Machine Learning Journey 🚀

Welcome to my Machine Learning repository.

This repository documents my complete journey from Python fundamentals to industry-level Machine Learning, Deep Learning, MLOps, and Generative AI. The goal of this repository is not only to learn concepts but also to build projects, maintain notes, and create a strong foundation for a career in AI/ML.

---

🎯 Objective

• Learn Machine Learning from scratch.
• Build strong mathematical foundations.
• Understand algorithms from first principles.
• Implement concepts through code.
• Develop real-world projects.
• Learn deployment and MLOps.
• Prepare for ML/AI internships and jobs.
• Create a complete revision resource for future use.

---

🗺️ Roadmap

Phase 0: Python Foundations

• Variables
• Data Types
• Operators
• Input / Output
• Conditional Statements
• Loops
• Functions
• Strings
• Lists
• Tuples
• Sets
• Dictionaries
• OOP
• Exception Handling
• File Handling
• Modules & Packages

Projects

• Calculator
• BMI Calculator
• To-Do List
• Expense Tracker
• Student Management System

---

Phase 1: Mathematics for Machine Learning

Linear Algebra

• Scalars
• Vectors
• Matrices
• Matrix Operations
• Dot Product
• Eigenvalues & Eigenvectors
• Tensors

Calculus

• Limits
• Derivatives
• Partial Derivatives
• Gradients

Probability

• Random Variables
• Conditional Probability
• Bayes Theorem
• Probability Distributions
• Probability Distribution Functions (PDF, CDF)
• Gaussian (Normal) Distribution
• Non-Gaussian Distributions

Statistics

• Mean
• Median
• Mode
• Variance
• Standard Deviation
• Correlation
• Descriptive Statistics

---

Phase 2: Data Analysis

NumPy

• Arrays
• Broadcasting
• Vectorization
• Mathematical Operations

Pandas

• DataFrames
• Data Cleaning
• Data Manipulation
• Missing Values

Data Visualization

• Matplotlib
• Seaborn
• Exploratory Data Analysis (EDA)

Data Gathering

• Working with CSV Files
• Working with JSON & SQL Data
• Fetching Data from APIs
• Web Scraping (BeautifulSoup)

Understanding Your Data

• Shape, Data Types, Duplicates, Missing Values
• Descriptive Statistics of a Dataset

EDA Techniques

• Univariate Analysis
• Bivariate Analysis
• Multivariate Analysis
• Automated EDA (Pandas Profiling)

Data Cleaning

• Handling Missing Data (Complete Case Analysis, Numerical Imputation, Categorical Imputation, Missing Indicator, KNN & Iterative Imputer)
• Outlier Detection & Removal (Z-Score, IQR, Percentile / Winsorization)

Projects

• IPL Data Analysis
• Netflix Data Analysis
• Sales Data Analysis

---

Phase 3: SQL

• SELECT
• WHERE
• ORDER BY
• GROUP BY
• HAVING
• JOINs
• Subqueries
• Window Functions

---

Phase 4: Machine Learning

Supervised Learning

Regression

• Linear Regression
• Multiple Linear Regression
• Polynomial Regression

Classification

• Logistic Regression
• KNN
• Naive Bayes
• SVM

Tree-Based Models

• Decision Tree
• Random Forest

Ensemble Learning

• AdaBoost
• Gradient Boosting
• XGBoost
• LightGBM
• CatBoost

Unsupervised Learning

• K-Means Clustering
• Hierarchical Clustering
• PCA

Model Evaluation

• Accuracy
• Precision
• Recall
• F1 Score
• ROC-AUC
• Confusion Matrix

ML Foundations

• What is Machine Learning
• Types of Machine Learning
• Batch vs Online Learning
• Instance-Based vs Model-Based Learning
• Challenges in Machine Learning
• Applications of Machine Learning
• Machine Learning Development Life Cycle

Feature Engineering

• Feature Scaling (Standardization, Normalization)
• Encoding Categorical Data (Ordinal, One-Hot)
• Column Transformer
• Scikit-Learn Pipelines
• Function Transformers (Log, Reciprocal, Square Root)
• Power Transformers (Box-Cox, Yeo-Johnson)
• Binning & Binarization (Discretization)
• Handling Date & Time Variables
• Feature Construction & Splitting
• Curse of Dimensionality

Regression Concepts

• Gradient Descent (Batch, Stochastic, Mini-Batch)
• Regression Metrics (MAE, MSE, RMSE, R², Adjusted R²)
• Bias-Variance Tradeoff
• Regularization: Ridge (L2), Lasso (L1), ElasticNet

Classification Concepts

• Perceptron
• Maximum Likelihood Estimation
• Softmax Regression
• Type I & Type II Errors

Tree & Ensemble Concepts

• Entropy, Gini Impurity, Information Gain
• Decision Tree Hyperparameters & Feature Importance
• Regression Trees
• Voting Ensembles
• Bagging
• Stacking & Blending

Clustering Concepts

• K-Means Hyperparameters & Elbow Method

Model Selection & Tuning

• Cross-Validation (K-Fold, Stratified K-Fold, Leave-One-Out)
• Hyperparameter Tuning (GridSearchCV, RandomizedSearchCV)

Projects

• House Price Prediction
• Customer Churn Prediction
• Credit Risk Prediction
• Recommendation System
• End-to-End Toy Project

---

Phase 5: Deep Learning

Neural Networks

• Perceptron
• Multi-Layer Perceptron (MLP)
• Activation Functions
• Forward Propagation
• Loss Functions
• Backpropagation (What, How, Why)
• Optimizers
• Dropout & Regularization

Framework

• PyTorch
• TensorFlow & Keras

Architectures

• ANN
• CNN
  • CNN vs ANN
  • Backpropagation in CNN
  • Data Augmentation
  • Visualizing Filters & Feature Maps
  • Transfer Learning
• RNN
• LSTM
• GRU
• Transformers

Projects

• Image Classification
• Handwritten Digit Recognition
• Sentiment Analysis (RNN)

---

Phase 6: MLOps & Deployment

• Git & GitHub
• Docker
• FastAPI
• Model Serving
• CI/CD Basics
• Cloud Basics

Projects

• ML Model Deployment
• FastAPI Prediction Service
• Dockerized ML Application

---

Phase 7: Generative AI

Foundations

• LLM Basics
• Transformers
• Attention Mechanism

Practical AI

• Prompt Engineering
• Retrieval-Augmented Generation (RAG)
• Fine-Tuning
• AI Agents

Frameworks

• LangChain
• LangGraph
• LlamaIndex

Projects

• PDF Chatbot
• Resume Analyzer
• AI Research Assistant
• Interview Preparation Assistant

---

📂 Repository Structure

ML-Roadmap/
│
├── 00-Python/
├── 01-Math-for-ML/
├── 02-NumPy/
├── 03-Pandas/
├── 04-Data-Visualization/
├── 05-SQL/
├── 06-Machine-Learning/
├── 07-Deep-Learning/
├── 08-Generative-AI/
├── 09-MLOps/
│
└── README.md

---

📚 References

• CampusX: 100 Days of Machine Learning (YouTube)
• CampusX: 100 Days of Deep Learning (YouTube)