Data Science Course in Pune with Placement Assistance

Introduction to Python Programming

• What is Python programming language?
• Why is the Python programming language required for Data Science?
• What is Anaconda?
• Installation of Anaconda
• Understanding Jupyter Notebook
• Basic commands in Jupyter Notebook
• Understanding Python Syntax
• Data Types in Python broadly discussed

Literals, Keywords and Data Types

• What is an Identifier?
• Rules for Identifier Naming
• Inbuilt Keywords
• Variables and Data Types
• print() and input()

Python Operators

• Arithmetic Operators
• Assignment Operators
• Comparison Operators (Relational)
• Logical Operators
• Identity Operators

Conditional Statement

• What are Conditional Statements?
• if Statement
• if-else Syntax
• if-elif-else
• Nested if and if-else
• elif Ladder

While Loops & While-Else

• What is a Loop?
• Why Loops are Used?
• while Loop Syntax
• Control Flow
• Solving Pattern Problems

Lists

• What is a List?
• How to Define a List?
• Accessing List Elements Using Indexing and Slicing
• Built-in Methods
• Basic Examples Using Lists to Print Elements at Even Index, etc.

Tuple & Set

• What is a Tuple?
• How to Create a Tuple?
• Accessing Tuple Elements Using Indexing and Slicing
• Differences Between Lists and Tuples
• What is a Set?
• How to Create a Set?
• Built-in Methods
• Set Operations
• Manipulating and Accessing Sets

Dictionary

• What is a Dictionary?
• How to Create a Dictionary?
• Adding, Modifying and Retrieving Values from a Dictionary
• Getting All Methods
• Built-in Methods
• Differences Between Sets and Dictionaries
• Mutable vs Immutable Data Types

Strings

• What is a String?
• Create a String
• Accessing a String Using Indexing and Slicing
• Built-in Methods
• format() Method
• User Input / Dynamic Entry
• Type-Casting of Strings

For Loop, For-else & Comprehension

• Introduction to for Loop, range(), enumerate()
• For-else
• List Comprehension & Dictionary Comprehension
• Problem Solving with Respect to String Methods Utilizing for Loops & Conditional Statements Making Use of chr() and ord()
• Problem Solving with List and Dictionary
• Comprehension

Functions

• What is a Function?
• Why Functions are Used?
• Terminologies Used in Functions
• How to Define a Function?
• How to Call a Function?
• Positional and Keyword Arguments

Higher Order Functions

• Functions with/without Return Values
• Lambda Functions
• Map, Filter & Reduce
• Name Spaces
• Modules and Package
• Using Conditional Statements
• Using Loops
• Using Functions

Modules & Packages

• Modules and Package
• Date Time
• Random
• math, os
• Creating Custom Module

OOPS - Classes and Objects

• What is a Class?
• How to Create a Class?
• What are the Properties and Methods of a Class?
• What is an Object?
• How to Create an Object?
• How to Access the Properties and Methods of a Class Using an Object?
• What is a Constructor?
• What are the Types of Variables?
• What are the Types of Methods?
• Access Modifiers

Inheritance & Abstraction

• Inheritance
• Single Inheritance
• Multilevel Inheritance
• Multiple Inheritance
• Hierarchical Inheritance
• Hybrid Inheritance and MRO
• Abstraction

Polymorphism and Encapsulation

• Polymorphism
• Dynamically Typed or Duck Typing
• Operator, Method and Constructor Overloading
• Method and Constructor Overriding
• Encapsulation
• Setter and Getter

File Handling & Exception Handling

• What is a File?
• How to Create a File?
• How to Open a File?
• How to Close a File?
• Writing to a File
• Appending to a File
• Reading from a File
• Testing File's Existence
• What is an Exception?
• Raising Exceptions
• try-finally
• Custom Exceptions

VS Code & Streamlit Deployment

• What is Streamlit?
• Components of Streamlit
• Creating an Application with Streamlit
• VS Code, Setting Environment
• Executing Programs in VS Code

Backend with FastAPI

• Client-Server Architecture
• Introduction to FastAPI
• Request Methods
• Hands-on FastAPI
• Application Building
• Integration of FastAPI with Streamlit
• Case Study

GenAI: Enhanced Coding Fundamentals

• Introduction to AI-Assisted Coding
• ChatGPT for Code Generation and Explanation
• AI-Assisted Debugging and Code Optimization
• Generating Python Solutions with ChatGPT
• Hands-on AI-Assisted Coding for Data Science Tasks

Introduction to EDA

• How is EDA different from Python programming?
• EDA vs Python with Case Study
• Types of Data (Numerical, Categorical)
• Types of Analysis (Non-Visual and Visual, Univariate and Bivariate, Descriptive, Inferential & Probabilistic)

Descriptive Statistics

• What and Why Statistics?
• Data and its Measures
• Measures of Central Tendency (Univariate Analysis)
• Measures of Dispersion (Univariate Analysis)
• Measures of Correlations (Bivariate Analysis)

Core Numpy Operations

• Generating Random Numbers - np.random.rand, np.random.randn, np.random.randint, np.random.uniform
• Indexing and Slicing of Arrays (1D & 2D)
• Indexing with Boolean Arrays
• Updating Numpy Array
• Insert, Append and Delete
• Array Shape Manipulations - reshape, ravel and flatten, transpose
• Problem Solving

Mathematical & Statistical Functions

• Iterating over a 1D and 2D Numpy Array
• Iteration Using np.nditer()
• Python Operators on Numpy Array
• Numpy Maths - sqrt(), exp(), sin(), cos(), add(), subtract(), multiply(), divide(), dot(), @ Operator
• Numpy Statistics - sum(), min(), max(), mean(), median(), var(), std(), corrcoef()

Vectorization and Advanced Numpy Functions

• Array Manipulations - Concatenate, vstack, hstack, column_stack, hsplit, vsplit
• Sorting the Data in an Array - sort, argsort
• Broadcasting Arrays
• Numpy where, any

Introduction to Pandas

• Introduction to Pandas
• Pandas Series
• Pandas DataFrame
• Difference Between Series and DataFrame
• Creating Series and DataFrames

Data Exploration and Understanding

• Loading Data from CSV and Excel Files
• Understanding the DataFrame Structure
• DataFrame Non-Indexing Attributes
• DataFrame Utility Methods
• DataFrame Iteration Methods
• Mathematical Functions on Whole DataFrame
• Getting Column Index/Label
• Changing Column Labels
• Selecting, Swapping Columns
• Adding New Columns / Dropping Existing Columns
• Vectorized Arithmetic Operations
• Data Type Conversions
• Math and Statistical Functions on Columns

Groupby and Pivot on DataFrame

• Summarizing Data Using groupby()
• Multidimensional Aggregation Using pivot_table()
• Categorical Analysis Using crosstab

Working With Multiple Tables Using Joins (Merge Operation)

• Concatenation - Vertical and Horizontal Stacking
• Merging (merge) - Inner, Outer, Left and Right Joins
• Index-Based Merging

Handling Missing Values, String and Datetime Manipulations

• Types of Missing Data
• Identifying and Visualizing Missing Data
• Missing Value Imputation
• String Operations
• Working with Datetime

Advanced Data Transformations

• apply() and map()
• Window Functions (rolling(), expanding())
• Handling JSON Files
• JSON record_path Normalization

Univariate and Bivariate Statistical Analysis (Non-Visual)

• Measures of Shape
• Measure of Relationship
• With a Case Study - Descriptive Stats

Introduction to Data Visualization

• Understanding Visualization
• Basic Structure of a Plot - Figure, Axis, Title, Legends, Ticks, Labels, Subplots
• Creating Basic Plots with Raw Data
• Customizing the Plots - Colormaps, Axis Limits, Markers, Linestyles, Colors

Univariate Analysis with Matplotlib/Seaborn

• Univariate Plots for Numeric Data - Histogram, KDE, Boxplot, Violinplot
• Univariate Plots for Categorical Data - Barplot, Countplot

Bivariate and Multivariate Analysis with Matplotlib/Seaborn

• Plots Between Numerical Variables - Scatterplot, Heatmap, Lineplot
• Plots Between Categorical Variables - KDE Plot, Boxplot, Histogram, Boxenplot, Violinplot
• Plots Between a Numeric and a Categorical Variable - Countplot, Stacked Barplot
• Plots for Multivariate Analysis - Pairplot, Heatmap

Interactive Data Visualization with Plotly

• Interactive Plots for Numeric Data - Histogram, Boxplot, Violinplot, Densityplot
• Interactive Plots for Categorical Data - Bar Chart, Grouped Bar Chart, Pie Chart, Funnel Chart
• Interactive Plots for Bivariate Analysis - Scatterplot, Line Chart, Bubble Chart, Area Chart
• Interactive Plots for Multivariate Analysis - Heatmap, Scatter Matrix, Parallel Coordinates
• Advanced Plotly Visualizations - Subplots, Animations, Hover Interactions, Filters

Introduction to Probability

• Random Experiment
• Sample Space
• Event
• Axioms of Probability
• Basic Probability Examples

Frequency Tables

• Introduction to Frequency Tables
• Joint Probability
• Marginal Probability
• Conditional Probability

Introduction to Data Distributions, Discrete Data Distributions

• What is a Data Distribution?
• Why Study Data Distribution?
• Key Characteristics
• Types of Distributions
• Introduction to SciPy Library
• Bernoulli, Binomial, and Poisson

Continuous Data Distribution

• Uniform, Normal
• Exponential
• Log Normal
• Pareto Distribution
• 68-95-99.7% Rule
• Verify the Distribution Using QQ Plot

Feature Engineering

• Feature Scaling - Normalization and Standardization
• Data Transformation
• Log Transformation and Box-Cox

Introduction to Inferential Statistics

• Inferential Statistics
• Population vs Sample
• Why Inferential Statistics?
• Sampling Techniques - Convenience Sampling, Systematic Sampling, Simple Random Sampling, Stratified Sampling, Cluster Sampling
• Sampling in Pandas DataFrame

Central Limit Theorem and Point Estimate

• Performing Estimations
• Point Estimate Using Single Sample
• Central Limit Theorem
• Point Estimate Using m Samples

Confidence Interval Estimate

• Confidence Interval Estimates Using 1 Sample (Population Std is Known and Unknown)
• Confidence Level
• Significance Level
• Critical Value - z-score and t-score

Hypothesis Testing and Advanced Statistical Tests

• What is Hypothesis Testing?
• What is p-value?
• Important Hypothesis Tests
• Type I and Type II Errors
• Parametric and Non-Parametric Tests - Chi-Square Test, ANOVA

Simplifying Statistical Analysis with AI Tools

• Introduction to AI-Assisted Statistical Analysis - Role of GenAI in Statistics
• AI-Assisted Descriptive Statistics - Mean, Median, Mode, Variance and Standard Deviation
• AI-Assisted Statistical Analysis - Correlation, Distribution and Hypothesis Testing
• Interpreting Statistical Results with GenAI - Insights and Explanations
• Hands-on with AI Tools - Statistical Analysis and Interpretation

Regular Expressions

• Pattern Matching Basics
• Email, Phone Number & URL Extraction
• Text Cleaning & Data Validation
• Removing Special Characters
• Regex with Python (re module)

Ethical Web Scraping

• Requests Library
• BeautifulSoup
• HTML Parsing
• CSS Selectors & Inspect Element
• Extracting Tables, Text & Links
• Pagination Handling

Data Cleaning & Preprocessing

• Handling Missing Values
• Removing Duplicates
• String Cleaning
• Formatting & Standardization
• Data Transformation Using Pandas

Exploratory Data Analysis (EDA)

• Data Understanding & Profiling
• Statistical Summary
• Data Visualization Using Matplotlib & Seaborn
• Correlation & Trend Analysis
• Business Insights Generation

Project on EDA

• Collect Real-Time Data from Websites Ethically
• Clean and Preprocess Raw Datasets
• Apply Regex for Data Extraction & Validation
• Perform EDA and Generate Insights
• Build Industry-Oriented Projects

GenAI: Powered Data Wrangling with PandasAI

• Introduction to Data Wrangling - Data Cleaning, Transformation, Integration
• Introduction to PandasAI - AI-Assisted Data Manipulation
• AI-Powered Data Cleaning - Missing Values, Duplicates, Data Types
• AI-Assisted Data Transformation - Filtering, Sorting, Aggregation
• Natural Language Data Analysis - Querying and Exploring Data with PandasAI

Introduction to SQL

• Data
• What is Database?
• DBMS
• RDBMS
• SQL vs MySQL
• SQL vs NoSQL
• CRUD Operations
• Pandas vs SQL
• Client-Server Architecture
• Workbench Introduction

SQL Fundamentals

• Types of SQL Commands
• Data Types
• Constraints (PRIMARY KEY, AUTO_INCREMENT, NOT NULL, UNIQUE, DEFAULT, CHECK)
• Creating Tables with Constraints
• DDL (CREATE, ALTER, DROP, TRUNCATE)
• DML (INSERT, UPDATE, DELETE)

Multiple Tables

• Multiple Tables - Primary Key, Composite Key, Foreign Key
• Types of Relationships in SQL
• ER Diagram
• Case Study: On Relational Database

Data Exploration and Data Filtering (DQL and Operators)

• SELECT (Retrieve)
• Data Exploration - Selecting Columns; Performing LIMIT, DISTINCT, Aggregation Values, Indexing and Slicing Using OFFSET
• Data Filtering - Filtering Data Based on Conditions (with All Operators: LIKE, REGEXP, BETWEEN)
• GROUP BY (Aggregate Function)
• HAVING (Correlating with get_group in Pandas)
• ORDER BY
• CASE
• Order of Execution
• Case Study: A Case Study of Clauses

Joins, Unions and Subquery

• Types of Joins - INNER JOIN, Outer Join (LEFT, RIGHT), CROSS JOIN, SELF JOIN
• Set Operations - UNION, UNION ALL
• Subquery - Scalar Subquery, Multiple Subquery, Correlated Subquery

Temporary Tables

• Derived Table
• CTE
• Inbuilt Functions
• Window Functions
• Case Study: A Case Study of Temporary Tables

SQL Database Objects

• Views
• Stored Procedure
• Functions

Advanced Topics

• Transaction Control Language - ACID Properties, COMMIT, ROLLBACK, SAVEPOINT
• Triggers
• Type Conversion, Working with Date, Time & String Functions
• Connectivity of MySQL with Python (Pandas)

Project on MySQL

• Analyze normalized relational databases and ER diagrams based on real-world business requirements
• Import and manage CSV datasets in SQL databases
• Write SQL queries using filters, aggregations, sorting, and joins
• Develop advanced SQL solutions using CTEs, Views, Stored Procedures, and Window Functions
• Solve domain-specific business problems and generate actionable insights

GenAI-Powered SQL: Query Generation & Optimization

• Introduction to AI-Powered SQL - AI-Assisted SQL Concepts and Workflows
• AI-Assisted Query Generation - Natural Language to SQL
• AI-Assisted Query Optimization - Query Performance and Optimization
• SQL Debugging with GenAI - Error Identification and Correction
• Hands-on with AI-Powered SQL - Query Generation and Optimization

Excel Essentials for Data Analysis

• Introduction to Excel for Data Analysis
• Data Exploration Using Excel Functions
• Data Cleaning and Formatting in Excel
• Sorting, Filtering and Data Validation
• Conditional Formatting and Data Highlighting
• Lookup Functions: VLOOKUP, XLOOKUP and INDEX-MATCH
• Pivot Tables and Pivot Charts for Data Analysis
• Advanced Excel Functions for Data Analysis
• Case Study: Dash-boarding in Excel

Introduction to Power BI

• What is Business Intelligence?
• Power BI Introduction
• Quadrant Report
• Comparison with Other BI Tools
• Power BI Desktop Overview
• Power BI Workflow

Data Import and Data Visualizations

• Data Import Options in Power BI
• Import from Web (Hands-on)
• Why Visualization?
• Visualization Types
• Categorical Data Visualization
• Trend Data Visualization

Power Query

• Power Query Introduction
• Data Transformation - Its Benefits
• Introducing Ribbons
• Queries Panel
• M Language Briefing
• Power BI Data Types
• Changing Data Types of Columns
• Filtering
• Inbuilt Column Transformations
• Inbuilt Row Transformations
• Combine Queries
• Merge Queries

Power Pivot and Introduction to DAX

• Power Pivot
• Introduction to Data Modeling
• Relationship and Cardinality
• Relationship View
• Calculated Columns vs Measures
• DAX Introduction and Syntax

Data Analysis Expressions

• DAX Logical Functions
• DAX Text Functions
• DAX Math and Statistical Functions
• DAX Aggregation Functions
• DAX Filter Functions
• DAX Time Intelligence Functions
• Creating a Date Dimension Table
• Related Aspects with Tables

Login, Publish to Web and RLS

• Power BI Services
• Dashboard Creation
• Web Content, Image, Text Box
• Dashboard Formatting
• Sharing Your Dashboard
• RLS Introduction

Miscellaneous Topics

• Visual Interactions
• Drill Through
• Drill Down
• Conditional Formatting
• Creating Buttons in Power BI Reports
• Creating Python Script Visuals

Project on Power BI

• Understand business problems and define reporting objectives
• Load data from multiple sources into Power BI
• Clean and transform data using Power Query
• Build data models and establish relationships
• Create DAX measures and calculated columns
• Design interactive dashboards and reports
• Generate insights and business recommendations across multiple industry domains

GenAI: Enhanced Presentations with ChatGPT

• Introduction to AI-Enhanced Presentations - Role of GenAI in Data Storytelling
• AI-Assisted Content Creation - Insights, Summaries and Key Takeaways
• AI-Assisted Presentation Design - Structure, Visuals and Slide Content
• Data Storytelling with ChatGPT - Converting Analysis into Narratives
• Hands-on with ChatGPT - Creating Data-Driven Presentations

Machine Learning Foundations

• Why Machine Learning?
• AI vs ML vs Deep Learning
• Supervised vs Unsupervised Learning
• Regression vs Classification
• Machine Learning Workflow / Lifecycle

Problem Definition & Objective

• Business Problem Statement
• Defining ML Objectives
• Identifying Features and Target
• Identifying Regression or Classification Tasks

Feature Engineering

• Feature Transformation
• Feature Selection
• Feature Importance

Train-Test Split

• Training and Testing Data
• Importance of Data Splitting
• Avoiding Data Leakage

Numerical Data Preprocessing

• Numerical Feature Preprocessing
• Feature Scaling
• Types of Feature Scaling
• Standardization
• Normalization

Categorical Data Preprocessing

• Categorical Feature Preprocessing
• Encoding Techniques
• One-Hot Encoding
• Ordinal Encoding

Supervised Learning - Classification Algorithms

• Introduction to Classification
• K-Nearest Neighbors (KNN)
• Logistic Regression
• Naive Bayes
• Decision Tree

Supervised Learning - Regression Algorithms

• Introduction to Regression
• Linear Regression
• KNN for Regression
• Decision Tree for Regression

Data Collection

• Data Sources
• Data Collection Methods
• Loading and Understanding Datasets

Exploratory Data Analysis (EDA)

• Univariate, Bivariate and Multivariate Analysis
• Visual and Non-Visual Statistics
• Understanding Data Distributions and Relationships

Data Quality Assessment

• Identifying Duplicates
• Handling Null and Missing Values
• Detecting Outliers
• Data Type and Consistency Checks

Model Building with Scikit-learn

• Model Training and Prediction
• Applying Preprocessing and Models
• Building ML Pipelines
• Hands-on Model Implementation

Regression Evaluation Metrics

• Mean Absolute Error (MAE)
• Mean Squared Error (MSE)
• Root Mean Squared Error (RMSE)
• R² Score
• Adjusted R² Score

Classification Evaluation Metrics

• Confusion Matrix
• Accuracy, Precision and Recall
• F1 Score
• Classification Report

Hyperparameter Tuning

• Parameters vs Hyperparameters
• Introduction to Cross-Validation
• GridSearchCV
• RandomizedSearchCV
• Model Selection and Tuning

GenAI: Enhanced Machine Learning Case Study

• Problem Definition & Data Understanding - Problem Statement, Objectives and AI-Assisted Data Exploration
• EDA & Data Preparation - AI-Assisted EDA, Data Cleaning and Feature Engineering
• Model Building & Evaluation - AI-Assisted Model Selection, Training and Evaluation
• Model Optimization & Interpretation - AI-Assisted Hyperparameter Tuning and Result Interpretation
• Business Insights & Deployment - AI-Assisted Insights and Reporting

GenAI Fundamentals for Data Analysts

• Introduction to Generative AI
• Generative AI vs Traditional AI
• Applications of GenAI in Data Analytics
• Overview of GenAI Tools - ChatGPT, Gemini, Gamma

Understanding LLMs

• What are Large Language Models?
• Context, Prompts and Responses
• Data Relevance and Hallucinations
• Limitations of LLMs

Prompt Engineering Essentials for Data Analytics

• Introduction to Prompt Engineering
• Effective Prompt Structure
• Context, Role and Constraints
• Iterative Prompting and Refinement

Prompting for Data Tasks

• Prompts for Data Understanding
• Prompts for Data Cleaning and EDA
• Prompts for Data Interpretation

GenAI for Data Cleaning & EDA

• AI-Assisted Data Understanding
• Identifying Missing Values, Duplicates and Outliers

GenAI for Code & SQL

• AI-Assisted Python Code Generation
• Code Explanation and Debugging
• AI-Assisted SQL Query Generation
• Query Optimization and Validation

GenAI for Analytics Reporting

• Converting Analysis into Insights
• AI-Assisted Report, PPT and PDF Generation using ChatGPT
• Data Storytelling with GenAI
• Creating Presentations with Gamma

Multimodal GenAI for Data Analytics

• Understanding Text, Images and Tables with GenAI
• Extracting Information from Documents and Images
• Image and Chart Interpretation
• Multimodal Analysis with ChatGPT and Gemini

Automating Data Analytics Workflows

• Introduction to AI-Assisted Automation
• Automating Repetitive Analytics Tasks
• Connecting Data and GenAI Tools
• Workflow Design with GenAI

No-Code AI Automation with n8n

• Introduction to n8n
• Connecting AI Models with Data Sources
• Building AI-Assisted Analytics Workflows
• Automating Reports and Notifications

Responsible GenAI for Data Analytics

• AI Limitations and Hallucinations
• Data Privacy and Security
• Bias and Responsible AI Usage
• Human Validation and Oversight

GenAI: Enhanced Data Analytics Case Study

• Problem Definition and Data Understanding
• AI-Assisted EDA and Data Preparation
• AI-Assisted Analysis, Reporting and Visualization
• Workflow Automation using GenAI Tools
• Validating AI Outputs and Generating Business Insights

GenAI Tools & Future of Data Analytics

• Comparing GenAI Tools for Data Tasks
• Selecting the Right Tool for the Task
• Building Personal GenAI Workflows
• Staying Current with Emerging GenAI Tools

Ethics, Responsibility & Staying Current with GenAI

• AI Ethics, Bias and Responsible AI Usage
• Data Privacy, Security and Intellectual Property
• Hallucinations, Human Validation and AI Reliability
• Staying Current with Emerging GenAI Tools and Technologies

Synthetic Data & Image Generation

• Introduction to Synthetic Data Generation
• Generating Synthetic Data for Testing and Analysis
• Introduction to AI-Based Image Generation and Use Cases

Projects & Case Studies

• Retail Sales Analysis
• Student Performance Analysis
• PeopleOps Analytics
• HR Analytics - Employee Attrition & Performance Analysis
• Pricing Strategy Analysis
• AI-Augmented Business Intelligence

Text Preprocessing

• Text Data - Introduction to NLP
• Why Text Data is Hard to Work With
• Cleaning Text Data
• Tokenisation
• Stop Words
• Lemmatization
• Stemming

Text Transformation

• Bag of Words
• Term Frequency-Inverse Document Frequency (TF-IDF)
• Spam-Ham Detection

Working with Image Data

• Image Data - Understanding Images
• RGB Channels
• Images as 3D NumPy Arrays
• Image Case Study

Mathematical Foundations

• Introduction and Why Linear Algebra
• Fundamentals of Vectors and Matrices
• Unit Vector
• Matrix Operations
• Dot Product of Vectors
• Angle Between Two Vectors
• Projection of a Vector onto Another Vector
• Length of Projection
• Distances and Dot Products

kNN for Classification & Regression

• Intuition Behind KNN
• Developing the Algorithm for KNN
• Solving Classification Problems with KNN
• Solving Regression Problems with KNN
• Code Implementation for KNN
• Hyperparameter Tuning

Naive Bayes Derivation, Solving an Example with NB

• Derivation of Naive Bayes Algorithm
• Solving an Example
• Code Implementation
• NB Example

Decision Tree (DT) Algorithm

• Introduction to Rule-Based Approach to Solve Classification and Regression Problems
• Building Decision Trees
• ID3, C4.5, C5.0 Algorithms to Build Decision Trees
• Concept of Entropy, Information Gain and Gini Impurity
• Python Code Sample

DT for Classification and Regression

• Working of DT with Numerical Input Data
• DT for Regression
• Reduction of Variance
• Solving an Example with DT

Equation of Line and Linear Regression, Multiple Linear Regression

• Understanding Equation of a Line and Hyperplane
• Intuition Behind Linear Regression
• Building a Cost Function for Regression and Classification Problems
• Mathematical Formulation of Linear Regression
• Calculating the Errors
• Python Implementation
• Simple Linear Regression vs Multiple Linear Regression
• Issues with Multiple Linear Regression
• Python Implementation
• Issue of Multicollinearity
• Detecting Multicollinearity with VIF

Linear Regression Edge Cases

• Linear Regression with Polynomial Features
• Assumptions of Linear Regression
• Hands-on

Gradient Descent

• Understanding Differentiation of a Function
• Slope of Tangent
• Computing Derivative
• Computing Maxima and Minima
• Iterative Algorithm to Solve the Problem of Maxima and Minima
• Update Function of Gradient Descent

Logistic Regression

• Geometric Intuition Behind Logistic Regression
• Mathematical Formulation of Logistic Regression
• Signed Distance Formulation
• Sigmoid Function
• Numerical Instability Issue
• Assumptions of Logistic Regression
• Code Sample

Support Vector Machines

• Introduction to SVM
• Solving Classification Problems Using SVM
• Logistic Regression vs SVC
• Margin Maximization
• Hard Margin Support Vector Classifier
• Soft Margin Support Vector Classifier
• How Kernel Trick Works?
• Pros and Cons of SVC

Parallel Ensembles

• Introducing Model Ensembles
• Voting Ensembles
• Stacking
• Bagging - Random Forest Case Study

Sequential Ensembles

• Cascading
• Boosting
• AdaBoost
• GBDT
• XGBoost Case Study

Feature Engineering - Transformation & Selection

• Revision on Feature Transformation
• Feature Selection Introduction
• Variance Thresholding
• Variance Inflation Factor
• Recursive Feature Elimination
• Lasso Regularization
• Decision Tree for Feature Importance
• Implementation Using Python

Introduction to Unsupervised Learning and KMeans, KMeans++

• Understanding Unsupervised Learning
• Clustering
• Applications of Clustering
• K-Means Algorithm
• Python Code Sample
• KMeans++ Initialisation

Hierarchical Clustering, Customer Segmentation

• Introduction to Hierarchical Clustering
• Merging
• Linkage - Single, Centroid, Complete
• Dendrogram
• Cut Tree
• Solving Customer Segmentation Using Clustering

PCA and Use Case

• Introduction to Dimensionality Reduction
• Introduction to Principal Component Analysis
• Eigenvalues and Eigenvectors
• Orthogonality
• Transforming Eigenvalues
• Proportion of Variance Explained in PCA
• Code Implementation

Time Series Forecasting

• Introduction to Time Series Data
• Components of Time Series - Trend, Seasonality & Residuals
• Time Series Analysis and Visualization
• Time-Based Train-Test Split
• Introduction to Forecasting
• Forecasting with Machine Learning
• Model Evaluation for Time Series Forecasting
• Hands-on Time Series Forecasting Case Study

AutoML & GenAI-Assisted Modeling

Exclusively for ✳ TIH at IIT Bombay

• Introduction to AutoML
• Automated Data Preprocessing, Feature Engineering & Model Selection
• Introduction to GenAI-Assisted Machine Learning
• AI-Assisted Model Selection, Code Generation & Debugging
• AI-Assisted Model Interpretation and Insights
• Hands-on AutoML & GenAI-Assisted Modeling

Explainable AI: Model Interpretation with LIME & SHAP

Exclusively for ✳ TIH at IIT Bombay

• Introduction to Explainable AI (XAI) and Model Interpretability
• Importance of Model Interpretation in Machine Learning
• Global vs Local Model Interpretability
• Model Interpretation using SHAP (SHapley Additive exPlanations)
• Model Interpretation using LIME (Local Interpretable Model-Agnostic Explanations)
• Feature Importance and Prediction-Level Explanations
• Interpreting and Communicating Model Insights
• Hands-on LIME & SHAP Model Interpretation Case Study

Project on Machine Learning

• Understand business problems and define clear machine learning objectives
• Collect and integrate datasets from multiple sources or publicly available repositories
• Perform data cleaning, preprocessing, and feature engineering
• Conduct Exploratory Data Analysis (EDA) to identify trends, patterns, and relationships
• Prepare training, validation, and testing datasets using appropriate data-splitting strategies
• Build and train supervised and unsupervised machine learning models
• Evaluate model performance using appropriate evaluation metrics
• Optimize models using hyperparameter tuning and cross-validation
• Apply LIME and SHAP for model interpretability and explainable AI
• Interpret model predictions and translate findings into actionable business insights
• Implement MLOps practices using MLflow for experiment tracking and model management
• Track model parameters, metrics, versions, and training workflows
• Deploy machine learning applications using Streamlit
• Develop end-to-end ML pipelines for practical and scalable real-world applications

Introduction to Deep Learning and Artificial Neural Networks

• Understanding Biological Neuron
• Analogy between Biological and Artificial Neuron
• Single Layer Perceptron Model
• Understanding Weights, Bias and Activation

Perceptron Model

• Perceptron Learning Rule
• Artificial Neuron
• MLP / FCNN / ANN Model
• Nomenclature of ANN

Training Neural Network

• Forward Pass with Formulation
• Backward Pass (Without Formulation)
• Understanding Backpropagation Algorithm Using AutoGrad Methods like GradientTape in TensorFlow

ANN Model Building

• Classification Model Building Using TensorFlow / Keras
• Regression Model Building Using TensorFlow / Keras (As an Assignment)
• Evaluating Model

Neuron Activation Function and Output Functions

• Linear Activation
• Sigmoid Function
• Tanh Function
• ReLU Function (LeakyReLU, Parametric ReLU)
• Softmax Function

Optimizers

• Gradient Descent
• Mini-Batch Gradient Descent
• Momentum-Based Gradient Descent
• Adaptive Gradient Descent
• Adam
• RMSProp

Overfitting in ANN

• L1 and L2 Regularization
• Dropout Regularizer
• Early Stopping
• Batch Normalization

Hyperparameter Tuning in ANN

• Introduction to Optuna
• Creating a Study in Optuna
• Finding Hyperparameters Using Optuna
• Hyperparameter Importance Using Optuna

Project on ANN

• Understand business problems and define machine learning objectives.
• Collect datasets from multiple sources or work with publicly available datasets.
• Perform data cleaning and preprocessing.
• Split data into training, validation, and testing datasets.
• Build supervised ANN models.
• Evaluate model performance using appropriate metrics.
• Optimize models using hyperparameter tuning.
• Track model metrics, parameters, versions and training workflows.
• Interpret model outputs and generate actionable business insights.
• Deploy machine learning applications using Streamlit.
• Create end-to-end ML pipelines for scalable real-world applications.

Introduction to Text and its Preprocessing with NLTK or SpaCy

• Introduction to NLP
• Text Preprocessing Steps
• Bag of Words (BOW) and TF-IDF
• Coding for BOW and TF-IDF using NLTK / SpaCy

Word Embeddings - Word2Vec

• Word2Vec
• Autoencoders
• How Word2Vec algorithm works (CBOW, Skip-gram)

Case Study - Text Classification

• Text Data Classification Case Study

Sequence Modelling with RNN

• Introduction to RNN
• Training of RNN
• Types of RNN
• Text Classification

LSTM, GRU

• Limitations of RNN
• Idea of LSTM and GRU
• POS Tagging

Self Attention and Transformers - Seq2Seq Architecture

• Attention Mechanism
• Implementing Attention Layers
• Hands-on: RNN / LSTM + Attention
• Case Study: Machine Translation

Transformer Architecture

• Positional Encoding
• Self and Multi-Head Attention
• Masked Multi-Head Attention
• GPT with Autoregressive Language Modelling
• BERT with Auto-Encoding Language Modelling

Hugging Face API

• Introduction to Hugging Face
• Hugging Face Embeddings
• Case Study: Sentiment Analysis, Named Entity Recognition, Parts of Speech Tagging, Question & Answering

NLP Tasks using AutoClasses

• AutoClasses - Config, Tokenization and Models

Text Generation & Question Answering

• Text Summarization
• Text Translation

Evaluation Metrics

• Introduction to Evaluation Metrics
• BLEU
• ROUGE
• METEOR
• Perplexity

Hugging Face for Image and Audio Data

• Image Classification
• Image Detection
• Audio Classification

Project on Natural Language Processing (NLP)

• Understand real-world text analytics problems and define NLP objectives.
• Collect textual datasets from multiple sources or use publicly available datasets.
• Perform text cleaning, tokenization, stemming, and lemmatization.
• Convert text into numerical representations using TF-IDF, Word Embeddings, and basic transformer pipelines.
• Build NLP models for tasks such as Sentiment Analysis, Text Classification, Spam Detection, and Chatbots.
• Train and evaluate NLP models using appropriate performance metrics.
• Extract insights from unstructured textual data.
• Deploy NLP applications using Streamlit.
• Build scalable NLP solutions for real-world business use cases.

Introduction to LangChain

• Why LangChain?
• Import Chat Models
• Integrating with OpenAI / Gemini / Groq API
• LCEL Chain

Components of a Chain

• PromptTemplate
• ChatPromptTemplate
• SystemMessage, HumanMessage & AI Messages

LCEL Chain

• OutputParser - StrOutputParser, PydanticParser
• Build a Basic ChatBot

Runnables

• RunnablePassthrough
• RunnableParallel
• Runnable
• Case Study

Conversation Memory

• Adding Memory to LangChain Applications
• Context Window Optimization
• Conversation Summarization Techniques

Monitoring and Observability

• Introduction to Monitoring and Observability
• Observability Tools
• Tracing Implementation

RAG Fundamentals

• What is RAG? and Why RAG?
• Document Loaders (PDF, Web, CSV)
• Text Splitters & Chunking

Embeddings and Vector Database

• Introduction to Vector Databases
• Working with Vector Databases - FAISS, Pinecone, Weaviate
• Storing, Indexing and Retrieving Vector Embeddings
• Vector Stores
• Vector Embeddings
• Retrieval Chain

Hybrid RAG

• Keyword, Semantic and Hybrid Search
• Re-ranking
• Embedding Models & Similarity Measures
• Semantic Search using Vector Embeddings
• Metadata Filtering for Context-Aware Retrieval
• Combining Metadata Filtering with Hybrid Search

Exclusively for ✳ TIH at IIT Bombay

RAG Evaluation

• RAGAS Evaluation
• LLM-as-a-Judge
• End-to-End RAG Pipeline Architecture
• Building Production-Ready RAG Applications
• RAG with Multiple Data Sources and Documents

Exclusively for ✳ TIH at IIT Bombay

Tool Calling & Agents

• ReAct Loop
• Build a ReAct Agent using Create Agent
• Add Custom Tools (like Search and Wikipedia)
• Response Formatting
• Error Handling
• Memory with Checkpointer
• PII Middleware
• Tool Retry and Model Retry

Monitoring and Observability (MCP)

• MCP Client-Server Architecture
• Transport Protocol - stdio and HTTP
• JSON-RPC Protocol
• Creating MCP Host with MCP Client in LangChain

Introduction to LangGraph

• LangChain vs LangGraph
• What is State?
• State Schema - TypedDict

Building Workflows with LangGraph

• Building a Graph
• StateGraph - Adding Nodes and Edges
• Sequential, Parallel and Conditional Workflows

Conversational Chatbot with Memory and Tool

• Adding Memory to Graph
• InMemorySaver
• Add Tools to Chatbot

Streaming and Human In The Loop

• Streaming and its Types
• Human in the Loop (HITL)

LangGraph Application Deployment

• LangGraph Agent Deployment
• AgentChat UI

Fine-Tuning Transformers for NLP Tasks

• Trainer API, TrainingArguments
• Sequence-to-Sequence vs Causal SFT
• Case Study - Text Summarization

PEFT with LoRA and QLoRA

• PEFT
• Low-Rank Adaptation (LoRA)
• Bitsandbytes Integration
• QLoRA

Building End-to-End AI Applications

• AI Application Architecture - From Idea to Implementation
• Integrating LLMs, RAG, Tools & APIs
• Building End-to-End AI Applications with Streamlit
• Testing, Validation & Deployment of AI Applications

Project on GenAI

• Understand real-world business problems and define Generative AI objectives.
• Collect datasets from multiple sources or use publicly available datasets.
• Preprocess and prepare textual data for Generative AI applications.
• Work with Large Language Models (LLMs) and prompt engineering techniques.
• Build applications - AI Chatbots, Document Q&A Systems, Text Summarization, & Content Generation tools.
• Integrate vector databases and embeddings for semantic search and retrieval.
• Implement Retrieval-Augmented Generation (RAG) pipelines.
• Evaluate Generative AI applications using relevant qualitative and quantitative metrics.
• Implement observability, tracing, and monitoring using tools such as Langfuse.
• Track prompts, responses, token usage, latency, and application performance.
• Deploy Generative AI applications using FastAPI and Streamlit.
• Build scalable end-to-end Generative AI solutions for real-world business use cases.

Project on Agentic AI

• Understand real-world business problems and define Agentic AI objectives.
• Design AI agents capable of reasoning, planning, and task execution.
• Integrate Large Language Models (LLMs) with external tools and APIs.
• Build multi-step workflows using agent frameworks and orchestration techniques.
• Develop AI agents for tasks such as Automation, Research Assistance, Data Analysis, & Workflow Management.
• Implement memory, context handling, and conversational capabilities in AI agents.
• Build Retrieval-Augmented Generation (RAG) and tool-calling pipelines for intelligent task execution.
• Evaluate agent performance based on accuracy, efficiency, and task completion.
• Implement observability, tracing, and monitoring using tools such as Langfuse.
• Monitor agent workflows, reasoning steps, latency, and tool usage.
• Deploy Agentic AI applications using FastAPI and Streamlit.
• Build scalable autonomous AI systems for real-world business applications.

Building Production AI Applications

• FastAPI for AI Services
• Streamlit & Gradio
• API Design for AI Applications
• Authentication & Security

Exclusively for ✳ TIH at IIT Bombay

Containerization & Cloud

• Docker Essentials
• Deploying AI Applications
• Azure AI Services
• Azure AI Foundry

Exclusively for ✳ TIH at IIT Bombay

LLMOps

• Prompt Management
• Model Versioning
• Prompt Caching
• Cost Optimization

Exclusively for ✳ TIH at IIT Bombay

Evaluation & Monitoring

• Evaluating LLM Applications
• LangSmith
• RAGAS & DeepEval
• Hallucination Detection & Groundedness

Exclusively for ✳ TIH at IIT Bombay

Production Engineering

• Logging & Observability
• Tracing AI Applications
• Performance Optimization
• Scaling AI & Systems
• Enterprise AI Deployment
• Deploying Multi-Agent Applications
• CI/CD for AI
• Monitoring Production AI

Exclusively for ✳ TIH at IIT Bombay

Intro to Images and Image Preprocessing with OpenCV

• Introduction to an Image
• How Images are formed and stored in machines
• Introduction to OpenCV - Read, Write and Save images
• Converting to Different Color Spaces (RGB, BGR, HLS, HSV)
• Bitwise Operators on Images

Image Preprocessing with OpenCV

• Drawing on images
• Affine and Non-Affine Transformation
• Building Histograms for Images
• Edge detection and Blurring
• Read videos
• Capturing images with web camera
• Manipulating videos with previous operations on images

Introduction to Convolutional Neural Networks

• Introduction to CNN
• Why CNN over MLP
• How does Convolution work on images
• How does Color image and grayscale image work over convolutional layers
• Padding, Stride, Maxpooling Operations
• Convolution Arithmetic

Image Classification Case Study

• Image classification on Hand Written Dataset
• Face Mask Detection

CNN Architecture

• Pretrained Model Introduction
• AlexNet, VGG16 and Inception
• ResNet and Skip Connections

Case Study with Transfer Learning

• Plant Diseases Prediction using Transfer Learning
• Cifar using Transfer Learning
• Improving Face Mask Detection Model using Transfer Learning

Object Detection

• Intro To object Detection
• R-CNN
• Fast R-CNN
• Faster R-CNN

YOLO Algorithm

• Intro to Yolo Algorithm
• How Yolo works?
• Introduction to Roboflow

YOLO Case Study

• Helmet Detection using Yolo

Image Segmentation with Case Study

• Introduction to Image Segmentation
• A case study on Image Segmentation

Project on Computer Vision

• Understand image-based business problems and define computer vision objectives.
• Collect and preprocess image and video datasets.
• Perform image augmentation and normalization techniques.
• Build computer vision models using OpenCV, CNNs, and Transfer Learning.
• Develop applications such as Object Detection, Face Recognition, Image Classification, & Pose Estimation.
• Train and evaluate deep learning models using appropriate CV metrics.
• Optimize model performance for real-time inference.
• Integrate computer vision pipelines with live webcam and video streams.
• Deploy computer vision applications using Streamlit.
• Build end-to-end AI-powered vision systems for real-world applications.

Projects & Case Studies

• Retail Sales Analysis
• Student Performance Management System
• PeopleOps Analytics
• Workforce Retention & Performance Analysis
• Retail Price Optimization
• ML Credit Risk Intelligence
• Automated Image Classification for Smart Logistics
• AI-Augmented Business Intelligence
• Build & Deploy an Enterprise AI Assistant