Confirmation and setting of working directory

Working directory in R is the default location on your computer where R reads and writes files.

Setting the working directory ensures that your files are saved and loaded from the intended locations, streamlining your workflow

setwd("~/TMMS2024")

Installation and loading of necessary packages/libraries

Loading libraries

library(tidyverse)    ##for data manipulation
library(psych)          ##for description of  data
library(summarytools)   ##for summarizing data
library(sjmisc)       ##for data manipulation

Load Example data

malaria_data <- read.csv("mockdata_cases.csv")
mosquito_data <- read.csv("mosq_mock.csv")

Characterizing the data

Before we start visualizing our data, we need to understand the characteristics of our data. The goal is to get an idea of the data structure and to understand the relationships between variables.

Explore the structure and summary of the datasets

dim(malaria_data)             ##Dimension of the data set
[1] 514  10
str(malaria_data)             ##structure of the data set
'data.frame':   514 obs. of  10 variables:
 $ location      : chr  "mordor" "mordor" "mordor" "mordor" ...
 $ month         : int  1 9 1 6 4 7 2 5 12 5 ...
 $ year          : int  2020 2019 2019 2018 2019 2020 2019 2020 2019 2020 ...
 $ ages          : chr  "15_above" "5_to_14" "15_above" "5_to_14" ...
 $ total         : int  22 34 36 32 36 34 38 31 53 57 ...
 $ positive      : int  4 6 7 7 8 8 8 8 9 9 ...
 $ xcoord        : num  -20.3 -20.5 -19.7 -19.8 -20.1 ...
 $ ycoord        : num  29.4 29.4 30.5 30.1 30.6 ...
 $ prev          : num  0.182 0.176 0.194 0.219 0.222 ...
 $ time_order_loc: int  25 21 13 6 16 31 14 29 24 29 ...
head(malaria_data)      ##View the first few rows
  location month year     ages total positive    xcoord   ycoord      prev
1   mordor     1 2020 15_above    22        4 -20.25495 29.38997 0.1818182
2   mordor     9 2019  5_to_14    34        6 -20.47055 29.43265 0.1764706
3   mordor     1 2019 15_above    36        7 -19.70804 30.49507 0.1944444
4   mordor     6 2018  5_to_14    32        7 -19.84918 30.14912 0.2187500
5   mordor     4 2019 15_above    36        8 -20.14803 30.60721 0.2222222
6   mordor     7 2020 15_above    34        8 -19.31510 29.71290 0.2352941
  time_order_loc
1             25
2             21
3             13
4              6
5             16
6             31
summary(malaria_data)                       ##summary of descriptive statistics
   location             month             year          ages          
 Length:514         Min.   : 1.000   Min.   :2018   Length:514        
 Class :character   1st Qu.: 4.000   1st Qu.:2018   Class :character  
 Mode  :character   Median : 7.000   Median :2019   Mode  :character  
                    Mean   : 6.486   Mean   :2019                     
                    3rd Qu.: 9.000   3rd Qu.:2020                     
                    Max.   :12.000   Max.   :2020                     
     total          positive          xcoord           ycoord     
 Min.   : 20.0   Min.   :  0.00   Min.   :-21.84   Min.   :28.52  
 1st Qu.: 46.0   1st Qu.: 14.00   1st Qu.:-20.39   1st Qu.:29.64  
 Median :103.0   Median : 33.00   Median :-20.06   Median :29.99  
 Mean   :141.5   Mean   : 47.81   Mean   :-20.04   Mean   :30.00  
 3rd Qu.:206.0   3rd Qu.: 67.00   3rd Qu.:-19.71   3rd Qu.:30.32  
 Max.   :611.0   Max.   :264.00   Max.   :-18.79   Max.   :31.81  
      prev          time_order_loc 
 Min.   :-0.04545   Min.   : 1.00  
 1st Qu.: 0.24615   1st Qu.: 9.00  
 Median : 0.33016   Median :18.00  
 Mean   : 0.31518   Mean   :17.65  
 3rd Qu.: 0.39024   3rd Qu.:26.00  
 Max.   : 0.53488   Max.   :35.00  
describe(malaria_data)                     ##summary of descriptive statistics
               vars   n    mean     sd  median trimmed   mad     min     max
location*         1 514    3.00   1.43    3.00    3.00  1.48    1.00    5.00
month             2 514    6.49   3.37    7.00    6.50  4.45    1.00   12.00
year              3 514 2018.91   0.78 2019.00 2018.89  1.48 2018.00 2020.00
ages*             4 514    2.00   0.82    2.00    2.00  1.48    1.00    3.00
total             5 514  141.46 118.83  103.00  122.87 96.37   20.00  611.00
positive          6 514   47.81  46.52   33.00   39.75 34.10    0.00  264.00
xcoord            7 514  -20.04   0.49  -20.06  -20.05  0.50  -21.84  -18.79
ycoord            8 514   30.00   0.51   29.99   29.99  0.51   28.52   31.81
prev              9 514    0.32   0.10    0.33    0.32  0.11   -0.05    0.53
time_order_loc   10 514   17.65   9.93   18.00   17.63 13.34    1.00   35.00
                range  skew kurtosis   se
location*        4.00  0.00    -1.34 0.06
month           11.00 -0.03    -1.18 0.15
year             2.00  0.15    -1.33 0.03
ages*            2.00  0.01    -1.50 0.04
total          591.00  1.26     1.11 5.24
positive       264.00  1.75     3.48 2.05
xcoord           3.05  0.04    -0.26 0.02
ycoord           3.29  0.11     0.09 0.02
prev             0.58 -0.51    -0.15 0.00
time_order_loc  34.00  0.01    -1.20 0.44

We should also explore individual columns/variables

#malaria_data$location          ##values for a single column (locations)
#malaria_data$month            ##values for a single column (month)
#malaria_data$year             ##values for a single column (year)
unique(malaria_data$location)  ## unique values for a single column
[1] "mordor"     "narnia"     "neverwhere" "oz"         "wonderland"
table(malaria_data$location)   ## frequencies for a single column (location)

    mordor     narnia neverwhere         oz wonderland 
       105        104         96        104        105 
frq(malaria_data$location)
x <character> 
# total N=514 valid N=514 mean=3.00 sd=1.43

Value      |   N | Raw % | Valid % | Cum. %
-------------------------------------------
mordor     | 105 | 20.43 |   20.43 |  20.43
narnia     | 104 | 20.23 |   20.23 |  40.66
neverwhere |  96 | 18.68 |   18.68 |  59.34
oz         | 104 | 20.23 |   20.23 |  79.57
wonderland | 105 | 20.43 |   20.43 | 100.00
<NA>       |   0 |  0.00 |    <NA> |   <NA>
#prop.table(table(malaria_data$location)) # percentages for a single column
table(malaria_data$location, malaria_data$year)  # frequencies for multiple columns
            
             2018 2019 2020
  mordor       36   36   33
  narnia       36   36   32
  neverwhere   36   57    3
  oz           35   36   33
  wonderland   36   36   33

check for missing values in each column, as these can affect our visualizations.

sum(is.na(malaria_data))      ##checking for missing values in the data set
[1] 0

Check Columns with Missing values in the data set

library(kableExtra)
missing_values <- colSums(is.na(malaria_data))
kable(missing_values)
x
location 0
month 0
year 0
ages 0
total 0
positive 0
xcoord 0
ycoord 0
prev 0
time_order_loc 0

—————————————————————————

Challenge 1: Explore the structure and summary of the mosquito_data dataset

—————————————————————————

What are the dimensions of the dataset?

What are the column names?

What are the column types?

#sapply(mosquito_data, class)

What are some key variables or relationships that we can explore?

—————————————————————————

Data Visualization Using Base R Functions

—————————————————————————

First, we will look at some exploratory data visualization techniques using base R functions. The purpose of these plots is to help us understand the relationships between variables and characteristics of our data. They are useful for quickly exploring the data and understanding the relationships, but they are not great for sharing in scientific publications/presentations.

(OBJECTIVE) After completing this session, you should be able to;

Explain the various types of graphics available in R

List the possible file formats of graphic outputs

Describe the methods to save graphics as files

Describe the procedure to export graphs in Rstudio

Graphics in R

R includes powerful packages of graphics that help in data visualization. These graphics can be: Viewed on the screen, saved in various formats such as ,pdf, .png, .jpg etc and customized according to the varied graphic needs.

Types of Graphics

R supports 8 types of graphics: Bar charts, Pie Charts, Histogram, line charts, box plot, Kernel density plot, Heat map, word cloud.

Single variable comparison

#1. Histogram For one variable comparison, we can use hist() function to create a histogram. Histogram displays the distribution of continuous variable and the frequency of scores in each bin on y-axix by dividing the ranges of scores into bins on the x-axis

hist(malaria_data$prev)

hist(malaria_data$prev, col = "tomato")

Alternatively

hist(malaria_data$prev, 
    breaks = 5, 
    col = "tomato",
    border = "darkblue",
    main = "Distribution of Malaria Prevalence",
    xlab = "Malaria Prevalence",
    ylab = "Frequency")

#2. Kernel Density Plots These display the distribution of a continuous variable much more efficiently than histogram

The density plot is useful for visualizing changes in distributions of a continuous variable

density <- density(malaria_data$prev)

plot(density)
polygon(density, col="red",border="black")

#Save as PDF in Rstudio
pdf("Density Plots.pdf", width = 8, height = 6)      # Open PDF device
plot(density)                                               # Create the plot
polygon(density, col="red",border="black")                  
dev.off()                                                   # Close device & finalize the file
png 
  2

#3. Line chart Line charts represent a series of data point connected by a straight line and are generally used to visualize data that changes over time.

plot(malaria_data$total, malaria_data$positive, type ="l")

#4. Barplot Another useful function for single variable comparisons is barplot(). In this case, we will use the table() function to count the number of observations in each category, then use barplot() to create a barplot.

Barcharts are horizontal or vertical bars to show comparisons between categorical values. They represent lengths, frequency or proportions of categorical values

counts <- table(malaria_data$year)
barplot(counts)

counts <- table(malaria_data$year)
counts

2018 2019 2020 
 179  201  134 
barplot(counts,
        col=c("blue", "red", "green"),
        main= "Simple Bar chart",
        xlab= "Year",
        ylab="Frequency")

#Save as PNG in Rstudio
png("Simple Bar chart.png")                       # Open PNG device
barplot(counts,                                   # Create the plot
        col=c("red", "blue", "green"),
        main= "Simple Bar chart",
        xlab= "Year",
        ylab="Frequency")               
dev.off()                                          # Close device
png 
  2 
#Save as PDFin Rstudio
pdf("Simple Bar chart.pdf")                       # Open PDF device
barplot(counts,                                   # Create the plot
        col=c("red", "blue", "green"),
        main= "Simple Bar chart",
        xlab= "Year",
        ylab="Frequency")               
dev.off()                                          # Close device
png 
  2

Pie charts

It is a type of graph in which a circle is divided into sectors, each representing a proportion of the whole.

df <- prop.table(table(malaria_data$location))
p1 <- pie(df, 
          labels=paste(names(df),"(", round(df*100,1),"%)"),col=c("green","tomato","blue","purple","black"),
          main="Malaria cases Distribution by Location")

library(plotrix)
df <- prop.table(table(malaria_data$location))
p2 <- pie3D(df, 
          labels=paste(names(df),"(", round(df*100,1),"%)"),col=c("green","tomato","blue","purple","lightblue"),
          main="Malaria cases Distribution by Location")

library(plotly)
df <- as.data.frame(table(malaria_data$location))
colnames(df) <- c("location", "freq")


fig <- plot_ly(df,
               labels = ~df$location,
               values = ~df$freq,
               type = 'pie',
               hole = 0.3,                  # Makes a doughnut chart; set to 0 for a full pie chart
               textinfo = 'label+percent',  # Shows both labels and percentages
               marker = list(colors = colorRampPalette(c('blue', 'green', 'tomato', 'skyblue'))(nrow(df))))

fig

Multiple variables

For multiple variables, we can use plot() function to create a scatterplot, multiple bar chart, boxplot etc.

In this case, we will use plot() to create a scatterplot. The first argument in plot() is the x variable, and the second argument is the y variable.

scatterplot

plot(malaria_data$total, malaria_data$positive)

plot(malaria_data$total, malaria_data$positive, col="red")

#Save as JPEG in Rstudio
jpeg("Scatter plot.jpg")                                        # Open JPEG device
plot(malaria_data$total, malaria_data$positive, col="red")      # Create the plot
dev.off()                                                       # Close device
png 
  2

Multiple Bar chart

counts <- table(malaria_data$year,malaria_data$ages)
barplot(counts,
       col=c("red", "blue", "green"),
        main= "Multiple Bar chart",
        xlab= "Age Group",
        ylab="Frequency",
        legend=rownames(counts), beside=T)

# Boxplot

A boxplot, also known as a box-and-whisker plot, is a standardized way of displaying the distribution of data based on a five-number summary: minimum, first quartile (Q1), median, third quartile (Q3), and maximum.

Importance of Boxplots

boxplot(malaria_data$prev ~ malaria_data$location) 

boxplot(malaria_data$prev ~ malaria_data$location, col="tomato") 

#Save as TIFF in Rstudio
tiff("Box-and-Whisker plot.tiff", width = 800, height = 600)          # Open TIFF device
boxplot(malaria_data$prev ~ malaria_data$location, col="tomato")      # create the plot
dev.off ()                                                            # Close device
png 
  2

—————————————————————————

Challenge 2: Create R base visualizations of the ‘mosquito_data’ dataset

—————————————————————————

Are their any interesting patterns in individual variables/columns? Are there any relationships between variables/columns? # ————————————————————————– # Data Visualization with ggplot2 # ————————————————————————– Base R functions like hist() and barplot() are great for quickly exploring our data, but we may want to use more powerful visualization techniques when preparing outputs for scientific reports, presentations, and publications.

The ggplot2 package is a popular visualization package for R. It provides an easy-to-use interface for creating data visualizations. The ggplot2 package is based on the “grammar of graphics” and is a powerful way to create complex visualizations that are useful for creating scientific and publication-quality figures.

The “grammar of graphics” used in ggplot2 is a set of rules that are used to develop data visualizations using a layering approach. Layers are added using the ‘+’ operator.

Components of a ggplot

There are three main components of a ggplot: 1. The data: the dataset we want to visualize 2. The aesthetics: the visual properties from the data used in the plot 3. The geometries: the visual representations of the data (e.g., points, lines, bars)

The data

All ggplot2 plots require a data frame as input. Just running this line will produce a blank plot because we have stated which elements from the data we want to visualize or how we want to visualize them.

ggplot(data = malaria_data)

The aesthetics

Next, we need to specify the visual properties of the plot that are determined by the data. The aesthetics are specified using the aes() function. The output should now produce a blank plot but with determined visual properties (e.g., axes labels).

ggplot(data = malaria_data, aes(x = total, y = positive))

The geometries

Finally, we need to specify the visual representation of the data. The geometries are specified using the geom_* function. There are many different types of geometries that can be used in ggplot2. We will use geom_point() in this example and we will append it to the previous plot using the + operator. The output should now produce a plot with the specified visual representation of the data.

library(ggthemes)
ggplot(data = malaria_data, aes(x = total, y = positive)) + 
  geom_point()

ggplot(data = malaria_data, aes(x = total, y = positive)) + 
  geom_point(colour = "tomato")

library(ggpubr)
ggplot(data = malaria_data, aes(x = total, y = positive)) + 
  geom_point(colour = "tomato") +
  theme_classic()

ggplot(data = malaria_data, aes(x = total, y = positive)) + 
  geom_point(colour = "tomato") +
  theme_economist()

ggplot(data = malaria_data, aes(x = total, y = positive)) + 
  geom_point(colour = "tomato") +
  theme_pubclean()

ggplot(data = malaria_data, aes(x = total, y = positive, color = location)) + 
  geom_point() +
  theme_economist()

ggplot(data = malaria_data, aes(x = total, y = positive)) + 
  geom_point() +
  geom_smooth(method = "lm")  # The smooth geom add a smoothed line to the plot

ggplot(data = malaria_data, aes(x = total, y = positive, color = year)) + 
  geom_point() +
  facet_wrap(~year) +
  theme_bw()

ggplot(data = malaria_data, aes(x = total, y = positive, color = location)) + 
  geom_point() +
  facet_wrap(~year) +
  theme_bw()

ggplot(data = malaria_data, aes(x = total, y = positive, color = location)) + 
  geom_point() +
  geom_smooth(method = "lm") +  # The smooth geom add a smoothed line to the plot
  theme_classic()

ggplot(data = malaria_data, aes(x = total, y = positive, color = location)) + 
  geom_point() +
  stat_ellipse() +
  theme_classic()

ggplot(data = malaria_data, aes(x= prev))+
  geom_histogram(bins = 5, fill = "tomato", color = "blue") +
  theme_economist()

ggplot(data = malaria_data, aes(x= prev))+
  geom_histogram(bins = 5, fill = "tomato", color = "blue") +
  theme_classic()

#Here are some examples of different geom functions:

Example data

data <- data.frame(Category = c(“A”, “B”, “C”, “A”, “B”, “C”, “A”, “A”, “B”, “C”))

Plotting a bar chart

ggplot(data = malaria_data, aes(x = year)) +
  geom_bar(fill = "blue") +                    # the "fill" argument specifies the color of the bars
  theme_pubclean()

ggplot(data = malaria_data, aes(x = year)) +
  geom_bar(fill = "tomato") +
  labs(title="Simple Bar Plot",
       x="Year",
       y="Frequency",
       caption = "Source: Malaria data") +
  theme_classic()

When using the aes() function, the visual properties will be determined by a variable in the dataset. This allows us to visualize relationships between multiple variables at the same time.

# Compute the frequency
df <- malaria_data %>%
  group_by(year) %>%
  summarise(counts = n())

# Create the bar plot
ggplot(df, aes(x = year, y = counts)) +
  geom_bar(fill = "tomato", stat = "identity") +
  geom_text(aes(label = counts), vjust = -0.3) +
  labs(title="Simple Bar Plot",
       x="Year",
       y="Frequency",
       caption = "Source: Malaria data") +
  theme_classic()

Multiple Bar chart

#frq(malaria_data, ages)
ggplot(data = malaria_data, aes(x = ages, y=positive, fill = ages)) +
  geom_bar(stat = "identity") +
  labs(title="Multiple Bar Plot",
       x="Age Group",
       y="Malaria Positive Cases Reported",
       caption = "Source: Malaria data") +
  theme_classic()

# Create multiple bar plots using facet_wrap()
ggplot(data = malaria_data, aes(x = ages, y=positive, fill = ages)) +
  geom_bar(stat = "identity") +
  facet_wrap(~year) +
  labs(title="Multiple Bar Plot by year",
       x="Age Group",
       y="Malaria Positive Cases Reported",
       caption = "Source: Malaria data") +
  theme_classic()

Multiple Histogram

ggplot(data = malaria_data, aes(x= prev, fill = ages))+
  geom_histogram(bins = 10) +
  theme_classic()

ggplot(data = malaria_data, aes(x= prev, fill = ages))+
  geom_histogram(bins = 10, color ="black") +
  labs(title = "Multiple Histogram by Age group",
       x="Malaria Prevalance Rate",
       y="Numver of Malaria case",
       caption = "Source: Malaria data") +
  theme_classic()

ggplot(data = malaria_data, aes(x = prev, fill = ages)) +
  geom_histogram(color = "black") +
theme_classic()

# Density ridgeline plot The density ridgeline plot is useful for visualizing changes in distributions of a continuous variable, over time or space. Ridgeline plots are partially overlapping line plots that create the impression of a mountain range.

library(ggridges)
ggplot(malaria_data, aes(x = prev, y = ages, fill = ages)) +
  geom_density_ridges()

————————————————————————-

Challenge 3: Create ggplot2 visualizations of the ‘mosquito_data’ dataset

————————————————————————-

Are their any interesting patterns in individual variables/columns? How can we use the aes() function to view multiple variables in a single plot? Are there any additional geometries that may be useful for visualizing this dataset?

#The examples above show how to use colors for categorical variables, but we can also use custom color palettes for continuous variables.

ggplot(data = malaria_data, aes(x = total, y = positive, color = prev)) +
  geom_point() +
  scale_color_gradient(low = "blue", high = "red")

ggplot(data = malaria_data, aes(x = total, y = positive, color = prev)) +
  geom_point() +
  # use viridis package to create custom color palettes
  scale_color_viridis_c(option = "magma")  

ggplot(data = malaria_data, aes(x = location, y = prev)) +
  geom_boxplot(fill = "lightblue") +
  geom_jitter(alpha = 0.2) +
  theme_classic()

ggplot(data = malaria_data, aes(x = location, y = prev, fill = location)) +
  geom_boxplot() +
  geom_jitter(alpha = 0.2, aes(color = location)) +
  theme_classic()

library(ggpubr)
p <- ggplot(data = malaria_data, aes(x = location, y = prev, fill = location)) +
  geom_boxplot() +
  geom_jitter(alpha = 0.2, aes(color = location)) 
  # theme_classic()

#  Add p-value
p + stat_compare_means()

# Violin plots

Violin plots are similar to box plots, except that they also show the kernel probability density of the data at different values. Typically, violin plots will include a marker for the median of the data and a box indicating the interquartile range, as in standard box plots.

Key function:

geom_violin(): Creates violin plots. Key arguments: fill: Areas fill color Create basic violin plots with summary statistics:

ggplot(data = malaria_data, aes(x = location, y = prev)) +
  geom_violin(fill = "tomato") +
  geom_jitter(alpha = 0.2) +
  theme_classic()

Sinaplot

sinaplot is inspired by the strip chart and the violin plot. By letting the normalized density of points restrict the jitter along the x-axis, the plot displays the same contour as a violin plot, but resemble a simple strip chart for small number of data points (Sidiropoulos et al. 2015).

In this way the plot conveys information of both the number of data points, the density distribution, outliers and spread in a very simple, comprehensible and condensed format.

Key function: geom_sina() [ggforce]:

library(ggforce)
# Create some data
d1 <- data.frame(
  MalariaPositiveCases = c(rnorm(200, 4, 1), rnorm(200, 5, 2), rnorm(400, 6, 1.5)),
  ageGroup = rep(c("under 5 years", "5 to 15 years", "Above 15 years"), c(200, 200, 400)))

# Sinaplot
ggplot(d1, aes(ageGroup,  MalariaPositiveCases)) +
  geom_sina(aes(color = ageGroup), size = 0.7)+
  scale_color_manual(values =  c("red", "blue", "green"))

#Correlation matrix with ggally package

library(GGally)

# correlation analysis 
data(malaria_data)
ggpairs(malaria_data, columns = 5:6, ggplot2::aes(colour=location))

Scatterplot

library(ggplot2)
library(ggExtra)

g <- ggplot(malaria_data, aes(total, positive)) + 
  geom_count(color = "red") + 
  geom_smooth(method="lm", se=F) 

ggMarginal(g, type = "histogram", fill="blue")

ggMarginal(g, type = "boxplot", fill="transparent")

ggMarginal(g, type = "density", fill="blue")

library(leaflet)
# Sample data
attach(malaria_data)

# Create an interactive map with leaflet
leaflet(malaria_data) %>%
  addTiles() %>%
  addCircleMarkers(
    ~xcoord, ~ycoord,
    radius = ~prev *10,
    color = "red",
    stroke = FALSE,
    fillOpacity = 0.5,
    label = ~paste0(location, ": ", prev)) %>%
  addLegend("bottomright", 
            colors = "red", 
            labels = "Malaria Prevalence",
            title = "Prevalence")

Global Map using Malaria Data from KNBS

data <- read.csv("malaria_survey_data1.csv")

### Code the Counties and Give their Appropriate Name
data$County <- factor(data$County, levels = c(101, 201, 202, 203, 204, 205, 301, 302, 303, 304, 305, 306,
            401, 402, 403, 404, 405, 406, 407, 408, 501, 502, 503, 601, 602,
            603, 604, 605, 606, 701, 702, 703, 704, 705, 706, 707, 708, 709,
            710, 711, 712, 713, 714, 801, 802, 803, 804),
            labels = c("nairobi", "nyandarua", "nyeri", "kirinyaga", "muranga", "kiambu",
            "mombasa", "kwale", "kilifi", "tana river", "lamu", "taita taveta",
            "marsabit", "isiolo", "meru", "tharaka", "embu", "kitui", "machakos",
            "makueni", "garissa", "wajir", "mandera", "siaya", "kisumu", "migori",
            "homa bay", "kisii", "nyamira", "turkana", "west pokot", "samburu",
            "trans-nzoia", "baringo", "uasin gishu", "elgeyo marakwet", "nandi",
            "laikipia", "nakuru", "narok", "kajiado", "kericho", "bomet", "kakamega",
            "vihiga", "bungoma", "busia"))

gps <- read.csv("longitude_latitude.csv")
## Merge the data set
data <- merge(gps, data, by = "County", all.x = TRUE)

Mapping of Malaria Occurrences

library(leaflet)

# Create an interactive map with leaflet
leaflet(data) %>%
  addTiles() %>%
  addCircleMarkers(
    ~Longitude, ~Latitude,
    radius = ~Final_Malaria_Test_Results*3,
    color = "red",
    stroke = FALSE,
    fillOpacity = 0.5,
    label = ~paste0(County, ": ", Final_Malaria_Test_Results)) %>%
  addLegend("bottomright", 
            colors = "red", 
            labels = "Malaria Results",
            title = "Positive Malaria Test Results")
library(paletteer)
library(leaflet)
# Sample data 
africa <- read.csv("DatasetAfricaMalaria.csv", header = TRUE)

# Create an interactive map with leaflet
leaflet(africa) %>%
  addTiles() %>%
  addCircleMarkers(
    ~longitude, ~latitude,
    radius = ~Incidence.of.malaria..per.1.000.population.at.risk.*0.01,
    color = "red",
    stroke = FALSE,
    fillOpacity = 0.5,
    label = ~paste0(Country.Name, ": ", Incidence.of.malaria..per.1.000.population.at.risk.)) %>%
  addLegend("bottomright", 
            colors = "red", 
            labels = "Malaria Prevalence",
            title = "Prevalence in Africa")
dat<-data.frame(t=seq(0,2*pi,by=0.1))
xhrt<-function(t)16*sin(t)^3
yhrt<-function(t)13*cos(t)-5*cos(2*t)-2*cos(3*t)-cos(4*t) 
dat$y=yhrt(dat$t)
dat$x=xhrt(dat$t)
with(dat,plot(x,y,type="l"))
with(dat,polygon(x,y,col="red"))

# Load necessary libraries
library(ggplot2)
library(paletteer)

# Load the data
df <- read.csv("https://raw.githubusercontent.com/holtzy/The-Python-Graph-Gallery/master/static/data/simple-scatterplot.csv")

# Create the ggplot
ggplot(df, aes(x = gdpPercap, y = lifeExp, size = pop, color = continent)) +
  geom_point(size=3) +
  scale_fill_paletteer_d("nationalparkcolors::Acadia") +
  theme(legend.position = "none")