# Load necessary libraries
library(readr)
library(dplyr)
# Read the data file (replace "data.csv" with your actual file name)
data <- read_csv("data.csv")
# Function to detect outliers using Tukey's method
detect_outliers <- function(vector) {
Q1 <- quantile(vector, 0.25)
Q3 <- quantile(vector, 0.75)
IQR <- Q3 - Q1
lower_bound <- Q1 - 1.5 * IQR
upper_bound <- Q3 + 1.5 * IQR
outliers <- vector[vector < lower_bound | vector > upper_bound]
return(outliers)
}
# Function to determine distribution type
determine_distribution <- function(vector) {
skew <- skewness(vector)
if (skew < -1) {
return("Strongly Left Skewed")
} else if (skew > 1) {
return("Strongly Right Skewed")
} else if (skew < 0) {
return("Slightly Left Skewed")
} else if (skew > 0) {
return("Slightly Right Skewed")
} else {
return("Normal")
}
}
# Iterate through columns
for (col in names(data)) {
if (is.numeric(data[[col]])) {
outliers <- detect_outliers(data[[col]])
distribution <- determine_distribution(data[[col]])
cat("Column:", col, "\n")
cat("Distribution:", distribution, "\n")
if (length(outliers) > 0) {
cat("Outliers:", outliers, "\n")
} else {
cat("No outliers found.\n")
}
cat("\n")
}
}