library(ggplot2)program 15
Create multiple histogram using ggplot2::facet_wrap() to visualize how a variable is distributed to different groups in a built-in R dataset.
step1:load the librarys
step2:load the in-built 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 setosastep3:creating histogram layer
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()
Develop an r function to draw a density curve representing the probablitlity density function of a continuous varaiable,with seperate curves for each group,using ggplot2.
step1:load the necessary libraray
library(ggplot2) step2:define the function
plot_density_by_group <- function(data, continuous_var , group_var , fill_colors = NULL){
if(!(continuous_var %in% names(data)) || !(group_var %in% names(data))){ stop("invalid column names.make sure both varaiables exist in the dataset.")
}
p <- ggplot(data,aes_string(x = continuous_var , color = group_var , fill = group_var))+
geom_density(aplha = 0.4)+
labs(title = paste("density plot of",continuous_var,"by",group_var), x = "continous_var", y = "density")+
theme_minimal()
if (!is.null(fill_colors)) {
p <-p+scale_fill_manual(values = fill_colors)+
scale_color_manual(values = fill_colors)
}
return(p)
}step3::Load 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 setosastep 4: call the function with example
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.Warning in geom_density(aplha = 0.4): Ignoring unknown parameters: `aplha`
To generate basic box plot using ggplot2,enhanced with notches and outliers and grouped by a categorical variable using an in-built dataset in R.
step1:load the required package
library(ggplot2)step2:load the built-in 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 setosastep3:adding graph/layer
ggplot(iris,aes(x= Species,y = Sepal.Length))+
geom_boxplot(notch = TRUE,outlier.colour = "red",outlier.shape = 16,outlier.size = 2, fill="pink")+
labs(title = "box plot",
x ="Sepal.Length",
y = "Species")+
theme_minimal()
12.develop a script in R to create a violin plot displaying the distribution of a continuous variable,with a separate violins for each group using an inbuilt dataset.
step 1:load the library
library(ggplot2)step 2: Grouping variables
mtcars$cyl <- as.factor(mtcars$cyl)Step 3: Create a violin plot
ggplot(mtcars, aes(x=cyl, y=mpg, fill = cyl)) +
geom_violin(trim = FALSE) +
labs ( title = "Distribution of MPG by Number of Cylinders", x= "Number of Cylinders", y = "Miles Per Gallon (MPG)" )+
theme_minimal()
Write a R program to create many dotplots from the grouped data.comparing the distribution of varaiables across using ggplot2’s dodge position function
step1:load the library
library(ggplot2)
library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, uniondata("ToothGrowth")step2:load dataset
head(ToothGrowth) len supp dose
1 4.2 VC 0.5
2 11.5 VC 0.5
3 7.3 VC 0.5
4 5.8 VC 0.5
5 6.4 VC 0.5
6 10.0 VC 0.5table(ToothGrowth$dose)
0.5 1 2
20 20 20 class(ToothGrowth$dose)[1] "numeric"summary(ToothGrowth) len supp dose
Min. : 4.20 OJ:30 Min. :0.500
1st Qu.:13.07 VC:30 1st Qu.:0.500
Median :19.25 Median :1.000
Mean :18.81 Mean :1.167
3rd Qu.:25.27 3rd Qu.:2.000
Max. :33.90 Max. :2.000 ToothGrowth$dose <- as.factor(ToothGrowth$dose)ggplot(ToothGrowth,aes(x=dose,y=len,color=supp))+
geom_dotplot(binaxis = "y",
stackdir = "center",
#which direction to stack the dots. "up" (default), "down", "center", "centerwhole" (centered, but with dots aligned)
position = position_dodge(width = 0.8),
dotsize = 0.8,
#The diameter of the dots relative to binwidth
binwidth = 1.5)+#controls spacing of dots on y axis
labs(title="tooth length dose by suppliment type",
x = "Dose",
y ="length",
color="supplement")+
theme_minimal()
Develop an r program to calculate and visualize a co-relational matrix for a given a dataset,with color coded cells indicating the strength and direction of co-relations,using ggplot2 geom_tile function.
Step1:Load the library
library(ggplot2)
library(tidyr)
library(dplyr)step2:load 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 1data(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 -0.8676594step3:graph
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",
x = "",
y = ""
)+
theme(axis.text.x = element_text(angle = 45,hjust = 1))