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 virginica
question 3
dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")
sum(is.na(dirty_iris$Petal.Length))
## [1] 19
question 4: to determine number of observations & percentage
that are complete
# sum(complete.cases(dirty_iris))
# (num_complete_obs/nrow(dirty_iris)) * 100
question 5: Still based on the dirty_iris data, besides missing
values, is there an another type of special values containing in the
numeric columns? Choose the one you found.
sapply(dirty_iris[,1:4], function(x) sum(is.infinite(x)))
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 0 0 0 1
question 6: Write R code to locate the above identified special
value and replace them with a missing value placeholder.
dirty_iris[,1:4][is.infinite(as.matrix(dirty_iris[,1:4]))] <- NA
sapply(dirty_iris[,1:4], function(x) sum(is.infinite(x)))
## Sepal.Length Sepal.Width Petal.Length Petal.Width
## 0 0 0 0
question 7: Write R code to find out the observations that violate
these rules. How many observations violate the above rules?
dirty_iris$Sepal.Width <= 0
## [1] FALSE FALSE NA FALSE FALSE NA FALSE FALSE FALSE FALSE FALSE FALSE
## [13] FALSE FALSE FALSE TRUE NA FALSE FALSE NA FALSE NA FALSE FALSE
## [25] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [37] FALSE FALSE FALSE FALSE NA FALSE NA FALSE FALSE FALSE NA FALSE
## [49] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [73] FALSE NA FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [85] FALSE FALSE FALSE FALSE FALSE FALSE FALSE NA FALSE FALSE FALSE FALSE
## [97] FALSE NA FALSE FALSE FALSE FALSE FALSE FALSE FALSE NA FALSE FALSE
## [109] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE NA FALSE FALSE FALSE
## [121] FALSE FALSE FALSE FALSE FALSE FALSE FALSE NA FALSE TRUE FALSE FALSE
## [133] NA FALSE FALSE FALSE FALSE FALSE FALSE FALSE NA NA FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE
dirty_iris$Sepal.Length > 30
## [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [13] FALSE FALSE NA FALSE FALSE FALSE NA FALSE FALSE FALSE FALSE FALSE
## [25] NA FALSE FALSE TRUE FALSE NA FALSE FALSE FALSE FALSE FALSE FALSE
## [37] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [49] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE NA FALSE FALSE
## [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE NA FALSE FALSE FALSE FALSE
## [73] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [85] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [97] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [109] FALSE FALSE FALSE FALSE FALSE NA FALSE FALSE FALSE FALSE NA NA
## [121] FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [133] FALSE FALSE FALSE FALSE FALSE NA FALSE FALSE FALSE FALSE FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE
# violations <- dirty_iris[rule1_violation | rule2_violation, ]
violations <- dirty_iris[dirty_iris$Sepal.Width <= 0 | dirty_iris$Sepal.Length > 30, ]
violations
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## NA NA NA NA NA <NA>
## NA.1 NA NA NA NA <NA>
## NA.2 NA NA NA NA <NA>
## 16 5.0 -3 3.5 1.0 versicolor
## NA.3 NA NA NA NA <NA>
## NA.4 NA NA NA NA <NA>
## NA.5 NA NA NA NA <NA>
## NA.6 NA NA NA NA <NA>
## NA.7 NA NA NA NA <NA>
## 28 73.0 29 63.0 NA virginica
## NA.8 NA NA NA NA <NA>
## NA.9 NA NA NA NA <NA>
## NA.10 NA NA NA NA <NA>
## NA.11 NA NA NA NA <NA>
## NA.12 NA NA NA NA <NA>
## NA.13 NA NA NA NA <NA>
## NA.14 NA NA NA NA <NA>
## NA.15 NA NA NA NA <NA>
## NA.16 NA NA NA NA <NA>
## NA.17 NA NA NA NA <NA>
## NA.18 NA NA NA NA <NA>
## NA.19 NA NA NA NA <NA>
## NA.20 NA NA NA NA <NA>
## NA.21 NA NA NA NA <NA>
## 125 49.0 30 14.0 2.0 setosa
## NA.22 NA NA NA NA <NA>
## 130 5.7 0 1.7 0.3 setosa
## NA.23 NA NA NA NA <NA>
## NA.24 NA NA NA NA <NA>
## NA.25 NA NA NA NA <NA>
## NA.26 NA NA NA NA <NA>
which(dirty_iris$Sepal.Width <= 0 | dirty_iris$Sepal.Length > 30)
## [1] 16 28 125 130
question 8: Write R code to achieve the error correction task
which(dirty_iris$Sepal.Width <= 0)
## [1] 16 130
dirty_iris_fixed <- dirty_iris
neg_idx <- which(dirty_iris_fixed$Sepal.Width < 0)
dirty_iris_fixed$Sepal.Width[neg_idx] <- abs(dirty_iris_fixed$Sepal.Width[neg_idx])
zero_idx <- which(dirty_iris_fixed$Sepal.Width == 0)
dirty_iris_fixed$Sepal.Width[zero_idx] <- NA
dirty_iris_fixed$Sepal.Width[c(neg_idx, zero_idx)]
## [1] 3 NA
which(dirty_iris_fixed$Sepal.Width <= 0)
## integer(0)
question 9: Write the R code to do the imputation as specified
above. Mark the ones if your attached R code could achieve the
task.
# install.packages("VIM")
library(VIM)
## Loading required package: colorspace
## Loading required package: grid
## VIM is ready to use.
## Suggestions and bug-reports can be submitted at: https://github.com/statistikat/VIM/issues
##
## Attaching package: 'VIM'
## The following object is masked from 'package:datasets':
##
## sleep
dirty_iris_imputed <- kNN(dirty_iris_fixed, variable = "Petal.Width", k = 5)
## Sepal.Length Sepal.Width Petal.Length Sepal.Length Sepal.Width Petal.Length
## 0.0 2.2 0.0 73.0 30.0 63.0
sum(is.na(dirty_iris_imputed$Petal.Width))
## [1] 0
# Sepal.Width → mean
mean_val <- mean(dirty_iris_fixed$Sepal.Width, na.rm = TRUE)
dirty_iris_fixed$Sepal.Width[is.na(dirty_iris_fixed$Sepal.Width)] <- mean_val
# Petal.Length → median
median_val <- median(dirty_iris_fixed$Petal.Length, na.rm = TRUE)
dirty_iris_fixed$Petal.Length[is.na(dirty_iris_fixed$Petal.Length)] <- median_val
# Sepal.Length → regression
reg_model <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width,
data = dirty_iris_fixed, na.action = na.exclude)
missing_idx <- which(is.na(dirty_iris_fixed$Sepal.Length))
dirty_iris_fixed$Sepal.Length[missing_idx] <- predict(reg_model, dirty_iris_fixed[missing_idx, ])
# Petal.Width → kNN (using VIM)
library(VIM)
dirty_iris_imputed <- kNN(dirty_iris_fixed, variable = "Petal.Width", k = 5)
## Sepal.Length Sepal.Width Petal.Length Sepal.Length Sepal.Width Petal.Length
## 0.0 2.2 0.0 73.0 30.0 63.0
# Check missing values after all imputations
colSums(is.na(dirty_iris_imputed))
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 0 0 0 0 0
## Petal.Width_imp
## 0