dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")
P <- sum(is.na(dirty_iris$Petal.Length))complete_cases <- complete.cases(dirty_iris)
sum(complete_cases)## [1] 96mean(complete_cases)## [1] 0.64summary(dirty_iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width
## Min. : 0.000 Min. :-3.000 Min. : 0.00 Min. :0.1
## 1st Qu.: 5.100 1st Qu.: 2.800 1st Qu.: 1.60 1st Qu.:0.3
## Median : 5.750 Median : 3.000 Median : 4.50 Median :1.3
## Mean : 6.559 Mean : 3.391 Mean : 4.45 Mean :Inf
## 3rd Qu.: 6.400 3rd Qu.: 3.300 3rd Qu.: 5.10 3rd Qu.:1.8
## Max. :73.000 Max. :30.000 Max. :63.00 Max. :Inf
## NA's :10 NA's :17 NA's :19 NA's :12
## Species
## Length:150
## Class :character
## Mode :character
##
##
##
## dirty_iris[dirty_iris == Inf] <- NA
print(dirty_iris)## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 6.4 3.2 4.500 1.5 versicolor
## 2 6.3 3.3 6.000 2.5 virginica
## 3 6.2 NA 5.400 2.3 virginica
## 4 5.0 3.4 1.600 0.4 setosa
## 5 5.7 2.6 3.500 1.0 versicolor
## 6 5.3 NA NA 0.2 setosa
## 7 6.4 2.7 5.300 NA virginica
## 8 5.9 3.0 5.100 1.8 virginica
## 9 5.8 2.7 4.100 1.0 versicolor
## 10 4.8 3.1 1.600 0.2 setosa
## 11 5.0 3.5 1.600 0.6 setosa
## 12 6.0 2.7 5.100 1.6 versicolor
## 13 6.0 3.0 4.800 NA virginica
## 14 6.8 2.8 4.800 1.4 versicolor
## 15 NA 3.9 1.700 0.4 setosa
## 16 5.0 -3.0 3.500 1.0 versicolor
## 17 5.5 NA 4.000 1.3 versicolor
## 18 4.7 3.2 1.300 0.2 setosa
## 19 NA 4.0 NA 0.2 setosa
## 20 5.6 NA 4.200 1.3 versicolor
## 21 4.9 3.6 NA 0.1 setosa
## 22 5.4 NA 4.500 1.5 versicolor
## 23 6.2 2.8 NA 1.8 virginica
## 24 6.7 3.3 5.700 2.5 virginica
## 25 NA 3.0 5.900 2.1 virginica
## 26 4.6 3.2 1.400 0.2 setosa
## 27 4.9 3.1 1.500 0.1 setosa
## 28 73.0 29.0 63.000 NA virginica
## 29 6.5 3.2 5.100 2.0 virginica
## 30 NA 2.8 0.820 1.3 versicolor
## 31 4.4 3.2 NA 0.2 setosa
## 32 5.9 3.2 4.800 NA versicolor
## 33 5.7 2.8 4.500 1.3 versicolor
## 34 6.2 2.9 NA 1.3 versicolor
## 35 6.6 2.9 23.000 1.3 versicolor
## 36 4.8 3.0 1.400 0.1 setosa
## 37 6.5 3.0 5.500 1.8 virginica
## 38 6.2 2.2 4.500 1.5 versicolor
## 39 6.7 2.5 5.800 1.8 virginica
## 40 5.0 3.0 1.600 0.2 setosa
## 41 5.0 NA 1.200 0.2 setosa
## 42 5.8 2.7 3.900 1.2 versicolor
## 43 0.0 NA 1.300 0.4 setosa
## 44 5.8 2.7 5.100 1.9 virginica
## 45 5.5 4.2 1.400 0.2 setosa
## 46 7.7 2.8 6.700 2.0 virginica
## 47 5.7 NA NA 0.4 setosa
## 48 7.0 3.2 4.700 1.4 versicolor
## 49 6.5 3.0 5.800 2.2 virginica
## 50 6.0 3.4 4.500 1.6 versicolor
## 51 5.5 2.6 4.400 1.2 versicolor
## 52 4.9 3.1 NA 0.2 setosa
## 53 5.2 2.7 3.900 1.4 versicolor
## 54 4.8 3.4 1.600 0.2 setosa
## 55 6.3 3.3 4.700 1.6 versicolor
## 56 7.7 3.8 6.700 2.2 virginica
## 57 5.1 3.8 1.500 0.3 setosa
## 58 NA 2.9 4.500 1.5 versicolor
## 59 6.4 2.8 5.600 NA virginica
## 60 6.4 2.8 5.600 2.1 virginica
## 61 5.0 2.3 3.300 NA versicolor
## 62 7.4 2.8 6.100 1.9 virginica
## 63 4.3 3.0 1.100 0.1 setosa
## 64 5.0 3.3 1.400 0.2 setosa
## 65 7.2 3.0 5.800 1.6 virginica
## 66 6.3 2.5 4.900 1.5 versicolor
## 67 5.1 2.5 NA 1.1 versicolor
## 68 NA 3.2 5.700 2.3 virginica
## 69 5.1 3.5 NA NA setosa
## 70 5.0 3.5 1.300 0.3 setosa
## 71 6.1 3.0 4.600 1.4 versicolor
## 72 6.9 3.1 5.100 2.3 virginica
## 73 5.1 3.5 1.400 0.3 setosa
## 74 6.5 NA 4.600 1.5 versicolor
## 75 5.6 2.8 4.900 2.0 virginica
## 76 4.9 2.5 4.500 NA virginica
## 77 5.5 3.5 1.300 0.2 setosa
## 78 7.6 3.0 6.600 2.1 virginica
## 79 5.1 3.8 0.000 0.2 setosa
## 80 7.9 3.8 6.400 2.0 virginica
## 81 6.1 2.6 5.600 1.4 virginica
## 82 5.4 3.4 1.700 0.2 setosa
## 83 6.1 2.9 4.700 1.4 versicolor
## 84 5.4 3.7 1.500 0.2 setosa
## 85 6.7 3.0 5.200 2.3 virginica
## 86 5.1 3.8 1.900 NA setosa
## 87 6.4 2.9 4.300 1.3 versicolor
## 88 5.7 2.9 4.200 1.3 versicolor
## 89 4.4 2.9 1.400 0.2 setosa
## 90 6.3 2.5 5.000 1.9 virginica
## 91 7.2 3.2 6.000 1.8 virginica
## 92 4.9 NA 3.300 1.0 versicolor
## 93 5.2 3.4 1.400 0.2 setosa
## 94 5.8 2.7 5.100 1.9 virginica
## 95 6.0 2.2 5.000 1.5 virginica
## 96 6.9 3.1 NA 1.5 versicolor
## 97 5.5 2.3 4.000 1.3 versicolor
## 98 6.7 NA 5.000 1.7 versicolor
## 99 5.7 3.0 4.200 1.2 versicolor
## 100 6.3 2.8 5.100 1.5 virginica
## 101 5.4 3.4 1.500 0.4 setosa
## 102 7.2 3.6 NA 2.5 virginica
## 103 6.3 2.7 4.900 NA virginica
## 104 5.6 3.0 4.100 1.3 versicolor
## 105 5.1 3.7 NA 0.4 setosa
## 106 5.5 NA 0.925 1.0 versicolor
## 107 6.5 3.0 5.200 2.0 virginica
## 108 4.8 3.0 1.400 NA setosa
## 109 6.1 2.8 NA 1.3 versicolor
## 110 4.6 3.4 1.400 0.3 setosa
## 111 6.3 3.4 NA 2.4 virginica
## 112 5.0 3.4 1.500 0.2 setosa
## 113 5.1 3.4 1.500 0.2 setosa
## 114 NA 3.3 5.700 2.1 virginica
## 115 6.7 3.1 4.700 1.5 versicolor
## 116 7.7 2.6 6.900 2.3 virginica
## 117 6.3 NA 4.400 1.3 versicolor
## 118 4.6 3.1 1.500 0.2 setosa
## 119 NA 3.0 5.500 2.1 virginica
## 120 NA 2.8 4.700 1.2 versicolor
## 121 5.9 3.0 NA 1.5 versicolor
## 122 4.5 2.3 1.300 0.3 setosa
## 123 6.4 3.2 5.300 2.3 virginica
## 124 5.2 4.1 1.500 0.1 setosa
## 125 49.0 30.0 14.000 2.0 setosa
## 126 5.6 2.9 3.600 1.3 versicolor
## 127 6.8 3.2 5.900 2.3 virginica
## 128 5.8 NA 5.100 2.4 virginica
## 129 4.6 3.6 NA 0.2 setosa
## 130 5.7 0.0 1.700 0.3 setosa
## 131 5.6 2.5 3.900 1.1 versicolor
## 132 6.7 3.1 4.400 1.4 versicolor
## 133 4.8 NA 1.900 0.2 setosa
## 134 5.1 3.3 1.700 0.5 setosa
## 135 4.4 3.0 1.300 NA setosa
## 136 7.7 3.0 NA 2.3 virginica
## 137 4.7 3.2 1.600 0.2 setosa
## 138 NA 3.0 4.900 1.8 virginica
## 139 6.9 3.1 5.400 2.1 virginica
## 140 6.0 2.2 4.000 1.0 versicolor
## 141 5.0 NA 1.400 0.2 setosa
## 142 5.5 NA 3.800 1.1 versicolor
## 143 6.6 3.0 4.400 1.4 versicolor
## 144 6.3 2.9 5.600 1.8 virginica
## 145 5.7 2.5 5.000 2.0 virginica
## 146 6.7 3.1 5.600 2.4 virginica
## 147 5.6 3.0 4.500 1.5 versicolor
## 148 5.2 3.5 1.500 0.2 setosa
## 149 6.4 3.1 NA 1.8 virginica
## 150 5.8 2.6 4.000 NA versicolorviolation <- subset(dirty_iris, (Sepal.Width <= 0) | (Sepal.Length > 30))
num_violations <- nrow (violation)#Question 6
violation_width <- subset(dirty_iris, (Sepal.Width > 0))
num_violations <- nrow(violation_width)#Question 7
iris$Sepal.Width[is.na(iris$Sepal.Width)] <- mean(iris$Sepal.Width, na.rm = TRUE)
iris$Petal.Length[is.na(iris$Petal.Length)] <- median(iris$Petal.Length, na.rm = TRUE)
lm_model <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width, data = iris)
iris$Sepal.Length[is.na(iris$Sepal.Length)] <- predict(lm_model, newdata = iris[is.na(iris$Sepal.Length), ])