Machine Learning Basics
A lightweight execution-visualization book.
Data Preparation
Train-Test Split (Fixed)
Min-Max Scaling
Standardize Features
Encode Labels
Nearest Neighbors
Euclidean Distance
kNN Classify by Majority Vote
kNN Regress by Mean
Linear Regression
Normal Equation (1D)
Predict from Fitted Line
Mean Squared Error
Gradient Step (One Weight)
Logistic Classification
Sigmoid Function
Logistic Predict (Given Weights)
Threshold Probabilities
Log Loss (Small Example)
Decision Trees
Gini Impurity
Entropy and Information Gain
Best Split (Gini Scan)
Decision Stump Predict
Clustering
Assign to Centroids
Update Centroids
K-Means One Iteration
Cluster Inertia
Evaluation Metrics
Confusion Matrix Counts
Accuracy Score
Precision, Recall, and F1
Mean Absolute Error
Model Workflow
Cross-Validation Fold Manual
Compare Two Model Scores
Fit-Predict Pipeline