🌾 FasalSathi

Smart Agricultural Assistant for Farmers in India

---

📋 Quick Navigation

🚀 Get Started Setup in 5 minutes

🌟 Features What we offer

🤖 ML Models 95% accurate AI

🤝 Contribute Join the team

---

🌟 Features

📱 Core Functionality

• Modern Dashboard - Material Design 3 interface with quick access to all features
• User Profiles - Personalized farmer accounts with location-based services
• Multi-language - Hindi, English, Marathi, Gujarati & more

🌤️ Weather Intelligence

• Real-time Data - Integration with OpenWeatherMap API for 200+ Indian cities
• 7-Day Forecast - Hourly weather breakdowns with farming recommendations
• Offline Mode - Realistic simulation when internet unavailable

🤖 AI Assistant

• Voice Recognition - Ask farming questions using voice
• Image Analysis - Upload crop photos for AI-powered diagnosis
• Text-to-Speech - Listen to responses in local languages
• Smart Chat - Interactive conversation for agricultural queries

🌾 ML Crop Recommendation

• 95% Accurate - AI-based crop recommendations using soil & environmental data
• Soil Analysis - Advanced soil type detection with 92% accuracy
• Smart Suggestions - Region-specific recommendations with confidence scores

🏛️ Government Schemes

• Scheme Database - Access agricultural government programs
• Eligibility Check - Verify eligibility for different schemes
• Application Guide - Step-by-step help with applications

---

��️ Tech Stack

Mobile	Machine Learning	Backend
Kotlin 1.9.10	Random Forest (95% accuracy)	OpenWeatherMap API
Material Design 3	Gradient Boosting (92% accuracy)	Firebase
Room Database	TensorFlow + scikit-learn	RESTful APIs
MVVM Architecture	OpenCV Image Processing	Cloud Storage

---

🚀 Quick Start

⚡ One-Command Setup

# Clone repository
git clone https://github.com/AnuranjanJain/FasalSathi.git
cd FasalSathi

# For Android Development
./build.sh -i

# For ML Development  
./setup_ml.sh

📱 Android Setup

Click to expand detailed steps

Prerequisites: Android Studio, JDK 8+, Android SDK (API 21+)

1. Open in Android Studio

   • File → Open → Select FasalSathi folder
   • Wait for Gradle sync

2. Build & Run

   ./build.sh -i              # Build and install
   ./gradlew assembleDebug    # Build only

3. Run in Android Studio

   • Press Shift+F10 or click Run ▶️

🐍 ML Pipeline Setup

Click to expand detailed steps

Prerequisites: Python 3.8+, pip

1. Automated Setup (Recommended)

   ./setup_ml.sh

2. Manual Setup

   python3 -m venv venv
   source venv/bin/activate          # Linux/Mac
   # venv\Scripts\activate           # Windows
   pip install -r requirements.txt
   python ml_pipeline/train_models.py

---

🤖 ML Models

Model	Type	Accuracy	Speed	Size
🌾 Crop Recommendation	Random Forest	95.2%	<100ms	484 MB
🏔️ Soil Detection	Gradient Boosting	92.1%	<50ms	32 MB
📸 Image Classifier	CNN (TensorFlow)	89.5%	<200ms	116 MB

Quick Test

from ml_pipeline.fixed_predictor import FixedModelPredictor

predictor = FixedModelPredictor("ml_pipeline/models")
result = predictor.predict_crop({
    'n': 90, 'p': 42, 'k': 43, 'ph': 6.5,
    'temperature': 25, 'humidity': 70, 'rainfall': 800
})

print(f"🌾 Crop: {result['crop']}")
print(f"📊 Confidence: {result['confidence']:.1%}")

---

📁 Project Structure

FasalSathi/
├── app/                    # Android application (Kotlin)
│   ├── src/main/          # Source code
│   │   ├── java/          # Kotlin files (UI, data, ML integration)
│   │   └── res/           # Resources (layouts, strings, images)
│   └── src/test/          # Unit & integration tests
├── ml_pipeline/            # Machine Learning (Python)
│   ├── train_models.py    # Model training
│   ├── fixed_predictor.py # Production predictor
│   └── models/            # Trained models (516 MB)
├── Datasets/              # Training datasets
├── build.sh               # Build automation script
├── setup_ml.sh            # ML setup script
└── README.md              # This file

---

🔨 Build Commands

./build.sh        # Build debug APK
./build.sh -i     # Build and install on device
./build.sh -r     # Build release APK
./build.sh -c     # Clean build
./gradlew test    # Run tests

---

🧪 Testing

# Unit tests
./gradlew test

# Integration tests (requires device)
./gradlew connectedAndroidTest

# Test coverage report
./gradlew jacocoTestReport

---

🤝 Contributing

We welcome contributions! Here's how:

1. Fork the repository
2. Create a feature branch: git checkout -b feature/amazing-feature
3. Commit changes: git commit -m 'feat: add amazing feature'
4. Push to branch: git push origin feature/amazing-feature
5. Open a Pull Request

Commit Convention

feat: new feature
fix: bug fix
docs: documentation
style: formatting
refactor: code restructuring
test: add tests
chore: maintenance

---

🐛 Troubleshooting

Gradle Sync Failed

./gradlew clean
./gradlew build --refresh-dependencies

Device Not Detected

adb devices
adb kill-server
adb start-server

Python Import Errors

source venv/bin/activate
pip install --upgrade -r requirements.txt

Out of Memory

Add to gradle.properties:

org.gradle.jvmargs=-Xmx4096m
org.gradle.daemon=true
org.gradle.parallel=true

---

📊 Performance

Metric	Value
APK Size (Debug)	15-20 MB
APK Size (Release)	10-15 MB
Cold Start Time	< 2s
Memory Usage	50-80 MB
ML Inference	< 100ms

---

🗺️ Roadmap

Current (v1.1) ✅

• Core features, ML models, Weather system, Multi-language

Next (v1.2) 🚧

• Offline mode, Enhanced disease detection, Market prices, Push notifications

Future (v2.0) 💡

• Community forum, SMS access, Satellite imagery, Government API integration

---

📄 License

This project is licensed under the MIT License - see LICENSE for details.

---

🙏 Acknowledgments

• Smart India Hackathon 2025 - Project opportunity
• OpenWeatherMap - Weather data API
• scikit-learn - ML framework
• Android Community - Libraries and support

---

📞 Contact

---

⭐ Star us on GitHub if you find this helpful!

---

⬆ Back to Top