Iris Flower Statistics

#Load packages. Examine data

library(tidyverse)

## ── Attaching packages ──────────────────────────────────────────────────────────────────────────── tidyverse 1.3.0 ──

## ✓ ggplot2 3.2.1     ✓ purrr   0.3.3
## ✓ tibble  2.1.3     ✓ dplyr   0.8.3
## ✓ tidyr   1.0.0     ✓ stringr 1.4.0
## ✓ readr   1.3.1     ✓ forcats 0.4.0

## ── Conflicts ─────────────────────────────────────────────────────────────────────────────── tidyverse_conflicts() ──
## x dplyr::filter() masks stats::filter()
## x dplyr::lag()    masks stats::lag()

data(iris)
head(iris)
summary(iris)
str(iris)
species_count = nrow(iris) / 3 
# 3 is the number of species.
# Assumption is made that all species have the same number of observations.

#Function to print stats for you

print_stats = function(species, label, value){
  cat(paste0(c(species, label, toString(value), "\n")))
}

#Statistics for irises, histograms, and dataframe

species_list = c("Setosa", "Versicolor", "Virginica")
# Create dataframe for statistics. 
# List of species is added and other data will be added later.
iris_stats = data.frame(species = species_list)

# Iterate through each species in species_list. 
# Calculate and print statistics, and plot histogram for petal length
# Add statistics to iris_stats dataframe.
for (i in 1:3) {
  species = species_list[i]
  indices = ((i-1)*species_count+1):(i*species_count)
  
  # Calculate statistics
  mean_sepal_length = mean(iris$Sepal.Length[indices])
  median_sepal_width = median(iris$Sepal.Width[indices], na.rm = TRUE)
  max_petal_length = max(iris$Petal.Length[indices])
  min_petal_length = min(iris$Petal.Length[indices])
  min_petal_width = min(iris$Petal.Width[indices])
  
  # Print statistics
  print_stats(species, "Mean Sepal Length:", mean_sepal_length)
  print_stats(species, "Median Sepal Width:", median_sepal_width)
  print_stats(species, "Max Petal Length:", max_petal_length)
  print_stats(species, "Min Petal Width:", min_petal_width)
  cat("\n")
  
  # Append stats to dataframe
  iris_stats$mean_sepal_lengths[i] = mean_sepal_length
  iris_stats$median_sepal_widths[i] = median_sepal_width
  iris_stats$max_petal_lengths[i] = max_petal_length
  iris_stats$min_petal_widths[i] = min_petal_width
  
  # Plot histogram for petal length
  print(ggplot(data = iris[indices,], aes(iris$Petal.Length[indices])) + 
    geom_histogram(breaks = seq(min_petal_length*.9,max_petal_length*1.1, 
      by = (max_petal_length-min_petal_length)/15), fill = "Grey", col = "White") + 
    labs(title = paste0(species, " Petal Lengths:"), x = "Length", y = "Count"))
}

## Setosa Mean Sepal Length: 5.006 
## Setosa Median Sepal Width: 3.4 
## Setosa Max Petal Length: 1.9 
## Setosa Min Petal Width: 0.1

## Versicolor Mean Sepal Length: 5.936 
## Versicolor Median Sepal Width: 2.8 
## Versicolor Max Petal Length: 5.1 
## Versicolor Min Petal Width: 1

## Virginica Mean Sepal Length: 6.588 
## Virginica Median Sepal Width: 3 
## Virginica Max Petal Length: 6.9 
## Virginica Min Petal Width: 1.4

iris_stats