prg5

Implement an R program to create a histogram illustrating the distribution of a continuous variable, with overlays of density curves for each group, using ggplot2.

---

Step 1: Load required library

We first load the ggplot2package , which is used for data visualiztion in R.

library(ggplot2)

Warning: package 'ggplot2' was built under R version 4.5.3

---

Step 2 : Explore the in built dataset

str(iris)

'data.frame':   150 obs. of  5 variables:
 $ Sepal.Length: num  5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
 $ Sepal.Width : num  3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
 $ Petal.Length: num  1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
 $ Petal.Width : num  0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
 $ Species     : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...

head(iris)

  Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1          5.1         3.5          1.4         0.2  setosa
2          4.9         3.0          1.4         0.2  setosa
3          4.7         3.2          1.3         0.2  setosa
4          4.6         3.1          1.5         0.2  setosa
5          5.0         3.6          1.4         0.2  setosa
6          5.4         3.9          1.7         0.4  setosa

head(iris,n=2)

  Sepal.Length Sepal.Width Petal.Length Petal.Width Species
1          5.1         3.5          1.4         0.2  setosa
2          4.9         3.0          1.4         0.2  setosa

tail(iris)

    Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
145          6.7         3.3          5.7         2.5 virginica
146          6.7         3.0          5.2         2.3 virginica
147          6.3         2.5          5.0         1.9 virginica
148          6.5         3.0          5.2         2.0 virginica
149          6.2         3.4          5.4         2.3 virginica
150          5.9         3.0          5.1         1.8 virginica

tail(iris,n=3)

    Sepal.Length Sepal.Width Petal.Length Petal.Width   Species
148          6.5         3.0          5.2         2.0 virginica
149          6.2         3.4          5.4         2.3 virginica
150          5.9         3.0          5.1         1.8 virginica

---

Step 3.1 Initialize the Graph

# Start ggplot with iris dataset
# Map Petal.Length to x-axis and fill by Species

p <- ggplot(data = iris, aes(x= Petal.Length , fill = Species))

# Add histogram with density scalling

p <- p + geom_histogram(aes(y = ..density..),
alpha = 0.4,
position = "identity",
bins = 30)
p

Warning: The dot-dot notation (`..density..`) was deprecated in ggplot2 3.4.0.
ℹ Please use `after_stat(density)` instead.

p <- p + geom_density(aes(color=Species), size = 1.2)

Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.

p

p <- p + labs(
  title = "Distribution of Petal.Length with group-wise density curves",
  x = "Petal Length",
  y = "density")+
  theme_minimal()
p

p <- p + labs(
  title = "Distribution of Petal.Length with group-wise density curves",
  x = "Petal Length",
  y = "density")+
  theme_minimal()+
  theme(legend.position = 'top')
p