In r programming fit multiple linear regression model

IN R programming
(a) Pre-processing: Check the data to see if there is any missing value. The simplest approach to deal with the missing values is to remove the rows with any missing values. Use are free to pick other methods from literature to deal with missing data. Remember that the final data provided to the regression models should not have any missing value. Also, make sure that the variables have the correct type. For example, “station” number doesn’t really have a numerical meaning! Or the date should not be included as a predictor.
(b) Split the data into three parts. Based on the “date”, consider the first 60% for training (Train), the next 20% for validation (Valid), and the last 20% for testing (Test). We will not touch the test set until the very end step.
(c) Initial Model: Fit a multiple linear regression model on the training data. Use this model to make prediction on the validation set. Then, calculate RMSE on the validation set using the following formula in below pic
Explore and discuss this model, its quality, significance of variables, residuals,