🌾 Crop Yield Prediction 🌱

🚀 Overview

The Crop Yield Prediction project aims to classify soil fertility based on various soil properties using machine learning models 🤖. It categorizes soil into three classes:

• 🟢 0 - Less Fertile
• 🟡 1 - Fertile
• 🔴 2 - Highly Fertile

We use key soil nutrients and properties like Nitrogen (N), Phosphorous (P), Potassium (K), pH level, Electrical Conductivity (ec), Organic Carbon (oc), and other micronutrients to predict soil fertility.

👨‍💻 Team Members

• 🎯 Tanishq Thuse
• 🔥 Kavish Paraswar
• ⚡ Swaraj Patil
• 🚀 Neel Sahastrabudhe

📊 Dataset

We used the Soil Fertility Dataset available on Kaggle 📂:
🔗 Dataset Link

📌 Dataset Details:
✅ 1288 samples
✅ 12 input features
✅ 1 target variable (Fertility Classification: 0, 1, 2)

---

📂 Project Structure

🔍 1. Data Exploration - Understanding feature distributions and correlations
🛠 2. Data Preprocessing - Splitting data into training and validation sets
🧠 3. Model Training - Implementing ML models:

• 🌳 Random Forest Classifier
• 🦠 Gaussian Naive Bayes
• ⚡ Support Vector Machine (SVM)
• 📍 K-Nearest Neighbors (KNN)
  📊 4. Model Evaluation - Analyzing accuracy & classification reports
  🔧 5. Data Modification - Improving model performance

---

🔑 Features Used

Feature	Description
N	Nitrogen (NH4+) ratio
P	Phosphorous ratio
K	Potassium ratio
pH	Soil acidity level
ec	Electrical Conductivity
oc	Organic Carbon
S	Sulfur content
Zn, Fe, Cu, Mn, B	Micronutrient levels
Output	Fertility Class (0, 1, 2)

---

📦 Libraries Used

📊 Pandas - Data manipulation
➕ NumPy - Numerical computations
📉 Matplotlib & Seaborn - Data visualization
🤖 Scikit-learn - Machine Learning models

---

🚀 How to Run the Project

1️⃣ Clone the Repository

git clone https://github.com/your-repo/crop-yield-prediction.git
cd crop-yield-prediction

2️⃣ Install Dependencies

pip install -r requirements.txt

3️⃣ Run the Jupyter Notebook

jupyter notebook GFG_Project.ipynb

4️⃣ Follow the Notebook Sections

📌 Sections:
✅ Data Exploration
✅ Data Preprocessing
✅ Model Training
✅ Model Evaluation

---

🏆 Results

🎯 Random Forest Classifier achieved 94.95% accuracy! 🎯
🔹 Model performance can be improved further by:

• Hyperparameter tuning 🛠
• Feature engineering 🧪

---

🔮 Future Work

📌 Feature Engineering - Add more soil properties for better predictions
📌 Hyperparameter Tuning - Use Grid Search / Random Search
📌 Deployment - Convert the model into a web app or API 🌐

---

🏁 Conclusion

The Crop Yield Prediction project successfully uses Machine Learning in agriculture to optimize soil management and maximize crop yields 🌾.

🔬 Future improvements can make it more accurate & scalable for real-world applications! 🚀

---

📜 License

This project is licensed under the MIT License 📜. See the LICENSE file for details.

---

✨ Team Rocket 🚀
📅 Date: 31/01/2025