Module 8

library(tidymodels)

## ── Attaching packages ────────────────────────────────────── tidymodels 1.3.0 ──

## ✔ broom        1.0.7     ✔ recipes      1.1.1
## ✔ dials        1.4.0     ✔ rsample      1.2.1
## ✔ dplyr        1.1.4     ✔ tibble       3.2.1
## ✔ ggplot2      3.5.1     ✔ tidyr        1.3.1
## ✔ infer        1.0.7     ✔ tune         1.3.0
## ✔ modeldata    1.4.0     ✔ workflows    1.2.0
## ✔ parsnip      1.3.0     ✔ workflowsets 1.1.0
## ✔ purrr        1.0.4     ✔ yardstick    1.3.2

## ── Conflicts ───────────────────────────────────────── tidymodels_conflicts() ──
## ✖ purrr::discard() masks scales::discard()
## ✖ dplyr::filter()  masks stats::filter()
## ✖ dplyr::lag()     masks stats::lag()
## ✖ recipes::step()  masks stats::step()

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ readr     2.1.5
## ✔ lubridate 1.9.4     ✔ stringr   1.5.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ readr::col_factor() masks scales::col_factor()
## ✖ purrr::discard()    masks scales::discard()
## ✖ dplyr::filter()     masks stats::filter()
## ✖ stringr::fixed()    masks recipes::fixed()
## ✖ dplyr::lag()        masks stats::lag()
## ✖ readr::spec()       masks yardstick::spec()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Modeling tasks: 1. Is this a supervised or unsupervised learning problem? Why? Supervised because I am giving it specific inputs and requesting specific outputs when I run the task.

2. There are 16 variables in this data set. Which variable is the response variable and which variables are the predictor variables (aka features)?

Response: cmedv Predictor: all other variables

3. Given the type of variable cmedv is, is this a regression or classification problem?

Regression Problem

4. Fill in the blanks to import the Boston housing data set (boston.csv). Are there any missing values? What is the minimum and maximum values of cmedv? What is the average cmedv value?

boston <- readr::read_csv('Module-8/boston.csv')

## Rows: 506 Columns: 16
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## dbl (16): lon, lat, cmedv, crim, zn, indus, chas, nox, rm, age, dis, rad, ta...
## 
## 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.

missing_values <- colSums(is.na(boston))
print(missing_values)

##     lon     lat   cmedv    crim      zn   indus    chas     nox      rm     age 
##       0       0       0       0       0       0       0       0       0       0 
##     dis     rad     tax ptratio       b   lstat 
##       0       0       0       0       0       0

min_cmedv <- min(boston$cmedv)
max_cmedv <- max(boston$cmedv)
avg_cmedv <- mean(boston$cmedv)
median_cmedv <- median(boston$cmedv)

5. Fill in the blanks to split the data into a training set and test set using a 70-30% split. Be sure to include the set.seed(123) so that your train and test sets are the same size as mine.

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

boston_split

## <Training/Testing/Total>
## <352/154/506>

6. How many observations are in the training set and test set?

352 observations are in the training set and 154 observations are in the testing set.

7. Compare the distribution of cmedv between the training set and test set. Do they appear to have the same distribution or do they differ significantly?

ggplot(boston_train, aes(x = cmedv))+
  geom_line(stat = 'density', trim = TRUE, color = 'blue')+
  geom_line(data = boston_test, stat= 'density', trim = TRUE, color = 'red')

8. Fill in the blanks to fit a linear regression model using the rm feature variable to predict cmedv and compute the RMSE on the test data. What is the test set RMSE?

# fit model
lm1 <- linear_reg() %>%
  fit(cmedv ~ rm, data = boston_train)
# compute the RMSE on the test data
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

9. Fill in the blanks to fit a linear regression model using all available features to predict cmedv and compute the RMSE on the test data. What is the test set RMSE? Is this better than the previous model’s performance?

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

# compute the RMSE on the test data
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

10. Fit a K-nearest neighbor model that uses all available features to predict cmedv and compute the RMSE on the test data. What is the test set RMSE? Is this better than the previous two models’ performances?

# fit model
knn <- nearest_neighbor() %>%
  set_engine("kknn") %>%
  set_mode("regression") %>%
  fit(cmedv ~ ., data = boston_train)

# compute the RMSE on the test data
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