Crop-Yield-Rate-Analysis

We primarily aimed to analyze how each state's water quality affects the crop yield, we had taken 2 different data set, initially we cleaned the dataset i.e removing NULLs, modifying state names, etc and then merged it based on the common year and states to achieve a common dataset to analyze the relationship between the yeilds of crops based on the contaminants present in the water in each state. We used a set of models to analyze the data. Models used: Linear and Multilinear Regression, Random Forest, Neural Network.