Load in libraries

library(readr)
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

library(ggplot2)

#Read in the data

cereal = read.csv("Cereal.csv")

a) Use head(cereal) to view the first few lines and class(cereal) to confirm it’s a data frame.

head(cereal, n=5)

##                        name mfr type calories protein fat sodium fiber carbo
## 1                 100%_Bran   N    C       70       4   1    130    10     5
## 2         100%_Natural_Bran   Q    C      120       3   5     15     2     8
## 3                  All-Bran   K    C       70       4   1    260     9     7
## 4 All-Bran_with_Extra_Fiber   K    C       50       4   0    140    14     8
## 5            Almond_Delight   R    C      110       2   2    200     1    14
##   sugars potass vitamins shelf weight cups   rating
## 1      6    280       25     3      1 0.33 68.40297
## 2      8    135        0     3      1 1.00 33.98368
## 3      5    320       25     3      1 0.33 59.42551
## 4      0    330       25     3      1 0.50 93.70491
## 5      8     -1       25     3      1 0.75 34.38484

class(cereal)

## [1] "data.frame"

b) Use colnames(cereal) for column names and dim(cereal) or nrow(cereal) for the number of rows.

colnames(cereal)

##  [1] "name"     "mfr"      "type"     "calories" "protein"  "fat"     
##  [7] "sodium"   "fiber"    "carbo"    "sugars"   "potass"   "vitamins"
## [13] "shelf"    "weight"   "cups"     "rating"

nrow(cereal)

## [1] 77

dim(cereal)

## [1] 77 16

c) Extract the calories column

Cal = cereal$calories

d) Extract rows 1 to 10 from the cereal data frame.

cereal[1:10, ]

##                         name mfr type calories protein fat sodium fiber carbo
## 1                  100%_Bran   N    C       70       4   1    130  10.0   5.0
## 2          100%_Natural_Bran   Q    C      120       3   5     15   2.0   8.0
## 3                   All-Bran   K    C       70       4   1    260   9.0   7.0
## 4  All-Bran_with_Extra_Fiber   K    C       50       4   0    140  14.0   8.0
## 5             Almond_Delight   R    C      110       2   2    200   1.0  14.0
## 6    Apple_Cinnamon_Cheerios   G    C      110       2   2    180   1.5  10.5
## 7                Apple_Jacks   K    C      110       2   0    125   1.0  11.0
## 8                    Basic_4   G    C      130       3   2    210   2.0  18.0
## 9                  Bran_Chex   R    C       90       2   1    200   4.0  15.0
## 10               Bran_Flakes   P    C       90       3   0    210   5.0  13.0
##    sugars potass vitamins shelf weight cups   rating
## 1       6    280       25     3   1.00 0.33 68.40297
## 2       8    135        0     3   1.00 1.00 33.98368
## 3       5    320       25     3   1.00 0.33 59.42551
## 4       0    330       25     3   1.00 0.50 93.70491
## 5       8     -1       25     3   1.00 0.75 34.38484
## 6      10     70       25     1   1.00 0.75 29.50954
## 7      14     30       25     2   1.00 1.00 33.17409
## 8       8    100       25     3   1.33 0.75 37.03856
## 9       6    125       25     1   1.00 0.67 49.12025
## 10      5    190       25     3   1.00 0.67 53.31381

e) Filter the cereal data frame to include only rows where mfr is “K” and assign it to Kelloggs.

Kelloggs = cereal |> filter(mfr == "K")

week 1

2026-08-07

Load in libraries

a) Use head(cereal) to view the first few lines and class(cereal) to confirm it’s a data frame.

b) Use colnames(cereal) for column names and dim(cereal) or nrow(cereal) for the number of rows.

c) Extract the calories column

d) Extract rows 1 to 10 from the cereal data frame.

e) Filter the cereal data frame to include only rows where mfr is “K” and assign it to Kelloggs.