# vaishnaviborusumedi/eeg-seizure-prediction-api architecture

> Architecture diagram of the GitHub repository vaishnaviborusumedi/eeg-seizure-prediction-api, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-08). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/vaishnaviborusumedi/eeg-seizure-prediction-api
- Repository: https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api

## Overview

This repository trains a seizure-risk classifier from EEG features, saves the fitted pipeline, and serves single and batch predictions through FastAPI. The training workflow loads and splits the dataset, tunes a scaled Random Forest, evaluates it, and writes a model artifact. At runtime, the API loads that artifact and exposes prediction, health, and model-information endpoints. Source excerpts support the training and inference calls; endpoint coverage is also documented in the README.

Main entry points: [`main.py`](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py) (FastAPI app), [`train.py`](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/train.py) (Load and split), [`model.pkl`](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/model.pkl) (Fitted model), [`dataset.csv`](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/dataset.csv) (EEG dataset)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_training["Model training"]
  node_dataset[("EEG dataset<br/>[dataset.csv]")]
  node_prep["Load and split<br/>[train.py]"]
  node_tune["Tune pipeline<br/>[train.py]"]
  node_evaluate["Evaluate model<br/>[train.py]"]
end

subgraph group_serving["Prediction API"]
  node_api["FastAPI app<br/>[main.py]"]
  node_health["Health check<br/>[main.py]"]
  node_info["Model info<br/>[main.py]"]
  node_single["Single prediction<br/>[main.py]"]
  node_batch["Batch prediction<br/>[main.py]"]
  node_risk["Risk result<br/>[main.py]"]
end

subgraph group_artifacts["Model artifact"]
  node_artifact["Fitted model<br/>[model.pkl]"]
end

node_analyst(("Operator"))

node_dataset -->|"loads rows"| node_prep
node_prep -->|"splits data"| node_tune
node_tune -->|"fits best model"| node_evaluate
node_evaluate -->|"saves model"| node_artifact
node_analyst -->|"checks status"| node_health
node_analyst -->|"requests details"| node_info
node_analyst -->|"submits features"| node_single
node_analyst -->|"submits batch"| node_batch
node_artifact -->|"loaded at startup"| node_api
node_single -->|"handled by"| node_api
node_batch -->|"handled by"| node_api
node_api -->|"returns predictions"| node_risk

click node_dataset "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/dataset.csv"
click node_prep "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/train.py"
click node_tune "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/train.py"
click node_evaluate "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/train.py"
click node_artifact "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/model.pkl"
click node_api "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py"
click node_health "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py"
click node_info "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py"
click node_single "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py"
click node_batch "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py"
click node_risk "https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.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_dataset,node_prep,node_tune,node_evaluate toneBlue
class node_api,node_health,node_info,node_single,node_batch,node_risk toneAmber
class node_artifact toneMint
class node_analyst toneIndigo
```

## Components

### Model training

- [EEG dataset](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/dataset.csv): `dataset.csv`
- [Load and split](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/train.py): `train.py`
- [Tune pipeline](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/train.py): `train.py`
- [Evaluate model](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/train.py): `train.py`

### Prediction API

- [FastAPI app](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py): `main.py`
- [Health check](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py): `main.py`
- [Model info](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py): `main.py`
- [Single prediction](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py): `main.py`
- [Batch prediction](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py): `main.py`
- [Risk result](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/main.py): `main.py`

### Model artifact

- [Fitted model](https://github.com/vaishnaviborusumedi/eeg-seizure-prediction-api/blob/main/model.pkl): `model.pkl`

### Other components

- **Operator**

## Connections

- EEG dataset → Load and split: loads rows (evidence: `train.py`)
- Load and split → Tune pipeline: splits data (evidence: `train.py`)
- Tune pipeline → Evaluate model: fits best model (evidence: `train.py`)
- Evaluate model → Fitted model: saves model (evidence: `train.py`)
- Operator → Health check: checks status (evidence: `README.md`)
- Operator → Model info: requests details (evidence: `README.md`)
- Operator → Single prediction: submits features (evidence: `README.md`)
- Operator → Batch prediction: submits batch (evidence: `README.md`)
- Fitted model → FastAPI app: loaded at startup (evidence: `main.py`)
- Single prediction → FastAPI app: handled by (evidence: `main.py`)
- Batch prediction → FastAPI app: handled by (evidence: `main.py`)
- FastAPI app → Risk result: returns predictions (evidence: `main.py`)
