Module Lab 8

Packages required:

library(kknn)
library(tidymodels)

Q1: Is this a supervised or unsupervised learning problem? Why?

This is a supervised because we are using predictor variables to predict a known response variable (cmedv)

Q2: There are 16 variables in this data set. Which variable is the response variable and which variables are the predictor variables (aka features)?

cmedv is the response variable. All others are predictor variables

Q3: Is this a regression or classification problem?

This is a regression problem because the response variable cmedv is continuous

Q4: Import data set + Missing value + Statistic

boston <- readr::read_csv("C:/Users/thanh/OneDrive - University of Cincinnati/Nie/F24_Data mining/boston.csv")

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

sum(is.na(boston))

[1] 0

summary(boston$cmedv)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
   5.00   17.02   21.20   22.53   25.00   50.00 

Q5: Split data set:

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

Q6: Number of observation in training set and test set:

nrow(train)  #training set

[1] 352

nrow(test)   #test set

[1] 154

Q7: Comparision the distribution of cmedv between 2 sets:

library(ggplot2)
ggplot(train, aes(x = cmedv)) + geom_histogram(binwidth = 1) + ggtitle("Training Set cmedv Distribution")

ggplot(test, aes(x = cmedv)) + geom_histogram(binwidth = 1) + ggtitle("Test Set cmedv Distribution")

Q8: Fit a linear regression model with rm as the predictor

lm1 <- linear_reg() %>%
  fit(cmedv ~ rm, data = train)

lm1 %>%
  predict(new_data = test) %>%
  bind_cols(test %>% select(cmedv)) %>%
  rmse(truth = cmedv, estimate = .pred)

Q9:

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

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

Q10:

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

# Compute the RMSE on the test data
knn %>%
  predict(new_data = test) %>%
  bind_cols(test %>% select(cmedv)) %>%
  rmse(truth = cmedv, estimate = .pred)