Predition practice

library(caret)

## Warning: package 'caret' was built under R version 4.0.3

## Loading required package: lattice

## Loading required package: ggplot2

library(tidymodels)

## Warning: package 'tidymodels' was built under R version 4.0.3

## -- Attaching packages -------------------------------------- tidymodels 0.1.1 --

## v broom     0.7.0      v recipes   0.1.14
## v dials     0.0.9      v rsample   0.0.8 
## v dplyr     1.0.2      v tibble    3.0.3 
## v infer     0.5.3      v tidyr     1.1.2 
## v modeldata 0.1.0      v tune      0.1.1 
## v parsnip   0.1.3      v workflows 0.2.1 
## v purrr     0.3.4      v yardstick 0.0.7

## Warning: package 'dials' was built under R version 4.0.3

## Warning: package 'infer' was built under R version 4.0.3

## Warning: package 'modeldata' was built under R version 4.0.3

## Warning: package 'parsnip' was built under R version 4.0.3

## Warning: package 'recipes' was built under R version 4.0.3

## Warning: package 'rsample' was built under R version 4.0.3

## Warning: package 'tune' was built under R version 4.0.3

## Warning: package 'workflows' was built under R version 4.0.3

## Warning: package 'yardstick' was built under R version 4.0.3

## -- Conflicts ----------------------------------------- tidymodels_conflicts() --
## x purrr::discard()         masks scales::discard()
## x dplyr::filter()          masks stats::filter()
## x dplyr::lag()             masks stats::lag()
## x purrr::lift()            masks caret::lift()
## x yardstick::precision()   masks caret::precision()
## x yardstick::recall()      masks caret::recall()
## x yardstick::sensitivity() masks caret::sensitivity()
## x yardstick::specificity() masks caret::specificity()
## x recipes::step()          masks stats::step()

library(tidyverse)

## -- Attaching packages --------------------------------------- tidyverse 1.3.0 --

## v readr   1.3.1     v forcats 0.5.0
## v stringr 1.4.0

## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x readr::col_factor() masks scales::col_factor()
## x purrr::discard()    masks scales::discard()
## x dplyr::filter()     masks stats::filter()
## x stringr::fixed()    masks recipes::fixed()
## x dplyr::lag()        masks stats::lag()
## x purrr::lift()       masks caret::lift()
## x readr::spec()       masks yardstick::spec()

library(anesr)

data("timeseries_2016")
anes16 <- timeseries_2016
rm(timeseries_2016)

clean <- function(x){ifelse(x < 0, NA, x)}

anes16_clean <- anes16 %>%
  mutate(across(everything(), clean)) %>%
  select(PID = V161158x , Gender = V161342, Income = V161361x, Religion = V161265x,
       Education = V161270, Age = V161267, Ideology = V161126, Race = V161310x, P_reg = V161019, GunAccess = V161188, BuildWall = V161196, ObamaMuslim = V162255, Trump_Fav = V161087, Hannity = V161430) %>%
  mutate(across(c(PID, Gender, Income, Religion, Education, Ideology, Race, P_reg, GunAccess, BuildWall, ObamaMuslim, Hannity),as.factor)) %>%
  drop_na()

set.seed(131313)
split1 <- initial_split(anes16_clean, prop = .7)
Train_Data <- training(split1)
Test_Data<-testing(split1)

anes_recipe <- recipe(Trump_Fav ~ ., data = Train_Data) %>% 
  step_dummy(PID, Gender, Income, Religion, Education, Ideology, Race,P_reg, BuildWall, ObamaMuslim, GunAccess, Hannity) %>%
  step_center(Age, Trump_Fav) %>%
  step_scale(Age, Trump_Fav) %>%
  prep(training = Train_Data)

baked_train <- bake(anes_recipe, new_data = Train_Data)
baked_test <- bake(anes_recipe, new_data = Test_Data)



set.seed(131313)
trump_lm <- train(
  Trump_Fav ~ ., 
  data = Train_Data, 
  method = "lm",
  trControl = trainControl(method = "cv", number = 5)
)

## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading

## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading

## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading

## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading

## Warning in predict.lm(modelFit, newdata): prediction from a rank-deficient fit
## may be misleading

trump_lm[["results"]]

##   intercept     RMSE  Rsquared      MAE   RMSESD RsquaredSD    MAESD
## 1      TRUE 22.61495 0.5816795 16.84226 1.279475 0.04982805 1.389257