Author: Lucky Sharma
Focus: Data Science, Machine Learning & Deep Learning
Level: Beginner to Advanced
- Quick Start Guide
- Learning Path
- Repository Structure
- Interactive Notebooks
- Prerequisites
- How to Use This Repository
This repository contains comprehensive Jupyter notebooks covering the complete ML journey from Python basics to advanced deep learning concepts. Each notebook is designed to be interactive, beginner-friendly, and hands-on.
✅ Python Programming Fundamentals
✅ Data Manipulation & Analysis (Pandas, NumPy)
✅ Data Visualization (Matplotlib, Seaborn, Plotly)
✅ Statistical Analysis for ML
✅ Machine Learning Algorithms
✅ Natural Language Processing (NLP)
✅ Computer Vision & Object Detection
✅ Deep Learning Frameworks
Follow this step-by-step path for optimal learning:
Duration: 1-2 Weeks
| # | Notebook | Topics Covered | Difficulty |
|---|---|---|---|
| 1 | 01_Lucky Sharma DataCuration_Using_Python.ipynb | Python basics, data types, variables, loops, functions | ⭐ Beginner |
| 2 | 02_Lucky Sharma DataCuration_Using_Python.ipynb | Classes, objects, OOP, pattern problems | ⭐ Beginner |
| 3 | 03 (Q) Lucky Sharma DataCuration_Using_Python.ipynb | Practice questions & exercises | ⭐⭐ Beginner+ |
Key Skills: Variables, loops, functions, lists, tuples, dictionaries, sets, string manipulation
Duration: 3-5 Days
| # | Notebook | Topics Covered | Difficulty |
|---|---|---|---|
| 4 | 04 (Numpy) Lucky Sharma DataCuration_Using_Python.ipynb | NumPy arrays, operations, broadcasting, linear algebra | ⭐⭐ Intermediate |
Key Skills: Array manipulation, vectorization, mathematical operations, matrix operations
Duration: 1-2 Weeks
| # | Notebook | Topics Covered | Difficulty |
|---|---|---|---|
| 5 | Pandas01_From_Zero.ipynb | DataFrame basics, reading/writing data, indexing | ⭐⭐ Intermediate |
| 6 | Pandas02_Lucky_Sharma_DataCuration_Using_Pythonipynb.ipynb | Data cleaning, transformation, aggregation | ⭐⭐ Intermediate |
| 7 | Pandas03_Analysis_Projects.ipynb | Real-world data analysis projects | ⭐⭐⭐ Advanced |
| 8 | Pandas04_Handling_Outliers.ipynb | Outlier detection & treatment techniques | ⭐⭐⭐ Advanced |
Key Skills: Data cleaning, wrangling, merging, grouping, statistical analysis
Duration: 1-2 Weeks
| # | Notebook | Topics Covered | Difficulty |
|---|---|---|---|
| 9 | Visulization_01_Matplotlib01_From_Basic_to_Advance.ipynb | Matplotlib fundamentals, plots, customization | ⭐⭐ Intermediate |
| 10 | Visulization_02_Matplotlib02_Ass_Questions.ipynb | Matplotlib practice problems | ⭐⭐ Intermediate |
| 11 | Visulization_03_Seaborn_Python.ipynb | Statistical visualizations with Seaborn | ⭐⭐ Intermediate |
| 12 | Visulization_04_Plotly_Python.ipynb | Interactive plots with Plotly | ⭐⭐⭐ Advanced |
| 13 | Visulization_05_Dashboard_Plotly.ipynb | Building interactive dashboards | ⭐⭐⭐ Advanced |
| 14 | Visulization_06_Time_Series_Analysis.ipynb | Time series visualization & forecasting | ⭐⭐⭐ Advanced |
Key Skills: Line plots, bar charts, heatmaps, scatter plots, interactive visualizations, dashboards
Duration: 4-7 Days
| # | Notebook | Topics Covered | Difficulty |
|---|---|---|---|
| 15 | Statics_01_ML.ipynb | Descriptive statistics, probability, distributions | ⭐⭐ Intermediate |
| 16 | Statics_02_ML.ipynb | Hypothesis testing, confidence intervals | ⭐⭐⭐ Advanced |
Key Skills: Mean, median, standard deviation, hypothesis testing, probability distributions
Duration: 2-3 Weeks
| # | Notebook | Topics Covered | Difficulty |
|---|---|---|---|
| 17 | ML01_Machine_Learning.ipynb | ML introduction, supervised/unsupervised learning | ⭐⭐ Intermediate |
| 18 | ML02_Machine_Learning_10Minutes.ipynb | Quick ML overview & algorithms | ⭐⭐ Intermediate |
| 19 | Scikit-Learn_Machine-Learning.ipynb | Scikit-learn library, model training & evaluation | ⭐⭐⭐ Advanced |
Key Skills: Regression, classification, clustering, model evaluation, feature engineering
Duration: 1 Week
| # | Notebook | Topics Covered | Difficulty |
|---|---|---|---|
| 20 | ML03_Reinforcement_Learning_RL_01.ipynb | RL basics, Q-learning, policy gradients | ⭐⭐⭐⭐ Expert |
Key Skills: Agent-environment interaction, rewards, Q-learning, policy optimization
Duration: 1-2 Weeks
| # | Notebook | Topics Covered | Difficulty |
|---|---|---|---|
| 21 | Natural_Language_Processing-Machine_Learning.ipynb | NLP fundamentals, text preprocessing, modeling | ⭐⭐⭐ Advanced |
| 22 | Text-Annotation-NLP.ipynb | Text annotation techniques for NLP | ⭐⭐⭐ Advanced |
| 23 | Image-Annotation-NLP.ipynb | Image annotation for vision + NLP tasks | ⭐⭐⭐ Advanced |
Key Skills: Tokenization, sentiment analysis, named entity recognition, text classification
Duration: 1-2 Weeks
| # | Notebook | Topics Covered | Difficulty |
|---|---|---|---|
| 24 | Bounding_Box_Annotation_Beginner_Object_Detection_with_YOLOv8_and_LabelImg.ipynb | Object detection, YOLO, bounding boxes | ⭐⭐⭐⭐ Expert |
| 25 | Pascal VOC (XML) to YOLO format_using_python.ipynb | Format conversion, annotation pipelines | ⭐⭐⭐ Advanced |
| 26 | Video-Annotation.ipynb | Video annotation & tracking | ⭐⭐⭐⭐ Expert |
Key Skills: Image processing, object detection, YOLO, annotation tools, format conversion
📦 ML-Repository
├── 📁 Notebooks/
│ ├── 🐍 Python Basics (01-03)
│ ├── 🔢 NumPy (04)
│ ├── 📊 Pandas (Pandas01-04)
│ ├── 📈 Visualization (Visulization_01-06)
│ ├── 📐 Statistics (Statics_01-02)
│ ├── 🤖 Machine Learning (ML01-03, Scikit-Learn)
│ ├── 💬 NLP (Natural_Language_Processing, Text/Image-Annotation)
│ └── 👁️ Computer Vision (Bounding_Box, Pascal VOC, Video-Annotation)
├── 📁 Data/
│ ├── annotations/ (XML annotation files)
│ ├── images/ (Sample images)
│ └── masks/ (Image masks)
├── 📄 Assignment_01.ipynb
└── 📄 README.md
All notebooks are designed with:
- ✨ Interactive Code Cells - Run and experiment with code
- 📝 Detailed Comments - Understanding every line of code
- 🎯 Practice Exercises - Hands-on learning activities
- 📊 Visual Outputs - See results immediately
- 🔗 Real-World Examples - Practical applications
- Python 3.8+
- Jupyter Notebook or Google Colab (recommended for beginners)
- VS Code (optional, for local development)
Install all required libraries:
pip install numpy pandas matplotlib seaborn plotly scikit-learn tensorflow keras opencv-python nltkOr use requirements file:
pip install -r requirements.txt- Minimum 4GB RAM (8GB+ recommended for ML models)
- GPU recommended for deep learning notebooks (optional)
- Start from Phase 1 - Don't skip Python fundamentals
- Follow Sequential Order - Each phase builds on the previous
- Practice Exercises - Complete all coding exercises
- Run Every Cell - Type and run code yourself (don't just read)
- Take Notes - Document your learnings
- Quick Review Phase 1-2 - Refresh Python & NumPy
- Focus on Phase 3-6 - Master data analysis & ML
- Build Projects - Apply learnings to real datasets
- Explore Advanced Topics - NLP, Computer Vision, RL
- Jump to specific topics of interest
- Use as reference material
- Contribute improvements via pull requests
- Build upon existing notebooks
- Click on any notebook link above
- Open with Google Colab
- Click "Runtime" → "Run all"
- No setup required! 🎉
# Clone repository
git clone <your-repo-url>
# Navigate to directory
cd ML-Repository
# Install dependencies
pip install -r requirements.txt
# Launch Jupyter
jupyter notebook
# Open desired notebook and start learning!- Install Python & Jupyter extensions
- Open repository folder
- Click on any .ipynb file
- Select Python kernel and run cells
- 📖 "Python for Data Analysis" by Wes McKinney
- 📖 "Hands-On Machine Learning" by Aurélien Géron
- 📖 "Deep Learning" by Ian Goodfellow
- 🎓 Coursera: Machine Learning by Andrew Ng
- 🎓 Fast.ai: Practical Deep Learning
- 🎓 Kaggle Learn: Free micro-courses
- 🏆 Kaggle Competitions
- 🏆 LeetCode (Python practice)
- 🏆 HackerRank (ML challenges)
Contributions are welcome! If you find errors or have improvements:
- Fork the repository
- Create a feature branch
- Make your changes
- Submit a pull request
Author: Lucky Sharma
Role: ML Enthusiast & Data Science Learner
Status: Actively Learning & Updating
💡 Questions? Open an issue or reach out!
- ✔️ Code along with notebooks
- ✔️ Experiment with parameters
- ✔️ Build mini-projects
- ✔️ Join ML communities
- ✔️ Read documentation
- ❌ Skip fundamentals
- ❌ Just copy-paste code
- ❌ Ignore errors
- ❌ Rush through concepts
- ❌ Learn in isolation
Track your progress:
Phase 1: Python Foundations
- Complete Python basics notebooks
- Understand data structures
- Master loops and functions
- Solve practice problems
Phase 2-3: Data Processing
- NumPy array operations
- Pandas DataFrame manipulation
- Data cleaning techniques
- Complete analysis project
Phase 4: Visualization
- Create all plot types
- Build interactive dashboard
- Time series analysis
Phase 5-6: Machine Learning
- Understand ML algorithms
- Train classification models
- Perform model evaluation
- Complete ML project
Phase 7-9: Advanced Topics
- Reinforcement learning basics
- NLP text processing
- Object detection with YOLO
- Build end-to-end project
Document your learning journey here!
- Total Notebooks: 26+
- Topics Covered: 50+
- Difficulty Levels: 4 (Beginner to Expert)
- Estimated Learning Time: 8-12 weeks (self-paced)
Latest Update: January 2026
- ✨ Added comprehensive learning roadmap
- 📚 Organized notebooks by difficulty
- 🎯 Created interactive guide
- 📊 Enhanced documentation