Overview The Crop Yield Prediction Per Country project involves the development of a machine learning model to predict crop yields for various countries using historical agricultural data. The objective is to predict future crop production based on factors like past yield data, climate variables, and other relevant features. This model can help in making data-driven decisions for improving agricultural practices and ensuring better crop management at a global scale.
Features Data Collection: The project uses historical agricultural data from multiple countries, providing a global perspective on crop yields and the factors that influence them. Data Preprocessing: The data undergoes cleaning and preprocessing using Pandas and NumPy to handle missing values, outliers, and feature transformations. Machine Learning Model: A variety of machine learning techniques are employed, including regression models, to predict crop yield. The model is fine-tuned for optimal performance through feature engineering. Model Evaluation: Achieved 80% accuracy in predicting crop yields, ensuring the model's reliability for future yield predictions.
Technologies Used Python: Programming language used for data analysis and model development. Pandas & NumPy: For data manipulation, cleaning, and feature engineering. Scikit-learn: For building and training machine learning models. Jupyter Notebook: For executing the code and documenting the analysis and model development process.
Dataset - yield_df.csv file
Accuracy & Performance The machine learning model achieved an accuracy of 80% in predicting crop yields. Model optimization was carried out through feature engineering, improving its predictive performance.