How to graph my multiple linear regression model (caret)? - r

Question

I have created an multiple linear regression model and would now like to plot it. But I can't seem to figure it out. Any help would be greatly appreciated! I used baruto to find the feature attributes and then used train() to get the model. When I try to plot model_lm I get the error:
There are no tuning parameters with more than 1 value.
Here is my code at what I have attempted so far:
rt_train <- rttotal2
rt_train$year <- NULL
#rt_train$box_office <- NULL
#impute na and address multicoliniearity
preproc <- preProcess(rt_train, method = c("knnImpute","center",
"scale"))
rt_proc <- predict(preproc, rt_train)
rt_proc$box_office <- rt_train$box_office
sum(is.na(rt_proc))
titles <- rt_proc$titles
rt_proc$titles <- NULL
#rt_train$interval <- as.factor(rt_train$interval)
dmy <- dummyVars(" ~ .", data = rt_proc,fullRank = T)
rt_transform <- data.frame(predict(dmy, newdata = rt_proc))
index <- createDataPartition(rt_transform$interval, p =.75, list = FALSE)
train_m <- rt_transform[index, ]
rt_test <- rt_transform[-index, ]
str(rt_train)
y_train <- train_m$box_office
y_test <-rt_test$box_office
train_m$box_office <- NULL
rt_test$box_office <- NULL
#selected feature attributes
boruta.train <- Boruta(interval~., train_m, doTrace =1)
#graph to see most important var to interval
lz<-lapply(1:ncol(boruta.train$ImpHistory),function(i)
boruta.train$ImpHistory[is.finite(boruta.train$ImpHistory[,i]),i])
names(lz) <- colnames(boruta.train$ImpHistory)
plot(boruta.train, xlab = "", xaxt = "n")
Labels <- sort(sapply(lz,median))
axis(side = 1,las=2,labels = names(Labels),
at = 1:ncol(boruta.train$ImpHistory), cex.axis = 0.7)
#get most important attributes
final.boruta <- TentativeRoughFix(boruta.train)
print(final.boruta)
getSelectedAttributes(final.boruta, withTentative = F)
boruta.rt_df <- attStats(final.boruta)
boruta.rt_df
boruta.rt_df <- setDT(boruta.rt_df, keep.rownames = TRUE)[]
predictors <- boruta.rt_df %>%
filter(., decision =="Confirmed") %>%
select(., rn)
predictors <- unlist(predictors)
control <- trainControl(method="repeatedcv",
number=10,
repeats=6)
#look at residuals
#p-value is very small so reject H0 that predictors have no effect so
#we can use rotten tomatoes to predict box_office ranges
train_m$interval <- NULL
model_lm <- train(train_m[,predictors],
y_train, method='lm',
trControl = control, tuneLength = 10)
model_lm #.568
#
plot(model_lm)
plot(model_lm)
z <- varImp(object=model_lm)
z <- setDT(z, keep.rownames = TRUE)
z$model <- NULL
z$calledFrom <- NULL
row.names(z)
plot(varImp(object=model_lm),main="Linear Model Variable Importance")
predictions<-predict.train(object=model_lm,rt_test[,predictors],type="raw")
table(predictions)
#get coeff
interc <- coef(model_lm$finalModel)
slope <- coef(model_lm$finalModel)
ggplot(data = rt_train, aes(y = box_office)) +
geom_point() +
geom_abline(slope = slope, intercept = interc, color = 'red')
This is what some of my input looks like. Thank you!!

Answer 1

Here is an example using the inbuilt data set cars:
data(cars, package = "datasets")
library(caret)
build the model
control <- trainControl(method = "repeatedcv",
number = 10,
repeats = 6)
model_lm <- train(dist ~ speed, data = cars, method='lm',
trControl = control, tuneLength = 10)
I will assume you would like to plot the final model.
You can use the caret predict.train function to get the predictions from the model and plot them:
pred <- predict(model_lm, cars)
pred <- data.frame(pred = pred, speed = cars$speed)
additionally you can provide the cars data set to geom point and plot the observations:
library(ggplot2)
ggplot(data = pred)+
geom_line(aes(x = speed, y = pred))+
geom_point(data = cars, aes(x=speed, y = dist))
if you would like to obtain the confidence or prediction interval you can use the predict.lm function on model_lm$finalModel:
Here is an example for the prediction interval:
pred <- predict(model_lm$finalModel, cars, se.fit = TRUE, interval = "prediction")
pred <- data.frame(pred = pred$fit[,1], speed = cars$speed, lwr = pred$fit[,2], upr = pred$fit[,3])
pred_int <- ggplot(data = pred)+
geom_line(aes(x = speed, y = pred))+
geom_point(data = cars, aes(x = speed, y = dist)) +
geom_ribbon(aes(ymin = lwr, ymax = upr, x = speed), alpha = 0.2)
or the confidence interval:
pred <- predict(model_lm$finalModel, cars, se.fit = TRUE, interval = "confidence")
pred <- data.frame(pred = pred$fit[,1], speed = cars$speed, lwr = pred$fit[,2], upr = pred$fit[,3])
pred_conf <- ggplot(data = pred)+
geom_line(aes(x = speed, y = pred))+
geom_point(data = cars, aes(x = speed, y = dist)) +
geom_ribbon(aes(ymin = lwr, ymax = upr, x = speed), alpha = 0.2)
plotting them side by side:
library(cowplot)
plot_grid(pred_int, pred_conf)
to plot the linear dependence on two variables you can use a 3D plot, for more than 3 it will be a problem.