# nadigsrujan/fabfederate architecture

> Architecture diagram of the GitHub repository nadigsrujan/fabfederate, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-11-22). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/nadigsrujan/fabfederate
- Repository: https://github.com/nadigsrujan/fabfederate

## Overview

FabFederate-CNC is a local research application for estimating CNC milling-tool wear from recorded sensor data. The documented workflow prepares NASA recordings, trains centralized/local baselines and Flower federated models, evaluates held-out cases, and explains saved-model predictions. A FastAPI backend serves saved study artifacts and prediction features to a React research workspace. The graph also preserves the distinct data-preparation, federated-training, evaluation, and SHAP capabilities. Several backend paths are documented but unsampled; their internal call relationships are therefore not inferred.

Main entry points: [`frontend/src/App.tsx`](https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/App.tsx) (Application shell), [`src/pipelines/study.py`](https://github.com/nadigsrujan/fabfederate/blob/main/src/pipelines/study.py) (Study orchestration), [`src/api/app.py`](https://github.com/nadigsrujan/fabfederate/blob/main/src/api/app.py) (Research API), [`src/data/preprocessing.py`](https://github.com/nadigsrujan/fabfederate/blob/main/src/data/preprocessing.py) (Preprocessing)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_ui["Research workspace"]
  node_app["Application shell<br/>[App.tsx]"]
  node_study_state["Study state<br/>[experiments.ts]"]
  node_overview["Study overview<br/>[OverviewPage.tsx]"]
  node_experiments["Experiment results"]
  node_clients["Client analysis<br/>[ClientsPage.tsx]"]
  node_dataset_view["Dataset view<br/>[DatasetPage.tsx]"]
  node_estimate["Wear estimator<br/>[EstimatePage.tsx]"]
end

subgraph group_api["Local API"]
  node_backend["Research API<br/>[app.py]"]
end

subgraph group_data["Data preparation"]
  node_acquisition["Data acquisition<br/>[acquisition.py]"]
  node_loaders["Dataset loaders<br/>[nasa_loader.py]"]
  node_preparation["Preprocessing<br/>[preprocessing.py]"]
  node_features["Signal features"]
  node_partitioning["Client partitioning<br/>[partitioning.py]"]
end

subgraph group_models["Modeling"]
  node_study_pipeline["Study orchestration<br/>[study.py]"]
  node_baseline_training["Baseline training<br/>[train.py]"]
  node_federation["Federated training<br/>[server.py]"]
  node_federated_clients["Logical clients<br/>[client.py]"]
  node_mlp["Neural model<br/>[mlp.py]"]
  node_bundles["Model bundles<br/>[bundle.py]"]
end

subgraph group_analysis["Evaluation and inference"]
  node_metrics["Error metrics<br/>[metrics.py]"]
  node_reports["Research reports<br/>[report.py]"]
  node_inference["File inference<br/>[pipeline.py]"]
  node_shap["SHAP explanations<br/>[shap_explainer.py]"]
end

node_researcher(("Researcher"))

node_researcher -->|"uses"| node_app
node_app -->|"loads state"| node_study_state
node_app -->|"renders"| node_overview
node_app -->|"renders"| node_experiments
node_app -->|"renders"| node_clients
node_app -->|"renders"| node_dataset_view
node_app -->|"renders"| node_estimate
node_study_state -->|"requests data"| node_backend
node_backend -->|"serves study"| node_study_state
node_study_pipeline -->|"prepares dataset"| node_preparation
node_study_pipeline -->|"runs baselines"| node_baseline_training
node_study_pipeline -->|"runs federation"| node_federation
node_study_pipeline -->|"evaluates predictions"| node_metrics
node_study_pipeline -->|"explains predictions"| node_shap
node_federation -->|"dispatches training"| node_federated_clients
node_federated_clients -->|"trains model"| node_mlp
node_inference -->|"loads model"| node_bundles
node_inference -->|"requests explanation"| node_shap
node_researcher -->|"prepares recordings"| node_acquisition
node_acquisition -.->|"loads NASA data"| node_loaders
node_preparation -.->|"extracts features"| node_features
node_preparation -.->|"partitions data"| node_partitioning
node_backend -.->|"serves predictions"| node_inference
node_backend -.->|"serves reports"| node_reports

click node_app "https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/App.tsx"
click node_study_state "https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/lib/experiments.ts"
click node_overview "https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/OverviewPage.tsx"
click node_experiments "https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/ExperimentsPage.tsx"
click node_clients "https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/ClientsPage.tsx"
click node_dataset_view "https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/DatasetPage.tsx"
click node_estimate "https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/EstimatePage.tsx"
click node_backend "https://github.com/nadigsrujan/fabfederate/blob/main/src/api/app.py"
click node_study_pipeline "https://github.com/nadigsrujan/fabfederate/blob/main/src/pipelines/study.py"
click node_acquisition "https://github.com/nadigsrujan/fabfederate/blob/main/src/data/acquisition.py"
click node_loaders "https://github.com/nadigsrujan/fabfederate/blob/main/src/data/nasa_loader.py"
click node_preparation "https://github.com/nadigsrujan/fabfederate/blob/main/src/data/preprocessing.py"
click node_features "https://github.com/nadigsrujan/fabfederate/blob/main/src/data/feature_extraction.py"
click node_partitioning "https://github.com/nadigsrujan/fabfederate/blob/main/src/data/partitioning.py"
click node_baseline_training "https://github.com/nadigsrujan/fabfederate/blob/main/src/models/train.py"
click node_federation "https://github.com/nadigsrujan/fabfederate/blob/main/src/federated/server.py"
click node_federated_clients "https://github.com/nadigsrujan/fabfederate/blob/main/src/federated/client.py"
click node_mlp "https://github.com/nadigsrujan/fabfederate/blob/main/src/models/mlp.py"
click node_metrics "https://github.com/nadigsrujan/fabfederate/blob/main/src/evaluation/metrics.py"
click node_reports "https://github.com/nadigsrujan/fabfederate/blob/main/src/evaluation/report.py"
click node_inference "https://github.com/nadigsrujan/fabfederate/blob/main/src/inference/pipeline.py"
click node_bundles "https://github.com/nadigsrujan/fabfederate/blob/main/src/models/bundle.py"
click node_shap "https://github.com/nadigsrujan/fabfederate/blob/main/src/explainability/shap_explainer.py"

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_app,node_study_state,node_overview,node_experiments,node_clients,node_dataset_view,node_estimate toneBlue
class node_backend toneAmber
class node_acquisition,node_loaders,node_preparation,node_features,node_partitioning toneMint
class node_study_pipeline,node_baseline_training,node_federation,node_federated_clients,node_mlp,node_bundles toneRose
class node_metrics,node_reports,node_inference,node_shap,node_researcher toneIndigo
```

## Components

### Research workspace

- [Application shell](https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/App.tsx): `frontend/src/App.tsx`
- [Study state](https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/lib/experiments.ts): `frontend/src/lib/experiments.ts`
- [Study overview](https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/OverviewPage.tsx): `frontend/src/pages/OverviewPage.tsx`
- [Experiment results](https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/ExperimentsPage.tsx): `frontend/src/pages/ExperimentsPage.tsx`
- [Client analysis](https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/ClientsPage.tsx): `frontend/src/pages/ClientsPage.tsx`
- [Dataset view](https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/DatasetPage.tsx): `frontend/src/pages/DatasetPage.tsx`
- [Wear estimator](https://github.com/nadigsrujan/fabfederate/blob/main/frontend/src/pages/EstimatePage.tsx): `frontend/src/pages/EstimatePage.tsx`

### Local API

- [Research API](https://github.com/nadigsrujan/fabfederate/blob/main/src/api/app.py): `src/api/app.py`

### Data preparation

- [Data acquisition](https://github.com/nadigsrujan/fabfederate/blob/main/src/data/acquisition.py): `src/data/acquisition.py`
- [Dataset loaders](https://github.com/nadigsrujan/fabfederate/blob/main/src/data/nasa_loader.py): `src/data/nasa_loader.py`
- [Preprocessing](https://github.com/nadigsrujan/fabfederate/blob/main/src/data/preprocessing.py): `src/data/preprocessing.py`
- [Signal features](https://github.com/nadigsrujan/fabfederate/blob/main/src/data/feature_extraction.py): `src/data/feature_extraction.py`
- [Client partitioning](https://github.com/nadigsrujan/fabfederate/blob/main/src/data/partitioning.py): `src/data/partitioning.py`

### Modeling

- [Study orchestration](https://github.com/nadigsrujan/fabfederate/blob/main/src/pipelines/study.py): `src/pipelines/study.py`
- [Baseline training](https://github.com/nadigsrujan/fabfederate/blob/main/src/models/train.py): `src/models/train.py`
- [Federated training](https://github.com/nadigsrujan/fabfederate/blob/main/src/federated/server.py): `src/federated/server.py`
- [Logical clients](https://github.com/nadigsrujan/fabfederate/blob/main/src/federated/client.py): `src/federated/client.py`
- [Neural model](https://github.com/nadigsrujan/fabfederate/blob/main/src/models/mlp.py): `src/models/mlp.py`
- [Model bundles](https://github.com/nadigsrujan/fabfederate/blob/main/src/models/bundle.py): `src/models/bundle.py`

### Evaluation and inference

- [Error metrics](https://github.com/nadigsrujan/fabfederate/blob/main/src/evaluation/metrics.py): `src/evaluation/metrics.py`
- [Research reports](https://github.com/nadigsrujan/fabfederate/blob/main/src/evaluation/report.py): `src/evaluation/report.py`
- [File inference](https://github.com/nadigsrujan/fabfederate/blob/main/src/inference/pipeline.py): `src/inference/pipeline.py`
- [SHAP explanations](https://github.com/nadigsrujan/fabfederate/blob/main/src/explainability/shap_explainer.py): `src/explainability/shap_explainer.py`

### Other components

- **Researcher**

## Connections

- Researcher → Application shell: uses (evidence: `README.md`)
- Application shell → Study state: loads state (evidence: `frontend/src/App.tsx`)
- Application shell → Study overview: renders (evidence: `frontend/src/App.tsx`)
- Application shell → Experiment results: renders (evidence: `frontend/src/App.tsx`)
- Application shell → Client analysis: renders (evidence: `frontend/src/App.tsx`)
- Application shell → Dataset view: renders (evidence: `frontend/src/App.tsx`)
- Application shell → Wear estimator: renders (evidence: `frontend/src/App.tsx`)
- Study state → Research API: requests data (evidence: `README.md`)
- Research API → Study state: serves study (evidence: `README.md`)
- Study orchestration → Preprocessing: prepares dataset (evidence: `src/pipelines/study.py`)
- Study orchestration → Baseline training: runs baselines (evidence: `src/pipelines/study.py`)
- Study orchestration → Federated training: runs federation (evidence: `src/pipelines/study.py`)
- Study orchestration → Error metrics: evaluates predictions (evidence: `src/pipelines/study.py`)
- Study orchestration → SHAP explanations: explains predictions (evidence: `src/pipelines/study.py`)
- Federated training → Logical clients: dispatches training (evidence: `src/federated/server.py`)
- Logical clients → Neural model: trains model (evidence: `src/federated/client.py`)
- File inference → Model bundles: loads model (evidence: `src/inference/pipeline.py`)
- File inference → SHAP explanations: requests explanation (evidence: `src/inference/pipeline.py`)
- Researcher → Data acquisition: prepares recordings (evidence: `README.md`)
- Data acquisition → Dataset loaders: loads NASA data
- Preprocessing → Signal features: extracts features
- Preprocessing → Client partitioning: partitions data
- Research API → File inference: serves predictions
- Research API → Research reports: serves reports
