# gardkl/project1 architecture

> Architecture diagram of the GitHub repository gardkl/project1, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-06). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/gardkl/project1
- Repository: https://github.com/gardkl/project1

## Overview

This coursework project runs a notebook-based study of polynomial regression on Runge’s function. Its documented workflow covers OLS, Ridge and Lasso, bootstrap bias–variance analysis, cross-validation and gradient-based optimization; figures are reproducible notebook outputs. The sampled regression module implements data generation, polynomial features, OLS/Ridge fitting and prediction, and metrics. The notebook was not sampled, so its internal call structure and links to library functions remain unverified.

Main entry points: [`Project1/code/Project1_gard.ipynb`](https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb) (Project notebook), [`Project1/code/regression.py`](https://github.com/gardkl/project1/blob/main/Project1/code/regression.py) (Fit and predict), [`Project1/results`](https://github.com/gardkl/project1/tree/main/Project1/results) (Result figures)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_workflow["Notebook workflow"]
  node_notebook["Project notebook"]
  node_figures["Result figures"]
end

subgraph group_regression["Regression library"]
  node_runge["Runge data<br/>[regression.py]"]
  node_features["Polynomial features<br/>[regression.py]"]
  node_ols["OLS fitting<br/>[regression.py]"]
  node_ridge["Ridge fitting<br/>[regression.py]"]
  node_fitpredict["Fit and predict<br/>[regression.py]"]
  node_metrics["Model metrics<br/>[regression.py]"]
  node_lasso["Lasso regression"]
end

subgraph group_evaluation["Resampling and selection"]
  node_bootstrap["Bootstrap analysis"]
  node_crossval["K-fold selection"]
end

subgraph group_optimization["Gradient optimization"]
  node_plain["Plain gradient descent"]
  node_momentum["Momentum descent"]
  node_adaptive["Adaptive optimizers"]
  node_sgd["Stochastic descent"]
end

node_user(("Coursework user"))

node_user -->|"runs cells"| node_notebook
node_notebook -->|"reproduces figures"| node_figures
node_notebook -.->|"uses library"| node_runge
node_notebook -->|"studies"| node_lasso
node_notebook -->|"analyzes"| node_bootstrap
node_notebook -->|"selects models"| node_crossval
node_notebook -->|"optimizes with"| node_plain
node_notebook -->|"optimizes with"| node_momentum
node_notebook -->|"optimizes with"| node_adaptive
node_notebook -->|"optimizes with"| node_sgd
node_runge -->|"generates samples for"| node_features
node_fitpredict -->|"builds"| node_features
node_fitpredict -->|"uses when unregularized"| node_ols
node_fitpredict -->|"uses when regularized"| node_ridge
node_fitpredict -.->|"returns predictions for evaluation"| node_metrics

click node_notebook "https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb"
click node_figures "https://github.com/gardkl/project1/tree/main/Project1/results"
click node_runge "https://github.com/gardkl/project1/blob/main/Project1/code/regression.py"
click node_features "https://github.com/gardkl/project1/blob/main/Project1/code/regression.py"
click node_ols "https://github.com/gardkl/project1/blob/main/Project1/code/regression.py"
click node_ridge "https://github.com/gardkl/project1/blob/main/Project1/code/regression.py"
click node_fitpredict "https://github.com/gardkl/project1/blob/main/Project1/code/regression.py"
click node_metrics "https://github.com/gardkl/project1/blob/main/Project1/code/regression.py"
click node_lasso "https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb"
click node_bootstrap "https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb"
click node_crossval "https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb"
click node_plain "https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb"
click node_momentum "https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb"
click node_adaptive "https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb"
click node_sgd "https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_notebook,node_figures,node_user toneBlue
class node_runge,node_features,node_ols,node_ridge,node_fitpredict,node_metrics,node_lasso toneAmber
class node_bootstrap,node_crossval toneMint
class node_plain,node_momentum,node_adaptive,node_sgd toneRose
```

## Components

### Notebook workflow

- [Project notebook](https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb): `Project1/code/Project1_gard.ipynb`
- [Result figures](https://github.com/gardkl/project1/tree/main/Project1/results): `Project1/results`

### Regression library

- [Runge data](https://github.com/gardkl/project1/blob/main/Project1/code/regression.py): `Project1/code/regression.py`
- [Polynomial features](https://github.com/gardkl/project1/blob/main/Project1/code/regression.py): `Project1/code/regression.py`
- [OLS fitting](https://github.com/gardkl/project1/blob/main/Project1/code/regression.py): `Project1/code/regression.py`
- [Ridge fitting](https://github.com/gardkl/project1/blob/main/Project1/code/regression.py): `Project1/code/regression.py`
- [Fit and predict](https://github.com/gardkl/project1/blob/main/Project1/code/regression.py): `Project1/code/regression.py`
- [Model metrics](https://github.com/gardkl/project1/blob/main/Project1/code/regression.py): `Project1/code/regression.py`
- [Lasso regression](https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb): `Project1/code/Project1_gard.ipynb`

### Resampling and selection

- [Bootstrap analysis](https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb): `Project1/code/Project1_gard.ipynb`
- [K-fold selection](https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb): `Project1/code/Project1_gard.ipynb`

### Gradient optimization

- [Plain gradient descent](https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb): `Project1/code/Project1_gard.ipynb`
- [Momentum descent](https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb): `Project1/code/Project1_gard.ipynb`
- [Adaptive optimizers](https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb): `Project1/code/Project1_gard.ipynb`
- [Stochastic descent](https://github.com/gardkl/project1/blob/main/Project1/code/Project1_gard.ipynb): `Project1/code/Project1_gard.ipynb`

### Other components

- **Coursework user**

## Connections

- Coursework user → Project notebook: runs cells (evidence: `README.md`)
- Project notebook → Result figures: reproduces figures (evidence: `README.md`)
- Project notebook → Runge data: uses library
- Project notebook → Lasso regression: studies (evidence: `README.md`)
- Project notebook → Bootstrap analysis: analyzes (evidence: `README.md`)
- Project notebook → K-fold selection: selects models (evidence: `README.md`)
- Project notebook → Plain gradient descent: optimizes with (evidence: `README.md`)
- Project notebook → Momentum descent: optimizes with (evidence: `README.md`)
- Project notebook → Adaptive optimizers: optimizes with (evidence: `README.md`)
- Project notebook → Stochastic descent: optimizes with (evidence: `README.md`)
- Runge data → Polynomial features: generates samples for (evidence: `Project1/code/regression.py`)
- Fit and predict → Polynomial features: builds (evidence: `Project1/code/regression.py`)
- Fit and predict → OLS fitting: uses when unregularized (evidence: `Project1/code/regression.py`)
- Fit and predict → Ridge fitting: uses when regularized (evidence: `Project1/code/regression.py`)
- Fit and predict → Model metrics: returns predictions for evaluation (evidence: `Project1/code/regression.py`)
