library(ggplot2) Warning: package 'ggplot2' was built under R version 4.4.3Program 15
9.Create multiple histograms using ggplot2 ::8facet_wrap() to visualize how a variable(e.g., Sepal.length) is distributed across different groups (e.g.,species) in a built-in R data set.
Step 1: Load required libraries
Step 2:Load dataset
data(iris) #load the first iris dataset
head(iris) #view the first few rows 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 setosaStep 3: Create histogram using facet_wrap for grouped data
ggplot(iris, aes(x = Sepal.Length)) +
geom_histogram(binwidth = 0.4, fill = "black", color = "pink") + facet_wrap(~ Species) + # Facet by Species
labs(title = "Distribution of Sepal Length by Species",
x = "Sepal Length (cm)",
y = "Frequency")+ theme_minimal()
10.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.
Step 1: Load Required Library
library(ggplot2)Step 2: Define the Function
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)
}Step 4: Example with Built-in iris Dataset
# 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.
Step 5: Example with Custom Colors
# 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)
11.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.
Step 1: Load Required Package
library(ggplot2)Step 2: Use an Inbuilt 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 setosastr(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 ...Step 3: Create a Notched Box Plot Grouped by Species
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 = "purple",
alpha = 0.7
)
p
12.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.
Step 1: Load Required Package
library(ggplot2)Step 2: Use an Inbuilt 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 setosastr(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 ...Step 3: Create the Violin Plot
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)
13.Write an R program to create multiple dot plots or group data , comparing the distribution of variables across different categories, using ggplot2’s position_dodge function.
Step 1: Load the required library
library(ggplot2)
library(dplyr)Warning: package 'dplyr' was built under R version 4.4.3
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionStep 2:Load the dataset
str("ToothGrowth") chr "ToothGrowth"data("ToothGrowth")
table(ToothGrowth$len)
4.2 5.2 5.8 6.4 7 7.3 8.2 9.4 9.7 10 11.2 11.5 13.6 14.5 15.2 15.5
1 1 1 1 1 1 1 1 2 2 2 1 1 3 2 1
16.5 17.3 17.6 18.5 18.8 19.7 20 21.2 21.5 22.4 22.5 23 23.3 23.6 24.5 24.8
3 2 1 1 1 1 1 1 2 1 1 1 2 2 1 1
25.2 25.5 25.8 26.4 26.7 27.3 29.4 29.5 30.9 32.5 33.9
1 2 1 4 1 2 1 1 1 1 1 table(ToothGrowth$dose)
0.5 1 2
20 20 20 Step 3:Create a dot plot
ToothGrowth$dose <- as.factor(ToothGrowth$dose)
ggplot(ToothGrowth, aes(x = dose, y = len, color = supp)) +
geom_dotplot(
binaxis = 'y',
stackdir = 'center',#direction to stack the dots
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()
14.Develop a R program to calculate and visualize a correlation matrix for a given dataset, with color coded cells indicating the strength and direction of correlation , using ggplot2, geom_tile function.
Step 1: Load the required library
library(ggplot2)
library(tidyr) Warning: package 'tidyr' was built under R version 4.4.3library(dplyr)Step 2: Dataset
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 1str(mtcars) 'data.frame': 32 obs. of 11 variables:
$ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
$ cyl : num 6 6 4 6 8 6 8 4 4 6 ...
$ disp: num 160 160 108 258 360 ...
$ hp : num 110 110 93 110 175 105 245 62 95 123 ...
$ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
$ wt : num 2.62 2.88 2.32 3.21 3.44 ...
$ qsec: num 16.5 17 18.6 19.4 17 ...
$ vs : num 0 0 1 1 0 1 0 1 1 1 ...
$ am : num 1 1 1 0 0 0 0 0 0 0 ...
$ gear: num 4 4 4 3 3 3 3 4 4 4 ...
$ carb: num 4 4 1 1 2 1 4 2 2 4 ...dim(mtcars)[1] 32 11data(mtcars)
cor_matrix <- cor(mtcars)
cor_matrix mpg cyl disp hp drat wt
mpg 1.0000000 -0.8521620 -0.8475514 -0.7761684 0.68117191 -0.8676594
cyl -0.8521620 1.0000000 0.9020329 0.8324475 -0.69993811 0.7824958
disp -0.8475514 0.9020329 1.0000000 0.7909486 -0.71021393 0.8879799
hp -0.7761684 0.8324475 0.7909486 1.0000000 -0.44875912 0.6587479
drat 0.6811719 -0.6999381 -0.7102139 -0.4487591 1.00000000 -0.7124406
wt -0.8676594 0.7824958 0.8879799 0.6587479 -0.71244065 1.0000000
qsec 0.4186840 -0.5912421 -0.4336979 -0.7082234 0.09120476 -0.1747159
vs 0.6640389 -0.8108118 -0.7104159 -0.7230967 0.44027846 -0.5549157
am 0.5998324 -0.5226070 -0.5912270 -0.2432043 0.71271113 -0.6924953
gear 0.4802848 -0.4926866 -0.5555692 -0.1257043 0.69961013 -0.5832870
carb -0.5509251 0.5269883 0.3949769 0.7498125 -0.09078980 0.4276059
qsec vs am gear carb
mpg 0.41868403 0.6640389 0.59983243 0.4802848 -0.55092507
cyl -0.59124207 -0.8108118 -0.52260705 -0.4926866 0.52698829
disp -0.43369788 -0.7104159 -0.59122704 -0.5555692 0.39497686
hp -0.70822339 -0.7230967 -0.24320426 -0.1257043 0.74981247
drat 0.09120476 0.4402785 0.71271113 0.6996101 -0.09078980
wt -0.17471588 -0.5549157 -0.69249526 -0.5832870 0.42760594
qsec 1.00000000 0.7445354 -0.22986086 -0.2126822 -0.65624923
vs 0.74453544 1.0000000 0.16834512 0.2060233 -0.56960714
am -0.22986086 0.1683451 1.00000000 0.7940588 0.05753435
gear -0.21268223 0.2060233 0.79405876 1.0000000 0.27407284
carb -0.65624923 -0.5696071 0.05753435 0.2740728 1.00000000cor_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 -0.8676594Step 3:Visualize using ggplot
ggplot(cor_df, aes(x = Var1, y = Var2, fill = Freq)) +
geom_tile(color = "white") + #Draw tile borders
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 = "Var1",
y = "Var2"
) +
theme(axis.text.x = element_text(angle = 45, hjust =1))