R Notebook

##Prerequisites:

library(vip)

Attaching package: ‘vip’

The following object is masked from ‘package:utils’:

    vi

##Data

boston <- read_csv("boston.csv")

Rows: 506 Columns: 16── Column specification ────────────────────
Delimiter: ","
dbl (16): lon, lat, cmedv, crim, zn, ind...
ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

##Split the data into a test and training set(70-30 split)

test <- testing(spl)

Error: object 'spl' not found

##Check predictor variables correlation

cmedv_cor <- corr_train[ , c("cmedv")] boston_correlation <- cor(boston)

Error: unexpected symbol in "cmedv_cor <- corr_train[ , c("cmedv")] boston_correlation"

##rm has the strongest positive correlation

##Plot the relationship between cmedv and rm

##Train a simple linear regression model with the predictor variables

##Compute the generalization RMSE for the above model

#Part 2: Multiple Linear Regression

##Compute the generalization RMSE for the model with all predictor variables.

##Using the full model with all predictor variables, identify the top 5 most influential predictor variables in our model.