🤖 AI & Machine Learning Practical Codes

📚 This repository is intended for educational purposes only. All notebooks are designed to support learning and are companion resources to the YouTube channel.

 

▲ Click the thumbnail to watch the full playlist

---

🌐 Live Cheatsheet Website

A visual map of all 125 topics with illustrations, formulas, and stage-by-stage grouping — optimised for desktop and mobile.

What's inside: 125 topic cards · 13 learning stages · click-to-expand modals with formulas, use-cases, and notebook links · dark/light theme · mobile-friendly layout

---

Practical Python examples for 116 Machine Learning and Data Science topics from my YouTube channel.

Difficulty legend:   🟢 Beginner  ·  🟡 Intermediate  ·  🔴 Advanced

🎯 What you'll find here

📖	Topic-wise practical code for every lecture
💻	Jupyter notebooks runnable locally
☁️	One-click cloud execution via Binder
🎬	Direct links to companion YouTube videos

🏆 Repository Goals

• 🔹 Keep each topic short, practical, and beginner-friendly.
• 🔹 Map every video to runnable Python code.
• 🔹 Make it easy for subscribers to fork, run, and learn.

📁 Project Structure

.
├── notebooks/
│   ├── 01_linear_regression/
│   │   └── linear_regression_starter.ipynb
│   ├── ... (topics 02–114)
│   ├── 115_real_world_project/
│   │   └── real_world_project_starter.ipynb   ← End-to-end capstone
│   ├── 116_advanced_time_series_ml/
│   ├── 117_stream_adaptive_learning/
│   ├── 118_denstream/
│   ├── 119_adwin/
│   ├── 120_vfdt_cvfdt/
│   ├── 121_drift_detection/
│   ├── 122_monic/
│   ├── 123_shap_values/
│   ├── 124_arima_sarima/
│   └── 125_clustream/
├── src/
│   ├── data/
│   ├── ml_basics/
│   └── utils/
├── requirements.txt
├── runtime.txt
├── environment.yml
├── CONTRIBUTING.md
└── README.md

🚀 Getting Started

▶ Option 1 — Run in the Cloud (No Setup Required)

Click any launch binder badge on a topic tile below, or launch the whole repo:

⏳ First build may take a few minutes. If it times out, simply retry.

---

💻 Option 2 — Run Locally (Jupyter)

1. Clone the repository.
2. Create and activate a virtual environment.
3. Install dependencies.
4. Start Jupyter Lab.

git clone https://github.com/ranjiGT/ai-machine-learning-codes.git
cd ai-machine-learning-codes

python3 -m venv .venv
source .venv/bin/activate

pip install --upgrade pip
pip install -r requirements.txt

jupyter lab

📖 Topic-to-Video Mapping

125 topics across 13 themes — click a section to expand. Each tile links to the interactive Binder notebook and its companion YouTube video.

🟦 Supervised Learning — Core Classifiers (01–17)  ·  🟢 Beginner → 🟡 Intermediate

Prerequisites: Python basics, NumPy, pandas. Start here if you are new to ML.

01. Linear Regression  ·	02. Logistic Regression  ·	03. Decision Trees  ·
04. Random Forest  ·	05. KNN  ·	06. PCA  ·
07. Naive Bayes  ·	08. Underfitting vs Overfitting  ·	09. Reduced Error Pruning  ·
10. Random Sampling  ·	11. Cross Validation  ·	12. Nested Cross Validation  ·
13. Hold-Out Method  ·	14. Hyperparameter Tuning  ·	15. Bootstrap Evaluation  ·
16. Ensemble Methods  ·	17. Hunt's Algorithm  ·

🟨 Probabilistic & Rule-Based Methods (18–26)  ·  🟡 Intermediate

Prerequisites: Topics 01–07 (core classifiers).

18. Impurity Measures  ·	19. Rule-Based Classifier  ·	20. Sequential Covering Algorithm  ·
21. Bayesian Belief Networks  ·	22. Artificial Neural Networks  ·	23. Feed Forward Neural Networks  ·
24. Support Vector Machine  ·	25. Maximal Margin Classifier  ·	26. Non-Linear SVM  ·

🟧 Class Imbalance & Evaluation Curves (27–30)  ·  🟡 Intermediate

Prerequisites: Topics 01–07, 11 (cross-validation).

27. Class Imbalance Problem and Solutions  ·   ·	28. SMOTE  ·	29. ROC and AUC Curves  ·
30. ISO Accuracy Lines  ·

🟩 Clustering (31–46)  ·  🟡 Intermediate

Prerequisites: Topics 06 (PCA), 11 (cross-validation). No labelled data required.

31. Unsupervised Learning - Clustering  ·   ·	32. K-means Clustering  ·	33. Bisecting K-means  ·
34. Cluster Similarity Measures  ·	35. Fuzzy C-Means  ·	36. DBSCAN Technique  ·
37. Mean-Shift Clustering  ·	38. Hierarchical Clustering  ·	39. Linkage Measures  ·
40. Cluster Validation Techniques  ·	41. Cohesion and Separation in Cluster  ·	42. Silhouette Coefficient  ·
43. Cophenetic Correlation Coefficient  ·	44. Hopkins Statistic  ·	45. Cluster Purity  ·
46. Rand Statistic and Jaccard Index  ·

🟪 Active Learning (47–56)  ·  🔴 Advanced

Prerequisites: Topics 01–17, 27–30 (evaluation).

47. Active Learning in Machine Learning  ·	48. Membership Query Synthesis  ·	49. Stream-Based Selective Sampling  ·
50. Pool-Based Sampling  ·	51. Uncertainty Sampling  ·	52. Query by Committee  ·
53. Expected Model Change  ·	54. Expected Error Reduction  ·	55. Variance Reduction in Active Learning  ·
56. Information Density in Active Learning  ·

🔵 Multi-label & Multi-class Classification (57–64)  ·  🟡 Intermediate

Prerequisites: Topics 01–07, 11.

57. Multi-class Classification (OvR and OvO)  ·	58. Multi-label Classification  ·	59. Problem Transformation Methods  ·
60. Binary Relevance  ·	61. Label Powerset  ·	62. Random K Labelsets (RAkEL)  ·
63. Multi-label Evaluation Metrics  ·	64. Multi-Target Classification  ·

🟫 Pattern Mining & Statistical Theory (65–74)  ·  🟡 Intermediate

Prerequisites: Topics 07 (Naive Bayes), basic probability.

65. Laplace Correction  ·	66. Association Rules  ·	67. Apriori Principle  ·
68. Item-set Lattice  ·	69. Lift Measure  ·	70. ECLAT  ·
71. Family-Wise Error Rate (FWER)  ·	72. False Discovery Rate (FDR)  ·	73. Singular Value Decomposition (SVD)  ·
74. Vapnik–Chervonenkis (VC) Dimension  ·

⬛ Concept Learning, Algorithms & Regression (75–85)  ·  🟡 Intermediate

Prerequisites: Topics 01, 03 (Decision Trees), 11.

75. Concept Learning  ·	76. Find-S Algorithm  ·	77. Candidate Elimination Algorithm  ·
78. Inductive Bias  ·	79. ID3 Algorithm  ·	80. Gradient Descent Algorithm  ·
81. Ridge Regression  ·	82. Lasso Regression  ·	83. Polynomial Regression  ·
84. Isotonic Regression  ·	85. Elastic Net Regression  ·

🔶 Dimensionality Reduction & Lazy Learning (86–90)  ·  🟡 Intermediate

Prerequisites: Topics 05 (KNN), 06 (PCA).

86. Linear Discriminant Analysis (LDA)  ·	87. t-SNE  ·	88. Lazy Learning Algorithms  ·
89. Weighted K-NN  ·	90. Case-Based Reasoning  ·

🔴 Deep Learning (91–107)  ·  🔴 Advanced

Prerequisites: Topics 22–23 (Neural Networks), 80 (Gradient Descent). Familiarity with NumPy recommended.

91. Introduction to Deep Neural Networks  ·	92. Structure of a Neuron  ·	93. Weight Matrix in Neural Networks  ·
94. Generalization of Neural Networks  ·	95. Learning Neural Networks  ·	96. Vectorization of Neural Networks  ·
97. Decision Boundary of Neural Networks  ·	98. The Chain Rule  ·	99. Backpropagation Algorithm  ·
100. The Delta Rule  ·	101. Vanishing and Exploding Gradients  ·	102. Step Activation Function  ·
103. Sigmoid Activation Function  ·	104. Hyperbolic Activation Function  ·	105. ReLU Activation Function  ·
106. Teacher Forcing in Deep Learning  ·	107. LSTM  ·

⚫ Advanced & Semi-Supervised Methods (108–113)  ·  🔴 Advanced

Prerequisites: Topics 01–30, 91–107 (Deep Learning basics).

108. Regression Evaluation Metrics  ·	109. Linear Learning Machines (LLMs)  ·	110. Kernel Function and Kernel Matrix  ·
111. Semi-Supervised Learning (SSL)  ·	112. Safe Semi-Supervised Learning (SSL)  ·	113. Semi-Supervised SVM (S3VM & TSVM)  ·

🎯 Advanced Activation Functions (114–114)  ·  🔴 Advanced

Prerequisites: Topics 91–107 (Deep Learning).

114. Softmax Activation Function  ·

🏁 End-to-End Real-World Project (115)  ·  🟡 Intermediate

Prerequisites: Topics 01–30 recommended. This notebook deliberately revisits concepts from across the course.

A capstone notebook that applies the concepts from the entire course to a real dataset.
We predict Heart Disease using the UCI Cleveland dataset, walking through every stage a practitioner faces:

EDA → Preprocessing → PCA → SMOTE → Multi-model benchmarking → Hyperparameter tuning → ROC/AUC → Feature importance

Concept	Topics revisited
Hold-out split & scaling	01, 13
PCA visualisation	06
SMOTE for class imbalance	28
5-fold cross-validation	11
GridSearchCV tuning	14
ROC-AUC evaluation	29
Classification report	63, 108

115. End-to-End Real-World ML Project

📈 Advanced Time Series ML (116)  ·  🔴 Advanced

Prerequisites: Topics 01, 11, 14, and basic understanding of lag/rolling features.

A practical advanced notebook focused on modern ML workflows for forecasting:

TimeSeriesSplit → Lag/Rolling features → RF/HistGB/SVR → Multi-step recursive forecasting

Concept	Topics revisited
Time-aware validation	11
Model tuning mindset	14
Feature engineering	01, 80
Forecast diagnostics	108

116. Advanced Time Series Analysis in ML	117. Stream-Based & Adaptive Learning	118. DenStream
119. ADWIN	120. VFDT & CVFDT	121. Concept Drift Detection
122. MONIC	123. SHAP Values	124. ARIMA & SARIMA
125. CluStream

Co-Author Setup

If you want to co-author with yatchmaster:

1. Add yatchmaster as a collaborator in GitHub repository settings.
2. Use feature branches and pull requests.
3. Add co-author trailers in commit messages when both contribute:

Co-authored-by: yatchmaster <their-email@users.noreply.github.com>

See CONTRIBUTING.md for a full workflow.

🤝 Contributing

Contributions are welcome from subscribers and learners. Please read CONTRIBUTING.md before opening pull requests.

📄 License

This project is licensed under the MIT License.

---

_{Made with ❤️ for learners · Subscribe on YouTube}