Module 8 Lab

library(tidymodels)
library(dplyr)
install.packages("parsnip")
library(parsnip)
readr::read_csv("boston.csv")
boston <- readr::read_csv("boston.csv")
sum(is.na(boston))
summary(boston$cmedv)

Part 5

set.seed(123)
boston_split <- initial_split(boston, prop = 0.7, strata = cmedv)
train <- training(boston_split)
test <- testing(boston_split)

Part 6

boston_split 

Part 7

library(ggplot2)
ggplot(mapping = aes(x = cmedv)) +
  geom_histogram(data = train, binwidth = 1, fill = "blue", alpha = 0.5) +
  geom_histogram(data = test, binwidth = 1, fill = "red", alpha = 0.5)

Part 8

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

part 9

lm2 <- linear_reg() %>%
  fit(cmedv ~ ., data = train)
lm2 %>%
  predict(test) %>%
  bind_cols(test %>% select(cmedv)) %>%
  rmse(truth = cmedv, estimate = .pred)

Part 10

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