Week 8 Lab

Lab Prep

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.4.4     ✔ tibble    3.2.1
## ✔ lubridate 1.9.3     ✔ tidyr     1.3.0
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(tidymodels)

## ── Attaching packages ────────────────────────────────────── tidymodels 1.1.1 ──
## ✔ broom        1.0.5      ✔ rsample      1.2.0 
## ✔ dials        1.2.1      ✔ tune         1.1.2 
## ✔ infer        1.0.6      ✔ workflows    1.1.4 
## ✔ modeldata    1.3.0      ✔ workflowsets 1.0.1 
## ✔ parsnip      1.2.0      ✔ yardstick    1.3.0 
## ✔ recipes      1.0.10     
## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ scales::discard() masks purrr::discard()
## ✖ dplyr::filter()   masks stats::filter()
## ✖ recipes::fixed()  masks stringr::fixed()
## ✖ dplyr::lag()      masks stats::lag()
## ✖ yardstick::spec() masks readr::spec()
## ✖ recipes::step()   masks stats::step()
## • Search for functions across packages at https://www.tidymodels.org/find/

library(kknn)
boston <- read.csv("C:/Users/edmic/OneDrive/Documents/BANA 4080/Data/boston.csv")

Question 4

max(boston$cmedv)

## [1] 50

min(boston$cmedv)

## [1] 5

median(boston$cmedv)

## [1] 21.2

mean(boston$cmedv)

## [1] 22.52885

sum(is.na(boston$cmedv))

## [1] 0

Question 5

set.seed(123)
boston_split <- initial_split(boston, prop = .7, strata = cmedv)
boston_train <- training(boston_split)
boston_test <- testing(boston_split)

Question 6

nrow(boston_train)

## [1] 352

nrow(boston_test)

## [1] 154

Question 7

ggplot(boston_train, aes(x = cmedv)) + 
  geom_line(stat = "density", 
            trim = TRUE) + 
  geom_line(data = boston_test, 
            stat = "density", 
            trim = TRUE, col = "red")

Question 8

lm1 <- linear_reg() %>%
  fit(cmedv ~ rm, data = boston_train)
lm1 %>%
  predict(boston_test) %>%
  bind_cols(boston_test %>% select(cmedv)) %>%
  rmse(truth = cmedv, estimate = .pred)

## # A tibble: 1 × 3
##   .metric .estimator .estimate
##   <chr>   <chr>          <dbl>
## 1 rmse    standard        6.83

Question 9

lm2 <- linear_reg() %>%
  fit(cmedv ~ ., data = boston_train)

lm2 %>%
  predict(boston_test) %>%
  bind_cols(boston_test %>% select(cmedv)) %>%
  rmse(truth = cmedv, estimate = .pred)

## # A tibble: 1 × 3
##   .metric .estimator .estimate
##   <chr>   <chr>          <dbl>
## 1 rmse    standard        4.83

Question 10

knn <- nearest_neighbor() %>%
  set_engine("kknn") %>%
  set_mode("regression") %>%
  fit(cmedv ~ ., data = boston_train)
knn %>%
  predict(boston_test) %>%
  bind_cols(boston_test %>% select(cmedv)) %>%
  rmse(truth = cmedv, estimate = .pred)

## # A tibble: 1 × 3
##   .metric .estimator .estimate
##   <chr>   <chr>          <dbl>
## 1 rmse    standard        3.37