load-in the necessary libraries

library(skimr)
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(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats   1.0.0     ✔ readr     2.1.5
## ✔ ggplot2   3.5.1     ✔ stringr   1.5.1
## ✔ lubridate 1.9.4     ✔ tibble    3.2.1
## ✔ purrr     1.0.2     ✔ tidyr     1.3.1

## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Q1. Read in and Inspect the data

data("iris")

skim(iris)

Data summary
Name	iris
Number of rows	150
Number of columns	5
_______________________
Column type frequency:
factor	1
numeric	4
________________________
Group variables	None

Variable type: factor

skim_variable	n_missing	complete_rate	ordered	n_unique	top_counts
Species	0	1	FALSE	3	set: 50, ver: 50, vir: 50

Variable type: numeric

skim_variable	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
Sepal.Length	1	5.84	0.83	4.3	5.1	5.80	6.4	7.9	▆▇▇▅▂
Sepal.Width	1	3.06	0.44	2.0	2.8	3.00	3.3	4.4	▁▆▇▂▁
Petal.Length	1	3.76	1.77	1.0	1.6	4.35	5.1	6.9	▇▁▆▇▂
Petal.Width	1	1.20	0.76	0.1	0.3	1.30	1.8	2.5	▇▁▇▅▃

# There are 5 variables with 150 observations

Q2. Create a new data frame iris1 that contains only the species virginica and versicolor with sepal lengths longer than 6 cm and sepal widths longer than 2.5 cm. How many observations and variables are in the data set?

iris1 <- iris %>%
  group_by(Species) %>%
  filter(Sepal.Length > 6,
         Sepal.Width > 2.5)
  
skim(iris1)

Data summary
Name	iris1
Number of rows	56
Number of columns	5
_______________________
Column type frequency:
numeric	4
________________________
Group variables	Species

Variable type: numeric

skim_variable	Species	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
Sepal.Length	versicolor	1	6.48	0.30	6.1	6.20	6.5	6.7	7.0	▇▅▅▆▃
Sepal.Length	virginica	1	6.79	0.52	6.1	6.40	6.7	7.2	7.9	▇▆▂▃▃
Sepal.Width	versicolor	1	2.99	0.16	2.8	2.90	3.0	3.1	3.3	▇▃▁▃▃
Sepal.Width	virginica	1	3.06	0.28	2.6	2.85	3.0	3.2	3.8	▇▇▇▁▂
Petal.Length	versicolor	1	4.58	0.25	4.0	4.40	4.6	4.7	5.0	▁▅▅▇▂
Petal.Length	virginica	1	5.70	0.52	4.8	5.35	5.6	6.0	6.9	▅▇▆▃▂
Petal.Width	versicolor	1	1.42	0.12	1.2	1.30	1.4	1.5	1.7	▇▇▅▁▁
Petal.Width	virginica	1	2.07	0.28	1.4	1.80	2.1	2.3	2.5	▂▅▃▆▇

# My df has 5 variables with 56 observations

Q3. create a iris2 data frame from iris1 that contains only the columns for Species, Sepal.Length, and Sepal.Width. How many observations and variables are in the data set?

iris2 <- iris1 %>%
  select(Species, Sepal.Length, Sepal.Width)

skim(iris2)

Data summary
Name	iris2
Number of rows	56
Number of columns	3
_______________________
Column type frequency:
numeric	2
________________________
Group variables	Species

Variable type: numeric

skim_variable	Species	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
Sepal.Length	versicolor	1	6.48	0.30	6.1	6.20	6.5	6.7	7.0	▇▅▅▆▃
Sepal.Length	virginica	1	6.79	0.52	6.1	6.40	6.7	7.2	7.9	▇▆▂▃▃
Sepal.Width	versicolor	1	2.99	0.16	2.8	2.90	3.0	3.1	3.3	▇▃▁▃▃
Sepal.Width	virginica	1	3.06	0.28	2.6	2.85	3.0	3.2	3.8	▇▇▇▁▂

# My df has 3 variables with 56 observations

Q4. Create an iris3 data frame from iris2 that orders the observations from largest to smallest sepal length. Show the first 6 rows of this data set.

iris3 <- iris2 %>%
  arrange(desc(Sepal.Length))

head(iris3)

## # A tibble: 6 × 3
## # Groups:   Species [1]
##   Species   Sepal.Length Sepal.Width
##   <fct>            <dbl>       <dbl>
## 1 virginica          7.9         3.8
## 2 virginica          7.7         3.8
## 3 virginica          7.7         2.6
## 4 virginica          7.7         2.8
## 5 virginica          7.7         3  
## 6 virginica          7.6         3

Q5. Create an iris4 data frame from iris3 that creates a column with a sepal area (length * width) value for each observation. How many observations and variables are in the data set?

iris4 <- iris3 %>%
  mutate(Sepal.Area = Sepal.Length * Sepal.Width)

skim(iris4)

Data summary
Name	iris4
Number of rows	56
Number of columns	4
_______________________
Column type frequency:
numeric	3
________________________
Group variables	Species

Variable type: numeric

skim_variable	Species	complete_rate	mean	sd	p0	p25	p50	p75	p100	hist
Sepal.Length	versicolor	1	6.48	0.30	6.10	6.20	6.50	6.70	7.00	▇▅▅▆▃
Sepal.Length	virginica	1	6.79	0.52	6.10	6.40	6.70	7.20	7.90	▇▆▂▃▃
Sepal.Width	versicolor	1	2.99	0.16	2.80	2.90	3.00	3.10	3.30	▇▃▁▃▃
Sepal.Width	virginica	1	3.06	0.28	2.60	2.85	3.00	3.20	3.80	▇▇▇▁▂
Sepal.Area	versicolor	1	19.39	1.58	17.08	18.20	19.14	20.77	22.40	▆▇▃▆▃
Sepal.Area	virginica	1	20.85	2.88	15.86	19.50	20.79	21.68	30.02	▃▇▃▁▁

# my df has 4 variables with 56 observations

Q6. Create iris5 that calculates the average sepal length, the average sepal width, and the sample size of the entire iris4 data frame and print iris5

iris5 <- data.frame(average.sepal.length = mean(iris4$Sepal.Length),
          average.sepal.width = mean(iris4$Sepal.Width), 
          sample.size = nrow(iris4)) 
print(iris5)

##   average.sepal.length average.sepal.width sample.size
## 1             6.698214            3.041071          56

Q7. Finally, create iris6 that calculates the average sepal length, the average sepal width, and the sample size for each species of in the iris4 data frame and print iris6.

iris6 <- iris4 %>%
  group_by(Species) %>%
  summarise(average.sepal.length = mean(iris4$Sepal.Length),
          average.sepal.width = mean(iris4$Sepal.Width), 
          sample.size = n())
print(iris6)

## # A tibble: 2 × 4
##   Species    average.sepal.length average.sepal.width sample.size
##   <fct>                     <dbl>               <dbl>       <int>
## 1 versicolor                 6.70                3.04          17
## 2 virginica                  6.70                3.04          39

Q8. In these exercises, you have successively modified different versions of the data frame iris1 iris2 iris3 iris4 iris5 iris6. At each stage, the output data frame from one operation serves as the input fro the next. A more efficient way to do this is to use the pipe operator %>% from the tidyr package. See if you can rework all of your previous statements (except for iris5) into an extended piping operation that uses iris as the input and generates irisFinal as the output

irisFinal <- iris %>%
  select(Species, Sepal.Length, Sepal.Width) %>%
  group_by(Species) %>%
  filter(Sepal.Length > 6,
         Sepal.Width > 2.5) %>%
   arrange(desc(Sepal.Length)) %>%
  mutate(Sepal.Area = Sepal.Length * Sepal.Width) %>%
  summarise(average.sepal.length = mean(Sepal.Length),
          average.sepal.width = mean(Sepal.Width), 
          sample.size = n())

print(irisFinal)

## # A tibble: 2 × 4
##   Species    average.sepal.length average.sepal.width sample.size
##   <fct>                     <dbl>               <dbl>       <int>
## 1 versicolor                 6.48                2.99          17
## 2 virginica                  6.79                3.06          39

Create a ‘longer’ data frame using the original iris data set with three columns named “Species”, “Measure”, “Value”. The column “Species” will retain the species names of the data set. The column “Measure” will include whether the value corresponds to Sepal.Length, Sepal.Width, Petal.Length, or Petal.Width and the column “Value” will include the numerical values of those measurements.

iris_longer <- iris %>%
  pivot_longer(!c(Species),names_to = "Measure",  values_to = "value")

print(iris_longer)

## # A tibble: 600 × 3
##    Species Measure      value
##    <fct>   <chr>        <dbl>
##  1 setosa  Sepal.Length   5.1
##  2 setosa  Sepal.Width    3.5
##  3 setosa  Petal.Length   1.4
##  4 setosa  Petal.Width    0.2
##  5 setosa  Sepal.Length   4.9
##  6 setosa  Sepal.Width    3  
##  7 setosa  Petal.Length   1.4
##  8 setosa  Petal.Width    0.2
##  9 setosa  Sepal.Length   4.7
## 10 setosa  Sepal.Width    3.2
## # ℹ 590 more rows

homework_seven

Isaac Buabeng

2025-02-28

load-in the necessary libraries

Q1. Read in and Inspect the data

Q2. Create a new data frame iris1 that contains only the species virginica and versicolor with sepal lengths longer than 6 cm and sepal widths longer than 2.5 cm. How many observations and variables are in the data set?

Q3. create a iris2 data frame from iris1 that contains only the columns for Species, Sepal.Length, and Sepal.Width. How many observations and variables are in the data set?

Q4. Create an iris3 data frame from iris2 that orders the observations from largest to smallest sepal length. Show the first 6 rows of this data set.

Q5. Create an iris4 data frame from iris3 that creates a column with a sepal area (length * width) value for each observation. How many observations and variables are in the data set?

Q6. Create iris5 that calculates the average sepal length, the average sepal width, and the sample size of the entire iris4 data frame and print iris5

Q7. Finally, create iris6 that calculates the average sepal length, the average sepal width, and the sample size for each species of in the iris4 data frame and print iris6.