prgm15.quarto

Author

sushmitha d.s

1.Create multiple histograms using ggplot2 to visualize how a variable is distributed across different groups in a built R dataset.

library(ggplot2)

ggplot(iris, aes(x = Sepal.Length)) +
  geom_histogram(binwidth = 0.3, fill = "skyblue", color = "black") +
  facet_wrap(~ Species) +  # creates a histogram for each species
  labs(
    title = "Distribution of Sepal Length by Species",
    x = "Sepal Length",
    y = "Count"
  ) +
  theme_minimal()

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

# Load required libraries
library(ggplot2)

# Use iris dataset: Continuous variable = Sepal.Length, Grouping variable = Species
data <- iris

# Plot density curves
ggplot(data, aes(x = Sepal.Length, color = Species, fill = Species)) +
  geom_density(alpha = 0.4, size = 1) +
  labs(title = "Density Plot of Sepal Length by Species",
       x = "Sepal Length",
       y = "Density") +
  theme_minimal() +
  theme(plot.title = element_text(hjust = 0.5))

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

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

library(ggplot2)
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

ggplot(iris, aes(x = Species, y = Sepal.Length)) +
  geom_boxplot(
    notch = TRUE,
    notchwidth = 0.5,
    outlier.colour = "red",
    outlier.shape = 16,
    fill = "skyblue"
  ) +
  labs(
    title = "Basic Box Plot",
    x = "Species",
    y = "Sepal Length"
  ) +
  theme_minimal()

4.Develop a script to create a violin plot displaying the distribution of a continous variable with separate violins for each plot .

library(ggplot2)
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

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)

5.Write an R program to create multiple dot plots for grouped data , comparing the distribution of variable across different using ggplot2’s position dodge function .

library(ggplot2)
data <- mtcars
data$cyl <- as.factor(data$cyl)
data$gear <- as.factor(data$gear)
ggplot(data, aes(x = cyl, y = mpg, color = gear)) +
  geom_dotplot(binaxis = 'y', stackdir = 'center', 
               position = position_dodge(width = 0.7),
               dotsize = 0.6) +
  labs(title = "Dot Plot of MPG by Cylinder and Gear",
       x = "Number of Cylinders",
       y = "Miles Per Gallon (MPG)",
       color = "Gear") +
 theme_minimal()

Bin width defaults to 1/30 of the range of the data. Pick better value with
`binwidth`.

6.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_time function .

# Load the library
library(ggplot2) 
library(tidyr)
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

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

#dim(mtcars)
str(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 ...

#use built-in mtcars dataset
data(mtcars)

# compute correlation matrix
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  1.00000000

#convert matrix to data frame for plotting
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

# Plot the correlation heatmap using ggplot2
ggplot(cor_df, aes(x = Var1, y = Var2, fill = Freq)) +
  geom_tile(color = "white") +
  scale_fill_gradient2(
    low = "blue",
    high = "red",
    mid = "white",
    midpoint = 0,
    limit = c(-1, 1),
    name = "Correlation"
  ) +
  geom_text(aes(label = round(Freq, 2)), size = 3) +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 45, vjust = 1, hjust = 1)) +
  labs(title = "Correlation Matrix (mtcars)",
       x = "",
       y = "")