FULL STACK DATA SCIENCE WITH GENERATIVE AI

Course Introduction :

In this Introduction, you will learn what will be taught in this course and benifits of this
course.

Python Introduction :
1. What is Programming?
2. What is Coding?
3. Python Library
4. Python Modules
5. Python Webframework
6. Flavours of Python
7. What can Python do?
8. Why Python?
9. Python Syntax compared to other programming languages
10. Python Installation

Integrated development environment installation

Fundamentals of Python
1. The print statement
2. Comments
3. Python Data Structures & Data Types
4. String Operations in Python
5. Python keywords
6. Python Variables
7. Python Type Conversions
8. Simple Input & Output

Python Operators
1. Arithmetic operators
2. Assignment operators
3. Comparison operators &Logical operators
4. Identity operators
5. Membership operators & Output
6. Simple Output Formatting
Python Conditional Statements
1. Indentation
2. The If statement and its’ related statement
3. An example with if and it’s related statement
4. Else
5. Nested If
6. Short Hand If
7. Short Hand If else & Continue
8. Examples for Conditional Statements

Python Iterative Statements

1. Indentation
2. The for statement and its’ related statement
3. An example with for and it’s related statement
4. While
5. Nested for
6. Nested While
7. Examples for Looping Statements

Python Jumping Statements

1. Indentation
2. The Break statement and its’ related statement
3. An example with Break and it’s related statement
4. Continue
5. Pass
6. Examples for Jumping Statements

Python Strings
1. String object basics
2. String methods
3. Splitting and Joining strings
4. String format functions

Python Lists
1. List object basics
2. List methods
3. List as Stack and Queues
4. List comprehensions
Python Tuples
1. Introduction to Tuples
2. Tuples with built-in functions
3. Tuple operations

Python Sets
1. Introduction to Sets
2. Sets with built-in functions
3. Set Operations
4. Set with functions

Python Dictionary
1. Introduction to Dictionary
2. Dictionary with built-in functions
3. Dictionary with functions

Python Functions
1. Defining a function
2. Calling a function
3. return statement Difference between return and print
4. Arguments
5. Parameters
6. Keyword arguments
7. Arbitrary argument
8. User defined functions
9. Nested functions
10. Functions with real time examples

Object-oriented Programming with Python

Introduction to Classes
i. Creation of Classes
ii. Real time examples of Classes
Creation of Objects
i. Init
ii. self keyword
iii. super keyword
Inheritance
Types of Inheritance:
i. Single Inheritance.
 ii. Multiple Inheritance.
iii. Multi-Level Inheritance.
iv. Hierarchical Inheritance

Polymorphism:
i. Method overloading
ii. Method overriding
Encapsulation
i. Private
ii. Public
iii. Protected
Data Abstraction
i. Abc class
ii. Abstract method
iii. Realtime example of Data Abstraction

Python Numpy (Numerical Python)

1. Introduction to Numpy
2. Numpy Installation
3. NumPy – Ndarray Object
4. NumPy – Data Types
5. NumPy – Array Attributes
6. NumPy – Array Creation Routines
7. NumPy – Array from Existing Data
8. Array From Numerical Ranges
9. NumPy – Indexing & Slicing
10. NumPy – Advanced Indexing
11. NumPy – Broadcasting
12. NumPy – Iterating Over Array
13. NumPy – Array Manipulation
14. NumPy – Binary Operators
15. NumPy – String Functions
16. NumPy – Mathematical Functions
17. NumPy – Arithmetic Operations
18. NumPy – Statistical Functions
19. Sort, Search & Counting Functions
20. NumPy – Byte Swapping
21. NumPy – Copies & Views
22. NumPy – Matrix Library
 23. NumPy – Linear Algebra

Python Pandas for Data Analysis

1. Introduction to Pandas
2. Pandas Installation
3. Python Pandas – Series
4. Python Pandas – DataFrame
5. Python Pandas – Panel
6. Python Pandas – Basic Functionality
7. Descriptive Statistics
8. Function Application
9. Python Pandas – Reindexing
10. Python Pandas – Iteration
11. Python Pandas – Sorting
12. Working with Text Data
13. Options & Customization
14. Indexing & Selecting Data
15. Statistical Functions
16. Python Pandas – Window Functions
17. Python Pandas – Date Functionality
18. Python Pandas – Timedelta
19. Python Pandas – Categorical Data
20. Python Pandas – Visualization
21. Python Pandas – IO Tools

Data Visualization with Matplotlib

Matplotlib

Fundamentals of Statistics
1. Descriptive and inferential Statistics
2. Sampling Methods
3. Types of Variables
4. Independent and dependent variables
5. Variable Measurement Scales
6. Frequency Distribution and Cumulative Frequency Distribution
7. Bar Graphs and Pie Charts
8. Histograms and stem & leaf plots
9. Arithmetic Mean for samples and populations
10. Central Tendency
11. Variance and Standard deviation for Population and sample
12. Percentiles and Quartiles
 13. Inter Quartile Ranges and Box Plots
14. Outliers in data
15. Skewness for the data
16. The normal curves
17. Z-scores and z-test for the data

Probability for Data Science

1. Basics of probability
2. Addition Rule
3. Multiplication Rule
4. Permutations
5. Combination
6. Discrete and Continuous Random Variables
7. Discrete probability distribution
8. Probability Histogram
9. Mean and Expected values of discrete random variables
10. Variance and standard deviation of discrete random variables

Advanced Statistics
1. Binomial distribution
2. Normal distribution
3. Quadrants
4. Pearsons correlation
5. Hypothesis testing with Pearson’s r
6. Spearman correlation
7. Central Limit theorem
8. Sample proportions
9. Confidence intervals about the mean, population, standard deviation
10. NULL and alternative Hypotheses
11. Type I and Type II Errors
12. One-Tailed and Two-Tailed Tests

Machine Learning Introduction for DataScience

1. What is Data?
 2. Difference between CPU and GPU
3. Parallel and sequence processors
4. How data will be arranged in the axis
5. Types of machine learnings
6. What is classification?
7. What is regression?
8. What is clustering?
9. Performance metrics
10. What are errors?
11. What are all the libraries in Machine Learning?
12. Knowing about Tensorflow, Keras, Scikit-Learn, etc.
13. Explorative Data Analysis
14. Bias and variance

Machine Learning for DataScience

1. Linear Regression Maths
2. Linear Regression building from scratch without libraries
3. Linear Regression Building with Libraries (Scikit Learn)
4. Maths for the Mean Squared Error, Squared Error, Absolute Squared Error.
5. Writing Code from scratch for Mean Squared error
6. Writing Code from scratch for Squared error
7. Writing Code from scratch for absolute Squared error
8. Logistic Regression Maths
9. Logistic Regression building from scratch without libraries
10. Logistic Regression Building with Libraries (Scikit Learn)
11. Maths for the Accuracy, Precision, Recall, F1-Score
12. Writing Code from scratch for Accuracy
13. Writing Code from scratch for Precision
14. Writing Code from scratch for Recall
15. Writing Code from scratch for F1-Score
16. Writing code for all the metrics using sklearn (MSE, SE, Accuracy, Precision, etc..)

Decision Tree
1. Introduction to Decision Trees
Definition and concept of decision trees
Advantages and disadvantages of decision trees
Applications in classification and regression

2. Building a Decision Tree

 Concept of root node, internal nodes, and leaf nodes
Splitting criteria and recursive partitioning
Measures of impurity:
Gini Index
Entropy and Information Gain
Gain Ratio
Chi-square
3. Decision Tree Algorithms
1. ID3 (Iterative Dichotomiser 3)
2. C4.5 and C5.0 algorithms
3. CART (Classification and Regression Tree)
4. Overfitting and Pruning
1. Causes of overfitting in trees
2. Pre-pruning (early stopping)
3. Post-pruning (reduced error pruning, cost complexity pruning)
5. Handling Different Data Types
1. Continuous vs categorical attributes
2. Missing value handling
3. Feature selection importance
6. Evaluation of Decision Trees
1. Confusion matrix
2. Accuracy, precision, recall, F1-score
3. ROC and AUC
7. Implementation
Decision Tree using scikit-learn
Visualizing the tree structure
Case study: Classification problem (e.g., Titanic dataset)

Random Forest
1. Introduction to Ensemble Learning
1. Definition and concept of ensemble methods
2. Types: Bagging, Boosting, Stacking
3. Why ensemble learning improves accuracy
2. Random Forest Basics
1. Concept of Random Forest as an ensemble of decision trees
2. Working principle and architecture
3. Bootstrapping and feature randomness
3. Random Forest Algorithm
1. Steps to build a Random Forest
2. Out-of-bag (OOB) error estimation
 3. Feature importance calculation
4. Hyperparameter Tuning
1. Number of trees (n_estimators)
2. Max depth and min samples split
3. Criterion (gini, entropy)
4. Max features and bootstrap parameters
5. Handling Overfitting and Bias
1. Bias-variance tradeoff in Random Forest
2. Comparison with single decision tree
3. Techniques to improve model generalization
6. Evaluation Metrics
1. Classification metrics: Accuracy, Precision, Recall, F1-score
2. Regression metrics: RMSE, MAE, R² score
3. Feature importance visualization
7. Implementation
1. Random Forest using scikit-learn
2. Feature importance and visualization
3. Case study: Predictive analytics using Random Forest

Deep Learning
1. What is Perceptron?
2. Neurons in humans and AI?
3. What is a single layers perceptron?
4. Neural Networks
5. Hidden Layers
6. Weights and bias
7. Neural networks maths behind it
8. Tensorflow and Keras introduction
9. Building neural networks with TensorFlow
10. Activation functions
11. Gradient descent algorithms
12. Feedforward network
13. Backpropagation
14. Error and accuracy

Artificial Neural Networks (ANN)

1. Introduction to Neural Networks
1. Definition and motivation of ANN
 2. Biological neuron vs Artificial neuron
3. Applications of neural networks in AI and ML
2. Basic Concepts
1. Structure of a neuron: weights, bias, activation function
2. Types of activation functions: Sigmoid, Tanh, ReLU, Leaky ReLU, Softmax
3. Network architectures: Single-layer and Multi-layer perceptrons
3. Learning in Neural Networks
1. Supervised, unsupervised, and reinforcement learning
2. Cost/loss functions and gradient descent
3. Backpropagation algorithm (step-by-step working)
4. Training and Optimization
1. Batch vs Mini-batch vs Stochastic gradient descent
2. Learning rate scheduling and optimizers (SGD, Adam, RMSProp)
3. Overfitting and underfitting concepts
4. Regularization techniques: Dropout, L1/L2 regularization, early stopping
5. Deep Neural Networks (DNN)
1. Concept of deep learning and hidden layers
2. Vanishing and exploding gradient problems
3. Batch normalization
4. Introduction to frameworks: TensorFlow, Keras, PyTorch
6. Applications of ANN
1. Image classification and pattern recognition
2. Medical diagnosis, speech recognition, financial forecasting
3. Case study using Python implementation
Recurrent Neural Networks (RNN)
1. Introduction to Sequential Data
a. Difference between feed-forward and recurrent networks
b. Understanding time series and sequence modeling
c. Applications: NLP, speech recognition, sentiment analysis
2. Architecture of RNN
1. Structure and working of a recurrent neuron
2. Forward and backward propagation through time (BPTT)
3. Exploding and vanishing gradient problems in RNNs
3. Types of RNNs
1. One-to-One, One-to-Many, Many-to-One, and Many-to-Many models
2. Bidirectional RNNs
3. Deep RNNs
4. Advanced RNN Architectures
1. Long Short-Term Memory (LSTM) networks – architecture and gates
2. Gated Recurrent Units (GRU) – architecture and differences from LSTM
3. Comparison: Vanilla RNN vs LSTM vs GRU
5. Training and Optimization
1. Truncated BPTT
2. Gradient clipping
 3. Dropout in RNNs
4. Regularization and tuning parameters
6. Applications of RNNs
1. Language modeling and text generation
2. Machine translation
3. Speech-to-text conversion
4. Stock market prediction
5. Practical implementation using Keras or PyTorch
Natural Language Processing (NLP)
1. What is Corpus?
2. What are Tokens?
3. What are Engrams?
4. What is Tokenization?
1. What is White-space Tokenization?
2. What is Regular Expression Tokenization?
What is Normalization?
a. What is Stemming?
b. What is Lemmatization?
Part of Speech tags in NLP

Transformers Core Concepts (NLP)

1. Embeddings
1. Concept of word embeddings in NLP
2. Difference between one-hot encoding and embeddings
3. Word2Vec, GloVe, and FastText overview
4. Positional embeddings in Transformers
5. How embeddings capture semantic meaning
6. Tokenization and subword embeddings (BPE, WordPiece)
7. Visualization of embedding spaces
2. Encoder
1. Purpose of the encoder in Transformer architecture
2. Input processing using embeddings and positional encodings
3. Self-attention mechanism within encoder layers
4. Layer normalization and residual connections
5. Feed-forward neural network after attention
6. Stacking multiple encoder layers for deeper context
7. Output representations for downstream NLP tasks
3. Decoder
1. Role of the decoder in sequence generation
2. Masked self-attention to prevent information leakage
 3. Encoder-decoder attention for contextual understanding
4. Feed-forward layers and normalization
5. Token prediction using linear + softmax layer
6. Autoregressive text generation process
7. Applications in translation, summarization, and dialogue
4. “Attention Is All You Need” Paper
1. Introduction to the 2017 Vaswani et al. paper
2. Motivation: Overcoming RNN and LSTM limitations
3. Key innovations introduced:
a. Self-attention mechanism
b. Positional encoding
c. Multi-head attention Encoder-decoder parallel processing
4. Architecture details and training process
5. Results on translation tasks (WMT 2014 English-German, English-French)
[Link]: Parallelism, scalability, interpretability
6. Foundation for modern NLP models (BERT, GPT, T5, etc.)

Prompt Engineering Fundamentals

1. Prompt Engineering
2. Prompt Structure
3. Prompt Components
4. Zero-shot Prompting
5. Few-shot Prompting
6. Chain-of-thought Prompting
7. Prompt Templates
8. Prompt Variables
9. Best Practices
10. Common Pitfalls
11. Prompt Testing
12. Iteration Strategies
LangChain Basics
1. Introduction to LangChain framework
2. Installation and setup
3. LangChain architecture overview
4. Components: Models, Prompts, Chains, Agents
Models and Prompts
 1. Connecting different LLM models (OpenAI, Claude, Llama)
2. PromptTemplates and their types → Output parsers
3. Model parameters (temperature, tokens, etc.)
4. Prompt composition techniques
Text Processing Tasks
1. Summarizing: Single vs multi-document, extractive vs abstractive
2. Inferring: Sentiment analysis, topic extraction, entity recognition
3. Transforming: Translation, format conversion, tone adjustment
4. Expanding: Content generation, creative writing, email drafting
Memory Systems
1. ConversationBufferMemory
2. ConversationSummaryMemory
3. ConversationBufferWindowMemory
4. Entity memory
5. Storing and retrieving conversation context
Chains
1. LLMChain basics
2. Sequential chains
3. Router chains
4. MapReduce chains
5. Combining multiple chains
6. Custom chain creation

Question-Answering Systems
1. Document loaders and text splitters
2. Vector stores and embeddings → Retrieval methods
3. RAG (Retrieval Augmented Generation)
4. Building a simple QA bot
5. Source citation and context management

Building ChatBots
1. Conversational flow design
2. Context management in chat
3. Multi-turn conversation handling
4. Personality and tone customization
5. Error handling and fallbacks
6. Streaming responses
AI Agents
1. What are agents and when to use them
2. Agent types (ReAct, OpenAI Functions, etc.)
3. Tools and toolkits
4. Custom tool creation
 5. Agent execution and debugging
Evaluation
1. Prompt evaluation metrics
2. Response quality assessment
3. Cost optimization strategies
4. A/B testing prompts
5. Debugging LangChain applications
6. Performance monitoring
Large Language Model(LLMs)
OpenAI
1. Introduction
2. API Call and Body Structure
3. Limits / Cost
4. Advantages / Disadvantages
5. Fine Tuning
Llama
1. Introduction
2. API Call and Body Structure
3. Limits / Cost 4. Advantages / Disadvantages
4. Fine Tuning

Claude
1. Introduction
2. API Call and Body Structure
3. Limits / Cost
4. Advantages / Disadvantages
5. Fine Tuning

DeepSeek
1. Introduction
2. API Call and Body Structure
3. Limits / Cost
4. Advantages / Disadvantages
5. Fine Tuning
OLLAMA(LLM at your laptop)
1. Model Download
1. Set up environment and dependencies
2. Download models and tokenizers
3. Verify configuration and GPU support
2. Model Terminal Usage
 1. Run models via CLI
2. Generate text with custom prompts
3. Tune output using temperature and top-p
3. Model API Calls
1. Load models in Python using Transformers
2. Generate and stream responses
3. Integrate with apps or scripts
3. Configuration Tuning
1. Optimize performance and memory
2. Use quantization for speed
3. Evaluate accuracy and efficiency
Best Practices & Deployment
1. Production considerations
2. Error handling and logging
3. Cost optimization
4. Security and API key management
5. Scaling considerations
6. Integration with applications

Real-time Projects
1. HealthLLM: Transformer-Driven Personalized Wellness
Companion for Children
A next-generation AI health companion leveraging large language models and
transformer architectures to deliver adaptive, age-aware, and personalized wellness
guidance for kids.

2. AgroRAG: Retrieval-Augmented Intelligence Platform for

Precision Agriculture and Crop Advisory

An LLM-integrated agricultural advisory system that combines real-time environmental

data retrieval with transformer-based reasoning for optimized crop management and
disease prevention.

3. Personal Health Advisory System Leveraging Machine

Learning(ML)and Large Language Models(LLM)
This project develops an intelligent Personal Health Advisory System that uses Machine
Learning and Large Language Models (LLMs) to provide personalized health insights and
lifestyle recommendations. By analyzing user data such as age, gender, symptoms, and health
habits, the system predicts potential health risks and offers preventive advice. It can also
interact conversationally, answering health-related queries in a natural, human-like manner,
helping users make informed decisions and maintain better well-being.

4. Real-Time Traffic Analysis Tool for Network Security using

Artificial Intelligence (AI)

This project focuses on developing a Real-Time Network Traffic Analysis Tool that leverages
Artificial Intelligence (AI) to monitor, detect, and prevent suspicious activities within a
network. The system analyzes live traffic data to identify anomalies, intrusions, and security
threats, ensuring enhanced network performance and data protection. By using AI-driven
algorithms, it provides automated threat detection, real-time alerts, and intelligent insights to
strengthen overall cybersecurity.

[Link]: Transformer-Based Personalized Financial Planning and

Goal Optimization Assistant

A smart financial planning platform leveraging large language models and reinforcement-
driven personalization to help users set, monitor, and achieve financial goals efficiently.
 FullStack DataScience with GenerativeAI in Telugu

We Provide
1. 2 Months Live Classes + 1 Month Internship
2. Daily Recordings
3. Study Material
4. Certification
5. 100% Placement Assistance
1. Mock Interviews
2. Resume Building
3. RealTime Projects
4. Daily 25 Job Notifications
6. Topic wise interview questions
7. 24/7 Community for Doubts
8. 5 Real Time Projects

Price: Rs 8999 [Emi Available]

Timings:7Pm to 9Pm IST

Date : 10 December 2025