AutoML Research Platform (Local Simulation Edition)

This is a modern, single-page AutoML Dashboard built with React, TypeScript, and Tailwind CSS.

It is designed to simulate a professional Machine Learning workflow (Upload -> Preprocessing -> Training -> Evaluation) directly in the browser. No Python backend or API keys are required; all training processes and visualizations are simulated using advanced mathematical logic within the frontend.

🚀 Features

• Data Upload: Parse CSV files locally and view data statistics.
• Exploratory Data Analysis (EDA): Interactive histograms, value counts, and correlation heatmaps.
• Preprocessing Pipeline: Configure imputation, scaling, encoding, and class balancing (SMOTE).
• Model Configuration: Select ML (Random Forest, XGBoost), DL (CNN, LSTM), or NLP models with hyperparameter tuning.
• Visualizations:
  • Interactive ROC Curves, Confusion Matrices, and Learning Curves.
  • Data Projections: Simulated PCA, t-SNE, and UMAP visualizations.
  • Explainability: Simulated SHAP and LIME charts explaining model decisions.
• Dark Mode: Fully responsive UI with a professional dark/light theme.

🛠️ Prerequisites

You need Node.js installed on your computer.

• Download Node.js (Version 16+ recommended)

📦 Installation Steps

1. Download/Clone the project Download the project files into a folder (e.g., automl-platform).

2. Open Terminal Navigate to the project folder in your terminal or command prompt:

   cd path/to/automl-platform
   

3. Install Dependencies Run the following command to install the necessary libraries (React, Tailwind, Recharts, Lucide Icons):

   npm install
   

   Note: If you haven't initialized a package.json yet, copy the package.json file provided in the code into your root directory first.

4. Start the Application Run the development server: