# sakshihase26/phishing-url-detection-using-machine-learning architecture

> Architecture diagram of the GitHub repository sakshihase26/phishing-url-detection-using-machine-learning, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2025-06-20). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/sakshihase26/phishing-url-detection-using-machine-learning
- Repository: https://github.com/sakshihase26/phishing-url-detection-using-machine-learning

## Overview

##### (implied) file structure
- Even though all we see is “Phishing_URL_Detection.zip” plus README.md, a typical unpacked structure will include:
- data/           – raw URL datasets, labeled examples
- src/            – Python modules for preprocessing, feature-engineering, model code
- notebooks/      – exploratory data analysis and prototyping notebooks
- models/         – serialized model artifacts (e.g., .pkl, .joblib)
- scripts/        – training and evaluation CLI scripts
- requirements.txt / environment.yml
- deployment/     – API server or Docker files

##### README for additional insights
- The README title “Phishing-URL-Detection-Using-Machine-Learning” tells us the focus is on building a classifier. We expect sections on dependencies (scikit-learn, pandas, Flask/FastAPI) and usage (how to train and how to call predict).

## Diagram (Mermaid)

```mermaid
flowchart TB
    %% Training Pipeline
    subgraph "Training Pipeline"
        direction TB
        RawData["Raw Data Store"]:::datastore
        Preprocess["Data Preprocessing"]:::process
        FeatureEng["Feature Engineering"]:::process
        ModelTrain["Model Training & Evaluation"]:::process
        ModelRegistry["Model Registry"]:::datastore
    end

    RawData --> Preprocess
    Preprocess --> FeatureEng
    FeatureEng --> ModelTrain
    ModelTrain --> ModelRegistry

    %% Serving / Inference
    subgraph "Serving Pipeline"
        direction TB
        Client["Client / UI / Email Gateway"]:::external
        PredictionAPI["Prediction API (Flask/FastAPI)"]:::process
        Logging["Logging & Monitoring"]:::process
    end

    Client -->|HTTP/JSON| PredictionAPI
    PredictionAPI -->|"load model"| ModelRegistry
    PredictionAPI -->|"log requests"| Logging
    PredictionAPI -->|HTTP/JSON| Client

    %% Notebooks for EDA and prototyping
    Notebook["Jupyter Notebooks"]:::process
    Notebook --> RawData
    Notebook --> ModelRegistry

    classDef datastore fill:#BBEFFF,stroke:#333,stroke-width:1px
    classDef process fill:#C2F0C2,stroke:#333,stroke-width:1px
    classDef external fill:#FFD699,stroke:#333,stroke-width:1px
```
