Program 15

Author

Varsha GB-1NT23IS243-D

  1. 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 built-in R dataset.

Step 1: Load the required libraries

library(ggplot2)

Step 2: Load 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

Step 3: Creating histogram plot

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()

  1. 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 the required libraries

library(ggplot2)

Step 2: 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 variables exist in the dataset.")
  }
  
  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()
  
  #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(p)
}

Step 3: Example with Built-in iris dataset

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 4: Example with custom colors

custom_colors <- c("setosa" = "steelblue",
                   "versicolor" = "forestgreen",
                   "virginica" = "darkorange")

plot_density_by_group(iris, "Petal.Length", "Species", fill_colors = custom_colors)

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

Step 1 : Load the required library

library(ggplot2)

Step 2 : Load the required 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

Step 3 : Create box plot with notches

ggplot(iris, aes(x=Species, y=Sepal.Length)) +
  geom_boxplot(
    notch = TRUE,
    notchwidth = 0.6,
    outlier.colour = "black",
    fill = "pink" ) + 
labs(title="Box plot",
     x = "Species",
     y = "Sepal length") + 
  theme_minimal()

  1. Develop a script in R to create a violin plot displaying the distribution of continuous variable, with separate violins for each group using ggplot2

Step 1 : Load the required library

library(ggplot2)

Step 2 : Load 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 ...

Step 3 : Create violin plot using ggplot2

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

  1. 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)

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

Step 2 : Load the dataset

data(ToothGrowth)
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  0.5
str(ToothGrowth)
'data.frame':   60 obs. of  3 variables:
 $ len : num  4.2 11.5 7.3 5.8 6.4 10 11.2 11.2 5.2 7 ...
 $ supp: Factor w/ 2 levels "OJ","VC": 2 2 2 2 2 2 2 2 2 2 ...
 $ dose: num  0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 0.5 ...
table(ToothGrowth$dose)

0.5   1   2 
 20  20  20

Step 3 : Create multiple dot plots

ToothGrowth$dose <- as.factor(ToothGrowth$dose)

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
  ) +
  labs(title = "Dot plot of Toothlength by Dosage and Supplement type",
       x = "Dose",
       y = "Tooth length",
       color = "Supplement type") +
  theme_minimal()

  1. Develop a R program to calculate and visualize correlation matrix for a given dataset, with color coded cells indicating the strength and relations of correlations, using ggplot2::geom_tile function.

Step 1 : Load the required library

library(ggplot2)
library(tidyr)
library(dplyr)

Step 2 : Load the dataset

data(mtcars)
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
cor_matrix <- cor(mtcars)
cor_df <- as.data.frame(as.table(cor_matrix))
cor_df
    Var1 Var2        Freq
1    mpg  mpg  1.00000000
2    cyl  mpg -0.85216196
3   disp  mpg -0.84755138
4     hp  mpg -0.77616837
5   drat  mpg  0.68117191
6     wt  mpg -0.86765938
7   qsec  mpg  0.41868403
8     vs  mpg  0.66403892
9     am  mpg  0.59983243
10  gear  mpg  0.48028476
11  carb  mpg -0.55092507
12   mpg  cyl -0.85216196
13   cyl  cyl  1.00000000
14  disp  cyl  0.90203287
15    hp  cyl  0.83244745
16  drat  cyl -0.69993811
17    wt  cyl  0.78249579
18  qsec  cyl -0.59124207
19    vs  cyl -0.81081180
20    am  cyl -0.52260705
21  gear  cyl -0.49268660
22  carb  cyl  0.52698829
23   mpg disp -0.84755138
24   cyl disp  0.90203287
25  disp disp  1.00000000
26    hp disp  0.79094859
27  drat disp -0.71021393
28    wt disp  0.88797992
29  qsec disp -0.43369788
30    vs disp -0.71041589
31    am disp -0.59122704
32  gear disp -0.55556920
33  carb disp  0.39497686
34   mpg   hp -0.77616837
35   cyl   hp  0.83244745
36  disp   hp  0.79094859
37    hp   hp  1.00000000
38  drat   hp -0.44875912
39    wt   hp  0.65874789
40  qsec   hp -0.70822339
41    vs   hp -0.72309674
42    am   hp -0.24320426
43  gear   hp -0.12570426
44  carb   hp  0.74981247
45   mpg drat  0.68117191
46   cyl drat -0.69993811
47  disp drat -0.71021393
48    hp drat -0.44875912
49  drat drat  1.00000000
50    wt drat -0.71244065
51  qsec drat  0.09120476
52    vs drat  0.44027846
53    am drat  0.71271113
54  gear drat  0.69961013
55  carb drat -0.09078980
56   mpg   wt -0.86765938
57   cyl   wt  0.78249579
58  disp   wt  0.88797992
59    hp   wt  0.65874789
60  drat   wt -0.71244065
61    wt   wt  1.00000000
62  qsec   wt -0.17471588
63    vs   wt -0.55491568
64    am   wt -0.69249526
65  gear   wt -0.58328700
66  carb   wt  0.42760594
67   mpg qsec  0.41868403
68   cyl qsec -0.59124207
69  disp qsec -0.43369788
70    hp qsec -0.70822339
71  drat qsec  0.09120476
72    wt qsec -0.17471588
73  qsec qsec  1.00000000
74    vs qsec  0.74453544
75    am qsec -0.22986086
76  gear qsec -0.21268223
77  carb qsec -0.65624923
78   mpg   vs  0.66403892
79   cyl   vs -0.81081180
80  disp   vs -0.71041589
81    hp   vs -0.72309674
82  drat   vs  0.44027846
83    wt   vs -0.55491568
84  qsec   vs  0.74453544
85    vs   vs  1.00000000
86    am   vs  0.16834512
87  gear   vs  0.20602335
88  carb   vs -0.56960714
89   mpg   am  0.59983243
90   cyl   am -0.52260705
91  disp   am -0.59122704
92    hp   am -0.24320426
93  drat   am  0.71271113
94    wt   am -0.69249526
95  qsec   am -0.22986086
96    vs   am  0.16834512
97    am   am  1.00000000
98  gear   am  0.79405876
99  carb   am  0.05753435
100  mpg gear  0.48028476
101  cyl gear -0.49268660
102 disp gear -0.55556920
103   hp gear -0.12570426
104 drat gear  0.69961013
105   wt gear -0.58328700
106 qsec gear -0.21268223
107   vs gear  0.20602335
108   am gear  0.79405876
109 gear gear  1.00000000
110 carb gear  0.27407284
111  mpg carb -0.55092507
112  cyl carb  0.52698829
113 disp carb  0.39497686
114   hp carb  0.74981247
115 drat carb -0.09078980
116   wt carb  0.42760594
117 qsec carb -0.65624923
118   vs carb -0.56960714
119   am carb  0.05753435
120 gear carb  0.27407284
121 carb carb  1.00000000

Step 3 : Visualize using ggplot2::geom_tile

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) +
  labs( title = "Correlation Matrix (mtcars)",
        x = "Var1",
        y = "Var2" ) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))