# chandrahaas11/minor-project architecture

> Architecture diagram of the GitHub repository chandrahaas11/minor-project, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-01). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/chandrahaas11/minor-project
- Repository: https://github.com/chandrahaas11/minor-project

## Overview

This is a command-line explainable-AI pipeline for detecting financial distress risk in the Give-Me-Some-Credit dataset. Its principal workflow loads and prepares ARFF data, explores it, trains and evaluates classifiers, generates SHAP and LIME explanations, and writes a summary report. The main module orchestrates the stages; preprocessing and the modeling and explanation modules provide the core internal computation. Source excerpts show the orchestration and several outputs; some report and explanation details are documented in source comments, while the README is empty.

Main entry points: [`project/src/main.py`](https://github.com/chandrahaas11/minor-project/blob/main/project/src/main.py) (Pipeline runner), [`project/src/model.py`](https://github.com/chandrahaas11/minor-project/blob/main/project/src/model.py) (Train and evaluate), [`project/src/explainability.py`](https://github.com/chandrahaas11/minor-project/blob/main/project/src/explainability.py) (SHAP explanations), [`project/results/plots`](https://github.com/chandrahaas11/minor-project/tree/main/project/results/plots) (Analysis and model plots)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_orchestration["Pipeline orchestration"]
  node_pipeline["Pipeline runner<br/>[main.py]"]
end

subgraph group_data["Data preparation and analysis"]
  node_prep["Preprocessing<br/>[preprocessing.py]"]
  node_eda["Exploratory analysis<br/>[eda.py]"]
end

subgraph group_modeling["Risk modeling"]
  node_models["Train and evaluate<br/>[model.py]"]
end

subgraph group_explanations["Model explanations"]
  node_shap["SHAP explanations<br/>[explainability.py]"]
  node_lime["LIME explanations<br/>[explainability.py]"]
end

subgraph group_outputs["Results"]
  node_reportgen["Report generation<br/>[report.py]"]
  node_metrics["Model metrics<br/>[model_metrics.csv]"]
  node_plots["Analysis and model plots"]
  node_explanationfiles["Explanation artifacts"]
  node_reportfile["Pipeline report<br/>[report.md]"]
end

node_operator(("CLI operator"))
node_dataset["ARFF dataset"]

node_operator -->|"runs"| node_pipeline
node_dataset -->|"loads"| node_prep
node_pipeline -->|"calls"| node_prep
node_prep -->|"returns splits"| node_pipeline
node_pipeline -->|"calls"| node_eda
node_pipeline -->|"calls"| node_models
node_models -->|"writes"| node_metrics
node_models -->|"generates"| node_plots
node_eda -->|"saves plots"| node_plots
node_pipeline -->|"calls"| node_shap
node_pipeline -->|"calls"| node_lime
node_shap -->|"explains predictions"| node_models
node_lime -->|"explains predictions"| node_models
node_shap -->|"saves plots"| node_plots
node_shap -->|"writes SHAP values"| node_explanationfiles
node_lime -->|"saves plots"| node_plots
node_lime -->|"writes explanations"| node_explanationfiles
node_pipeline -->|"calls"| node_reportgen
node_reportgen -->|"writes"| node_reportfile

click node_pipeline "https://github.com/chandrahaas11/minor-project/blob/main/project/src/main.py"
click node_prep "https://github.com/chandrahaas11/minor-project/blob/main/project/src/preprocessing.py"
click node_eda "https://github.com/chandrahaas11/minor-project/blob/main/project/src/eda.py"
click node_models "https://github.com/chandrahaas11/minor-project/blob/main/project/src/model.py"
click node_shap "https://github.com/chandrahaas11/minor-project/blob/main/project/src/explainability.py"
click node_lime "https://github.com/chandrahaas11/minor-project/blob/main/project/src/explainability.py"
click node_reportgen "https://github.com/chandrahaas11/minor-project/blob/main/project/src/report.py"
click node_metrics "https://github.com/chandrahaas11/minor-project/blob/main/project/results/model_metrics.csv"
click node_plots "https://github.com/chandrahaas11/minor-project/tree/main/project/results/plots"
click node_explanationfiles "https://github.com/chandrahaas11/minor-project/tree/main/project/results/explanations"
click node_reportfile "https://github.com/chandrahaas11/minor-project/blob/main/project/results/report.md"

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_pipeline toneBlue
class node_prep,node_eda toneAmber
class node_models toneMint
class node_shap,node_lime toneRose
class node_reportgen,node_metrics,node_plots,node_explanationfiles,node_reportfile,node_operator,node_dataset toneIndigo
```

## Components

### Pipeline orchestration

- [Pipeline runner](https://github.com/chandrahaas11/minor-project/blob/main/project/src/main.py): `project/src/main.py`

### Data preparation and analysis

- [Preprocessing](https://github.com/chandrahaas11/minor-project/blob/main/project/src/preprocessing.py): `project/src/preprocessing.py`
- [Exploratory analysis](https://github.com/chandrahaas11/minor-project/blob/main/project/src/eda.py): `project/src/eda.py`

### Risk modeling

- [Train and evaluate](https://github.com/chandrahaas11/minor-project/blob/main/project/src/model.py): `project/src/model.py`

### Model explanations

- [SHAP explanations](https://github.com/chandrahaas11/minor-project/blob/main/project/src/explainability.py): `project/src/explainability.py`
- [LIME explanations](https://github.com/chandrahaas11/minor-project/blob/main/project/src/explainability.py): `project/src/explainability.py`

### Results

- [Report generation](https://github.com/chandrahaas11/minor-project/blob/main/project/src/report.py): `project/src/report.py`
- [Model metrics](https://github.com/chandrahaas11/minor-project/blob/main/project/results/model_metrics.csv): `project/results/model_metrics.csv`
- [Analysis and model plots](https://github.com/chandrahaas11/minor-project/tree/main/project/results/plots): `project/results/plots`
- [Explanation artifacts](https://github.com/chandrahaas11/minor-project/tree/main/project/results/explanations): `project/results/explanations`
- [Pipeline report](https://github.com/chandrahaas11/minor-project/blob/main/project/results/report.md): `project/results/report.md`

### Other components

- **CLI operator**
- **ARFF dataset**

## Connections

- CLI operator → Pipeline runner: runs (evidence: `project/src/main.py`)
- ARFF dataset → Preprocessing: loads (evidence: `project/src/preprocessing.py`)
- Pipeline runner → Preprocessing: calls (evidence: `project/src/main.py`)
- Preprocessing → Pipeline runner: returns splits (evidence: `project/src/main.py`)
- Pipeline runner → Exploratory analysis: calls (evidence: `project/src/main.py`)
- Pipeline runner → Train and evaluate: calls (evidence: `project/src/main.py`)
- Train and evaluate → Model metrics: writes (evidence: `project/src/model.py`)
- Train and evaluate → Analysis and model plots: generates (evidence: `project/src/model.py`)
- Exploratory analysis → Analysis and model plots: saves plots (evidence: `project/src/eda.py`)
- Pipeline runner → SHAP explanations: calls (evidence: `project/src/main.py`)
- Pipeline runner → LIME explanations: calls (evidence: `project/src/main.py`)
- SHAP explanations → Train and evaluate: explains predictions (evidence: `project/src/explainability.py`)
- LIME explanations → Train and evaluate: explains predictions (evidence: `project/src/explainability.py`)
- SHAP explanations → Analysis and model plots: saves plots (evidence: `project/src/explainability.py`)
- SHAP explanations → Explanation artifacts: writes SHAP values (evidence: `project/src/explainability.py`)
- LIME explanations → Analysis and model plots: saves plots (evidence: `project/src/explainability.py`)
- LIME explanations → Explanation artifacts: writes explanations (evidence: `project/src/explainability.py`)
- Pipeline runner → Report generation: calls (evidence: `project/src/main.py`)
- Report generation → Pipeline report: writes (evidence: `project/src/report.py`)
