Untitled

Program 15

Objective

Create multiple histograms using ggplot2::facet_wrap() to visualize how a variable (e.g. Sepal.Length) is distributed across different groups(e.g. Species) in a built-in R dataset.

library(ggplot2)
#Load the iris dataset
data(iris)
#View the first few rows of the dataset
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

# Create histograms using facet_wrap for grouped data
ggplot(iris, aes(x = Sepal.Length)) +
  geom_histogram(binwidth = 0.3, fill = "skyblue", color = "black") +
  facet_wrap(~ Species) +
  labs(title = "Distribution of Sepal Length by Species",
       x = "Sepal Length (cm)",
       y = "Frequency") +
  theme_minimal()

Objective

Develop an R function to draw a density curve representing the probability density function of a continuous variable, with separate curves for each group, using ggplot2.

library(ggplot2)
plot_density_by_group <- function(data, continuous_var, group_var, fill_colors = NULL) {
  # Check if the specified columns exist
  if (!(continuous_var %in% names(data)) || !(group_var %in% names(data))) {
    stop("Invalid column names. Make sure both variables exist in the dataset.")
  }

  # Create the ggplot object
  p <- ggplot(data, aes_string(x = continuous_var, color = group_var, fill = group_var)) +
    geom_density(alpha = 0.4) +
    labs(title = paste("Density Plot of", continuous_var, "by", group_var),
         x = continuous_var,
         y = "Density") +
    theme_minimal()

  # Apply custom fill colors if provided
  if (!is.null(fill_colors)) {
    p <- p + scale_fill_manual(values = fill_colors) +
             scale_color_manual(values = fill_colors)
  }

  # Return the plot
  return(p)
}
# Basic usage
plot_density_by_group(iris, "Sepal.Length", "Species")

Warning: `aes_string()` was deprecated in ggplot2 3.0.0.
ℹ Please use tidy evaluation idioms with `aes()`.
ℹ See also `vignette("ggplot2-in-packages")` for more information.

# Define custom colors
custom_colors <- c("setosa" = "steelblue",
                   "versicolor" = "forestgreen",
                   "virginica" = "darkorange")

# Plot with custom colors
plot_density_by_group(iris, "Petal.Length", "Species", fill_colors = custom_colors)

Objective

To generate a basic box plot using ggplot2, enhanced with notches and outliers, and grouped by a categorical variable using an in-built dataset in R.

# install.packages("ggplot2") # Uncomment if needed
library(ggplot2)# Load and preview the dataset
data(iris)
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

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 ...

ggplot(iris, aes(x = Species, y = Sepal.Length)) +
  geom_boxplot(
    notch = TRUE,
    notchwidth = 0.6,
    outlier.color = "red",
    outlier.shape = 16,
    fill = "skyblue",
    alpha = 0.7
  ) +
  labs(
    title = "Sepal Length Distribution by Iris Species",
    subtitle = "Box Plot with Notches and Outlier Highlighting",
    x = "Species",
    y = "Sepal Length (cm)"
  ) +
  theme_minimal()

p=ggplot(iris, aes(x = Species, y = Sepal.Length))
p

p=p+ geom_boxplot(

)
p

p=p+ geom_boxplot(
  notch = TRUE,
    notchwidth = 0.6,
    outlier.color = "red",
    outlier.shape = 16,
    fill = "skyblue",
    alpha = 0.7
)
p

Objective

To create a violin plot using ggplot2 in R that displays the distribution of a continuous variable with separate violins for each group using an in-built dataset.

library(ggplot2)
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

data(iris)
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 ...

ggplot(iris, aes(x = Species, y = Petal.Length, fill = Species)) +
  geom_violin(trim = FALSE, alpha = 0.6, color = "black") +
  labs(
    title = "Distribution of Petal Length by Iris Species",
    x = "Species",
    y = "Petal Length (cm)"
  ) +
  theme_minimal(base_size = 14)

Dot Plot for Grouped Data using ggplot2

Write a R program to create multiple dot plots for grouped data, comparing the distributions of variables across different categories, using ggplot2’s position _dodge function.

library(ggplot2)
library(dplyr)

Attaching package: 'dplyr'

The following objects are masked from 'package:stats':

    filter, lag

The following objects are masked from 'package:base':

    intersect, setdiff, setequal, union

# Convert dose to a factor for grouping
ToothGrowth$dose <- as.factor(ToothGrowth$dose)

# Plot with defined binwidth
ggplot(ToothGrowth, aes(x = dose, y = len, color = supp)) +
  geom_dotplot(
    binaxis = 'y',
    stackdir = 'center',
    position = position_dodge(width = 0.8),
    dotsize = 0.6,
    binwidth = 1.5  # Controls spacing of dots on y-axis
  ) +
  labs(
    title = "Dot Plot of Tooth Length by Dose and Supplement Type",
    x = "Dose (mg/day)",
    y = "Tooth Length",
    color = "Supplement Type"
  ) +
  theme_minimal()

Correlation Matrix Visualization using ggplot2

Develop a R program to calculate and visualize co-relation matrix for a given dataset, with color coded cells indicating the strength and direction of co-relation using ggplot2 and geom_tile function.

library(ggplot2)
library(dplyr)
library(tidyr)
head(mtcars)

                   mpg cyl disp  hp drat    wt  qsec vs am gear carb
Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1

data(mtcars)
cor_matrix <- cor(mtcars)
cor_df <-as.data.frame(as.table(cor_matrix))
head(cor_df)

  Var1 Var2       Freq
1  mpg  mpg  1.0000000
2  cyl  mpg -0.8521620
3 disp  mpg -0.8475514
4   hp  mpg -0.7761684
5 drat  mpg  0.6811719
6   wt  mpg -0.8676594

ggplot(cor_df, aes(x=Var1, y=Var2, fill = Freq)) +
  geom_tile(color = "white") + 
  scale_fill_gradient2(
    low= "blue", mid= "white", high= "red",
    midpoint = 0, limit = c(-1,1),
    name = "Correlation"
  ) + 
  geom_text(aes(label = round(Freq, 2)), size = 3) + 
  theme_minimal() +
  labs(
     title = "Correlation Matrix (mtcars)",
    x = "", y = ""
  ) +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))