dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")
sum(is.na(dirty_iris$Petal.Length))
## [1] 19
num_complete <- sum(complete.cases(dirty_iris))
total_rows <- nrow(dirty_iris)
percent_complete <- (num_complete / total_rows) * 100
unique(dirty_iris$Sepal.Length)
## [1] 6.4 6.3 6.2 5.0 5.7 5.3 5.9 5.8 4.8 6.0 6.8 NA 5.5 4.7 5.6
## [16] 4.9 5.4 6.7 4.6 73.0 6.5 4.4 6.6 0.0 7.7 7.0 5.2 5.1 7.4 4.3
## [31] 7.2 6.1 6.9 7.6 7.9 4.5 49.0
unique(dirty_iris$Sepal.Width)
## [1] 3.2 3.3 NA 3.4 2.6 2.7 3.0 3.1 3.5 2.8 3.9 -3.0 4.0 3.6 29.0
## [16] 2.9 2.2 2.5 4.2 3.8 2.3 3.7 4.1 30.0 0.0
unique(dirty_iris$Petal.Length)
## [1] 4.500 6.000 5.400 1.600 3.500 NA 5.300 5.100 4.100 4.800
## [11] 1.700 4.000 1.300 4.200 5.700 5.900 1.400 1.500 63.000 0.820
## [21] 23.000 5.500 5.800 1.200 3.900 6.700 4.700 4.400 5.600 3.300
## [31] 6.100 1.100 4.900 4.600 6.600 0.000 6.400 5.200 1.900 4.300
## [41] 5.000 0.925 6.900 14.000 3.600 3.800
unique(dirty_iris$Petal.Width)
## [1] 1.5 2.5 2.3 0.4 1.0 0.2 NA 1.8 0.6 1.6 1.4 1.3 0.1 2.1 2.0 1.2 1.9 2.2 0.3
## [20] 1.1 Inf 1.7 2.4 0.5
dirty_iris[] <- lapply(dirty_iris, function(x) {
if (is.numeric(x)) {
x[is.nan(x)] <- NA
}
return(x)
})
sapply(dirty_iris, function(x) sum(is.nan(x)))
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 0 0 0 0 0
violations <- dirty_iris[
(dirty_iris$Sepal.Width <= 0 | is.na(dirty_iris$Sepal.Width)) |
(dirty_iris$Sepal.Length > 30),
]
violations
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 3 6.2 NA 5.400 2.3 virginica
## 6 5.3 NA NA 0.2 setosa
## NA NA NA NA NA <NA>
## 16 5.0 -3 3.500 1.0 versicolor
## 17 5.5 NA 4.000 1.3 versicolor
## NA.1 NA NA NA NA <NA>
## 20 5.6 NA 4.200 1.3 versicolor
## 22 5.4 NA 4.500 1.5 versicolor
## NA.2 NA NA NA NA <NA>
## 28 73.0 29 63.000 NA virginica
## NA.3 NA NA NA NA <NA>
## 41 5.0 NA 1.200 0.2 setosa
## 43 0.0 NA 1.300 0.4 setosa
## 47 5.7 NA NA 0.4 setosa
## NA.4 NA NA NA NA <NA>
## NA.5 NA NA NA NA <NA>
## 74 6.5 NA 4.600 1.5 versicolor
## 92 4.9 NA 3.300 1.0 versicolor
## 98 6.7 NA 5.000 1.7 versicolor
## 106 5.5 NA 0.925 1.0 versicolor
## NA.6 NA NA NA NA <NA>
## 117 6.3 NA 4.400 1.3 versicolor
## NA.7 NA NA NA NA <NA>
## NA.8 NA NA NA NA <NA>
## 125 49.0 30 14.000 2.0 setosa
## 128 5.8 NA 5.100 2.4 virginica
## 130 5.7 0 1.700 0.3 setosa
## 133 4.8 NA 1.900 0.2 setosa
## NA.9 NA NA NA NA <NA>
## 141 5.0 NA 1.400 0.2 setosa
## 142 5.5 NA 3.800 1.1 versicolor
nrow(violations)
## [1] 31
invalid_sepal_width <- which(dirty_iris$Sepal.Width <= 0)
dirty_iris$Sepal.Width[invalid_sepal_width] <- sapply(
dirty_iris$Sepal.Width[invalid_sepal_width],
function(x) if (x == 0) NA else abs(x)
)
sum(dirty_iris$Sepal.Width <= 0, na.rm = TRUE)
## [1] 0