This repository contains code for a machine learning crop yield prediction model trained using random forest regression. It contains data cleaning of the dataset, data analysis and visualization, model evaluation and hyperparameter tunning. K-means clustering was used as the unsupervised learning algorithm. The dataset used was obtained from kaggle and contains rainfall, temperature, pesticides, crop, year and country as independent features and yield as the dependent feature.
Link to the dataset https://www.kaggle.com/datasets/patelris/crop-yield-prediction-dataset
Below ia a latex term paper report for the above project.
Below is the link to my youtube channel with videos where I was explaining my progress throughout the project.