Load the Dataset
dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")
Check the number of missing values in Petal.Length
sum(is.na(dirty_iris$Petal.Length))
## [1] 19
Number of complete observations
num_complete <- sum(complete.cases(dirty_iris))
num_complete
## [1] 96
Percent of complete observations
percent_complete <- (num_complete / nrow(dirty_iris)) * 100
percent_complete
## [1] 64
Numeric columns
str(dirty_iris)
## 'data.frame': 150 obs. of 5 variables:
## $ Sepal.Length: num 6.4 6.3 6.2 5 5.7 5.3 6.4 5.9 5.8 4.8 ...
## $ Sepal.Width : num 3.2 3.3 NA 3.4 2.6 NA 2.7 3 2.7 3.1 ...
## $ Petal.Length: num 4.5 6 5.4 1.6 3.5 NA 5.3 5.1 4.1 1.6 ...
## $ Petal.Width : num 1.5 2.5 2.3 0.4 1 0.2 NA 1.8 1 0.2 ...
## $ Species : chr "versicolor" "virginica" "virginica" "setosa" ...
Find unique special values
sapply(dirty_iris[, sapply(dirty_iris, is.numeric)], unique)
## $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
##
## $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
##
## $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
##
## $Petal.Width
## [1] 1.5 2.5 2.3 0.4 1.0 0.2 NA 1.8 0.6 1.6 1.4 1.3 0.1 2.1 2.0 1.2 1.9 2.2 0.3
## [20] 1.1 Inf 1.7 2.4 0.5
Locate missing value
num_cols <- c("Sepal.Length", "Sepal.Width", "Petal.Length", "Petal.Width")
Replace ? with NA
dirty_iris[num_cols][dirty_iris[num_cols] == "?"] <- NA
View cleaned dataset
head(dirty_iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 6.4 3.2 4.5 1.5 versicolor
## 2 6.3 3.3 6.0 2.5 virginica
## 3 6.2 NA 5.4 2.3 virginica
## 4 5.0 3.4 1.6 0.4 setosa
## 5 5.7 2.6 3.5 1.0 versicolor
## 6 5.3 NA NA 0.2 setosa
Convert the numeric columns from character to numeric
dirty_iris[num_cols] <- lapply(dirty_iris[num_cols], as.numeric)
Rule violations
violations <- subset(dirty_iris, Sepal.Width <= 0 | Sepal.Length > 30)
Count how many violations
nrow(violations)
## [1] 4
Mean
dirty_iris$Sepal.Width[is.na(dirty_iris$Sepal.Width)] <-
mean(dirty_iris$Sepal.Width, na.rm = TRUE)
Knn
if(!require(VIM)) install.packages("VIM")
## Loading required package: VIM
## Warning: package 'VIM' was built under R version 4.4.3
## 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
library(VIM)
dirty_iris <- kNN(dirty_iris, variable = "Petal.Width", k = 5)
## Sepal.Length Sepal.Width Petal.Length Sepal.Length Sepal.Width Petal.Length
## 0 -3 0 73 30 63