SMART-CROP-RECOMMENDATIONS

KO | EN

gitlite — search

#python #typescript #golang #nextjs #streamlit #go #react #css #html #linux #java #cli

SMART-CROP-RECOMMENDATIONS

★ 48 Open GitHub ↗

Welcome to Smart Crop Recommendations, a machine learning-powered project designed to revolutionize agriculture by suggesting the best crop to grow based on environmental and soil parameters.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# 🌾 SMART-CROP-RECOMMENDATIONS

🚀 **Empowering Smart Agriculture Using AI** 🤖🌱

Welcome to **Smart Crop Recommendations**, a machine learning-powered project designed to revolutionize agriculture by suggesting the best crop to grow based on environmental and soil parameters.

> "Feed the future with data-driven decisions."

---

## 🌟 Key Features

* 🌿 **Crop Recommendation:** Suggests the most suitable crop using smart ML algorithms
* 🪲 **Fertilizer Advice:** Recommends fertilizers based on nutrient levels
* 💉 **Disease Detection (Optional):** Detect plant diseases from images
* ☁️ **Weather Integration (Optional):** Real-time insights using weather APIs
* 📊 **User-Friendly Dashboard:** Built with Streamlit for ease of use

---

## 🧠 Algorithms Used

| Algorithm              | Emoji | Use Case                               |
| ---------------------- | ----- | -------------------------------------- |
| Decision Tree          | 🌳    | Interpretable decisions                |
| Random Forest          | 🌲    | High accuracy with multiple trees      |
| XGBoost                | 🚀    | Fast and powerful boosting             |
| K-Nearest Neighbors    | 🤖    | Simple & intuitive similarity matching |
| Support Vector Machine | 🔠    | Effective for small to medium datasets |
| Naive Bayes            | 🤝    | Works well with probabilistic features |
| Logistic Regression    | 📈    | Good for binary classification         |

---

## 🔧 Tech Stack

| Component           | Technology                           |
| ------------------- | ------------------------------------ |
| 🧠 Machine Learning | Scikit-learn, XGBoost                |
| 🌐 Web App          | Streamlit                            |
| 📦 Model Storage    | Pickle (.pkl files)                  |
| 📊 Dataset          | CSV (Kaggle or agricultural sources) |

---

## 📁 Project Structure

```
📆 smart-crop-recommendations
🔽🔀 app.py               # Main Streamlit app
🔽🔀 crop_model.pkl       # Trained crop ML model
🔽🔀 fertilizer_model.pkl # Fertilizer suggestion model
🔽🔀 dataset.csv          # Training dataset
🔽🔀 requirements.txt     # Python dependencies
🔽🔀 README.md            # Project description
```

---

## ▶️ Get Started

### 📅 Step 1: Clone the Repository

```bash
git clone https://github.com/yourusername/smart-crop-recommendations.git
cd smart-crop-recommendations
```

### 🔧 Step 2: Install Requirements

```bash
pip install -r requirements.txt
```

### 🔥 Step 3: Run the App

```bash
streamlit run app.py
```

---

## 🌿 Input Parameters

* 🧪 **Nitrogen (N)**
* 🧪 **Phosphorous (P)**
* 🧪 **Potassium (K)**
* 🌡️ **Temperature** (°C)
* 💧 **Humidity** (%)
* ⚗️ **pH Level**
* 🌧️ **Rainfall** (mm)

---

## 📸 Preview
![AgriNex - Google Chrome 09-05-2025 09_50_26](https://github.com/user-attachments/assets/c4ef5010-97b7-474b-8948-d975596a0637)

---

## 📃 Dataset Source

* Kaggle Crop Recommendation Dataset or other reliable agricultural data sources.
* *((https://www.kaggle.com/datasets/emmarex/plantdisease))*

---

## 👨‍💼 Author

**Aayush Kumar**

---

## 🌟 Support

If this project helped you, please give it a ⭐ on GitHub and share it with others!

Together, let's innovate agriculture! 🤾🌟

SMART-CROP-RECOMMENDATIONS

Explore Similar Repositories

Was this content helpful?

Recent Feedback

Download README