1.1 Overview of Data Science

• Definition and importance of data science

• The data science lifecycle

• Key roles in data science: Data Analyst, Data Scientist, Data Engineer

1.2 Introduction to Excel for Data Analysis

• Excel interface and basic operations

• Data entry and formatting

• Basic formulas and functions (SUM, AVERAGE, COUNT, MAX, MIN)

1.3 Advanced Excel Functions

• Logical functions (IF, AND, OR, NOT)

• Lookup functions (VLOOKUP, HLOOKUP, INDEX-MATCH)

• Text functions (LEFT, RIGHT, MID, CONCATENATE)

• Date and time functions

1.4 Data Cleaning and Preparation in Excel

• Removing duplicates

• Handling missing values

• Text to columns

• Data validation

1.5 Excel Pivot Tables and Charts

• Creating and customizing pivot tables

• Pivot charts and slicers

• Calculated fields and items

1.6 Excel Data Analysis Tools

• Descriptive statistics using Data Analysis ToolPak

• Correlation and regression analysis

• What-if analysis: Goal Seek and Scenario Manager

1.7 Introduction to Power Query

• Importing data from various sources

• Basic data transformation operations

• Creating and managing queries

1.8 Excel Macros and VBA Basics

• Recording and running macros

• Introduction to VBA programming

• Creating simple user-defined functions

2.1 Introduction to Databases and SQL

• Relational database concepts

• SQL overview and importance in data analysis

• Setting up a database environment (e.g., MySQL, PostgreSQL)

2.2 Basic SQL Queries

• SELECT statement and retrieving data

• Filtering with WHERE clause

• Sorting with ORDER BY

• Limiting results with LIMIT / TOP

2.3 Working with Multiple Tables

• Joins: INNER, LEFT, RIGHT, FULL OUTER

• UNION and UNION ALL

• Subqueries

2.4 Aggregations and Group Operations

• Aggregate functions (COUNT, SUM, AVG, MAX, MIN)

• GROUP BY clause

• HAVING clause for filtering groups

2.5 Advanced SQL Techniques

• Window functions

• Common Table Expressions (CTEs)

• CASE statements

• Handling NULL values

2.6 Data Manipulation with SQL

• INSERT, UPDATE, and DELETE operations

• Creating and altering tables

• Views and temporary tables

2.7 Optimizing SQL Queries

• Understanding query execution plans

• Indexing basics

• Query optimization techniques

2.8 SQL for Data Analysis Projects

• Cohort analysis

• Customer segmentation

• Funnel analysis

• Time series analysis with SQL

3.1 Introduction to Tableau

• Overview of Tableau products

• Tableau interface and workspace

• Connecting to data sources

3.2 Creating Basic Visualizations

• Bar charts and histograms

• Line charts and area charts

• Scatter plots and bubble charts

• Pie charts and treemaps

3.3 Working with Dimensions and Measures

• Understanding dimensions and measures

• Discrete vs. continuous fields

• Changing aggregation methods

• Creating calculated fields

3.4 Advanced Chart Types

• Box plots and violin plots

• Gantt charts

• Bullet graphs

• Waterfall charts

3.5 Maps and Geospatial Analysis

• Creating basic maps

• Custom territories and geocoding

• Using map layers

• Spatial calculations

3.6 Dashboards and Stories

• Designing effective dashboards

• Adding interactivity with actions and filters

• Creating Tableau stories for presentations

3.7 Advanced Tableau Techniques

• Table calculations

• Level of Detail (LOD) expressions

• Parameters and what-if analysis

• Trend lines and forecasting

3.8 Tableau Best Practices and Optimization

• Performance optimization techniques

• Best practices for visual design

• Sharing and publishing visualizations

• Tableau Server basics

4.1 Introduction to Power BI

• Overview of Power BI suite (Desktop, Service, Mobile)

• Power BI interface and components

• Connecting to various data sources

4.2 Data Transformation with Power Query

• Power Query Editor interface

• Basic data cleaning operations

• Combining and merging queries

• Creating custom columns and measures

4.3 Data Modeling in Power BI

• Creating relationships between tables

• Star schema vs. snowflake schema

• Hierarchies and date tables

• Best practices for data modeling

4.4 DAX (Data Analysis Expressions)

• Introduction to DAX language

• Creating calculated columns and measures

• Time intelligence functions

• Advanced DAX functions (CALCULATE, FILTER, ALL)

4.5 Visualizations in Power BI

• Creating and customizing standard charts

• Matrix and table visualizations

• Custom visuals from AppSource

• Creating and using map visualizations

4.6 Power BI Reports and Dashboards

• Designing effective reports

• Implementing interactivity with slicers and filters

• Creating and sharing dashboards

• Mobile-optimized reports

4.7 Power BI Service and Collaboration

• Publishing reports to Power BI Service

• Creating app workspaces

• Implementing row-level security

• Sharing and collaborating on reports

4.8 Advanced Power BI Features

• Power BI Dataflows

• AI insights and quick measures

• Real-time streaming datasets

• Embedding Power BI reports

5.1 Introduction to Python

• Setting up Python environment (Anaconda, Jupyter Notebook)

• Python syntax and basic data types

• Control structures (if-else, loops)

• Functions and modules

5.2 Data Structures in Python

• Lists, tuples, and dictionaries

• Sets and arrays

• List comprehensions

• Working with strings

5.3 NumPy for Numerical Computing

• NumPy arrays and operations

• Array indexing and slicing

• Broadcasting

• Linear algebra operations

5.4 Pandas for Data Manipulation

• Series and DataFrame objects

• Reading and writing data (CSV, Excel, SQL)

• Data cleaning and preprocessing

• Merging, grouping, and aggregating data

5.5 Data Visualization with Matplotlib and Seaborn

• Creating basic plots with Matplotlib

• Customizing plot appearance

• Statistical data visualization with Seaborn

• Interactive plotting with Plotly

5.6 Exploratory Data Analysis (EDA)

• Descriptive statistics

• Correlation analysis

• Handling missing data

• Outlier detection and treatment

5.7 Web Scraping and API Interaction

• HTML basics and inspecting web pages

• Web scraping with BeautifulSoup

• Working with APIs (requests library)

• Parsing JSON data

5.8 Introduction to Object-Oriented Programming (OOP)

• Classes and objects

• Inheritance and polymorphism

• Creating custom data structures

• Best practices in OOP for data science

6.1 Introduction to Machine Learning

• Types of machine learning (supervised, unsupervised, reinforcement)

• The machine learning workflow

• Train-test split and cross-validation

• Bias-variance tradeoff

6.2 Scikit-learn Library

• Overview of scikit-learn

• Data preprocessing techniques

• Feature selection and engineering

• Pipeline and FeatureUnion

6.3 Supervised Learning: Regression

• Linear regression

• Polynomial regression

• Regularization techniques (Ridge, Lasso)

• Decision trees and random forests for regression

6.4 Supervised Learning: Classification

• Logistic regression

• Support Vector Machines (SVM)

• Decision trees and random forests for classification

• Naive Bayes classifiers

6.5 Unsupervised Learning

• K-means clustering

• Hierarchical clustering

• Principal Component Analysis (PCA)

• t-SNE for dimensionality reduction

6.6 Ensemble Methods

• Bagging and Random Forests

• Boosting algorithms (AdaBoost, Gradient Boosting)

• Stacking ensembles

• Voting classifiers

6.7 Model Evaluation and Hyperparameter Tuning

• Metrics for regression and classification

• Confusion matrix and ROC curves

• Grid search and random search

• Automated machine learning (AutoML) tools

7.1 Introduction to Neural Networks

• Artificial neurons and activation functions

• Feedforward neural networks

• Backpropagation algorithm

• Gradient descent optimization

7.2 Deep Learning Frameworks: TensorFlow and Keras

• TensorFlow basics and computational graphs

• Keras API overview

• Building and training simple neural networks

• Saving and loading models

7.3 Convolutional Neural Networks (CNNs)

• Convolution and pooling operations

• CNN architectures (LeNet, AlexNet, VGG)

• Transfer learning with pre-trained models

• Image classification and object detection

7.4 Recurrent Neural Networks (RNNs)

• Sequential data and RNN architecture

• Long Short-Term Memory (LSTM) networks

• Gated Recurrent Units (GRUs)

• Applications in text generation and sentiment analysis

7.5 Autoencoders and Generative Models

• Autoencoder architecture and applications

• Variational Autoencoders (VAEs)

• Introduction to Generative Adversarial Networks (GANs)

• Style transfer and image generation

7.6 Natural Language Processing with Deep Learning

• Word embeddings (Word2Vec, GloVe)

• Sequence-to-sequence models

• Attention mechanisms

• Transformer architecture and BERT

8.1 LLM Models from Hugging Face

• Installing and setting up Hugging Face environment

• Pretrained language models and their usage

• NLP tasks with Hugging Face (classification, NER, Q&A, text generation)

• Hugging Face Pipelines for streamlining NLP workflows

• Fine-tuning pretrained models for specific tasks

• Deploying Hugging Face models to different environments

• Case Study: Bank Customers Complaints Classification

8.2 LangChain Fundamentals

• Introduction to LangChain

• Getting started with LangChain installation and setup

• Main components in LangChain

• Working with LangChain and OpenAI

• LangChain with Hugging Face models

• LangChain Chains and working with Prompts

8.3 LangChain Model I/O

• Basic Document Loader and Chain on loaded documents

• CSV Loader and WebBaseLoader

• Wikipedia, PyPDFLoader, and BSHTMLLoader

• Output Parsers: CSV Parser and Pydantic

8.4 LangChain – Retrieval-Augmented Generation (RAG)

• Building a Retrieval Chain

• Understanding Refine, MapReduce, and MapRerank

• Embeddings: understanding, download, and visualization

• Prompt composition and templates

• Using multiple LLMs (Chains)

• Working with Data Loaders and Text Splitters

• Introducing ChromaDB

• Working with various Chains (Conversational Retrieval QA, Retrieval QA, Summarization, API)

8.5 LangChain Memory and Chatbots

• Concept of Memory and ConversationBufferMemory

• Four types of memory in LangChain

• Building applications with memory

• Chatbot using LangChain and ConversationalRetrievalChain

• Chatbot with RAG

• Tool-Chatbot: talk to multiple documents

8.6 LangChain Agents and Tools

• Concept of Tools and LangChain Agents

• ReAct (Reasoning and Acting) prompting

• SerpApi Tool and PPT Maker App

• CSV Agent and App: Talk to your Data

• Creating custom tools

9.1 Introduction to Agentic AI

• Understanding AI agents vs. traditional AI models

• What makes AI agentic: autonomy, goals, and tool use

• The role of LLMs in agent-based systems

• Real-world applications and use cases

• Overview of the agent ecosystem (frameworks, orchestration, integrations)

9.2 Core Concepts and Architecture

• Key components: Perception, Reasoning, Planning, Action

• Memory systems: short-term vs. long-term memory in agents

• Prompt engineering for agents

• Multi-agent collaboration patterns

• Evaluation metrics for agents

9.3 Agentic AI Frameworks Overview

• Comparing major frameworks: AutoGen, CrewAI, LangChain Agents, LlamaIndex Agents

• When to use which framework — trade-offs and strengths

• Interoperability between frameworks

• Case studies of production-grade agent systems

9.4 Building with AutoGen

• Introduction to AutoGen and its architecture

• Creating single-agent workflows

• Multi-agent conversations and task delegation

• Integrating tools and APIs with AutoGen agents

• Error handling and resilience in AutoGen agents

• Project: Build a two-agent research & writing system

9.5 Building with CrewAI

• CrewAI basics and setup

• Roles, skills, and task distribution in CrewAI

• Orchestrating multiple agents for a business process

• Dynamic role assignment and runtime decision-making

• Integrating external APIs with CrewAI agents

• Project: Build a customer-support agent crew

9.6 n8n for Agentic Automation

• Introduction to n8n as a visual workflow orchestrator

• Connecting LLMs and agents into n8n workflows

• Webhooks, triggers, and event-driven agents

• Passing context between n8n nodes and agents

• Real-time data pipelines for agents using n8n

• Project: Build a Telegram chatbot agent with n8n backend

9.7 MCP (Model Context Protocol)

• Understanding the MCP specification

• How MCP enables tools and data access for agents

• Setting up an MCP server and integrating it into workflows

• MCP client-server communication in agent systems

• Using MCP with AutoGen, CrewAI, and n8n

• Project: Create an MCP-enabled knowledge retrieval agent

9.8 Scaling Multi-Agent Systems

• Strategies for scaling agent-based systems

• Resource management and orchestration at scale

• Monitoring, debugging, and logging in agent ecosystems

• Real-world challenges and solutions in deploying multi-agent AI