Activity (Graded)

Execute the following cell to load the tidyverse library:

library(tidyverse)

Execute the following cell to load the data. Refer to this website http://archive.ics.uci.edu/ml/datasets/Auto+MPG for details on the dataset:

autompg = read.table(
  "http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data",
  quote = "\"",
  comment.char = "",
  stringsAsFactors = FALSE)
head(autompg,20)

Task 1: print the structure of the unedited data set. How many samples and features are there?

str(autompg)
print("There are 398 samples and 9 features.") 

Execute the following cell to assign names to the columns of the dataframe:

colnames(autompg) = c("mpg", "cyl", "disp", "hp", "wt", "acc", "year", "origin", "name")

Task-2: complete the code segment below to remove samples with missing horsepower (hp) values represented as a “?” in the dataset.

autompg = autompg %>% filter(hp != '?')
print(autompg)

Task-3: complete the code segment below to remove samples with the name “plymouth reliant”

autompg = autompg %>% filter(name != "plymouth reliant")
print(autompg)

Task-4: complete the code segment below to select all features except ‘name’

autompg = autompg %>% select(-"name")
(autompg)

Execute the following cell to change the type of hp values from character to numeric:

autompg$hp = as.numeric(autompg$hp)

Execute the following code cell to modify ‘origin’ column to reflect local (1) and international models (0)

autompg = autompg %>% mutate(origin = ifelse(!(origin %in% c(2, 3)), 'local', 'international'))
head(autompg, 20)

Task 5: print the structure of the dataframe. What types are the columns ‘cyl’ and ‘origin’?

str(autompg)
print("'cyl' is integer type and 'origin' is character type.")

Task-6: complete the code segment below to change the types of ‘cyl’ and ‘origin’ columns to factor

catcols = c('cyl', 'origin')
autompg[catcols] = lapply(autompg[catcols], as.factor)
str(autompg)

Task-7: complete the code segment below to create a scatter plot of mpg vs. displacement by color coding the points according to the origin (local or international), Comment on what you observe:

p = ggplot(data =autompg , aes(x = mpg , y = disp , color = factor(origin))) +
  geom_point(size = 1.8)
p
# As mpg increases, displacement decreases. International cars have more mileage than local cars. Local cars have more displacement which keeps decreasing as the mileage increases.