R Notebook

dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")
dirty_iris <- read.csv("https://raw.githubusercontent.com/edwindj/datacleaning/master/data/dirty_iris.csv")
sum(is.na(dirty_iris$Sepal.Length))

[1] 10

percent_complete <- (num_complete / nrow(dirty_iris)) * 100 
cat("Number of complete observations:", num_complete, "\n")

Number of complete observations: 96 

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

Percentage of complete observations: 64 %

cat("Number of Inf values in numeric columns:\n")

Number of Inf values in numeric columns:

print(inf_values)

Sepal.Length  Sepal.Width Petal.Length  Petal.Width 
           0            0            0            1 

cat("\nNumber of NaN values in numeric columns:\n")

Number of NaN values in numeric columns:

print(nan_values)

Sepal.Length  Sepal.Width Petal.Length  Petal.Width 
           0            0            0            0 

cat("Special values have been replaced with NA.\n")

Error: unexpected symbol in:
"
cat"

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

Number of observations violating the rules: 4 

cat("Rows violating the rules:\n")

Rows violating the rules: