Generative AI & ML Job Oriented Program

2.1 File Handling: Reading and Writing Files (Text and CSV)

2.2 Parsing CSV Files with the csv Module

2.3 Error Handling with Try/Except Blocks

2.4 Introduction to Numpy Arrays and Array Operations

2.5 Reshaping, Indexing, and Slicing Numpy Arrays

2.6 Applying Mathematical Functions and Aggregations to Numpy Arrays

2.7 Working with Multi-Dimensional Data

Hands-On:

• Write a script that reads customer data from a text file and prints it to the console.
• Write a program to read sales data from a CSV file, calculate total sales per product, and write the results to a new CSV file.
• Create a Numpy array from a dataset and perform basic statistical operations (sum, mean, variance).
• Reshape a multi-dimensional array and apply transformations (e.g., logarithmic, square root).

3.1 Introduction to Pandas DataFrames and Series

3.2 Loading Data from CSV, Excel, or SQL Databases

3.3 Basic Data Frame Operations (Selection, Filtering, Sorting, Grouping)

3.4 Handling Missing Data

3.5 Data Cleaning Techniques (Dealing with Missing Data, Duplicates, Outliers)

3.6 Data Transformation: Renaming Columns, Changing Data Types, Applying Functions   

3.7 Handling Dates and Times with pd.to_datetime()

3.8 Combining and Merging DataFrames

Hands-On:

• oad a sales dataset into a Pandas DataFrame and perform operations such as filtering for specific products, sorting by sales, and handling missing values.
• Write a script to group sales data by region and calculate total sales for each region.
• Clean a dataset by removing duplicates, filling missing values, and transforming date columns into a standard format.
• Merge two DataFrames containing customer and sales data, then calculate total sales per customer.

4.1 Descriptive Statistics with Pandas (mean(), median(), mode(), std())

4.2 Data Visualization using Matplotlib and Seaborn (Bar Plots, Histograms, Box Plots)

4.3 Correlation Analysis and Pairwise Relationships

4.4 Detecting and Visualizing Outliers

4.5 Advanced Visualization Techniques with Matplotlib and Seaborn

4.6 Line Plots, Scatter Plots, and Pie Charts

4.7 Customizing Plots (Titles, Labels, Legends, Colors)

4.8 Creating Subplots and Multi-Panel Figures

Hands-On:

• Perform an EDA on a dataset, calculate basic statistics, and visualize relationships using bar plots and histograms.
• Visualize correlations between numeric variables in a dataset and create a heatmap.
• Create a multi-panel visualization showing sales trends over time and sales distribution by product.
• Generate a pie chart to show the market share of different products.

5.1 Introduction to Databases with SQLAlchemy

5.2 Writing SQL Queries from Python Using SQLAlchemy ORM

5.3 Loading Data from SQL Databases into Pandas

5.4 Writing Data Back to SQL Databases from Pandas

5.5 Introduction to Views, Stored Procedures, Functions, and Performance Optimization in Databases

Hands-On:

• Write a Python script that connects to a SQL database, extracts sales data, and loads it into a Pandas DataFrame for analysis.
• Perform analysis on the data (e.g., find the top customers by revenue) and write the results back to the–

6.1 Univariate Analysis

6.2 Bi Variate Analysis

6.3 Multi Variate Analysis

6.4 Central Tendencies Mean, Median, Mode, Variance Standard Deviation,

6.5 Distribution Probability Distribution

6.6 Normal Distribution

6.7 Hypothesis Testing

6.8 Confidence Interval

6.9 Correlation Vs Covariance

6.10 Central Limit Theorm P value/ Alpha

6.11 Intro to Advance/ Inferential Statistics Hypothesis Testing

6.12 T test Z test Chi Square Anova

7.1 What is Machine Learning?

7.2 Why Machine Learning?

7.3 Limitations of Machine Learning

7.4 Prediction Modelling Linear Regression

7.5 Sales Predictions and Forecasting

7.6 Classification using Logistics Regression

7.7 Overview of Supervised and Unsupervised Learning

Hands-On:

• Identify examples of supervised and unsupervised learning from a given dataset.
• Churn Analysis
• Fraud Analysis

8.1 Introduction to scikit-learn

8.2 Core Components of Scikit-learn for Machine learning

8.3 Understanding Regression Problems

8.4 Define regression problems

8.5 Dependent and independent variables, and their roles.

8.6 Train a Regression model using scikit-learn.

8.7 Techniques for assessing model performance

8.8 Techniques for improving model performance, such as feature scaling and polynomial regression.

8.9 Train a K-Means model on the dataset and visualize the clusters formed.

Hands-On:

• Install scikit-learn and load a sample dataset. Practice importing and understanding datasets within scikit-learn.Load a dataset with continuous target variables and identify the dependent and independent variables.
• Train a simple linear regression model on a sample dataset, such as predicting house prices
• Evaluate the trained regression model using MSE and R² on both the training and test datasets
• Improve the regression model by scaling features and applying polynomial regression; compare model results.

9.1 Linear Regression

9.2 Logistics Regression

9.3 Decision Trees

9.4 Random Forest

9.5 Support Vector Machine (SVM)

9.6 K-Nearest Neighbors (KNN)

14.7 Time Series Forecasting

Hands-On:

• Classifying Heart Disease Risk with Logistics Regression
• Customer Churn Prediction with Decision Tree
• Predicting Stock Prices using Time Series Forcasting

10.1 K-Means Clustering

10.2 Dimensionality Reduction

10.3 Linear Discriminant Analysis (LDA)

10.4 Principal Component Analysis (PCA)

Hands-On:

• Linear Discriminant Analysis (LDA) Exercise: Facial Recognition
• Principal Component Analysis (PCA) Exercise: Image Compression
• Feature Reduction and Classification in a High-Dimensional Dataset

11.1 Overview of Deep Learning and Neural Networks

11.2 Difference between DS VS ML VS AI

11.3 Setting up TensorFlow, Keras, and PyTorch environments

11.4 Introduction to Tensors, Computation Graphs, and Autograd

11.5 Basics of building and training models in TensorFlow and PyTorch

Hands-On:

• Set up TensorFlow, Keras, and PyTorch environments.
• Create a simple neural network in both TensorFlow and PyTorch.
• Implement basic tensor operations (addition, multiplication, reshaping).
• Visualize computation graphs in TensorFlow.

12.1 Artificial Neural Networks (ANN)

12.2 Convolutional Neural Networks (CNN)

12.3 Recurrent Neural Networks (RNN)

12.4 Introduction to Transfer Learning

Hands-On:

• Build and train a basic ANN for a simple classification task (e.g., MNIST dataset).
• Implement a CNN for image recognition using a standard dataset (e.g., CIFAR-10).
• Train an RNN model to predict a sequence (e.g., text generation or temperature prediction).
• Apply transfer learning to a CNN model for a custom image dataset

13.1 Long Short-Term Memory Networks (LSTM)

13.1 Graph Neural Networks (GNN)

13.2 Advanced Recurrent Architectures: Bidirectional RNN, GRU

13.3 Hyperparameter Tuning and Model Optimization

Hands-On:

• Train an LSTM model on a time-series dataset (e.g., stock prices or weather data).
• Implement a GNN to classify nodes in a graph dataset.
• Experiment with Bidirectional RNNs on text data.
• Perform hyperparameter tuning on a CNN model to optimize accuracy.

14.1 Introduction to NLP concepts and text preprocessing (tokenization, stemming)

14.2 Using NLTK for basic NLP tasks

14.3 Text classification using deep learning (RNN, LSTM)

14.4 Sentiment analysis and text generation

Hands-On:

• Preprocess a text dataset using NLTK (e.g., tokenization, stop word removal).
• Build a text classification model (e.g., spam detection) using an RNN or LSTM.
• Train a sentiment analysis model on movie reviews or Twitter data.
• Experiment with a text generation model for generating sentences or paragraphs.

15.1 Advanced CNNs and image processing techniques

15.2 Object detection and YOLO (You Only Look Once) for real-time detection

15.3 Transfer Learning with pre-trained image models (e.g., ResNet, Inception)

15.4 Fine-tuning models for specific tasks

Hands-On:

• Train a CNN for a custom image recognition task (e.g., animal classification).
• Apply YOLO for real-time object detection in images or videos.
• Experiment with transfer learning using a pre-trained model on a new dataset.
• Fine-tune the YOLO model on a specific category of objects (e.g., cars or animals).

16.1 What is Generative AI?

16.2 Difference between Discriminative vs. Generative models

16.3 Use cases: Chatbots, Image Generation, Code Assistants

16.4 Overview of Text, Image, Audio, and Video generation

17.1 What are Large Language Models (LLMs)?

17.2 Transformer architecture & attention mechanism

17.3 Tokenization, embeddings, context windows

17.4 Pretraining vs. Fine-tuning vs. In-context learning

17.5 Zero-shot, few-shot, and chain-of-thought prompting

17.6 Prompt design best practices

17.7 Prompt debugging

Hands-On:

• Tools: Hugging Face Transformers, OpenAI Playground
  

18.1 OpenAI API (ChatGPT, DALL·E, Whisper)

18.2 Hugging Face Inference API

18.3 Building apps using LLM APIs

19.1 LangChain essentials (chains, agents, memory)

19.2 Working with vector stores (Pinecone, FAISS, Chroma)

19.3 Retrieval-Augmented Generation (RAG)

19.4 Connecting LLMs to PDFs, websites, and SQL

20.1 Introduction to LoRA, PEFT, and parameter-efficient fine-tuning

20.2 Fine-tune small open-source models on your own data

20.3 Use cases: domain-specific chatbots, customer service models

Hosting on Hugging Face Spaces, Streamlit Cloud, or Vercel

Handling tokens, secrets, and error logging

UI/UX best practices for GenAI apps

22.1 Introduction to MLOps

22.2 MLOps vs. DevOps

22.3 SDLC Basics

22.4 What is Cloud Computing

22.5 AWS Introduction

22.6 S3

22.7 Waterfall vs AGILE vs DevOps vs MLOps

22.8 MLOps Phases

22.9 Model Packaging

23.1 Git Essentials

23.2 Configuring Git

23.3 Branching

23.4 Git Workflow

23.5 Repo

23.6 Git Commands

23.7 Tracking and managing changes to code

23.8 Source Code Management

23.9 Tracking and Saving Changes in Files

24.1 Introduction to CI/CD

24.2 CI/CD Challenges

24.3 CI/CD Implementation in ML

24.4 Popular DevOps Tools

24.5 AWS CodeCommit

24.6 AWS CodePipeline

24.7 AWS CodeBuild

24.8 AWS CodeDeploy

25.1 Docker Architecture

25.2 Docker for Machine Learning

25.3 Continuous Deployment

25.4 Writing a Dockerfile to Create an Image

25.5 Installing Docker Compose

25.6 Configuring Local Registry

25.7 Container Orchestration

25.8 Application Deployment

25.9 Kubernetes Core Concepts

26.1: CV Preperation

26.2: Interview Preperation

26.3: LinkedIn Profile Update

26.4: Expert Tips & Tricks