Assignment5.0

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

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

## [1] 19

num_complete_cases <- sum(complete.cases(dirty_iris))
percent_complete_cases <- (num_complete_cases / nrow(dirty_iris)) * 100
cat("Number of complete observations:", num_complete_cases, "\n")

## Number of complete observations: 96

cat("Percentage of complete observations:", percent_complete_cases, "%\n")

## Percentage of complete observations: 64 %

special_values <- sapply(dirty_iris, function(x) {
  if (is.numeric(x)) {
    list(
      Inf_values = sum(is.infinite(x)),
      NaN_values = sum(is.nan(x))
    )
  } else {
    NULL
  }
})
print(special_values)

## $Sepal.Length
## $Sepal.Length$Inf_values
## [1] 0
## 
## $Sepal.Length$NaN_values
## [1] 0
## 
## 
## $Sepal.Width
## $Sepal.Width$Inf_values
## [1] 0
## 
## $Sepal.Width$NaN_values
## [1] 0
## 
## 
## $Petal.Length
## $Petal.Length$Inf_values
## [1] 0
## 
## $Petal.Length$NaN_values
## [1] 0
## 
## 
## $Petal.Width
## $Petal.Width$Inf_values
## [1] 1
## 
## $Petal.Width$NaN_values
## [1] 0
## 
## 
## $Species
## NULL

violations <- dirty_iris[(dirty_iris$Sepal.Width <= 0) | (dirty_iris$Sepal.Length > 30), ]
nrow(violations)

## [1] 31

dirty_iris[] <- lapply(dirty_iris, function(x) {
  if (is.numeric(x)) {
    x[is.infinite(x)] <- NA  # Replace Inf and -Inf with NA
    x[is.nan(x)] <- NA        # Replace NaN with NA
  }
  return(x)
})
sapply(dirty_iris, function(x) sum(is.na(x)))

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

invalid_sepal_width <- dirty_iris$Sepal.Width <= 0
invalid_sepal_length <- dirty_iris$Sepal.Length > 30
violating_rows <- which(invalid_sepal_width | invalid_sepal_length)
num_violations <- length(violating_rows)
cat("Number of observations violating the rules:", num_violations, "\n")

## Number of observations violating the rules: 4

dirty_iris[violating_rows, ]

##     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

NA

## [1] NA

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)

model_sepal_length <- lm(Sepal.Length ~ Sepal.Width + Petal.Length + Petal.Width, data = dirty_iris)

dirty_iris$Sepal.Length[is.na(dirty_iris$Sepal.Length)] <- predict(model_sepal_length, newdata = dirty_iris[is.na(dirty_iris$Sepal.Length), ])