BMI values were predicted using the PIMA Indians dataset using linear regression and gradient descent. Dataset: https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database
The steps taken were as follows:
- Load the data
- Clean the dataset (seting target value, setting features, addressing missing values, and correcting types)
- Normalize the data
- Split the dataset into an 80% training and 20% testing set
- Define an error calculation method
- Define a gradient descent method
- Define a MSE method (mean squared error)
- Define a prediction method (dot product of weights and features)
- Train the model using the methods defined above
- Predict and tune the model