Question 3

d <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")
sum(is.na(d$Petal.Length))
## [1] 19

Question 4

sum(complete.cases(d))
## [1] 96
mean(complete.cases(d)) * 100
## [1] 64

Question 5

sapply(d[sapply(d, is.numeric)], function(x) c(
  sum(is.nan(x)),
  sum(is.infinite(x) & x > 0, na.rm = TRUE),
  sum(is.infinite(x) & x < 0, na.rm = TRUE)
))
##      Sepal.Length Sepal.Width Petal.Length Petal.Width
## [1,]            0           0            0           0
## [2,]            0           0            0           1
## [3,]            0           0            0           0

Question 6

which(is.infinite(as.matrix(d)), arr.ind = TRUE)
##      row col
which(is.nan(as.matrix(d)), arr.ind = TRUE)
##      row col
d[sapply(d, is.numeric)] <- lapply(d[sapply(d, is.numeric)], function(x) {x[is.infinite(x) | is.nan(x)] <- NA; x})

Question 7

bad <- which(d$Sepal.Width <= 0 | d$Sepal.Length > 30)
d[bad, ]
##     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
## 16           5.0          -3          3.5         1.0 versicolor
## 28          73.0          29         63.0          NA  virginica
## 125         49.0          30         14.0         2.0     setosa
## 130          5.7           0          1.7         0.3     setosa
length(bad)
## [1] 4

Question 8

d[d$Sepal.Width < 0 & !is.na(d$Sepal.Width), "Sepal.Width"] <- abs(d$Sepal.Width[d$Sepal.Width < 0 & !is.na(d$Sepal.Width)])
d$Sepal.Width[d$Sepal.Width == 0] <- NA
d[bad, ]
##     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
## 16           5.0           3          3.5         1.0 versicolor
## 28          73.0          29         63.0          NA  virginica
## 125         49.0          30         14.0         2.0     setosa
## 130          5.7          NA          1.7         0.3     setosa

Question 9

d$Sepal.Length[d$Sepal.Length > 30] <- NA
d$Sepal.Width[is.na(d$Sepal.Width)] <- mean(d$Sepal.Width, na.rm = TRUE)
d$Petal.Length[is.na(d$Petal.Length)] <- median(d$Petal.Length, na.rm = TRUE)
library(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
d <- kNN(d, variable = "Petal.Width", k = 5, imp_var = FALSE)
m <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width, data = d)
i <- is.na(d$Sepal.Length)
d$Sepal.Length[i] <- predict(m, newdata = d[i, ])
colSums(is.na(d))
## Sepal.Length  Sepal.Width Petal.Length  Petal.Width      Species 
##            0            0            0            0            0