Assignment 5

Olivia Thompson

2/28/25

Question One

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

missing_values <- sum(is.na(dirty_iris$Petal.Length))
missing_values

Question Two

complete_cases <- complete.cases(dirty_iris)
complete_cases
num_complete_cases <- sum(complete_cases)
percentage_complete_cases <- (num_complete_cases / nrow(dirty_iris)) * 100
num_complete_cases
percentage_complete_cases

Question Three

numeric_columns <- dirty_iris[sapply(dirty_iris, is.numeric)]
negative_inf_values <- sapply(numeric_columns, function(x) sum(is.infinite(x) & x < 0))
negative_inf_values

numeric_columns <- dirty_iris[sapply(dirty_iris, is.numeric)]
positive_inf_values <- sapply(numeric_columns, function(x) sum(is.infinite(x) & x > 0))
positive_inf_values

Question Four

numeric_columns <- dirty_iris[sapply(dirty_iris, is.numeric)]
inf_rows <- sapply(numeric_columns, function(x) which(is.infinite(x)))
inf_rows

dirty_iris[sapply(dirty_iris, is.numeric)] <- apply(dirty_iris[sapply(dirty_iris, is.numeric)], 2, function(x) {
  x[is.infinite(x)] <- NA  
  return(x)
})
dirty_iris[86, ]

Question Five

violating_rows <- dirty_iris[dirty_iris$Sepal.Width <= 0 | dirty_iris$Sepal.Length > 30,]
num_violations <- nrow(violating_rows)
print(paste("Number of observations violating the rules:", num_violations))
print("Violating observations:")
print(violating_rows)

violating_sepal_width <- which(dirty_iris$Sepal.Width <= 0)
violating_sepal_length <- which(dirty_iris$Sepal.Length > 30)
violating_indices <- unique(c(violating_sepal_width, violating_sepal_length))
violating_rows <- dirty_iris[violating_indices, ]
n_violations <- length(violating_indices)
n_violations

Question Six

violating_indices <- which(!is.na(dirty_iris$Sepal.Width) & dirty_iris$Sepal.Width <= 0)

print("Violating Observations Before Correction:")
print(dirty_iris[violating_indices, ])


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

print("Corrected Observations:")
print(dirty_iris[violating_indices, ])

Question Seven

pacman::p_load(dplyr, Hmisc)

also installing the dependencies ‘checkmate’, ‘gridExtra’, ‘htmlTable’, ‘viridis’, ‘Formula’

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.4/checkmate_2.3.2.tgz'
Content type 'application/x-gzip' length 778249 bytes (760 KB)
==================================================
downloaded 760 KB

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.4/gridExtra_2.3.tgz'
Content type 'application/x-gzip' length 1105951 bytes (1.1 MB)
==================================================
downloaded 1.1 MB

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.4/htmlTable_2.4.3.tgz'
Content type 'application/x-gzip' length 422165 bytes (412 KB)
==================================================
downloaded 412 KB

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.4/viridis_0.6.5.tgz'
Content type 'application/x-gzip' length 3016921 bytes (2.9 MB)
==================================================
downloaded 2.9 MB

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.4/Formula_1.2-5.tgz'
Content type 'application/x-gzip' length 158398 bytes (154 KB)
==================================================
downloaded 154 KB

trying URL 'https://cran.rstudio.com/bin/macosx/big-sur-arm64/contrib/4.4/Hmisc_5.2-2.tgz'
Content type 'application/x-gzip' length 3603982 bytes (3.4 MB)
==================================================
downloaded 3.4 MB

The downloaded binary packages are in
    /var/folders/1l/8hyc8g4x08lgfhk57drrsq6h0000gn/T//Rtmpsd6XKD/downloaded_packages

Hmisc installed

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)

lm_model <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width, data = dirty_iris)
dirty_iris$Sepal.Length[is.na(dirty_iris$Sepal.Length)] <- predict(lm_model, newdata = dirty_iris[is.na(dirty_iris$Sepal.Length), ])

dirty_iris$Petal.Width <- impute(dirty_iris$Petal.Width, method = "knn")

head(dirty_iris)