with Copilot (context-aware prompts)

iii.No-code AI tools like Zapier + OpenAI

• Introduction to prompt evaluation and testing

 Mini Project Options: Build a chatbot-like prompt flow

 Create a prompt-based tutor/quiz assistant

 Automate a task using prompt templates

Module 1: Intro to Statistics & Types of Data (1 hour)

 Topics:

• Descriptive vs Inferential Statistics
• Population vs Sample
• Types of Data (Numerical, Categorical)
• Levels of Measurement (Nominal, Ordinal, Interval, Ratio)

 Module 2: Descriptive Statistics (2 hours)

 Topics

• Central Tendency: Mean, Median, Mode
• Dispersion: Range, Standard Deviation
• Visualizing with Histograms, Boxplots

 Module 3: Probability & Distributions (1.5 hours)

 Topics:

• Basic Probability Rules
• Introduction to Distributions: Normal, Binomial
• Central Limit Theorem (concept only)

 Module 4: Inferential Statistics (2.5 hours)

 Topics:

• Hypothesis Testing Basics: Null, Alternative, p-value
• T-tests (1-sample and 2-sample)
• Confidence Intervals

 Module 5: Correlation & Regression (2 hours)

• Correlation vs Causation
• Pearson Correlation
• Simple Linear Regression
• R-squared interpretation

 Module 6: Mini Project & Recap (1 hour)

 Topics:

• Choose a dataset (sales, customer, HR, etc.)
• Do EDA + describe key insights
• Run a basic hypothesis test or regression

Module 1: Sheets Essentials + Basic Formulas (1.5 hours)

 Topics:

• Navigating Google Sheets: rows, columns, sheets
• Formatting: wrap text, freeze panes, data types
• Simple math: +, -, *, /
• Functions: SUM(), AVERAGE(), COUNT(), IF()

 Module 2: Data Cleaning & Lookup Functions (1 hour)

 Topics:

• Clean text: TRIM(), SPLIT(), SUBSTITUTE()
• Remove duplicates
• Lookup basics: VLOOKUP(), IFERROR()
• Sort and Filter data

 Module 3: Data Summarization with Pivot Tables (1 hour)

 Topics:

• Create pivot tables from a raw dataset
• Summarize sales by region, month, etc.
• Use calculated fields in pivot
• Quick filters in pivots

 Module 4: Charts & Dashboards (1 hour)

 Topics:

• Create charts: bar, line, pie
• Sparkline for quick visuals
• Link charts to pivot tables
• Dashboard layout tips (titles, spacing, interactivity)

 Module 5: Collaboration + Importing Data (0.5 hour)

 Topics:

• Sharing sheets with permissions
• Comments & version history
• Importing data: Google Forms, CSV, IMPORTRANGE()

 Module 6: Quick Project (1 hour)

• Mini Project Options: Build a dashboard for mock sales data
• Create a cleaned, summarized, and visualized version of form submissions
• Use pivot + chart to track expenses or grade

Module 1: Introduction to Git & GitHub (1 hour)

 Topics:

• Why use Git in data analysis?
• Git vs GitHub: what’s the difference?
• Version control for notebooks, scripts, datasets
• Install Git and set up GitHub account

 Module 2: Git Basics – Local Workflow (1.5 hours)

 Topics:

• Git init, status, add, commit
• Checking history with log
• File tracking (.csv, .ipynb, .py, .xlsx)
• Creating a .gitignore for large data files

 Module 3: Working with GitHub (1.5 hours)

 Topics:

• Create a remote GitHub repo
• Pushing local project to GitHub
• Cloning from GitHub
• pull vs fetch
• Syncing changes between local & remote

Module 4: Collaboration & Branching (2 hours)

• Branching: checkout, merge, rebase (basic)
• Pull Requests (PR): creating and reviewing
• Resolving merge conflicts
• GitHub Issues & Project Boards (basic overview)

 Module 5: Best Practices for Data Analysts (1–1.5 hours)

 Topics:

• Project folder structure for analysis
• Committing datasets – when and when not to
• Writing good commit messages
• Using GitHub for portfolio and showcasing projects
• Using GitHub Pages to publish results

Module 1: Introduction to R & RStudio (1.5 hours)

 Topics:

• Why use R for data analysis?
• Installing R and RStudio
• RStudio interface: scripts, console, environment
• Basic syntax: variables, data types, operators
• Writing and executing simple scripts
• Hands-on: Create and run a basic script that performs calculations

 Module 2: Data Structures in R (2 hours)

 Topics:

• Vectors, Lists, Matrices, Data Frames, Factors
• Indexing and subsetting
• Basic data type conversions
• Hands-on: Create and manipulate vectors, data frames

 Module 3: Data Import, Export & Cleaning (2.5 hours)

 Topics:

• Importing CSV, Excel using readr, readxl
• Exporting datasets
• Handling missing values: is.na(), na.omit()
• Renaming, recoding, filtering data
• Hands-on: Clean a messy CSV file using dplyr

 Module 4: Data Manipulation with dplyr & tidyr (3 hours)

 Topics:

• select(), filter(), mutate(), arrange(), summarise(), group_by()
• Combining data: left_join(), bind_rows()
• Tidying data: pivot_longer(), pivot_wider()
• Hands-on: Summarize sales/HR data using dplyr pipelines

 Module 5: Data Visualization with ggplot2 (3 hours)

 Topics:

• Grammar of graphics basics
• Scatter plots, bar plots, histograms, boxplots
• Aesthetic mappings and facets
• Customizing themes and labels
• Hands-on: Visualize trends in data using different plots

Module 6: Descriptive & Inferential Statistics (3 hours)

 Topics:

• Mean, Median, Mode, SD, IQR using summary() and psych package
• Frequency tables, proportions
• Hypothesis Testing: t-test, chi-square test, correlation
• Confidence intervals
• Hands-on: Perform statistical summary and tests on sample datasets

 Module 7: Linear Regression & Modeling (2.5 hours)

 Topics:

• Simple and Multiple Linear Regression using lm()
• Model diagnostics: R-squared, residuals
• Predicting with new data
• Visualizing regression lines with ggplot2
• Hands-on: Predict sales or prices from input variables

 Module 8: Projects & Best Practices (2.5 hours)

 Topics:

• Structuring R projects using RStudio Projects
• Writing reusable code with functions
• Using RMarkdown for reporting
• Project ideas: sales report, churn analysis, survey analysis