data("iris")There are 150 observations and 5 variables (Sepal.Lenght, Sepal Width, Petal.Length,Petal.Width and species)library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── 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 errorsdata("iris")
print(iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 8 5.0 3.4 1.5 0.2 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## 11 5.4 3.7 1.5 0.2 setosa
## 12 4.8 3.4 1.6 0.2 setosa
## 13 4.8 3.0 1.4 0.1 setosa
## 14 4.3 3.0 1.1 0.1 setosa
## 15 5.8 4.0 1.2 0.2 setosa
## 16 5.7 4.4 1.5 0.4 setosa
## 17 5.4 3.9 1.3 0.4 setosa
## 18 5.1 3.5 1.4 0.3 setosa
## 19 5.7 3.8 1.7 0.3 setosa
## 20 5.1 3.8 1.5 0.3 setosa
## 21 5.4 3.4 1.7 0.2 setosa
## 22 5.1 3.7 1.5 0.4 setosa
## 23 4.6 3.6 1.0 0.2 setosa
## 24 5.1 3.3 1.7 0.5 setosa
## 25 4.8 3.4 1.9 0.2 setosa
## 26 5.0 3.0 1.6 0.2 setosa
## 27 5.0 3.4 1.6 0.4 setosa
## 28 5.2 3.5 1.5 0.2 setosa
## 29 5.2 3.4 1.4 0.2 setosa
## 30 4.7 3.2 1.6 0.2 setosa
## 31 4.8 3.1 1.6 0.2 setosa
## 32 5.4 3.4 1.5 0.4 setosa
## 33 5.2 4.1 1.5 0.1 setosa
## 34 5.5 4.2 1.4 0.2 setosa
## 35 4.9 3.1 1.5 0.2 setosa
## 36 5.0 3.2 1.2 0.2 setosa
## 37 5.5 3.5 1.3 0.2 setosa
## 38 4.9 3.6 1.4 0.1 setosa
## 39 4.4 3.0 1.3 0.2 setosa
## 40 5.1 3.4 1.5 0.2 setosa
## 41 5.0 3.5 1.3 0.3 setosa
## 42 4.5 2.3 1.3 0.3 setosa
## 43 4.4 3.2 1.3 0.2 setosa
## 44 5.0 3.5 1.6 0.6 setosa
## 45 5.1 3.8 1.9 0.4 setosa
## 46 4.8 3.0 1.4 0.3 setosa
## 47 5.1 3.8 1.6 0.2 setosa
## 48 4.6 3.2 1.4 0.2 setosa
## 49 5.3 3.7 1.5 0.2 setosa
## 50 5.0 3.3 1.4 0.2 setosa
## 51 7.0 3.2 4.7 1.4 versicolor
## 52 6.4 3.2 4.5 1.5 versicolor
## 53 6.9 3.1 4.9 1.5 versicolor
## 54 5.5 2.3 4.0 1.3 versicolor
## 55 6.5 2.8 4.6 1.5 versicolor
## 56 5.7 2.8 4.5 1.3 versicolor
## 57 6.3 3.3 4.7 1.6 versicolor
## 58 4.9 2.4 3.3 1.0 versicolor
## 59 6.6 2.9 4.6 1.3 versicolor
## 60 5.2 2.7 3.9 1.4 versicolor
## 61 5.0 2.0 3.5 1.0 versicolor
## 62 5.9 3.0 4.2 1.5 versicolor
## 63 6.0 2.2 4.0 1.0 versicolor
## 64 6.1 2.9 4.7 1.4 versicolor
## 65 5.6 2.9 3.6 1.3 versicolor
## 66 6.7 3.1 4.4 1.4 versicolor
## 67 5.6 3.0 4.5 1.5 versicolor
## 68 5.8 2.7 4.1 1.0 versicolor
## 69 6.2 2.2 4.5 1.5 versicolor
## 70 5.6 2.5 3.9 1.1 versicolor
## 71 5.9 3.2 4.8 1.8 versicolor
## 72 6.1 2.8 4.0 1.3 versicolor
## 73 6.3 2.5 4.9 1.5 versicolor
## 74 6.1 2.8 4.7 1.2 versicolor
## 75 6.4 2.9 4.3 1.3 versicolor
## 76 6.6 3.0 4.4 1.4 versicolor
## 77 6.8 2.8 4.8 1.4 versicolor
## 78 6.7 3.0 5.0 1.7 versicolor
## 79 6.0 2.9 4.5 1.5 versicolor
## 80 5.7 2.6 3.5 1.0 versicolor
## 81 5.5 2.4 3.8 1.1 versicolor
## 82 5.5 2.4 3.7 1.0 versicolor
## 83 5.8 2.7 3.9 1.2 versicolor
## 84 6.0 2.7 5.1 1.6 versicolor
## 85 5.4 3.0 4.5 1.5 versicolor
## 86 6.0 3.4 4.5 1.6 versicolor
## 87 6.7 3.1 4.7 1.5 versicolor
## 88 6.3 2.3 4.4 1.3 versicolor
## 89 5.6 3.0 4.1 1.3 versicolor
## 90 5.5 2.5 4.0 1.3 versicolor
## 91 5.5 2.6 4.4 1.2 versicolor
## 92 6.1 3.0 4.6 1.4 versicolor
## 93 5.8 2.6 4.0 1.2 versicolor
## 94 5.0 2.3 3.3 1.0 versicolor
## 95 5.6 2.7 4.2 1.3 versicolor
## 96 5.7 3.0 4.2 1.2 versicolor
## 97 5.7 2.9 4.2 1.3 versicolor
## 98 6.2 2.9 4.3 1.3 versicolor
## 99 5.1 2.5 3.0 1.1 versicolor
## 100 5.7 2.8 4.1 1.3 versicolor
## 101 6.3 3.3 6.0 2.5 virginica
## 102 5.8 2.7 5.1 1.9 virginica
## 103 7.1 3.0 5.9 2.1 virginica
## 104 6.3 2.9 5.6 1.8 virginica
## 105 6.5 3.0 5.8 2.2 virginica
## 106 7.6 3.0 6.6 2.1 virginica
## 107 4.9 2.5 4.5 1.7 virginica
## 108 7.3 2.9 6.3 1.8 virginica
## 109 6.7 2.5 5.8 1.8 virginica
## 110 7.2 3.6 6.1 2.5 virginica
## 111 6.5 3.2 5.1 2.0 virginica
## 112 6.4 2.7 5.3 1.9 virginica
## 113 6.8 3.0 5.5 2.1 virginica
## 114 5.7 2.5 5.0 2.0 virginica
## 115 5.8 2.8 5.1 2.4 virginica
## 116 6.4 3.2 5.3 2.3 virginica
## 117 6.5 3.0 5.5 1.8 virginica
## 118 7.7 3.8 6.7 2.2 virginica
## 119 7.7 2.6 6.9 2.3 virginica
## 120 6.0 2.2 5.0 1.5 virginica
## 121 6.9 3.2 5.7 2.3 virginica
## 122 5.6 2.8 4.9 2.0 virginica
## 123 7.7 2.8 6.7 2.0 virginica
## 124 6.3 2.7 4.9 1.8 virginica
## 125 6.7 3.3 5.7 2.1 virginica
## 126 7.2 3.2 6.0 1.8 virginica
## 127 6.2 2.8 4.8 1.8 virginica
## 128 6.1 3.0 4.9 1.8 virginica
## 129 6.4 2.8 5.6 2.1 virginica
## 130 7.2 3.0 5.8 1.6 virginica
## 131 7.4 2.8 6.1 1.9 virginica
## 132 7.9 3.8 6.4 2.0 virginica
## 133 6.4 2.8 5.6 2.2 virginica
## 134 6.3 2.8 5.1 1.5 virginica
## 135 6.1 2.6 5.6 1.4 virginica
## 136 7.7 3.0 6.1 2.3 virginica
## 137 6.3 3.4 5.6 2.4 virginica
## 138 6.4 3.1 5.5 1.8 virginica
## 139 6.0 3.0 4.8 1.8 virginica
## 140 6.9 3.1 5.4 2.1 virginica
## 141 6.7 3.1 5.6 2.4 virginica
## 142 6.9 3.1 5.1 2.3 virginica
## 143 5.8 2.7 5.1 1.9 virginica
## 144 6.8 3.2 5.9 2.3 virginica
## 145 6.7 3.3 5.7 2.5 virginica
## 146 6.7 3.0 5.2 2.3 virginica
## 147 6.3 2.5 5.0 1.9 virginica
## 148 6.5 3.0 5.2 2.0 virginica
## 149 6.2 3.4 5.4 2.3 virginica
## 150 5.9 3.0 5.1 1.8 virginica56 observations with 5 variableslibrary(tidyverse)
data("iris")
class(iris)## [1] "data.frame"iris1<-filter(iris, Species != "setosa", Sepal.Length > 6, Sepal.Width > 2.5)
print(iris1)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 7.0 3.2 4.7 1.4 versicolor
## 2 6.4 3.2 4.5 1.5 versicolor
## 3 6.9 3.1 4.9 1.5 versicolor
## 4 6.5 2.8 4.6 1.5 versicolor
## 5 6.3 3.3 4.7 1.6 versicolor
## 6 6.6 2.9 4.6 1.3 versicolor
## 7 6.1 2.9 4.7 1.4 versicolor
## 8 6.7 3.1 4.4 1.4 versicolor
## 9 6.1 2.8 4.0 1.3 versicolor
## 10 6.1 2.8 4.7 1.2 versicolor
## 11 6.4 2.9 4.3 1.3 versicolor
## 12 6.6 3.0 4.4 1.4 versicolor
## 13 6.8 2.8 4.8 1.4 versicolor
## 14 6.7 3.0 5.0 1.7 versicolor
## 15 6.7 3.1 4.7 1.5 versicolor
## 16 6.1 3.0 4.6 1.4 versicolor
## 17 6.2 2.9 4.3 1.3 versicolor
## 18 6.3 3.3 6.0 2.5 virginica
## 19 7.1 3.0 5.9 2.1 virginica
## 20 6.3 2.9 5.6 1.8 virginica
## 21 6.5 3.0 5.8 2.2 virginica
## 22 7.6 3.0 6.6 2.1 virginica
## 23 7.3 2.9 6.3 1.8 virginica
## 24 7.2 3.6 6.1 2.5 virginica
## 25 6.5 3.2 5.1 2.0 virginica
## 26 6.4 2.7 5.3 1.9 virginica
## 27 6.8 3.0 5.5 2.1 virginica
## 28 6.4 3.2 5.3 2.3 virginica
## 29 6.5 3.0 5.5 1.8 virginica
## 30 7.7 3.8 6.7 2.2 virginica
## 31 7.7 2.6 6.9 2.3 virginica
## 32 6.9 3.2 5.7 2.3 virginica
## 33 7.7 2.8 6.7 2.0 virginica
## 34 6.3 2.7 4.9 1.8 virginica
## 35 6.7 3.3 5.7 2.1 virginica
## 36 7.2 3.2 6.0 1.8 virginica
## 37 6.2 2.8 4.8 1.8 virginica
## 38 6.1 3.0 4.9 1.8 virginica
## 39 6.4 2.8 5.6 2.1 virginica
## 40 7.2 3.0 5.8 1.6 virginica
## 41 7.4 2.8 6.1 1.9 virginica
## 42 7.9 3.8 6.4 2.0 virginica
## 43 6.4 2.8 5.6 2.2 virginica
## 44 6.3 2.8 5.1 1.5 virginica
## 45 6.1 2.6 5.6 1.4 virginica
## 46 7.7 3.0 6.1 2.3 virginica
## 47 6.3 3.4 5.6 2.4 virginica
## 48 6.4 3.1 5.5 1.8 virginica
## 49 6.9 3.1 5.4 2.1 virginica
## 50 6.7 3.1 5.6 2.4 virginica
## 51 6.9 3.1 5.1 2.3 virginica
## 52 6.8 3.2 5.9 2.3 virginica
## 53 6.7 3.3 5.7 2.5 virginica
## 54 6.7 3.0 5.2 2.3 virginica
## 55 6.5 3.0 5.2 2.0 virginica
## 56 6.2 3.4 5.4 2.3 virginica#3. Now, 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?
56 observations with 3 variablesiris2<-select(iris1, Sepal.Length, Sepal.Width, Species)
print(iris2)## Sepal.Length Sepal.Width Species
## 1 7.0 3.2 versicolor
## 2 6.4 3.2 versicolor
## 3 6.9 3.1 versicolor
## 4 6.5 2.8 versicolor
## 5 6.3 3.3 versicolor
## 6 6.6 2.9 versicolor
## 7 6.1 2.9 versicolor
## 8 6.7 3.1 versicolor
## 9 6.1 2.8 versicolor
## 10 6.1 2.8 versicolor
## 11 6.4 2.9 versicolor
## 12 6.6 3.0 versicolor
## 13 6.8 2.8 versicolor
## 14 6.7 3.0 versicolor
## 15 6.7 3.1 versicolor
## 16 6.1 3.0 versicolor
## 17 6.2 2.9 versicolor
## 18 6.3 3.3 virginica
## 19 7.1 3.0 virginica
## 20 6.3 2.9 virginica
## 21 6.5 3.0 virginica
## 22 7.6 3.0 virginica
## 23 7.3 2.9 virginica
## 24 7.2 3.6 virginica
## 25 6.5 3.2 virginica
## 26 6.4 2.7 virginica
## 27 6.8 3.0 virginica
## 28 6.4 3.2 virginica
## 29 6.5 3.0 virginica
## 30 7.7 3.8 virginica
## 31 7.7 2.6 virginica
## 32 6.9 3.2 virginica
## 33 7.7 2.8 virginica
## 34 6.3 2.7 virginica
## 35 6.7 3.3 virginica
## 36 7.2 3.2 virginica
## 37 6.2 2.8 virginica
## 38 6.1 3.0 virginica
## 39 6.4 2.8 virginica
## 40 7.2 3.0 virginica
## 41 7.4 2.8 virginica
## 42 7.9 3.8 virginica
## 43 6.4 2.8 virginica
## 44 6.3 2.8 virginica
## 45 6.1 2.6 virginica
## 46 7.7 3.0 virginica
## 47 6.3 3.4 virginica
## 48 6.4 3.1 virginica
## 49 6.9 3.1 virginica
## 50 6.7 3.1 virginica
## 51 6.9 3.1 virginica
## 52 6.8 3.2 virginica
## 53 6.7 3.3 virginica
## 54 6.7 3.0 virginica
## 55 6.5 3.0 virginica
## 56 6.2 3.4 virginica#4. 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<-arrange(iris2, by = desc(Sepal.Length))
head(iris3)## Sepal.Length Sepal.Width Species
## 1 7.9 3.8 virginica
## 2 7.7 3.8 virginica
## 3 7.7 2.6 virginica
## 4 7.7 2.8 virginica
## 5 7.7 3.0 virginica
## 6 7.6 3.0 virginica#5. 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?
56 variables and 4 variables iris4<-mutate(iris3, Ratio = Sepal.Length*Sepal.Width)
print(iris4)## Sepal.Length Sepal.Width Species Ratio
## 1 7.9 3.8 virginica 30.02
## 2 7.7 3.8 virginica 29.26
## 3 7.7 2.6 virginica 20.02
## 4 7.7 2.8 virginica 21.56
## 5 7.7 3.0 virginica 23.10
## 6 7.6 3.0 virginica 22.80
## 7 7.4 2.8 virginica 20.72
## 8 7.3 2.9 virginica 21.17
## 9 7.2 3.6 virginica 25.92
## 10 7.2 3.2 virginica 23.04
## 11 7.2 3.0 virginica 21.60
## 12 7.1 3.0 virginica 21.30
## 13 7.0 3.2 versicolor 22.40
## 14 6.9 3.1 versicolor 21.39
## 15 6.9 3.2 virginica 22.08
## 16 6.9 3.1 virginica 21.39
## 17 6.9 3.1 virginica 21.39
## 18 6.8 2.8 versicolor 19.04
## 19 6.8 3.0 virginica 20.40
## 20 6.8 3.2 virginica 21.76
## 21 6.7 3.1 versicolor 20.77
## 22 6.7 3.0 versicolor 20.10
## 23 6.7 3.1 versicolor 20.77
## 24 6.7 3.3 virginica 22.11
## 25 6.7 3.1 virginica 20.77
## 26 6.7 3.3 virginica 22.11
## 27 6.7 3.0 virginica 20.10
## 28 6.6 2.9 versicolor 19.14
## 29 6.6 3.0 versicolor 19.80
## 30 6.5 2.8 versicolor 18.20
## 31 6.5 3.0 virginica 19.50
## 32 6.5 3.2 virginica 20.80
## 33 6.5 3.0 virginica 19.50
## 34 6.5 3.0 virginica 19.50
## 35 6.4 3.2 versicolor 20.48
## 36 6.4 2.9 versicolor 18.56
## 37 6.4 2.7 virginica 17.28
## 38 6.4 3.2 virginica 20.48
## 39 6.4 2.8 virginica 17.92
## 40 6.4 2.8 virginica 17.92
## 41 6.4 3.1 virginica 19.84
## 42 6.3 3.3 versicolor 20.79
## 43 6.3 3.3 virginica 20.79
## 44 6.3 2.9 virginica 18.27
## 45 6.3 2.7 virginica 17.01
## 46 6.3 2.8 virginica 17.64
## 47 6.3 3.4 virginica 21.42
## 48 6.2 2.9 versicolor 17.98
## 49 6.2 2.8 virginica 17.36
## 50 6.2 3.4 virginica 21.08
## 51 6.1 2.9 versicolor 17.69
## 52 6.1 2.8 versicolor 17.08
## 53 6.1 2.8 versicolor 17.08
## 54 6.1 3.0 versicolor 18.30
## 55 6.1 3.0 virginica 18.30
## 56 6.1 2.6 virginica 15.86#6. 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<-summarize(iris4, Sepal_average_Length = mean(Sepal.Length), Sepal_average_Width = mean(Sepal.Width),Sample_Size = n())
print(iris5)## Sepal_average_Length Sepal_average_Width Sample_Size
## 1 6.698214 3.041071 56#7. 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<-group_by(iris4, Species)
iris6<-summarize(iris6, Sepal_average_Length = mean(Sepal.Length), Sepal_average_Width = mean(Sepal.Width),Sample_Size = n())
print(iris6)## # A tibble: 2 × 4
## Species Sepal_average_Length Sepal_average_Width Sample_Size
## <fct> <dbl> <dbl> <int>
## 1 versicolor 6.48 2.99 17
## 2 virginica 6.79 3.06 39#8. 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<-filter(iris,Species != "setosa", Sepal.Length > 6, Sepal.Width > 2.5) %>%
group_by(Species) %>%
summarize(Sepal_average_Length = mean(Sepal.Length), Sepal_average_Width = mean(Sepal.Width),Sample_Size = n())
print(irisFinal)## # A tibble: 2 × 4
## Species Sepal_average_Length Sepal_average_Width Sample_Size
## <fct> <dbl> <dbl> <int>
## 1 versicolor 6.48 2.99 17
## 2 virginica 6.79 3.06 39#9. 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 %>%
pivot_longer(cols=Sepal.Length:Sepal.Width:Petal.Length:Petal.Width,
names_to = "Measure",
values_to= "Value")## Warning in x:y: numerical expression has 2 elements: only the first used## Warning in x:y: numerical expression has 3 elements: only the first used## # 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