Chapter 01: Introduction to Machine Learning

NOTE: Access and run the source code for this notebook here.

Regression problems

Code for Figure 1.1:

df <- AmesHousing::make_ames()
x <- matrix(sort(df$Gr_Liv_Area)[floor(seq(1, nrow(df), length.out = 15))], 15, 1)
y <- matrix(sort(df$Year_Built)[floor(seq(1, nrow(df), length.out = 15))], 1, 15)
z <- 25051 + 3505*(log(x^.9) %*% log(y)) - 5*as.vector(x) 
c <- matrix(c(.92, .95, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, .95), 1, 15)
z <- sweep(z, MARGIN = 2, c, `*`)

par(mar = c(0.1, 0.1, 0.1, 0.1))
persp(
  x = x,
  y = y,
  z = z,
  xlab = "Square footage",
  ylab = "Year built",
  zlab = "Sale price",
  theta = -45,
  phi = 25,
  col = viridis::viridis(100)
)

Classification problems

Code for Figure 1.2:

# code to create graphic
library(DiagrammeR)
 grViz("
   
   digraph boxes_and_circles {
     node [shape = circle]
     x1; x2; x3;
     
     node [shape = box]
     Model;
     
     node [shape = triangle]
     Yes; No;
 
     x1->Model; x2->Model; x3->Model; Model->No; Model->Yes;
 }")

The data sets

• Ames homes sales data

# access data
ames <- AmesHousing::make_ames()

# initial dimension
dim(ames)

[1] 2930   81

# response variable
head(ames$Sale_Price)

[1] 215000 105000 172000 244000 189900 195500

• Employee attrition information originally provided by IBM Watson Analytics Lab.

# access data
attrition <- rsample::attrition

# initial dimension
dim(attrition)

[1] 1470   31

# response variable
head(attrition$Attrition)

[1] Yes No  Yes No  No  No 
Levels: No Yes

• MNIST handwritten numbers data

#access data
mnist <- dslabs::read_mnist()
names(mnist)

[1] "train" "test" 

# initial feature dimensions
dim(mnist$train$images)

[1] 60000   784

# response variable
head(mnist$train$labels)

[1] 5 0 4 1 9 2

• Grocery items and quantities purchased.

# URL to download/read in the data
url <- "https://koalaverse.github.io/homlr/data/my_basket.csv"

# Access data
my_basket <- readr::read_csv(url)

# Print dimensions
dim(my_basket)

[1] 2000   42

# Peek at response variable
my_basket