Assignment 5

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

sum(is.na(dirty_iris))

## [1] 58

sum(is.na(dirty_iris$Petal.Length))

## [1] 19

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

percent_complete <- (num_complete / nrow(dirty_iris)) * 100

sum(is.na(dirty_iris))

## [1] 58

sum(is.nan(as.matrix(dirty_iris)))

## [1] 0

sum(is.infinite(as.matrix(dirty_iris)) & dirty_iris > 0)

## [1] 0

sum(is.infinite(as.matrix(dirty_iris)) & dirty_iris < 0)

## [1] 0

cat("NA count:", sum(is.na(dirty_iris)), "\n")

## NA count: 58

cat("NaN count:", sum(is.nan(as.matrix(dirty_iris))), "\n")

## NaN count: 0

cat("Inf count:", sum(is.infinite(as.matrix(dirty_iris)) & dirty_iris > 0), "\n")

## Inf count: 0

cat("-Inf count:", sum(is.infinite(as.matrix(dirty_iris)) & dirty_iris < 0), "\n")

## -Inf count: 0

dirty_iris_matrix <- as.matrix(dirty_iris)

dirty_iris_matrix[is.nan(dirty_iris_matrix)] <- NA

summary(dirty_iris_matrix)

##  Sepal.Length       Sepal.Width        Petal.Length       Petal.Width       
##  Length:150         Length:150         Length:150         Length:150        
##  Class :character   Class :character   Class :character   Class :character  
##  Mode  :character   Mode  :character   Mode  :character   Mode  :character  
##    Species         
##  Length:150        
##  Class :character  
##  Mode  :character

violating_rows <- which(dirty_iris$Sepal.Width <= 0 | dirty_iris$Sepal.Length > 30)

violating_data <- dirty_iris[violating_rows, ]

num_violations <- nrow(violating_data)

cat(num_violations)

## 4

invalid_sepal_width <- which(dirty_iris$Sepal.Width <= 0)

cat("Observations with invalid Sepal.Width:\n")

## Observations with invalid Sepal.Width:

print(dirty_iris[invalid_sepal_width, ])

##     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
## 16           5.0          -3          3.5         1.0 versicolor
## 130          5.7           0          1.7         0.3     setosa

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

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

cat("Updated Sepal.Width values:\n")

## Updated Sepal.Width values:

print(dirty_iris[invalid_sepal_width, ])

##     Sepal.Length Sepal.Width Petal.Length Petal.Width    Species
## 16           5.0           3          3.5         1.0 versicolor
## 130          5.7          NA          1.7         0.3     setosa

library(DMwR2)

## Warning: package 'DMwR2' was built under R version 4.4.2

## Registered S3 method overwritten by 'quantmod':
##   method            from
##   as.zoo.data.frame zoo

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)

summary(dirty_iris)

##   Sepal.Length     Sepal.Width      Petal.Length     Petal.Width 
##  Min.   : 0.000   Min.   : 2.200   Min.   : 0.000   Min.   :0.1  
##  1st Qu.: 5.100   1st Qu.: 2.825   1st Qu.: 1.700   1st Qu.:0.3  
##  Median : 5.750   Median : 3.100   Median : 4.500   Median :1.3  
##  Mean   : 6.559   Mean   : 3.462   Mean   : 4.456   Mean   :Inf  
##  3rd Qu.: 6.400   3rd Qu.: 3.462   3rd Qu.: 5.100   3rd Qu.:1.8  
##  Max.   :73.000   Max.   :30.000   Max.   :63.000   Max.   :Inf  
##  NA's   :10                                         NA's   :12   
##    Species         
##  Length:150        
##  Class :character  
##  Mode  :character  
##                    
##                    
##                    
##