🌾 Smart Crop Recommendation System

An AI-powered full-stack web application that predicts the best crop to cultivate based on soil parameters (N, P, K, pH) and climate conditions. The system features a microservices architecture with a Python-based Machine Learning service and a Node.js API Gateway, all connected to a responsive frontend.

✨ Features

• Dual Prediction Modes:
  • 📍 Location Based: Auto-loads state-specific soil data (N, P, K) for Indian states; users only provide current climate info.
  • ⚙️ Manual Mode: Allows detailed input of all parameters including Nitrogen, Phosphorus, Potassium, Temperature, Humidity, pH, and Rainfall.
• 🧠 Machine Learning: Uses a Random Forest Classifier trained on agricultural data to predict optimal crops with high confidence.
• 📊 Analytics Dashboard: Tracks total predictions, top recommended crops, and usage statistics.
• ⚡ Microservices Architecture: Separates the ML inference engine (Flask) from the application logic and database management (Node.js).

📂 Project Structure

├── flask_api/             # Python Flask Service
│   └── app.py             # ML Inference API
├── frontend/              # User Interface
│   ├── index.html         # Main dashboard
│   ├── script.js          # Frontend logic & API calls
│   └── style.css          # Styling
├── ml_backend/            # Model Training & Data
│   ├── model_train.py     # Script to train Random Forest model
│   ├── test_model.py      # Script to test model accuracy
│   └── crop_recommendation.csv # Dataset (Required)
└── node_api/              # API Gateway & Database
    └── server.js          # Express server & MongoDB connection

🐍 Flask API Setup (Prediction Engine)

This service loads the trained model and handles prediction requests from the Node.js server.

# Navigate to the Flask API directory
cd ../flask_api

# Install dependencies
pip install flask flask-cors numpy

# Start the Flask Server
python app.py
Status: The Flask server will run on http://localhost:5000.

🌐 Node.js API Setup (Backend & Database)

This is the main API gateway that communicates with the frontend, database, and Flask service.

# Navigate to the Node API directory
cd ../node_api

# Install Node.js dependencies
npm install express mongoose cors axios dotenv

# Start the Node Server
node server.js

Status: The Node API will run on http://localhost:3000. Database: Ensure your MongoDB is running on mongodb://localhost:27017/crop_recommendation or update the connection string in server.js.

💻 Frontend Setup (User Interface)

The frontend is a static web application that connects to the Node.js API.

Navigate to the frontend/ folder.

Open index.html in your web browser.

Recommended: Use a local development server (like VS Code's Live Server extension) to open index.html. This avoids CORS issues that can occur when opening HTML files directly from the file system.

🔌 API Documentation

The system uses Node.js (Port 3000) as the primary entry point for the frontend.

Method          Endpoint          
POST            /api/predictManual   
POST            /api/predict-by-location
GET             /api/states
GET             /api/stats

🛠️ Tech Stack

Frontend: HTML5, CSS3, Vanilla JavaScript

API Gateway: Node.js, Express.js

ML Engine: Python, Flask, Scikit-learn

Database: MongoDB

Data Processing: Pandas, NumPy