Week 4 - LDA, QDA & KNN

Download template here

library(tidymodels)
library(nycflights13)
library(discrim)

We will be using the add-on package discrim to access functions to perform discriminant analysis models with parsnip and kknn to perform KNN methods. If the system prompts you to install a package, or gives you a “package not found” error, simply run install.packages("packagename") once to install it.

The data set

We will be using the same flights data set from the nycflights13 package. nycflights13 is an R data package containing all out-bound flights from NYC.

We will build a classification model that sees if any given flight is delayed or not. Furthermore, let us trim down the number of variables we are working with. Lastly, let us select to only work with flights taken place during the first month.

flights1 <- flights %>%
  mutate(delay = factor(arr_delay > 0, c(TRUE, FALSE),
                        c("Delayed", "On time"))) %>%
  filter(month == 1, !is.na(delay)) %>%
  select(delay, hour, minute, dep_delay, carrier, distance)

now that we have performed some cleaning, will we proceed to perform a train-test split.

flights_split <- initial_split(flights1)

flights_train <- training(flights_split)
flights_test <- testing(flights_split)

Now would be a good time to do EDA, but we habe already done the EDA for this section of the data last week, so we will jump right

Modeling

We will repeat the modeling we did last week but this time use a LDA, QDA and KNN specification.

The specification for each of these models can be found here in the following chunk.

lda_spec <- discrim_linear() %>%
  set_mode("classification") %>%
  set_engine("MASS")

qda_spec <- discrim_quad() %>%
  set_mode("classification") %>%
  set_engine("MASS")

knn_spec <- nearest_neighbor(neighbors = 5) %>%
  set_mode("classification") %>%
  set_engine("kknn")

Notice how nearest_neighbor() reqruires that we set a number of neighbors.

YOUR TURN

Fit each of these modes to see how dep_delay and distance affects delay. Evaluate the performance of each if the models using conf_mat() and accuracy().