Assignment 4

#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

num_complete <- sum(complete.cases(dirty_iris))

perc_complete <- mean(complete.cases(dirty_iris))*100

#Question 5

dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")

colSums(is.na(dirty_iris))

## Sepal.Length  Sepal.Width Petal.Length  Petal.Width      Species 
##           10           17           19           12            0

colSums(sapply(dirty_iris, function(x) is.nan(x)))

## Sepal.Length  Sepal.Width Petal.Length  Petal.Width      Species 
##            0            0            0            0            0

colSums(sapply(dirty_iris, function(x) is.infinite(x)))

## Sepal.Length  Sepal.Width Petal.Length  Petal.Width      Species 
##            0            0            0            1            0

which(sapply(dirty_iris$Sepal.Length, is.nan))

## integer(0)

which(sapply(dirty_iris$Sepal.Width, is.nan))

## integer(0)

which(sapply(dirty_iris$Petal.Length, is.nan))

## integer(0)

which(sapply(dirty_iris$Petal.Width, is.nan))

## integer(0)

#Question 6

dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")


is.nan(dirty_iris$Sepal.Length)

##   [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [25] FALSE FALSE FALSE FALSE FALSE FALSE 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 FALSE FALSE FALSE
##  [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE 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 FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [121] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [133] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE

is.nan(dirty_iris$Sepal.Width)

##   [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [25] FALSE FALSE FALSE FALSE FALSE FALSE 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 FALSE FALSE FALSE
##  [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE 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 FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [121] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [133] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE

is.nan(dirty_iris$Petal.Length)

##   [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [25] FALSE FALSE FALSE FALSE FALSE FALSE 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 FALSE FALSE FALSE
##  [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE 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 FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [121] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [133] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE

is.nan(dirty_iris$Petal.Width)

##   [1] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [13] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
##  [25] FALSE FALSE FALSE FALSE FALSE FALSE 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 FALSE FALSE FALSE
##  [61] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE 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 FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [121] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [133] FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
## [145] FALSE FALSE FALSE FALSE FALSE FALSE

dirty_iris$Sepal.Length[is.nan(dirty_iris$Sepal.Length)] <- NA
dirty_iris$Sepal.Width[is.nan(dirty_iris$Sepal.Width)]   <- NA
dirty_iris$Petal.Length[is.nan(dirty_iris$Petal.Length)] <- NA
dirty_iris$Petal.Width[is.nan(dirty_iris$Petal.Width)]   <- NA


summary(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  
##                    
##                    
##                    
##

#Question 7

dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")


violations <- subset(dirty_iris, Sepal.Width <= 0 | Sepal.Length > 30)


violations

##     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

nrow(violations)

## [1] 4

#Question 8

dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")


dirty_iris$Sepal.Width <- as.numeric(dirty_iris$Sepal.Width)


dirty_iris$Sepal.Width[which(!is.na(dirty_iris$Sepal.Width) & dirty_iris$Sepal.Width < 0)] <- 
  abs(dirty_iris$Sepal.Width[which(!is.na(dirty_iris$Sepal.Width) & dirty_iris$Sepal.Width < 0)])

dirty_iris$Sepal.Width[dirty_iris$Sepal.Width == 0] <- NA


summary(dirty_iris$Sepal.Width)

##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max.    NA's 
##   2.200   2.800   3.000   3.462   3.300  30.000      18

#Question 9

library(caret)

## Loading required package: ggplot2

## Loading required package: lattice

dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")


dirty_iris$Sepal.Length <- as.numeric(dirty_iris$Sepal.Length)
dirty_iris$Sepal.Width  <- as.numeric(dirty_iris$Sepal.Width)
dirty_iris$Petal.Length <- as.numeric(dirty_iris$Petal.Length)
dirty_iris$Petal.Width  <- as.numeric(dirty_iris$Petal.Width)


dirty_iris$Sepal.Width[is.na(dirty_iris$Sepal.Width)] <- 
  mean(dirty_iris$Sepal.Width, na.rm = TRUE)
dirty_iris$Petal.Length[is.na(dirty_iris$Petal.Length)] <- 
  median(dirty_iris$Petal.Length, na.rm = TRUE)

Assignment 4

Michael O’Keefe

2025-10-03