Welcome to the 30 Days in Python challenge — a self-paced journey through foundational, intermediate, and advanced machine learning concepts using Python. This project documents my daily progress, insights, and solutions as I tackle real-world problems ranging from simple automation scripts to deploying AI-powered applications.
Each day focuses on solving a specific challenge, with hands-on code and explanations designed to deepen practical ML knowledge.
Build your core Python and data analysis skills:
- Day 1: Automate EDA & Report Generation
- Day 2: Handling Missing Data
- Day 3: Feature Engineering for Credit Scoring
- Day 4: Predicting Customer Churn (Logistic Regression)
- Day 5: Handwritten Digit Classification without ML libraries
- Day 6: Custom Evaluation Metrics (F1-score, MCC, AUC-ROC)
- Day 7: Time Series Decomposition
- Day 8: Scraping & Predicting House Prices
- Day 9: Build an Interactive AI Web App (Streamlit)
- Day 10: Create Your Own Mini Kaggle Challenge
Scale up with unsupervised learning, NLP, computer vision, and deployment:
- Day 11: Customer Segmentation (K-Means & DBSCAN)
- Day 12: Sentiment Analysis on Live Tweets
- Day 13: Real-Time Object Detection (YOLO)
- Day 14: Recommender System for Books
- Day 15: Explainable AI (SHAP & LIME)
- Day 16: Fake News Detection (NLP)
- Day 17: Fraud Detection (Anomaly Detection)
- Day 18: Deploying ML Models as APIs (FastAPI + Docker)
- Day 19: CNNs for Image Classification
- Day 20: AutoML for Tabular Data (H2O AutoML)
Enter the deep end with cutting-edge AI techniques and architectures:
- Day 21: Self-Supervised Learning for Images
- Day 22: AI-Powered Resume Screener (NLP)
- Day 23: Train a GAN for Fashion Design (StyleGAN)
- Day 24: Fine-tune BERT for Text Classification
- Day 25: Reinforcement Learning for Stock Trading
- Day 26: Graph Neural Networks for Social Recommendations
- Day 27: Multi-Modal Learning (Text + Images)
- Day 28: TinyML: Edge-Deployable Lightweight Models
- Day 29: Text-to-Image Generation (Stable Diffusion)
- Day 30: AI Chatbot with RAG (Retrieval-Augmented Generation)
Each day's challenge is in its own subfolder:
Each folder contains:
- 🧠 Challenge description
- 💻 Jupyter notebook or Python script
- 📊 Visuals, plots, and results
- 📝 Key takeaways
- To solidify machine learning skills with real projects.
- To build a portfolio that reflects practical experience.
- To make learning consistent and rewarding with daily goals.
- And honestly, because building cool stuff with Python is just fun. 😎
Feel free to explore any day's folder, clone this repo, run the notebooks, and try your own twists on the challenges!
git clone https://github.com/your-username/30-days-in-python.git
cd 30-days-in-python