Assignment 5

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

Question 1

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

## [1] 19

Question 2

num_complete <- sum(complete.cases(dirty_iris))
percent_complete <- (num_complete / nrow(dirty_iris)) * 100
num_complete

## [1] 96

percent_complete

## [1] 64

Question 3/4

sum(is.na(dirty_iris))

## [1] 58

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

## [1] 0

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

## [1] 0

sum(as.matrix(dirty_iris) == -Inf, na.rm = TRUE)

## [1] 0

Question 5

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

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

violations_length <- which(dirty_iris$Sepal.Length > 30)

violations <- unique(c(violations_width, violations_length))

violating_observations <- dirty_iris[violations, ]
print(violating_observations)

##     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
## 28          73.0          29         63.0          NA  virginica
## 125         49.0          30         14.0         2.0     setosa

length(violations)

## [1] 4

Question 6

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

dirty_iris$Sepal.Width <- ifelse(is.na(dirty_iris$Sepal.Width), NA, dirty_iris$Sepal.Width)

violations <- which(dirty_iris$Sepal.Width <= 0)
print(dirty_iris[violations, ]) 

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

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

print(dirty_iris[violations, ])  

##     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

write.csv(dirty_iris, "cleaned_iris.csv", row.names = FALSE)

Question 7

library(caret)

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

## Loading required package: ggplot2

## Loading required package: lattice

library(RANN)

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

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

dirty_iris[sapply(dirty_iris, is.infinite)] <- NA
dirty_iris[sapply(dirty_iris, is.nan)] <- NA

print(colSums(is.na(dirty_iris)))  

## Sepal.Length  Sepal.Width Petal.Length  Petal.Width      Species 
##           10           17           19           13            0

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)

clean_data <- dirty_iris[complete.cases(dirty_iris[, c("Petal.Length", "Petal.Width", "Sepal.Width")]), ]

if(nrow(clean_data) > 0) {
    lm_model <- lm(Sepal.Length ~ Petal.Length + Petal.Width + Sepal.Width, data = clean_data)
    missing_indices <- which(is.na(dirty_iris$Sepal.Length))
    dirty_iris$Sepal.Length[missing_indices] <- predict(lm_model, newdata = dirty_iris[missing_indices, ])
} else {
    stop("No complete cases available for linear regression.")
}

preProc <- preProcess(dirty_iris, method = "knnImpute")
dirty_iris <- predict(preProc, newdata = dirty_iris)

print(colSums(is.na(dirty_iris))) 

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